WO2024082658A1 - Method and system for temperature rise detection of air conditioner - Google Patents

Method and system for temperature rise detection of air conditioner Download PDF

Info

Publication number
WO2024082658A1
WO2024082658A1 PCT/CN2023/099817 CN2023099817W WO2024082658A1 WO 2024082658 A1 WO2024082658 A1 WO 2024082658A1 CN 2023099817 W CN2023099817 W CN 2023099817W WO 2024082658 A1 WO2024082658 A1 WO 2024082658A1
Authority
WO
WIPO (PCT)
Prior art keywords
temperature rise
electrical component
image
pixel
pixel coordinate
Prior art date
Application number
PCT/CN2023/099817
Other languages
French (fr)
Chinese (zh)
Inventor
徐文堂
张中晓
王明星
张吉义
郭子超
Original Assignee
青岛海尔空调器有限总公司
青岛海尔空调电子有限公司
海尔智家股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 青岛海尔空调器有限总公司, 青岛海尔空调电子有限公司, 海尔智家股份有限公司 filed Critical 青岛海尔空调器有限总公司
Publication of WO2024082658A1 publication Critical patent/WO2024082658A1/en

Links

Classifications

    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F1/00Room units for air-conditioning, e.g. separate or self-contained units or units receiving primary air from a central station
    • F24F1/06Separate outdoor units, e.g. outdoor unit to be linked to a separate room comprising a compressor and a heat exchanger
    • F24F1/20Electric components for separate outdoor units
    • F24F1/24Cooling of electric components
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • F24F11/30Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
    • F24F11/49Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring ensuring correct operation, e.g. by trial operation or configuration checks
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/52Radiation pyrometry, e.g. infrared or optical thermometry using comparison with reference sources, e.g. disappearing-filament pyrometer
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • G06V30/19Recognition using electronic means
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • G06V30/30Character recognition based on the type of data
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00Control inputs relating to air properties
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00Control inputs relating to air properties
    • F24F2110/50Air quality properties
    • F24F2110/64Airborne particle content

Definitions

  • the present application relates to the field of air conditioning technology, for example, to a method and system for detecting temperature rise of an air conditioner.
  • the electrical components in the electrical box of the outdoor unit of the air conditioner will release a lot of heat when working. If the temperature of the electrical components is too high when the outdoor unit is working, the outdoor unit of the air conditioner will not work properly. Therefore, it is necessary to test the temperature rise of the electrical components in the electrical box of the outdoor unit before leaving the factory to ensure that the temperature of the electrical components does not exceed the standard when the air conditioner outdoor unit is in use.
  • the relevant technology is to test the temperature rise of the electrical components of the outdoor unit during operation by bonding thermocouple wires to the electrical components in the electrical box of the outdoor unit.
  • thermocouple wires The related technology can only detect the temperature rise of electrical components connected to thermocouple wires. It is difficult to detect the temperature rise of some electrical components that are in special positions, small in size or cannot be connected to thermocouple wires, resulting in low coverage of temperature rise detection of electrical components in outdoor units.
  • the embodiments of the present disclosure provide a method and system for temperature rise detection of an air conditioner, which can improve the coverage of temperature rise detection of electrical components in an outdoor unit.
  • the method for detecting temperature rise of an air conditioner includes: acquiring an image containing an electrical component, wherein the electrical component is located in an outdoor unit of the air conditioner; performing electrical component recognition on the image to obtain recognized electrical components; recognizing a target temperature rise point in the image, wherein the target temperature rise point is a pixel point in the image that meets a preset condition; and The temperature rise of the identified electrical component is determined according to the target temperature rise point and the identified electrical component.
  • the performing electrical component recognition on the image includes: inputting the image into a preset electrical component recognition model to perform electrical component recognition to obtain recognized electrical components.
  • identifying the target temperature rise point in the image includes: inputting the image into a preset temperature recognition model for temperature recognition to obtain the temperature value corresponding to each pixel point on the image; and determining the pixel point corresponding to the temperature value that meets the preset conditions as the target temperature rise point.
  • determining the pixel point corresponding to the temperature value satisfying the preset condition as the target temperature rise point includes: determining the pixel point corresponding to the temperature value greater than or equal to the first preset threshold as the target temperature rise point.
  • determining the temperature rise of the identified electrical component based on the target temperature rise point and the identified electrical component includes: obtaining a first pixel coordinate and a second pixel coordinate; the first pixel coordinate is the pixel coordinate of the identified electrical component, and the second pixel coordinate is the pixel coordinate of the target temperature rise point; matching each of the first pixel coordinates with each of the second pixel coordinates to obtain a matching result; when the matching result is that the second pixel coordinate matches the first pixel coordinate, determining the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate.
  • the system for detecting temperature rise of an air conditioner includes: a temperature rise monitoring device, configured to obtain an image containing electrical components, wherein the electrical components are located in an outdoor unit of an air conditioner; identifying a target temperature rise point in the image, wherein the target temperature rise point is a pixel point in the image that meets a preset condition; an electrical component identification device, configured to identify electrical components in the image to obtain identified electrical components; and a control device, configured to determine the temperature rise of the identified electrical components based on the target temperature rise point and the identified electrical components.
  • the electrical component identification device includes: an electrical component identification module configured to input the image into a preset electrical component identification model to perform electrical component identification and obtain an identified electrical component.
  • the temperature rise monitoring device includes: a temperature recognition module, configured to input the image into a preset temperature recognition model for temperature recognition, and obtain the temperature value corresponding to each pixel point on the image; and determine the pixel point corresponding to the temperature value that meets the preset conditions as the target temperature rise point.
  • a temperature recognition module configured to input the image into a preset temperature recognition model for temperature recognition, and obtain the temperature value corresponding to each pixel point on the image; and determine the pixel point corresponding to the temperature value that meets the preset conditions as the target temperature rise point.
  • the temperature identification module is configured to determine the pixel points corresponding to the temperature values satisfying the preset conditions as the target temperature rise points in the following manner: determine the pixel points corresponding to the temperature values greater than or equal to the first preset threshold as the target temperature rise points.
  • the system for detecting temperature rise of an air conditioner further comprises: a positioning device configured to obtain a first pixel coordinate and a second pixel coordinate; match each of the first pixel coordinates with each of the second pixel coordinates to obtain a matching result; and send the matching result to the control module; wherein the first pixel coordinate is the pixel coordinate of the identified electrical component, and the second pixel coordinate is the pixel coordinate of the target temperature rise point; the control module The device is configured to determine the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate when the matching result is that the second pixel coordinate matches the first pixel coordinate.
  • the method and system for detecting the temperature rise of an air conditioner can achieve the following technical effects: by acquiring an image of the electrical components in the outdoor unit of the air conditioner and identifying the acquired image, the electrical components in the image and the target temperature rise points in the image are identified. The temperature rise of the identified electrical components is determined based on the identified electrical components and the target temperature rise points. In this way, the temperature rise of each electrical component is detected through the image of the electrical components in the outdoor unit, and the temperature rise of all electrical components contained in the image can be detected, thereby improving the coverage of temperature rise detection of the electrical components in the outdoor unit.
  • FIG1 is a schematic diagram of a method for detecting temperature rise of an air conditioner provided by an embodiment of the present disclosure
  • FIG2 is a schematic structural diagram of a temperature rise detection system for an air conditioner provided by an embodiment of the present disclosure
  • FIG3 is a schematic diagram of the structure of a temperature rise monitoring device provided in an embodiment of the present disclosure.
  • FIG4 is a schematic diagram of the structure of an electrical component identification device provided by an embodiment of the present disclosure.
  • FIG5 is a schematic structural diagram of another temperature rise detection system for an air conditioner provided by an embodiment of the present disclosure.
  • FIG6 is a schematic diagram of the structure of a positioning device provided in an embodiment of the present disclosure.
  • FIG. 7 is a schematic diagram of the structure of a control device provided in an embodiment of the present disclosure.
  • the character "/" indicates that the preceding and following objects are in an "or" relationship.
  • A/B indicates: A or B.
  • a and/or B means: A or B, or, A and B.
  • correspondence may refer to an association relationship or a binding relationship.
  • correspondence between A and B means that there is an association relationship or a binding relationship between A and B.
  • thermocouple wires By bonding thermocouple wires to detect the temperature rise of electrical components in the electrical box of the outdoor unit, only the electrical components connected to the thermocouple wires can be detected. It is difficult to perform temperature rise detection on electrical components in special positions, small in size or unable to connect thermocouple wires, resulting in low coverage of temperature rise detection. At the same time, by bonding thermocouple wires to detect temperature rise, it is necessary to arrange thermocouple wires at multiple points, which is cumbersome and labor-intensive, resulting in confusion of thermocouple wires and increased safety hazards. Thermocouple wires may also have poor contact or loose contact, resulting in inaccurate temperature rise detection results.
  • the present application uses an infrared camera to capture images of electrical components in the outdoor unit of the air conditioner, and identifies the electrical components in the image and the target temperature rise points in the image.
  • the temperature rise of the identified electrical components is determined based on the identified electrical components and the target temperature rise points. In this way, the temperature rise of each electrical component is detected by the image of the electrical components in the outdoor unit, and the temperature rise of all electrical components contained in the image can be detected, including the temperature rise of electrical components in some special positions, small in size or unable to connect thermocouple wires. This improves the coverage of temperature rise detection of electrical components in the outdoor unit.
  • thermocouple wires which reduces the workload and reduces safety hazards. There is no poor contact or loose contact, and the occurrence of inaccurate temperature rise detection results can be reduced.
  • the method for detecting temperature rise of an air conditioner provided in the embodiments of the present disclosure is applied to an electronic device, and the electronic device can be connected to the air conditioner, camera, etc. by connecting to the Internet, or can be directly connected to the air conditioner, camera, etc. by Bluetooth, wifi, etc.
  • the electronic device is, for example, a computer or a server.
  • the camera is, for example, an infrared camera or a thermal imaging camera.
  • the embodiment of the present disclosure provides a method for detecting temperature rise of an air conditioner, including:
  • Step S101 the electronic device acquires an image containing an electrical component, wherein the electrical component is located in an outdoor unit of an air conditioner.
  • Step S102 the electronic device performs electrical component recognition on the image containing the electrical component to obtain recognized electrical components.
  • Step S103 the electronic device identifies a target temperature rise point in the image, wherein the target temperature rise point is a pixel point in the image that meets a preset condition.
  • Step S104 the electronic device determines the temperature rise of the identified electrical component according to the target temperature rise point and the identified electrical component.
  • the method for detecting temperature rise of an air conditioner provided by the embodiment of the present disclosure is adopted.
  • the electrical components in the image and the target temperature rise points in the image are identified.
  • the temperature rise of the identified electrical components is determined based on the identified electrical components and the target temperature rise points. In this way, the temperature rise of each electrical component is detected by using the image of the electrical components in the outdoor unit, and the temperature rise of all electrical components contained in the image can be detected, thereby improving the coverage rate of temperature rise detection of the electrical components in the outdoor unit.
  • the electronic device is connected to a camera, and the electronic device acquires an image containing the electrical component, including: the electronic device acquires the image containing the electrical component through the camera.
  • the camera is an infrared camera.
  • the camera is a thermal imaging camera.
  • a camera is used to capture images of the interior of the electrical box of the air conditioner outdoor unit to obtain images containing electrical components.
  • the camera is set so that the area captured by the camera can fully cover all electrical components in the electrical box of the air conditioner outdoor unit, so that the captured image can include all electrical components in the electrical box, thereby improving the coverage rate of temperature rise detection of electrical components in the outdoor unit.
  • a pixel coordinate system before acquiring an image containing electrical components, it also includes: establishing a pixel coordinate system and an actual coordinate system of the object.
  • Establishing the pixel coordinate system includes: acquiring an initial image of the interior of the electrical box of the air conditioner outdoor unit through a camera. Taking the upper left corner of the initial image as the origin, horizontally to the right is the x-axis, and the x-axis is the horizontal axis. Vertically downward is the y-axis, and the y-axis is the vertical axis, and a pixel coordinate system is established. Among them, the coordinates in the pixel coordinate system are used to characterize the pixel coordinates of the pixel points in the image.
  • Establishing the actual coordinate system of the object includes: taking the upper left corner of the actual object corresponding to the initial image as the origin. Horizontally to the right is the u-axis, and the u-axis is the horizontal axis. Vertically downward is the v-axis, and the v-axis is the vertical axis, and a real object coordinate system is established. Among them, the coordinates in the real object coordinate system are used to characterize the actual coordinates of the object.
  • the u-axis of the real object coordinate system coincides with the x-axis of the pixel coordinate system, and the v-axis of the real object coordinate system coincides with the y-axis of the pixel coordinate system.
  • the pixel coordinate system and the real object coordinate system can be converted into each other.
  • the electronic device performs electrical component recognition on an image containing electrical components, including: the electronic device inputs the image containing electrical components into a preset electrical component recognition model to perform electrical component recognition, and obtains recognized electrical components.
  • the electrical components in the image are recognized using the electrical component recognition model, and the electrical components in the image can be automatically recognized, which is convenient for detecting the temperature rise of the electrical components.
  • the electrical component recognition model is obtained by: obtaining a first sample image with a first label, inputting the first sample image into a preset convolutional neural network model for training, and obtaining the electrical component recognition model.
  • the first sample image contains an electrical component.
  • the first label includes the name of the electrical component.
  • the first label also includes the pixel coordinates of the electrical component.
  • an image containing electrical components is input into a preset electrical component recognition model to perform electrical component recognition, and the electrical components in the image are recognized, and the recognized electrical components in the image are determined as recognized electrical components.
  • the recognized electrical components include the names and pixel coordinates of the recognized electrical components in the image.
  • the identified electrical component includes the name of the identified electrical component in the image.
  • the acquired image is processed to obtain the pixel coordinates of each pixel in the image.
  • the pixel coordinates of the identified electrical component are determined according to the pixel coordinates of each pixel in the image and the name of the identified electrical component.
  • the actual coordinates of the identified electrical component are determined using two coordinate systems that can be converted, the pixel coordinate system and the actual coordinate system of the object.
  • the electronic device identifies the target temperature rise point in the image, including: the electronic device inputs the image containing the electrical component into a preset temperature recognition model for temperature recognition, and obtains the temperature value corresponding to each pixel point on the image; and determines the pixel point corresponding to the temperature value that meets the preset condition as the target temperature rise point.
  • the temperature recognition model to perform temperature recognition on the pixel points in the image, the temperature value of each pixel point on the image can be automatically obtained, so as to facilitate the determination of the temperature rise of the identified electrical component according to the target temperature rise point.
  • the temperature recognition model is obtained by: obtaining a second sample image with a second label, inputting the second sample image into a preset convolutional neural network model for training, and obtaining the temperature recognition model.
  • the second label is the temperature of each pixel in the second sample image.
  • the electronic device collects a frame of image containing electrical components through a camera at a preset time interval, identifies the target temperature rise point in each frame of image containing electrical components, and determines the temperature rise of the identified electrical components for each frame of image containing electrical components. In this way, the temperature rise of the electrical components in the electrical box of the outdoor unit can be obtained in real time.
  • the electronic device inputs each frame of the image containing the electrical components into the preset temperature recognition model for temperature recognition.
  • the feature network in the temperature recognition model extracts features from the important frame images to obtain the depth feature map of the important frame images.
  • the depth feature map of the important frame images is propagated to the non-important frames corresponding to the important frame images by the optical flow method.
  • the important frame image is the image of the i-th frame containing the electrical components collected, and i is a positive integer.
  • the feature network extracts features from the first frame of the image containing the electrical components, and then the continuous 12 frames after the first frame are no longer feature extracted, but the depth feature map of the first frame is propagated to the continuous 12 frames after the first frame containing the electrical components.
  • the task network in the temperature recognition model performs temperature recognition on the depth feature map of each frame of the image to obtain the temperature value of each pixel in each frame of the image containing the electrical components. In this way, only the important frames are feature extracted, which reduces the computational complexity of the temperature recognition model, thereby improving the efficiency of temperature rise detection.
  • the feature network is a fully convolutional network.
  • the electronic device determines a pixel point corresponding to a temperature value satisfying a preset condition as a target temperature rise point, including: the electronic device determines a pixel point corresponding to a temperature value greater than a first preset threshold value as a target temperature rise point.
  • the first preset threshold is an ambient temperature value.
  • the temperature rise is the difference between the temperature of the electrical component in the working state and the ambient temperature.
  • the pixel points exceeding the ambient temperature are determined as the target temperature rise points. In this way, the temperature rise of the identified electrical component can be determined based on the pixel points exceeding the ambient temperature and the corresponding temperature values.
  • the electronic device determines the pixel points corresponding to the temperature values that meet the preset conditions as the target temperature rise points, including: the electronic device determines the pixel points corresponding to the temperature values greater than the first preset threshold as the temperature rise points, and determines the temperature rise points with temperature values greater than or equal to the second preset threshold as the target temperature rise points.
  • the second preset threshold is greater than the first preset threshold.
  • the electronic device determines the temperature rise of the identified electrical component according to the target temperature rise point and the identified electrical component, including: the electronic device obtains the first pixel coordinate and the second pixel coordinate, matches each first pixel coordinate with each second pixel coordinate, and obtains a matching result.
  • the electronic device determines the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate.
  • the first pixel coordinate is the pixel coordinate of the identified electrical component
  • the second pixel coordinate is the pixel coordinate of the target temperature rise point.
  • the temperature rise of the identified electrical component is determined according to the temperature value of the target temperature rise point. In this way, the temperature rise of all electrical components contained in the image can be detected, and the coverage rate of temperature rise detection of the electrical components in the outdoor unit is improved.
  • each identified electrical component in the image corresponds to one or more pixel coordinates.
  • Each second pixel coordinate is matched with the first pixel coordinate of each identified electrical component to obtain a matching result.
  • the matching result includes: there is a second pixel coordinate that matches the first pixel coordinate, or there is no second pixel coordinate that matches the first pixel coordinate.
  • There are one or more second pixel coordinates included in the first pixel coordinate that is, it is determined that there is a second pixel coordinate that matches the first pixel coordinate.
  • the first pixel coordinate does not include the second pixel coordinate, that is, it is determined that there is no second pixel coordinate that matches the first pixel coordinate.
  • determining the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate includes: determining the temperature value of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate, and determining the temperature value of the identified electrical component as the temperature rise of the identified electrical component. In this way, the temperature rise of all electrical components in the image is obtained, and the coverage of temperature rise detection of outdoor unit electrical components is improved.
  • the temperature of the identified electrical component corresponding to the first pixel coordinate is determined according to the temperature value corresponding to the second pixel coordinate.
  • the temperature rise condition includes: determining the temperature value of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate, and subtracting the temperature value of the identified electrical component from the ambient temperature to obtain the temperature rise condition of the identified electrical component. In this way, the temperature rise condition of all electrical components in the image is obtained, and the coverage rate of temperature rise detection of outdoor unit electrical components is improved.
  • the temperature value of the identified electrical component corresponding to the first pixel coordinate is determined based on the temperature value corresponding to the second pixel coordinate, including: when the first pixel coordinate of the identified electrical component contains multiple second pixel coordinates, the maximum temperature value or the minimum temperature value among the temperature values corresponding to the included second pixel coordinates, or a randomly selected temperature value is used as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
  • the temperature value of the identified electrical component corresponding to the first pixel coordinate is determined based on the temperature value corresponding to the second pixel coordinate, including: when the first pixel coordinate of the identified electrical component contains multiple second pixel coordinates, calculating the average value of the temperature values corresponding to the included second pixel coordinates, and using the average value as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
  • the temperature value of the identified electrical component corresponding to the first pixel coordinate is determined based on the temperature value corresponding to the second pixel coordinate, including: when the first pixel coordinate of the identified electrical component only contains one second pixel coordinate, the temperature value corresponding to the second pixel coordinate is used as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
  • the camera when the outdoor unit of the air conditioner is in operation, the camera is used to collect images of the interior of the outdoor unit electrical box to obtain images containing electrical components. Three electrical components, resistors, capacitors and inductors, and 10 target temperature rise points are identified in the image containing electrical components.
  • the temperature value corresponding to the first target temperature rise point A is 51°C
  • the temperature value corresponding to the second target temperature rise point B is 53°C
  • the temperature value corresponding to the third target temperature rise point C is 52°C
  • the temperature value corresponding to the fourth target temperature rise point D is 53°C
  • the temperature value corresponding to the fifth target temperature rise point E is 55°C
  • the temperature value corresponding to the sixth target temperature rise point F is 51°C
  • the temperature value corresponding to the seventh target temperature rise point G is 52°C
  • the temperature value corresponding to the eighth target temperature rise point H is 57°C
  • the temperature value corresponding to the ninth target temperature rise point I is 54°C
  • the temperature value corresponding to the tenth target temperature rise point J is 56°C.
  • the pixel coordinates corresponding to the resistor include the six target temperature rise points A, C, D, F, G, and H.
  • a temperature value can be randomly selected from the temperature values corresponding to the six target temperature rise points as the temperature value of the resistor, such as selecting 53°C corresponding to D as the temperature value of the resistor.
  • the pixel coordinates corresponding to the capacitor include the three target temperature rise points B, E, and J.
  • the maximum temperature value can be selected from the temperature values corresponding to the three target temperature rise points as the temperature value of the resistor, that is, 56°C corresponding to J is used as the temperature value of the capacitor.
  • the pixel coordinates corresponding to the inductor include the target temperature rise point I, so the 54°C corresponding to I is used as the temperature value of the inductor.
  • the method further includes: determining the identified electrical component in the actual object coordinate system according to the pixel coordinates of the identified electrical component.
  • the actual coordinates of the components are determined, and the actual coordinates of the identified electrical components and the temperature rise of the identified electrical components are displayed to the user. In this way, the user can understand the temperature rise of the electrical components of the outdoor unit in real time.
  • the electronic device is provided with a display screen, or the electronic device is connected to a display device.
  • Displaying the actual coordinates of the identified electrical component and the temperature rise of the identified electrical component to the user includes: displaying the actual coordinates of the identified electrical component and the temperature rise of the identified electrical component through the display device. Or, sending the actual coordinates of the identified electrical component and the temperature rise of the identified electrical component to a user terminal.
  • the user terminal includes a smart phone, etc.
  • the embodiment of the present disclosure provides a system 1 for detecting temperature rise of an air conditioner, comprising: a temperature rise monitoring device 2, an electrical component identification device 3 and a control device 4.
  • the temperature rise monitoring device 2 is configured to obtain an image containing electrical components, which are located in the outdoor unit of the air conditioner; identify the target temperature rise point in the image, and the target temperature rise point is a pixel point in the image that meets a preset condition.
  • the electrical component identification device 3 is configured to identify the electrical components of the image and obtain the identified electrical components.
  • the control device 4 is configured to determine the temperature rise of the identified electrical components based on the target temperature rise point and the identified electrical components.
  • the system for detecting temperature rise of an air conditioner provided by the embodiment of the present disclosure is used to obtain an image containing electrical components in the outdoor unit of the air conditioner, perform electrical component identification and temperature identification on the image containing electrical components, and obtain the identified electrical components and the target temperature rise point.
  • the temperature rise of the identified electrical components is determined based on the identified electrical components and the target temperature rise point. In this way, the temperature rise of each electrical component is detected through the image of the electrical components in the outdoor unit, and the temperature rise of all electrical components contained in the image can be detected, thereby improving the coverage of temperature rise detection of the electrical components in the outdoor unit.
  • FIG3 is a schematic diagram of the structure of the temperature rise monitoring device 2.
  • the temperature rise monitoring device 2 includes: a camera module 5, a temperature recognition module 7, and a second control unit 6.
  • the second control unit 6 is connected to the camera module 5 and the temperature recognition module 7 respectively, and the camera module 5 is connected to the temperature recognition module 7.
  • the second control unit 6 is connected to the control device 4.
  • the camera module 5 is connected to the electrical component recognition device 3.
  • the camera module is configured to acquire images containing electrical components.
  • the camera module is an infrared camera module.
  • the camera is a thermal imaging camera module.
  • a camera module is used to capture images of the interior of the electrical box of the air conditioner outdoor unit to obtain images containing electrical components.
  • the camera module is set so that the area captured by the camera module can fully cover all electrical components in the electrical box of the air conditioner outdoor unit, so that the captured image can include all electrical components in the electrical box, thereby improving the coverage rate of temperature rise detection of electrical components in the outdoor unit.
  • the camera module sends the acquired image containing the electrical components to the temperature recognition module.
  • the temperature recognition module is configured to input the image containing the electrical components into a preset temperature recognition model for temperature recognition, and obtain the temperature value corresponding to each pixel point on the image.
  • the temperature recognition model is used to perform temperature recognition on the pixels in the image, and the temperature value of each pixel on the image can be automatically obtained, so that the temperature rise of the identified electrical components can be determined according to the target temperature rise point.
  • the camera module collects an image containing an electrical component at a preset time interval
  • the temperature recognition module recognizes the target temperature rise point in each image containing an electrical component
  • the control device determines the temperature rise of the recognized electrical component for each image containing an electrical component. In this way, the temperature rise of the electrical components in the electrical box of the outdoor unit can be obtained in real time.
  • the temperature recognition module inputs each frame of the image containing electrical components into the preset temperature recognition model for temperature recognition.
  • the feature network in the temperature recognition model extracts features from the important frame images to obtain the depth feature map of the important frame images.
  • the depth feature map of the important frame images is propagated to the non-important frames corresponding to the important frame images by the optical flow method.
  • the important frame image is the image of the i-th frame containing electrical components collected, and i is a positive integer.
  • the feature network extracts features from the first frame of the image containing electrical components, and then the continuous 12 frames after the first frame are no longer feature extracted, but the depth feature map of the first frame is propagated to the continuous 12 frames after the first frame containing electrical components.
  • the task network in the temperature recognition model performs temperature recognition on the depth feature map of each frame image to obtain the temperature value of each pixel in each frame of the image containing electrical components. In this way, only feature extraction is performed on the important frames, which reduces the amount of calculation of the temperature recognition model, thereby improving the efficiency of temperature rise detection.
  • the feature network is a fully convolutional network.
  • the temperature recognition module is configured to determine the pixel points corresponding to the temperature values satisfying the preset conditions as the target temperature rise points in the following manner: the temperature recognition module determines the pixel points corresponding to the temperature values greater than or equal to the first preset threshold as the target temperature rise points.
  • the first preset threshold is an ambient temperature value.
  • the temperature rise is the difference between the temperature of the electrical component in the working state and the ambient temperature.
  • the pixel points exceeding the ambient temperature are determined as the target temperature rise points. In this way, the temperature rise of the identified electrical component can be determined based on the pixel points exceeding the ambient temperature and the corresponding temperature values.
  • the temperature recognition module determines the pixel points corresponding to the temperature values that meet the preset conditions as the target temperature rise points, including: the temperature recognition module determines the pixel points corresponding to the temperature values greater than the first preset threshold as the temperature rise points, and determines the temperature rise points with temperature values greater than or equal to the second preset threshold as the target temperature rise points.
  • the second preset threshold is greater than the first preset threshold.
  • FIG4 is a schematic diagram of the structure of the electrical component identification device 3.
  • the electrical component identification device 3 includes: an electrical component identification module 9 and a third control unit 8.
  • the third control unit 8 is connected to the control device 4.
  • the electrical component identification module 9 is connected to the third control unit 8 and is connected to the camera module 5.
  • the camera module sends the acquired image containing the electrical component to the electrical component identification module of the electrical component identification device.
  • the electrical component recognition module is configured to input an image containing electrical components into a preset electrical component recognition model to perform electrical component recognition and obtain recognized electrical components.
  • the electrical component recognition model to recognize electrical components in an image, the electrical components in the image can be automatically recognized, which is convenient for detecting the temperature rise of the electrical components.
  • the electrical component recognition module inputs an image containing electrical components into a preset electrical component recognition model to perform electrical component recognition, recognizes the electrical components in the image, and determines the recognized electrical components in the image as recognized electrical components.
  • the recognized electrical components include the names and pixel coordinates of the recognized electrical components in the image.
  • the system for detecting temperature rise of an air conditioner further includes a positioning device 10.
  • the positioning device 10 is connected to the temperature rise monitoring device 2, the electrical component identification device 3 and the control device 4 respectively.
  • FIG6 is a schematic diagram of the structure of the positioning device 10.
  • the positioning device 10 includes: a positioning calculation module 11, a pixel coordinate calculation module 12 and a fourth control unit 13.
  • the fourth control unit 13 is connected to the positioning calculation module 11 and the pixel coordinate calculation module 12.
  • the fourth control unit 13 is connected to the control device 4.
  • the pixel coordinate calculation module 12 is connected to the camera module 5 and the positioning calculation module 11.
  • the positioning calculation module 11 is connected to the electrical component recognition module 9.
  • the camera module sends the acquired image containing the electrical component to the pixel coordinate calculation module of the positioning device.
  • the positioning calculation module is configured to establish a pixel coordinate system and an actual coordinate system of the object.
  • the positioning calculation module establishes the pixel coordinate system in the following manner, including: obtaining an initial image of the interior of the electrical box of the air conditioner outdoor unit through the camera module. Taking the upper left corner of the initial image as the origin, horizontally to the right is the x-axis, and the x-axis is the horizontal axis. Vertically downward is the y-axis, and the y-axis is the vertical axis, and a pixel coordinate system is established. Among them, the coordinates in the pixel coordinate system are used to characterize the pixel coordinates of the pixel points in the image.
  • the positioning calculation module establishes the actual coordinate system of the object in the following manner, including: taking the upper left corner of the actual object corresponding to the initial image as the origin. Horizontally to the right is the u-axis, and the u-axis is the horizontal axis. Vertically downward is the v-axis, and the v-axis is the vertical axis, and a real object coordinate system is established. Among them, the coordinates in the real object coordinate system are used to characterize the real coordinates of the object.
  • the u-axis of the real object coordinate system coincides with the x-axis of the pixel coordinate system
  • the v-axis of the real object coordinate system coincides with the y-axis of the pixel coordinate system.
  • the pixel coordinate system and the real object coordinate system can be converted into each other.
  • the identified electrical component includes the name of the identified electrical component in the image.
  • the electrical component identification module sends the identified electrical component to the positioning calculation module.
  • the pixel coordinate calculation module processes the acquired image to obtain the pixel coordinates of each pixel in the image, and sends the pixel coordinates of each pixel in the image to the positioning calculation module.
  • the positioning calculation module determines the identified electrical component based on the pixel coordinates of each pixel in the image and the name of the identified electrical component.
  • the actual coordinates of the identified electrical components are determined by using the pixel coordinate system and the object's actual coordinate system, two coordinate systems that can be converted.
  • FIG. 7 is a schematic diagram of the structure of the control device 4, and the control device 4 includes: a control module 14, a data processing module 15, a display module 16, and a first control unit 17.
  • the first control unit 17 is connected to the control module 14, the data processing module 15, and the display module 16 respectively.
  • the control module 14 is connected to the second control unit 6, the third control unit 8, and the fourth control unit 13.
  • the data processing module 15 is connected to the display module 16.
  • the control module 14 of the control device sends instructions for controlling the temperature rise monitoring device, the electrical component identification device and the positioning device to start up, respectively, to the second control unit 6 of the temperature rise monitoring device, the third control unit 8 of the electrical component identification device and the fourth control unit 13 of the positioning device.
  • the data processing module 15 is connected to the temperature identification module 7 and the positioning calculation module 11.
  • the positioning calculation module sends the actual coordinates of the identified electrical components to the data processing module.
  • the temperature identification module sends the identified target temperature rise point and the corresponding temperature value to the data processing module.
  • the pixel coordinate calculation module of the positioning device is configured to obtain the first pixel coordinate and the second pixel coordinate, and send the first pixel coordinate and the second pixel coordinate to the positioning calculation module.
  • the positioning calculation module matches each first pixel coordinate with each second pixel coordinate, obtains a matching result, and sends the matching result to the control device.
  • the first pixel coordinate is the pixel coordinate of the identified electrical component
  • the second pixel coordinate is the pixel coordinate of the target temperature rise point.
  • the data processing module of the control device is configured to determine the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate when the matching result is that the second pixel coordinate matches the first pixel coordinate.
  • each identified electrical component in the image corresponds to one or more pixel coordinates.
  • the positioning calculation module matches each second pixel coordinate with the first pixel coordinate of each identified electrical component to obtain a matching result.
  • the matching result includes: there is a second pixel coordinate that matches the first pixel coordinate, or there is no second pixel coordinate that matches the first pixel coordinate.
  • There are one or more second pixel coordinates included in the first pixel coordinate that is, it is determined that there is a second pixel coordinate that matches the first pixel coordinate.
  • the first pixel coordinate does not include the second pixel coordinate, that is, it is determined that there is no second pixel coordinate that matches the first pixel coordinate.
  • the data processing module determines the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate in the following manner, including: determining the temperature value of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate, and determining the temperature value of the identified electrical component as the temperature rise of the identified electrical component. In this way, the temperature rise of all electrical components in the image is obtained, and the coverage of temperature rise detection of outdoor unit electrical components is improved.
  • the data processing module determines the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate in the following manner, including: determining the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate
  • the temperature value of the identified electrical component corresponding to the pixel coordinate is obtained by subtracting the temperature value of the identified electrical component from the ambient temperature to obtain the temperature rise of the identified electrical component. In this way, the temperature rise of all electrical components in the image is obtained, and the coverage of temperature rise detection of outdoor unit electrical components is improved.
  • the data processing module determines the temperature value of the identified electrical component corresponding to the first pixel coordinate based on the temperature value corresponding to the second pixel coordinate in the following manner, including: when the first pixel coordinate of the identified electrical component contains multiple second pixel coordinates, the maximum temperature value or the minimum temperature value among the temperature values corresponding to the included second pixel coordinates, or a randomly selected temperature value as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
  • the data processing module determines the temperature value of the identified electrical component corresponding to the first pixel coordinate based on the temperature value corresponding to the second pixel coordinate in the following manner, including: when the first pixel coordinate of the identified electrical component contains multiple second pixel coordinates, calculating the average value of the temperature values corresponding to the included second pixel coordinates, and using the average value as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
  • the data processing module determines the temperature value of the identified electrical component corresponding to the first pixel coordinate based on the temperature value corresponding to the second pixel coordinate in the following manner, including: when the first pixel coordinate of the identified electrical component contains only one second pixel coordinate, the temperature value corresponding to the second pixel coordinate is used as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
  • the data processing module sends the actual coordinates of the identified electrical component and the temperature rise of the identified electrical component to the display module.
  • the display module is configured to display the actual coordinates of the identified electrical component and the temperature rise of the identified electrical component.
  • the system for detecting temperature rise of an air conditioner further comprises: a power supply device and a communication device.
  • the power supply device is configured to supply power to the system for detecting temperature rise of the air conditioner.
  • the communication device is configured to realize communication connection among the temperature rise monitoring device, the positioning device, the electrical component identification device and the control device.
  • the user when the air conditioner outdoor unit is in operation, the user sends a control instruction to the second control unit of the temperature rise monitoring device through the control module, and the second control unit controls the camera module to collect images and sends the image containing the electrical components to the temperature recognition module, electrical component recognition device and positioning device of the temperature rise monitoring device.
  • the temperature recognition module of the temperature rise monitoring device uses a pre-trained convolutional neural network to perform temperature recognition on the image containing the electrical components to obtain the target temperature rise point.
  • the target temperature rise point and the corresponding temperature value are sent to the control device and the positioning device.
  • the electrical component recognition device performs electrical component recognition on the image containing the electrical components to obtain the recognized electrical components.
  • the recognized electrical components are sent to the positioning device and the control device.
  • the pixel coordinate calculation module of the positioning device obtains the pixel coordinates of each pixel in the image containing the electrical components. The pixel coordinates of each pixel in the image are sent to the positioning calculation module.
  • the positioning calculation module of the positioning device determines the pixel coordinates of the recognized electrical components based on the recognized electrical components and the pixel coordinates of each pixel in the image.
  • the positioning calculation module of the positioning device determines the pixel coordinates of the recognized electrical components based on the target temperature rise point and the pixel coordinates of each pixel in the image.
  • the pixel coordinates of the target temperature rise point are determined by the pixel coordinates of the identified electrical component.
  • the positioning calculation module matches the pixel coordinates of the target temperature rise point and sends the matching result to the control device.
  • the data processing module of the control device When the data processing module of the control device receives the matching result that the pixel coordinates of the electrical component match the pixel coordinates of the target temperature rise point, it determines the temperature rise of the identified electrical component according to the temperature value corresponding to the pixel coordinates of the target temperature rise point, and sends the temperature value of the identified electrical component to the display module for display. In this way, the temperature rise of each electrical component is detected through the image of the electrical component in the outdoor unit, and the temperature rise of all electrical components contained in the image can be detected, thereby improving the coverage rate of temperature rise detection of the electrical components in the outdoor unit.
  • the embodiment of the present disclosure provides a computer program, which, when executed by a computer, enables the computer to implement the above-mentioned method for detecting temperature rise of an air conditioner.
  • An embodiment of the present disclosure provides a computer program product, which includes computer instructions stored on a computer-readable storage medium.
  • the program instructions When executed by a computer, the computer implements the above-mentioned method for detecting temperature rise of an air conditioner.
  • the term “and/or” as used in this application refers to any and all possible combinations of one or more associated listings.
  • the term “comprise” and its variants “comprises” and/or including (comprising) refer to the existence of stated features, wholes, steps, operations, elements, and/or components, but do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and/or these groups.
  • the elements defined by the sentence “comprising a " do not exclude the existence of other identical elements in the process, method or device comprising the elements.
  • each embodiment may focus on the differences from other embodiments, and the same or similar parts between the embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.
  • each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for implementing the specified logical function.
  • the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The present application relates to the technical field of air conditioners, and discloses a method for temperature rise detection of an air conditioner. The method comprises: obtaining an image comprising an electric appliance element, the electric appliance element being located in an outdoor unit of an air conditioner; performing electric appliance element recognition on the image to obtain a recognized electric appliance element; recognizing a target temperature rise point in the image, wherein the target temperature rise point is a pixel point satisfying a preset condition in the image; and determining the temperature rise condition of the recognized electric appliance element according to the target temperature rise point and the recognized electric appliance element. Therefore, the temperature rise condition of each electric appliance element is detected by means of the image of the electric appliance element in the outdoor unit, so that the temperature rise condition of all electric appliance elements comprised in the image can be detected, thereby improving the coverage rate of temperature rise detection of the electric appliance elements in the outdoor unit. The present application further discloses a system for temperature rise detection of an air conditioner.

Description

用于空调器温升检测的方法及系统Method and system for detecting temperature rise of air conditioner
本申请基于申请号为202211267738.5、申请日为2022年10月17日的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此引入本申请作为参考。This application is based on the Chinese patent application with application number 202211267738.5 and application date October 17, 2022, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into this application as a reference.
技术领域Technical Field
本申请涉及空调技术领域,例如涉及一种用于空调器温升检测的方法及系统。The present application relates to the field of air conditioning technology, for example, to a method and system for detecting temperature rise of an air conditioner.
背景技术Background technique
空调器室外机的电器箱体内的电器元件在工作时会释放大量热量。若室外机工作时,电器元件的温度过高,会导致空调器室外机无法正常工作。因此,在出厂前需要对室外机电器箱体内的电器元件进行温升检测,确保空调室外机在使用时电器元件的温度不超过标准。目前,相关技术是通过对室外机电器箱体内的电器元件粘连热电偶线,来测试室外机在运行过程中电器元件的温升情况。The electrical components in the electrical box of the outdoor unit of the air conditioner will release a lot of heat when working. If the temperature of the electrical components is too high when the outdoor unit is working, the outdoor unit of the air conditioner will not work properly. Therefore, it is necessary to test the temperature rise of the electrical components in the electrical box of the outdoor unit before leaving the factory to ensure that the temperature of the electrical components does not exceed the standard when the air conditioner outdoor unit is in use. At present, the relevant technology is to test the temperature rise of the electrical components of the outdoor unit during operation by bonding thermocouple wires to the electrical components in the electrical box of the outdoor unit.
在实现本公开实施例的过程中,发现相关技术中至少存在如下问题:In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:
相关技术只能对与热电偶线相连的电器元件的温升进行检测,针对一些位置特殊、体积较小或者无法连接热电偶线的电器元件难以进行温升检测,使得对室外机内的电器元件进行温升检测的覆盖率低。The related technology can only detect the temperature rise of electrical components connected to thermocouple wires. It is difficult to detect the temperature rise of some electrical components that are in special positions, small in size or cannot be connected to thermocouple wires, resulting in low coverage of temperature rise detection of electrical components in outdoor units.
需要说明的是,在上述背景技术部分公开的信息仅用于加强对本申请的背景的理解,因此可以包括不构成对本领域普通技术人员已知的现有技术的信息。It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field.
发明内容Summary of the invention
为了对披露的实施例的一些方面有基本的理解,下面给出了简单的概括。所述概括不是泛泛评述,也不是要确定关键/重要组成元素或描绘这些实施例的保护范围,而是作为后面的详细说明的序言。In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key/critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.
本公开实施例提供了一种用于空调器温升检测的方法及系统,能够提高对室外机内的电器元件进行温升检测的覆盖率。The embodiments of the present disclosure provide a method and system for temperature rise detection of an air conditioner, which can improve the coverage of temperature rise detection of electrical components in an outdoor unit.
在一些实施例中,所述用于空调器温升检测的方法包括:获取包含电器元件的图像,所述电器元件位于空调器室外机内;对所述图像进行电器元件识别,获得已识别电器元件;识别所述图像中的目标温升点,所述目标温升点为所述图像中满足预设条件的像素点;根 据所述目标温升点和所述已识别电器元件确定已识别电器元件的温升情况。In some embodiments, the method for detecting temperature rise of an air conditioner includes: acquiring an image containing an electrical component, wherein the electrical component is located in an outdoor unit of the air conditioner; performing electrical component recognition on the image to obtain recognized electrical components; recognizing a target temperature rise point in the image, wherein the target temperature rise point is a pixel point in the image that meets a preset condition; and The temperature rise of the identified electrical component is determined according to the target temperature rise point and the identified electrical component.
在一些实施例中,所述对所述图像进行电器元件识别,包括:将所述图像输入预设的电器元件识别模型进行电器元件识别,获得已识别电器元件。In some embodiments, the performing electrical component recognition on the image includes: inputting the image into a preset electrical component recognition model to perform electrical component recognition to obtain recognized electrical components.
在一些实施例中,所述识别所述图像中的目标温升点,包括:将所述图像输入预设的温度识别模型进行温度识别,获得所述图像上各像素点对应的温度值;将满足预设条件的温度值对应的像素点确定为目标温升点。In some embodiments, identifying the target temperature rise point in the image includes: inputting the image into a preset temperature recognition model for temperature recognition to obtain the temperature value corresponding to each pixel point on the image; and determining the pixel point corresponding to the temperature value that meets the preset conditions as the target temperature rise point.
在一些实施例中,所述将满足预设条件的温度值对应的像素点确定为目标温升点,包括:将大于或等于第一预设阈值的温度值对应的像素点确定为目标温升点。In some embodiments, determining the pixel point corresponding to the temperature value satisfying the preset condition as the target temperature rise point includes: determining the pixel point corresponding to the temperature value greater than or equal to the first preset threshold as the target temperature rise point.
在一些实施例中,所述根据所述目标温升点和所述已识别电器元件确定已识别电器元件的温升情况,包括:获取第一像素坐标和第二像素坐标;所述第一像素坐标为所述已识别电器元件的像素坐标,所述第二像素坐标为所述目标温升点的像素坐标;将各所述第一像素坐标与各所述第二像素坐标进行匹配,获得匹配结果;在所述匹配结果为存在第二像素坐标与第一像素坐标匹配的情况下,根据所述第二像素坐标对应的温度值确定所述第一像素坐标对应的已识别电器元件的温升情况。In some embodiments, determining the temperature rise of the identified electrical component based on the target temperature rise point and the identified electrical component includes: obtaining a first pixel coordinate and a second pixel coordinate; the first pixel coordinate is the pixel coordinate of the identified electrical component, and the second pixel coordinate is the pixel coordinate of the target temperature rise point; matching each of the first pixel coordinates with each of the second pixel coordinates to obtain a matching result; when the matching result is that the second pixel coordinate matches the first pixel coordinate, determining the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate.
在一些实施例中,所述用于空调器温升检测的系统包括:温升监测装置,被配置为获取包含电器元件的图像,所述电器元件位于空调器室外机内;识别所述图像中的目标温升点,所述目标温升点为所述图像中满足预设条件的像素点;电器元件识别装置,被配置为对所述图像进行电器元件识别,获得已识别电器元件;控制装置,被配置为根据所述目标温升点和所述已识别电器元件确定已识别电器元件的温升情况。In some embodiments, the system for detecting temperature rise of an air conditioner includes: a temperature rise monitoring device, configured to obtain an image containing electrical components, wherein the electrical components are located in an outdoor unit of an air conditioner; identifying a target temperature rise point in the image, wherein the target temperature rise point is a pixel point in the image that meets a preset condition; an electrical component identification device, configured to identify electrical components in the image to obtain identified electrical components; and a control device, configured to determine the temperature rise of the identified electrical components based on the target temperature rise point and the identified electrical components.
在一些实施例中,所述电器元件识别装置包括:电器元件识别模块,被配置为将所述图像输入预设的电器元件识别模型进行电器元件识别,获得已识别电器元件。In some embodiments, the electrical component identification device includes: an electrical component identification module configured to input the image into a preset electrical component identification model to perform electrical component identification and obtain an identified electrical component.
在一些实施例中,所述温升监测装置包括:温度识别模块,被配置为将所述图像输入预设的温度识别模型进行温度识别,获得所述图像上各像素点对应的温度值;将满足预设条件的温度值对应的像素点确定为目标温升点。In some embodiments, the temperature rise monitoring device includes: a temperature recognition module, configured to input the image into a preset temperature recognition model for temperature recognition, and obtain the temperature value corresponding to each pixel point on the image; and determine the pixel point corresponding to the temperature value that meets the preset conditions as the target temperature rise point.
在一些实施例中,所述温度识别模块被配置为通过以下方式将满足预设条件的温度值对应的像素点确定为目标温升点:将大于或等于第一预设阈值的温度值对应的像素点确定为目标温升点。In some embodiments, the temperature identification module is configured to determine the pixel points corresponding to the temperature values satisfying the preset conditions as the target temperature rise points in the following manner: determine the pixel points corresponding to the temperature values greater than or equal to the first preset threshold as the target temperature rise points.
在一些实施例中,所述用于空调器温升检测的系统还包括:定位装置,被配置为获取第一像素坐标和第二像素坐标;将各所述第一像素坐标与各所述第二像素坐标进行匹配,获得匹配结果;将所述匹配结果发送给所述控制模块;其中,所述第一像素坐标为所述已识别电器元件的像素坐标,所述第二像素坐标为所述目标温升点的像素坐标;所述控制装 置,被配置为在所述匹配结果为存在第二像素坐标与第一像素坐标匹配的情况下,根据所述第二像素坐标对应的温度值确定所述第一像素坐标对应的已识别电器元件的温升情况。In some embodiments, the system for detecting temperature rise of an air conditioner further comprises: a positioning device configured to obtain a first pixel coordinate and a second pixel coordinate; match each of the first pixel coordinates with each of the second pixel coordinates to obtain a matching result; and send the matching result to the control module; wherein the first pixel coordinate is the pixel coordinate of the identified electrical component, and the second pixel coordinate is the pixel coordinate of the target temperature rise point; the control module The device is configured to determine the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate when the matching result is that the second pixel coordinate matches the first pixel coordinate.
本公开实施例提供的用于空调器温升检测的方法及系统,可以实现以下技术效果:通过获取空调器室外机内电器元件的图像,并对获取的图像进行识别,识别出图像中的电器元件和图像中的目标温升点。根据已识别电器元件和目标温升点确定识别出的电器元件的温升情况。这样,通过室外机内电器元件的图像来检测各电器元件的温升情况,能够对图像中包含的所有电器元件的温升情况进行检测,从而提高了对室外机内的电器元件进行温升检测的覆盖率。The method and system for detecting the temperature rise of an air conditioner provided by the embodiments of the present disclosure can achieve the following technical effects: by acquiring an image of the electrical components in the outdoor unit of the air conditioner and identifying the acquired image, the electrical components in the image and the target temperature rise points in the image are identified. The temperature rise of the identified electrical components is determined based on the identified electrical components and the target temperature rise points. In this way, the temperature rise of each electrical component is detected through the image of the electrical components in the outdoor unit, and the temperature rise of all electrical components contained in the image can be detected, thereby improving the coverage of temperature rise detection of the electrical components in the outdoor unit.
以上的总体描述和下文中的描述仅是示例性和解释性的,不用于限制本申请。The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
一个或多个实施例通过与之对应的附图进行示例性说明,这些示例性说明和附图并不构成对实施例的限定,附图中具有相同参考数字标号的元件示为类似的元件,附图不构成比例限制,并且其中:One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:
图1是本公开实施例提供的一个用于空调器温升检测的方法的示意图;FIG1 is a schematic diagram of a method for detecting temperature rise of an air conditioner provided by an embodiment of the present disclosure;
图2是本公开实施例提供的一个用于空调器温升检测系统的结构示意图;FIG2 is a schematic structural diagram of a temperature rise detection system for an air conditioner provided by an embodiment of the present disclosure;
图3是本公开实施例提供的温升监测装置的结构示意图;FIG3 is a schematic diagram of the structure of a temperature rise monitoring device provided in an embodiment of the present disclosure;
图4是本公开实施例提供的电器元件识别装置的结构示意图;FIG4 is a schematic diagram of the structure of an electrical component identification device provided by an embodiment of the present disclosure;
图5是本公开实施例提供的另一个用于空调器温升检测系统的结构示意图;FIG5 is a schematic structural diagram of another temperature rise detection system for an air conditioner provided by an embodiment of the present disclosure;
图6是本公开实施例提供的定位装置的结构示意图;FIG6 is a schematic diagram of the structure of a positioning device provided in an embodiment of the present disclosure;
图7是本公开实施例提供的控制装置的结构示意图。FIG. 7 is a schematic diagram of the structure of a control device provided in an embodiment of the present disclosure.
具体实施方式Detailed ways
为了能够更加详尽地了解本公开实施例的特点与技术内容,下面结合附图对本公开实施例的实现进行详细阐述,所附附图仅供参考说明之用,并非用来限定本公开实施例。在以下的技术描述中,为方便解释起见,通过多个细节以提供对所披露实施例的充分理解。然而,在没有这些细节的情况下,一个或多个实施例仍然可以实施。在其它情况下,为简化附图,熟知的结构和装置可以简化展示。In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.
本公开实施例的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本公开实施例的实施例。此外,术语“包括”和“具有”以 及他们的任何变形,意图在于覆盖不排他的包含。The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances to describe the embodiments of the present disclosure herein. In addition, the terms "including" and "having" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. and any variations thereof, are intended to cover a non-exclusive inclusion.
除非另有说明,术语“多个”表示两个或两个以上。Unless otherwise stated, the term "plurality" means two or more.
本公开实施例中,字符“/”表示前后对象是一种“或”的关系。例如,A/B表示:A或B。In the embodiment of the present disclosure, the character "/" indicates that the preceding and following objects are in an "or" relationship. For example, A/B indicates: A or B.
术语“和/或”是一种描述对象的关联关系,表示可以存在三种关系。例如,A和/或B,表示:A或B,或,A和B这三种关系。The term "and/or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and/or B means: A or B, or, A and B.
术语“对应”可以指的是一种关联关系或绑定关系,A与B相对应指的是A与B之间是一种关联关系或绑定关系。The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.
通过粘连热电偶线的方式对室外机电器箱体内的电器元件进行温升检测,只能检测与热电偶线相连的电器元件,针对特殊位置、体积较小或者无法连接热电偶线的电器元件难以进行温升检测,使得温升检测的覆盖率低。同时,通过粘连热电偶线的方式进行温升检测,需要多点布置热电偶线,工作繁琐,工作量大,导致热电偶线混乱,增加安全隐患。热电偶线也可能会出现接触不良或者接触松动的情况,从而出现温升检测结果不准确的情况。本申请通过红外摄像机对空调器室外机内的电器元件采集图像,识别出图像中的电器元件和图像中的目标温升点。根据已识别电器元件和目标温升点确定识别出的电器元件的温升情况。这样,通过室外机内电器元件的图像来检测各电器元件的温升情况,能够对图像中包含的所有电器元件的温升情况进行检测,包括对一些特殊位置、体积较小或者无法连接热电偶线的电器元件都能检测其温升情况。从而提高了对室外机内的电器元件进行温升检测的覆盖率。同时,通过对室外机内电器元件的图像来检测各电器元件的温升情况,不需要人工布置热电偶线,降低了工作量,同时还能够减少安全隐患。不存在接触不良或者接触松动的情况,还能够减少出现温升检测结果不准确的情况。By bonding thermocouple wires to detect the temperature rise of electrical components in the electrical box of the outdoor unit, only the electrical components connected to the thermocouple wires can be detected. It is difficult to perform temperature rise detection on electrical components in special positions, small in size or unable to connect thermocouple wires, resulting in low coverage of temperature rise detection. At the same time, by bonding thermocouple wires to detect temperature rise, it is necessary to arrange thermocouple wires at multiple points, which is cumbersome and labor-intensive, resulting in confusion of thermocouple wires and increased safety hazards. Thermocouple wires may also have poor contact or loose contact, resulting in inaccurate temperature rise detection results. The present application uses an infrared camera to capture images of electrical components in the outdoor unit of the air conditioner, and identifies the electrical components in the image and the target temperature rise points in the image. The temperature rise of the identified electrical components is determined based on the identified electrical components and the target temperature rise points. In this way, the temperature rise of each electrical component is detected by the image of the electrical components in the outdoor unit, and the temperature rise of all electrical components contained in the image can be detected, including the temperature rise of electrical components in some special positions, small in size or unable to connect thermocouple wires. This improves the coverage of temperature rise detection of electrical components in the outdoor unit. At the same time, by detecting the temperature rise of each electrical component through the image of the electrical components in the outdoor unit, there is no need to manually arrange thermocouple wires, which reduces the workload and reduces safety hazards. There is no poor contact or loose contact, and the occurrence of inaccurate temperature rise detection results can be reduced.
本公开实施例提供的用于空调器温升检测的方法应用于电子设备,电子设备可以通过连接互联网,与空调器、摄像机等进行通信连接,也可以直接通过蓝牙、wifi等方式与如上的空调器、摄像机等进行通信连接。在一些实施例中,电子设备例如为计算机或服务器等。摄像机例如为红外摄像机或热成像摄像机。The method for detecting temperature rise of an air conditioner provided in the embodiments of the present disclosure is applied to an electronic device, and the electronic device can be connected to the air conditioner, camera, etc. by connecting to the Internet, or can be directly connected to the air conditioner, camera, etc. by Bluetooth, wifi, etc. In some embodiments, the electronic device is, for example, a computer or a server. The camera is, for example, an infrared camera or a thermal imaging camera.
结合图1所示,本公开实施例提供一种用于空调器温升检测的方法,包括:As shown in FIG1 , the embodiment of the present disclosure provides a method for detecting temperature rise of an air conditioner, including:
步骤S101,电子设备获取包含电器元件的图像。其中,电器元件位于空调器室外机内。Step S101, the electronic device acquires an image containing an electrical component, wherein the electrical component is located in an outdoor unit of an air conditioner.
步骤S102,电子设备对包含电器元件的图像进行电器元件识别,获得已识别电器元件。Step S102: the electronic device performs electrical component recognition on the image containing the electrical component to obtain recognized electrical components.
步骤S103,电子设备识别图像中的目标温升点。其中,目标温升点为图像中满足预设条件的像素点。 Step S103, the electronic device identifies a target temperature rise point in the image, wherein the target temperature rise point is a pixel point in the image that meets a preset condition.
步骤S104,电子设备根据目标温升点和已识别电器元件确定已识别电器元件的温升情况。Step S104: the electronic device determines the temperature rise of the identified electrical component according to the target temperature rise point and the identified electrical component.
采用本公开实施例提供的用于空调器温升检测的方法,通过获取空调器室外机内电器元件的图像,并对获取的图像进行识别,识别出图像中的电器元件和图像中的目标温升点。根据已识别电器元件和目标温升点确定识别出的电器元件的温升情况。这样,通过室外机内电器元件的图像来检测各电器元件的温升情况,能够对图像中包含的所有电器元件的温升情况进行检测,从而提高了对室外机内的电器元件进行温升检测的覆盖率。The method for detecting temperature rise of an air conditioner provided by the embodiment of the present disclosure is adopted. By acquiring an image of electrical components in an outdoor unit of the air conditioner and identifying the acquired image, the electrical components in the image and the target temperature rise points in the image are identified. The temperature rise of the identified electrical components is determined based on the identified electrical components and the target temperature rise points. In this way, the temperature rise of each electrical component is detected by using the image of the electrical components in the outdoor unit, and the temperature rise of all electrical components contained in the image can be detected, thereby improving the coverage rate of temperature rise detection of the electrical components in the outdoor unit.
进一步地,电子设备连接摄像机,电子设备获取包含电器元件的图像,包括:电子设备通过摄像机获取包含电器元件的图像。可选地,摄像机为红外摄像机。或者,摄像机为热成像摄像机。Further, the electronic device is connected to a camera, and the electronic device acquires an image containing the electrical component, including: the electronic device acquires the image containing the electrical component through the camera. Optionally, the camera is an infrared camera. Alternatively, the camera is a thermal imaging camera.
在一些实施例中,利用摄像机对空调器室外机电器箱体内部进行图像采集,获取包含电器元件的图像。通过对摄像机进行设置,使摄像机拍摄到的区域能够全部覆盖空调器室外机电器箱体内的所有电器元件,从而使得采集到的图像,能够包含电器箱体内的所有电器元件,从而能够提高对室外机内的电器元件进行温升检测的覆盖率。In some embodiments, a camera is used to capture images of the interior of the electrical box of the air conditioner outdoor unit to obtain images containing electrical components. The camera is set so that the area captured by the camera can fully cover all electrical components in the electrical box of the air conditioner outdoor unit, so that the captured image can include all electrical components in the electrical box, thereby improving the coverage rate of temperature rise detection of electrical components in the outdoor unit.
在一些实施例中,获取包含电器元件的图像之前,还包括:建立像素坐标系和物体实际坐标系。建立像素坐标系,包括:通过摄像机获取空调器室外机电器箱体内部的初始图像。以初始图像的左上角为原点,水平向右为x轴,x轴为横轴。竖直向下为y轴,y轴为纵轴,建立像素坐标系。其中,像素坐标系中的坐标用于表征图像中像素点的像素坐标。建立物体实际坐标系,包括:以初始图像对应的实际物体的左上角为原点。水平向右为u轴,u轴为横轴。竖直向下为v轴,v轴为纵轴,建立实际物体坐标系。其中,实际物体坐标系中的坐标用于表征物体的实际坐标。实际物体坐标系的u轴与像素坐标系的x轴相重合,实际物体坐标系的v轴与像素坐标系的y轴相重合。像素坐标系和实际物体坐标系可以相互转化。In some embodiments, before acquiring an image containing electrical components, it also includes: establishing a pixel coordinate system and an actual coordinate system of the object. Establishing the pixel coordinate system includes: acquiring an initial image of the interior of the electrical box of the air conditioner outdoor unit through a camera. Taking the upper left corner of the initial image as the origin, horizontally to the right is the x-axis, and the x-axis is the horizontal axis. Vertically downward is the y-axis, and the y-axis is the vertical axis, and a pixel coordinate system is established. Among them, the coordinates in the pixel coordinate system are used to characterize the pixel coordinates of the pixel points in the image. Establishing the actual coordinate system of the object includes: taking the upper left corner of the actual object corresponding to the initial image as the origin. Horizontally to the right is the u-axis, and the u-axis is the horizontal axis. Vertically downward is the v-axis, and the v-axis is the vertical axis, and a real object coordinate system is established. Among them, the coordinates in the real object coordinate system are used to characterize the actual coordinates of the object. The u-axis of the real object coordinate system coincides with the x-axis of the pixel coordinate system, and the v-axis of the real object coordinate system coincides with the y-axis of the pixel coordinate system. The pixel coordinate system and the real object coordinate system can be converted into each other.
可选地,电子设备对包含电器元件的图像进行电器元件识别,包括:电子设备将包含电器元件的图像输入预设的电器元件识别模型进行电器元件识别,获得已识别电器元件。这样,利用电器元件识别模型对图像中的电器元件进行识别,能够自动识别出图像中的电器元件,便于对电器元件的温升情况进行检测。Optionally, the electronic device performs electrical component recognition on an image containing electrical components, including: the electronic device inputs the image containing electrical components into a preset electrical component recognition model to perform electrical component recognition, and obtains recognized electrical components. In this way, the electrical components in the image are recognized using the electrical component recognition model, and the electrical components in the image can be automatically recognized, which is convenient for detecting the temperature rise of the electrical components.
其中,电器元件识别模型通过以下方式获取:获取带有第一标签的第一样本图像,将第一样本图像输入预设的卷积神经网络模型进行训练,获得电器元件识别模型。其中,第一样本图像中包含有电器元件。第一标签包括电器元件的名称。可选地,第一标签还包括电器元件的像素坐标。 The electrical component recognition model is obtained by: obtaining a first sample image with a first label, inputting the first sample image into a preset convolutional neural network model for training, and obtaining the electrical component recognition model. The first sample image contains an electrical component. The first label includes the name of the electrical component. Optionally, the first label also includes the pixel coordinates of the electrical component.
在一些实施例中,将包含电器元件的图像输入预设的电器元件识别模型进行电器元件识别,识别出图像中的电器元件,将图像中识别出的电器元件确定为已识别电器元件。其中,已识别电器元件包括图像中已识别电器元件的名称和像素坐标。In some embodiments, an image containing electrical components is input into a preset electrical component recognition model to perform electrical component recognition, and the electrical components in the image are recognized, and the recognized electrical components in the image are determined as recognized electrical components. The recognized electrical components include the names and pixel coordinates of the recognized electrical components in the image.
在一些实施例中,已识别电器元件包括图像中已识别电器元件的名称。并对获取的图像进行处理,获得图像中各像素点的像素坐标。根据图像中各像素点的像素坐标和已识别电器元件的名称,确定出已识别电器元件的像素坐标。利用像素坐标系和物体实际坐标系这两个可以转换的坐标系来确定出已识别电器元件的实际坐标。In some embodiments, the identified electrical component includes the name of the identified electrical component in the image. The acquired image is processed to obtain the pixel coordinates of each pixel in the image. The pixel coordinates of the identified electrical component are determined according to the pixel coordinates of each pixel in the image and the name of the identified electrical component. The actual coordinates of the identified electrical component are determined using two coordinate systems that can be converted, the pixel coordinate system and the actual coordinate system of the object.
可选地,电子设备识别图像中的目标温升点,包括:电子设备将包含电器元件的图像输入预设的温度识别模型进行温度识别,获得图像上各像素点对应的温度值;将满足预设条件的温度值对应的像素点确定为目标温升点。这样,利用温度识别模型对图像中的像素点进行温度识别,能够自动获取图像上各像素点的温度值,从而便于根据目标温升点确定出已识别电器元件的温升情况。Optionally, the electronic device identifies the target temperature rise point in the image, including: the electronic device inputs the image containing the electrical component into a preset temperature recognition model for temperature recognition, and obtains the temperature value corresponding to each pixel point on the image; and determines the pixel point corresponding to the temperature value that meets the preset condition as the target temperature rise point. In this way, by using the temperature recognition model to perform temperature recognition on the pixel points in the image, the temperature value of each pixel point on the image can be automatically obtained, so as to facilitate the determination of the temperature rise of the identified electrical component according to the target temperature rise point.
其中,温度识别模型通过以下方式获取:获取带有第二标签的第二样本图像,将第二样本图像输入预设的卷积神经网络模型进行训练,获得温度识别模型。其中,第二标签为第二样本图像中各像素点的温度。The temperature recognition model is obtained by: obtaining a second sample image with a second label, inputting the second sample image into a preset convolutional neural network model for training, and obtaining the temperature recognition model. The second label is the temperature of each pixel in the second sample image.
在一些实施例中,电子设备通过摄像机每隔预设时长采集一帧包含电器元件的图像,电子设备识别每一帧包含电器元件的图像中的目标温升点,针对每一帧包含电器元件的图像确定已识别电器元件的温升情况。这样,能够实时获取室外机电器箱体内电器元件的温升情况。In some embodiments, the electronic device collects a frame of image containing electrical components through a camera at a preset time interval, identifies the target temperature rise point in each frame of image containing electrical components, and determines the temperature rise of the identified electrical components for each frame of image containing electrical components. In this way, the temperature rise of the electrical components in the electrical box of the outdoor unit can be obtained in real time.
电子设备将每一帧包含电器元件的图像都输入预设的温度识别模型进行温度识别。温度识别模型中的特征网络对重要帧图像进行特征提取,获得重要帧图像的深度特征图。并通过光流法将重要帧图像的深度特征图传播给该重要帧图像对应的非重要帧。其中,重要帧图像为采集的第i帧包含电器元件的图像,i为正整数。该重要帧图像对应的非重要帧为该重要帧图像之后的第k帧包含电器元件的图像,k=i+x,1≤x≤12,且x为正整数,例如,特征网络对第一帧包含电器元件的图像进行了特征提取,则该第一帧后的连续12帧都不再进行特征提取,而是将第一帧的深度特征图传播给该第一帧后的连续12帧包含电器元件的图像。温度识别模型中的任务网络对每一帧图像的深度特征图进行温度识别,获得每一帧包含电器元件的图像中各像素点的温度值。这样,只对重要帧进行特征提取,降低了温度识别模型的运算量,从而提高温升检测的效率。其中,特征网络为完全卷积网络。The electronic device inputs each frame of the image containing the electrical components into the preset temperature recognition model for temperature recognition. The feature network in the temperature recognition model extracts features from the important frame images to obtain the depth feature map of the important frame images. The depth feature map of the important frame images is propagated to the non-important frames corresponding to the important frame images by the optical flow method. Among them, the important frame image is the image of the i-th frame containing the electrical components collected, and i is a positive integer. The non-important frame corresponding to the important frame image is the image of the k-th frame containing the electrical components after the important frame image, k=i+x, 1≤x≤12, and x is a positive integer. For example, the feature network extracts features from the first frame of the image containing the electrical components, and then the continuous 12 frames after the first frame are no longer feature extracted, but the depth feature map of the first frame is propagated to the continuous 12 frames after the first frame containing the electrical components. The task network in the temperature recognition model performs temperature recognition on the depth feature map of each frame of the image to obtain the temperature value of each pixel in each frame of the image containing the electrical components. In this way, only the important frames are feature extracted, which reduces the computational complexity of the temperature recognition model, thereby improving the efficiency of temperature rise detection. Among them, the feature network is a fully convolutional network.
可选地,电子设备将满足预设条件的温度值对应的像素点确定为目标温升点,包括:电子设备将大于第一预设阈值的温度值对应的像素点确定为目标温升点。 Optionally, the electronic device determines a pixel point corresponding to a temperature value satisfying a preset condition as a target temperature rise point, including: the electronic device determines a pixel point corresponding to a temperature value greater than a first preset threshold value as a target temperature rise point.
在一些实施例中,第一预设阈值为环境温度值。温升为工作状态下电器元件的温度超过环境温度的差值。将超过环境温度的像素点确定为目标温升点。这样,根据超过环境温度的像素点及对应的温度值能够确定出已识别电器元件的温升情况。In some embodiments, the first preset threshold is an ambient temperature value. The temperature rise is the difference between the temperature of the electrical component in the working state and the ambient temperature. The pixel points exceeding the ambient temperature are determined as the target temperature rise points. In this way, the temperature rise of the identified electrical component can be determined based on the pixel points exceeding the ambient temperature and the corresponding temperature values.
可选地,电子设备将满足预设条件的温度值对应的像素点确定为目标温升点,包括:电子设备将大于第一预设阈值的温度值对应的像素点确定为温升点,将温度值大于或等于第二预设阈值的温升点确定为目标温升点。其中,第二预设阈值大于第一预设阈值。空调器室外机工作时,电器箱体内的电器元件会有一定温升,但如果电器元件的温度超过一定阈值,例如大于或等于第二预设阈值,则该电器元件工作异常。这样,根据温度值大于或等于第二预设阈值的像素点来确定已识别电器元件的温升情况,能够直接确定出已识别电器元件中处于工作异常的电器元件。Optionally, the electronic device determines the pixel points corresponding to the temperature values that meet the preset conditions as the target temperature rise points, including: the electronic device determines the pixel points corresponding to the temperature values greater than the first preset threshold as the temperature rise points, and determines the temperature rise points with temperature values greater than or equal to the second preset threshold as the target temperature rise points. Among them, the second preset threshold is greater than the first preset threshold. When the air conditioner outdoor unit is working, the electrical components in the electrical box will have a certain temperature rise, but if the temperature of the electrical components exceeds a certain threshold, for example, greater than or equal to the second preset threshold, the electrical components will work abnormally. In this way, the temperature rise of the identified electrical components is determined based on the pixel points with temperature values greater than or equal to the second preset threshold, and the electrical components that are working abnormally among the identified electrical components can be directly determined.
可选地,电子设备根据目标温升点和已识别电器元件确定已识别电器元件的温升情况,包括:电子设备获取第一像素坐标和第二像素坐标,将各第一像素坐标与各第二像素坐标进行匹配,获得匹配结果。在匹配结果为存在第二像素坐标与第一像素坐标匹配的情况下,电子设备根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温升情况。其中,第一像素坐标为已识别电器元件的像素坐标,第二像素坐标为目标温升点的像素坐标。通过获取空调器室外机内电器元件的图像,并对获取的图像进行识别,识别出图像中所有的电器元件和图像中的目标温升点。通过已识别电器元件的像素坐标和目标温升点的像素坐标的匹配结果,根据目标温升点的温度值来确定识别出的电器元件的温升情况。这样,能够实现对图像中包含的所有电器元件的温升情况进行检测,提高了对室外机内的电器元件进行温升检测的覆盖率。Optionally, the electronic device determines the temperature rise of the identified electrical component according to the target temperature rise point and the identified electrical component, including: the electronic device obtains the first pixel coordinate and the second pixel coordinate, matches each first pixel coordinate with each second pixel coordinate, and obtains a matching result. When the matching result is that the second pixel coordinate matches the first pixel coordinate, the electronic device determines the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate. Among them, the first pixel coordinate is the pixel coordinate of the identified electrical component, and the second pixel coordinate is the pixel coordinate of the target temperature rise point. By acquiring an image of the electrical components in the outdoor unit of the air conditioner and identifying the acquired image, all the electrical components in the image and the target temperature rise point in the image are identified. Through the matching result of the pixel coordinates of the identified electrical components and the pixel coordinates of the target temperature rise point, the temperature rise of the identified electrical component is determined according to the temperature value of the target temperature rise point. In this way, the temperature rise of all electrical components contained in the image can be detected, and the coverage rate of temperature rise detection of the electrical components in the outdoor unit is improved.
在一些实施例中,图像中的各已识别电器元件分别对应有一个或多个像素坐标。将各第二像素坐标分别与各已识别电器元件的第一像素坐标进行匹配,获得匹配结果。其中,匹配结果包括:存在第二像素坐标与第一像素坐标匹配,或,不存在第二像素坐标与第一像素坐标匹配。其中,存在一个或多个第二像素坐标被包含于第一像素坐标中,即确定存在第二像素坐标与第一像素坐标匹配。第一像素坐标中没有包含第二像素坐标,即确定不存在第二像素坐标与第一像素坐标匹配。In some embodiments, each identified electrical component in the image corresponds to one or more pixel coordinates. Each second pixel coordinate is matched with the first pixel coordinate of each identified electrical component to obtain a matching result. The matching result includes: there is a second pixel coordinate that matches the first pixel coordinate, or there is no second pixel coordinate that matches the first pixel coordinate. There are one or more second pixel coordinates included in the first pixel coordinate, that is, it is determined that there is a second pixel coordinate that matches the first pixel coordinate. The first pixel coordinate does not include the second pixel coordinate, that is, it is determined that there is no second pixel coordinate that matches the first pixel coordinate.
可选地,根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温升情况,包括:根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温度值,将已识别电器元件的温度值确定为识别电器元件的温升情况。这样,实现了对图像中所有电器元件的温升情况的获取,提高了对室外机电器元件温升检测的覆盖率。Optionally, determining the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate includes: determining the temperature value of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate, and determining the temperature value of the identified electrical component as the temperature rise of the identified electrical component. In this way, the temperature rise of all electrical components in the image is obtained, and the coverage of temperature rise detection of outdoor unit electrical components is improved.
可选地,根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的 温升情况,包括:根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温度值,将已识别电器元件的温度值与环境温度作差,获得已识别电器元件的温升情况。这样,实现了对图像中所有电器元件的温升情况的获取,提高了对室外机电器元件温升检测的覆盖率。Optionally, the temperature of the identified electrical component corresponding to the first pixel coordinate is determined according to the temperature value corresponding to the second pixel coordinate. The temperature rise condition includes: determining the temperature value of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate, and subtracting the temperature value of the identified electrical component from the ambient temperature to obtain the temperature rise condition of the identified electrical component. In this way, the temperature rise condition of all electrical components in the image is obtained, and the coverage rate of temperature rise detection of outdoor unit electrical components is improved.
可选地,根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温度值,包括:在已识别电器元件的第一像素坐标中包含有多个第二像素坐标的情况下,将被包含的第二像素坐标对应的温度值中的最大温度值,或,最小温度值,或,随机选取一个温度值作为第一像素坐标对应的已识别电器元件的温度值。Optionally, the temperature value of the identified electrical component corresponding to the first pixel coordinate is determined based on the temperature value corresponding to the second pixel coordinate, including: when the first pixel coordinate of the identified electrical component contains multiple second pixel coordinates, the maximum temperature value or the minimum temperature value among the temperature values corresponding to the included second pixel coordinates, or a randomly selected temperature value is used as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
可选地,根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温度值,包括:在已识别电器元件的第一像素坐标中包含有多个第二像素坐标的情况下,计算被包含的第二像素坐标对应的温度值的平均值,将该平均值作为第一像素坐标对应的已识别电器元件的温度值。Optionally, the temperature value of the identified electrical component corresponding to the first pixel coordinate is determined based on the temperature value corresponding to the second pixel coordinate, including: when the first pixel coordinate of the identified electrical component contains multiple second pixel coordinates, calculating the average value of the temperature values corresponding to the included second pixel coordinates, and using the average value as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
可选地,根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温度值,包括:在已识别电器元件的第一像素坐标中只包含一个第二像素坐标的情况下,将该第二像素坐标对应的温度值作为第一像素坐标对应的已识别电器元件的温度值。Optionally, the temperature value of the identified electrical component corresponding to the first pixel coordinate is determined based on the temperature value corresponding to the second pixel coordinate, including: when the first pixel coordinate of the identified electrical component only contains one second pixel coordinate, the temperature value corresponding to the second pixel coordinate is used as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
在一些实施例中,在空调器室外机处于工作的状态下,通过摄像机对室外机电器箱体内部进行图像采集,获取包含电器元件的图像。在包含电器元件的图像中识别到有3个电器元件,电阻、电容和电感,以及10个目标温升点。其中,第一个目标温升点A对应的温度值为51℃,第二个目标温升点B对应的温度值为53℃,第三个目标温升点C对应的温度值为52℃,第四个目标温升点D对应的温度值为53℃,第五个目标温升点E对应的温度值为55℃,第六个目标温升点F对应的温度值为51℃,第七个目标温升点G对应的温度值为52℃,第八个目标温升点H对应的温度值为57℃,第九个目标温升点I对应的温度值为54℃,第十个目标温升点J对应的温度值为56℃。将这10个目标温升点分别与电阻、电容、电感对应的像素坐标进行匹配。其中,电阻对应的像素坐标中包含有A、C、D、F、G、H这6个目标温升点,可以从这6个目标温升点对应的温度值中随机选取一个温度值作为电阻的温度值,如选择D对应的53℃作为电阻的温度值。电容对应的像素坐标中包含有B、E、J这3个目标温升点,可以从这3个目标温升点对应的温度值中选取最大温度值作为电阻的温度值,即J对应的56℃作为电容的温度值。电感对应的像素坐标中包含有I这个目标温升点,那么将I对应的54℃作为电感的温度值。In some embodiments, when the outdoor unit of the air conditioner is in operation, the camera is used to collect images of the interior of the outdoor unit electrical box to obtain images containing electrical components. Three electrical components, resistors, capacitors and inductors, and 10 target temperature rise points are identified in the image containing electrical components. Among them, the temperature value corresponding to the first target temperature rise point A is 51°C, the temperature value corresponding to the second target temperature rise point B is 53°C, the temperature value corresponding to the third target temperature rise point C is 52°C, the temperature value corresponding to the fourth target temperature rise point D is 53°C, the temperature value corresponding to the fifth target temperature rise point E is 55°C, the temperature value corresponding to the sixth target temperature rise point F is 51°C, the temperature value corresponding to the seventh target temperature rise point G is 52°C, the temperature value corresponding to the eighth target temperature rise point H is 57°C, the temperature value corresponding to the ninth target temperature rise point I is 54°C, and the temperature value corresponding to the tenth target temperature rise point J is 56°C. These 10 target temperature rise points are matched with the pixel coordinates corresponding to the resistors, capacitors and inductors respectively. Among them, the pixel coordinates corresponding to the resistor include the six target temperature rise points A, C, D, F, G, and H. A temperature value can be randomly selected from the temperature values corresponding to the six target temperature rise points as the temperature value of the resistor, such as selecting 53°C corresponding to D as the temperature value of the resistor. The pixel coordinates corresponding to the capacitor include the three target temperature rise points B, E, and J. The maximum temperature value can be selected from the temperature values corresponding to the three target temperature rise points as the temperature value of the resistor, that is, 56°C corresponding to J is used as the temperature value of the capacitor. The pixel coordinates corresponding to the inductor include the target temperature rise point I, so the 54°C corresponding to I is used as the temperature value of the inductor.
可选地,根据所述目标温升点和所述已识别电器元件确定已识别电器元件的温升情况之后,还包括:根据已识别电器元件的像素坐标在实际物体坐标系中确定出已识别电器元 件的实际坐标,并将已识别电器元件的实际坐标和该已识别电器元件的温升情况展示给用户。这样,能够便于用户实时了解室外机电器元件的温升情况。Optionally, after determining the temperature rise of the identified electrical component according to the target temperature rise point and the identified electrical component, the method further includes: determining the identified electrical component in the actual object coordinate system according to the pixel coordinates of the identified electrical component. The actual coordinates of the components are determined, and the actual coordinates of the identified electrical components and the temperature rise of the identified electrical components are displayed to the user. In this way, the user can understand the temperature rise of the electrical components of the outdoor unit in real time.
可选地,电子设备设置有显示屏,或,电子设备连接有显示装置。将已识别电器元件的实际坐标和该已识别电器元件的温升情况展示给用户,包括:通过显示装置显示已识别电器元件的实际坐标和该已识别电器元件的温升情况。或,将已识别电器元件的实际坐标和该已识别电器元件的温升情况发送给用户终端。其中,用户终端包括智能手机等。Optionally, the electronic device is provided with a display screen, or the electronic device is connected to a display device. Displaying the actual coordinates of the identified electrical component and the temperature rise of the identified electrical component to the user includes: displaying the actual coordinates of the identified electrical component and the temperature rise of the identified electrical component through the display device. Or, sending the actual coordinates of the identified electrical component and the temperature rise of the identified electrical component to a user terminal. The user terminal includes a smart phone, etc.
结合图2所示,本公开实施例提供一种用于空调器温升检测的系统1,包括:温升监测装置2,电器元件识别装置3和控制装置4。温升监测装置2被配置为获取包含电器元件的图像,电器元件位于空调器室外机内;识别图像中的目标温升点,目标温升点为图像中满足预设条件的像素点。电器元件识别装置3被配置为对图像进行电器元件识别,获得已识别电器元件。控制装置4被配置为根据目标温升点和已识别电器元件确定已识别电器元件的温升情况。As shown in FIG2 , the embodiment of the present disclosure provides a system 1 for detecting temperature rise of an air conditioner, comprising: a temperature rise monitoring device 2, an electrical component identification device 3 and a control device 4. The temperature rise monitoring device 2 is configured to obtain an image containing electrical components, which are located in the outdoor unit of the air conditioner; identify the target temperature rise point in the image, and the target temperature rise point is a pixel point in the image that meets a preset condition. The electrical component identification device 3 is configured to identify the electrical components of the image and obtain the identified electrical components. The control device 4 is configured to determine the temperature rise of the identified electrical components based on the target temperature rise point and the identified electrical components.
采用本公开实施例提供的用于空调器温升检测的系统,通过获取空调器室外机内包含电器元件的图像,对包含电器元件的图像进行电器元件识别和温度识别,获得已识别电器元件和目标温升点。根据已识别电器元件和目标温升点确定已识别电器元件的温升情况。这样,通过室外机内电器元件的图像来检测各电器元件的温升情况,能够对图像中包含的所有电器元件的温升情况进行检测,从而提高了对室外机内的电器元件进行温升检测的覆盖率。The system for detecting temperature rise of an air conditioner provided by the embodiment of the present disclosure is used to obtain an image containing electrical components in the outdoor unit of the air conditioner, perform electrical component identification and temperature identification on the image containing electrical components, and obtain the identified electrical components and the target temperature rise point. The temperature rise of the identified electrical components is determined based on the identified electrical components and the target temperature rise point. In this way, the temperature rise of each electrical component is detected through the image of the electrical components in the outdoor unit, and the temperature rise of all electrical components contained in the image can be detected, thereby improving the coverage of temperature rise detection of the electrical components in the outdoor unit.
结合图3所示,图3为温升监测装置2的结构示意图。温升监测装置2包括:摄像模块5、温度识别模块7和第二控制单元6。其中,第二控制单元6分别与摄像模块5和温度识别模块7连接,摄像模块5连接温度识别模块7。第二控制单元6与控制装置4连接。摄像模块5连接电器元件识别装置3。As shown in FIG3 , FIG3 is a schematic diagram of the structure of the temperature rise monitoring device 2. The temperature rise monitoring device 2 includes: a camera module 5, a temperature recognition module 7, and a second control unit 6. The second control unit 6 is connected to the camera module 5 and the temperature recognition module 7 respectively, and the camera module 5 is connected to the temperature recognition module 7. The second control unit 6 is connected to the control device 4. The camera module 5 is connected to the electrical component recognition device 3.
摄像模块被配置为获取包含电器元件的图像。可选地,摄像模块为红外摄像模块。或者,摄像机为热成像摄像模块。The camera module is configured to acquire images containing electrical components. Optionally, the camera module is an infrared camera module. Alternatively, the camera is a thermal imaging camera module.
在一些实施例中,利用摄像模块对空调器室外机电器箱体内部进行图像采集,获取包含电器元件的图像。通过对摄像模块进行设置,使摄像模块拍摄到的区域能够全部覆盖空调器室外机电器箱体内的所有电器元件,从而使得采集到的图像,能够包含电器箱体内的所有电器元件,从而能够提高对室外机内的电器元件进行温升检测的覆盖率。In some embodiments, a camera module is used to capture images of the interior of the electrical box of the air conditioner outdoor unit to obtain images containing electrical components. The camera module is set so that the area captured by the camera module can fully cover all electrical components in the electrical box of the air conditioner outdoor unit, so that the captured image can include all electrical components in the electrical box, thereby improving the coverage rate of temperature rise detection of electrical components in the outdoor unit.
摄像模块将获取的包含电器元件的图像发送给温度识别模块。The camera module sends the acquired image containing the electrical components to the temperature recognition module.
进一步地,温度识别模块被配置为将包含电器元件的图像输入预设的温度识别模型进行温度识别,获得图像上各像素点对应的温度值。将满足预设条件的温度值对应的像素点 确定为目标温升点。这样,利用温度识别模型对图像中的像素点进行温度识别,能够自动获取图像上各像素点的温度值,从而便于根据目标温升点确定出已识别电器元件的温升情况。Furthermore, the temperature recognition module is configured to input the image containing the electrical components into a preset temperature recognition model for temperature recognition, and obtain the temperature value corresponding to each pixel point on the image. In this way, the temperature recognition model is used to perform temperature recognition on the pixels in the image, and the temperature value of each pixel on the image can be automatically obtained, so that the temperature rise of the identified electrical components can be determined according to the target temperature rise point.
在一些实施例中,摄像模块每隔预设时长采集一帧包含电器元件的图像,温度识别模块识别每一帧包含电器元件的图像中的目标温升点,控制装置针对每一帧包含电器元件的图像确定已识别电器元件的温升情况。这样,能够实时获取室外机电器箱体内电器元件的温升情况。In some embodiments, the camera module collects an image containing an electrical component at a preset time interval, the temperature recognition module recognizes the target temperature rise point in each image containing an electrical component, and the control device determines the temperature rise of the recognized electrical component for each image containing an electrical component. In this way, the temperature rise of the electrical components in the electrical box of the outdoor unit can be obtained in real time.
温度识别模块将每一帧包含电器元件的图像都输入预设的温度识别模型进行温度识别。温度识别模型中的特征网络对重要帧图像进行特征提取,获得重要帧图像的深度特征图。并通过光流法将重要帧图像的深度特征图传播给该重要帧图像对应的非重要帧。其中,重要帧图像为采集的第i帧包含电器元件的图像,i为正整数。该重要帧图像对应的非重要帧为该重要帧图像之后的第k帧包含电器元件的图像,k=i+x,1≤x≤12,且x为正整数,例如,特征网络对第一帧包含电器元件的图像进行了特征提取,则该第一帧后的连续12帧都不再进行特征提取,而是将第一帧的深度特征图传播给该第一帧后的连续12帧包含电器元件的图像。温度识别模型中的任务网络对每一帧图像的深度特征图进行温度识别,获得每一帧包含电器元件的图像中各像素点的温度值。这样,只对重要帧进行特征提取,降低了温度识别模型的运算量,从而提高温升检测的效率。其中,特征网络为完全卷积网络。The temperature recognition module inputs each frame of the image containing electrical components into the preset temperature recognition model for temperature recognition. The feature network in the temperature recognition model extracts features from the important frame images to obtain the depth feature map of the important frame images. The depth feature map of the important frame images is propagated to the non-important frames corresponding to the important frame images by the optical flow method. Among them, the important frame image is the image of the i-th frame containing electrical components collected, and i is a positive integer. The non-important frame corresponding to the important frame image is the image of the k-th frame containing electrical components after the important frame image, k=i+x, 1≤x≤12, and x is a positive integer. For example, the feature network extracts features from the first frame of the image containing electrical components, and then the continuous 12 frames after the first frame are no longer feature extracted, but the depth feature map of the first frame is propagated to the continuous 12 frames after the first frame containing electrical components. The task network in the temperature recognition model performs temperature recognition on the depth feature map of each frame image to obtain the temperature value of each pixel in each frame of the image containing electrical components. In this way, only feature extraction is performed on the important frames, which reduces the amount of calculation of the temperature recognition model, thereby improving the efficiency of temperature rise detection. Among them, the feature network is a fully convolutional network.
进一步地,温度识别模块被配置为通过以下方式将满足预设条件的温度值对应的像素点确定为目标温升点:温度识别模块将大于或等于第一预设阈值的温度值对应的像素点确定为目标温升点。Further, the temperature recognition module is configured to determine the pixel points corresponding to the temperature values satisfying the preset conditions as the target temperature rise points in the following manner: the temperature recognition module determines the pixel points corresponding to the temperature values greater than or equal to the first preset threshold as the target temperature rise points.
在一些实施例中,第一预设阈值为环境温度值。温升为工作状态下电器元件的温度超过环境温度的差值。将超过环境温度的像素点确定为目标温升点。这样,根据超过环境温度的像素点及对应的温度值能够确定出已识别电器元件的温升情况。In some embodiments, the first preset threshold is an ambient temperature value. The temperature rise is the difference between the temperature of the electrical component in the working state and the ambient temperature. The pixel points exceeding the ambient temperature are determined as the target temperature rise points. In this way, the temperature rise of the identified electrical component can be determined based on the pixel points exceeding the ambient temperature and the corresponding temperature values.
可选地,温度识别模块将满足预设条件的温度值对应的像素点确定为目标温升点,包括:温度识别模块将大于第一预设阈值的温度值对应的像素点确定为温升点,将温度值大于或等于第二预设阈值的温升点确定为目标温升点。其中,第二预设阈值大于第一预设阈值。空调器室外机工作时,电器箱体内的电器元件会有一定温升,但如果电器元件的温度超过一定阈值,例如大于或等于第二预设阈值,则该电器元件工作异常。这样,根据温度值大于或等于第二预设阈值的像素点来确定已识别电器元件的温升情况,能够直接确定出已识别电器元件中处于工作异常的电器元件。 Optionally, the temperature recognition module determines the pixel points corresponding to the temperature values that meet the preset conditions as the target temperature rise points, including: the temperature recognition module determines the pixel points corresponding to the temperature values greater than the first preset threshold as the temperature rise points, and determines the temperature rise points with temperature values greater than or equal to the second preset threshold as the target temperature rise points. Among them, the second preset threshold is greater than the first preset threshold. When the air conditioner outdoor unit is working, the electrical components in the electrical box will have a certain temperature rise, but if the temperature of the electrical components exceeds a certain threshold, for example, greater than or equal to the second preset threshold, the electrical components will work abnormally. In this way, the temperature rise of the identified electrical components is determined based on the pixel points with temperature values greater than or equal to the second preset threshold, so that the electrical components that are working abnormally among the identified electrical components can be directly determined.
结合图4所示,图4为电器元件识别装置3的结构示意图。电器元件识别装置3包括:电器元件识别模块9和第三控制单元8。第三控制单元8与控制装置4连接。电器元件识别模块9与第三控制单元8连接,并连接摄像模块5。摄像模块将获取到的包含电器元件的图像发送给电器元件识别装置的电器元件识别模块。As shown in FIG4 , FIG4 is a schematic diagram of the structure of the electrical component identification device 3. The electrical component identification device 3 includes: an electrical component identification module 9 and a third control unit 8. The third control unit 8 is connected to the control device 4. The electrical component identification module 9 is connected to the third control unit 8 and is connected to the camera module 5. The camera module sends the acquired image containing the electrical component to the electrical component identification module of the electrical component identification device.
进一步地,电器元件识别模块被配置为将包含电器元件的图像输入预设的电器元件识别模型进行电器元件识别,获得已识别电器元件。这样,利用电器元件识别模型对图像中的电器元件进行识别,能够自动识别出图像中的电器元件,便于对电器元件的温升情况进行检测。Furthermore, the electrical component recognition module is configured to input an image containing electrical components into a preset electrical component recognition model to perform electrical component recognition and obtain recognized electrical components. In this way, by using the electrical component recognition model to recognize electrical components in an image, the electrical components in the image can be automatically recognized, which is convenient for detecting the temperature rise of the electrical components.
在一些实施例中,电器元件识别模块将包含电器元件的图像输入预设的电器元件识别模型进行电器元件识别,识别出图像中的电器元件,将图像中识别出的电器元件确定为已识别电器元件。其中,已识别电器元件包括图像中已识别电器元件的名称和像素坐标。In some embodiments, the electrical component recognition module inputs an image containing electrical components into a preset electrical component recognition model to perform electrical component recognition, recognizes the electrical components in the image, and determines the recognized electrical components in the image as recognized electrical components. The recognized electrical components include the names and pixel coordinates of the recognized electrical components in the image.
结合图5所示,该用于空调器温升检测的系统还包括:定位装置10。定位装置10分别连接温升监测装置2,电器元件识别装置3和控制装置4。5 , the system for detecting temperature rise of an air conditioner further includes a positioning device 10. The positioning device 10 is connected to the temperature rise monitoring device 2, the electrical component identification device 3 and the control device 4 respectively.
结合图6所示,图6为定位装置10的结构示意图。定位装置10包括:定位计算模块11、像素坐标计算模块12和第四控制单元13。其中,第四控制单元13连接定位计算模块11和像素坐标计算模块12。第四控制单元13与控制装置4连接。像素坐标计算模块12连接摄像模块5和定位计算模块11。定位计算模块11连接电器元件识别模块9。摄像模块将获取到的包含电器元件的图像发送给定位装置的像素坐标计算模块。As shown in FIG6 , FIG6 is a schematic diagram of the structure of the positioning device 10. The positioning device 10 includes: a positioning calculation module 11, a pixel coordinate calculation module 12 and a fourth control unit 13. Among them, the fourth control unit 13 is connected to the positioning calculation module 11 and the pixel coordinate calculation module 12. The fourth control unit 13 is connected to the control device 4. The pixel coordinate calculation module 12 is connected to the camera module 5 and the positioning calculation module 11. The positioning calculation module 11 is connected to the electrical component recognition module 9. The camera module sends the acquired image containing the electrical component to the pixel coordinate calculation module of the positioning device.
在一些实施例中,定位计算模块被配置为建立像素坐标系和物体实际坐标系。定位计算模块通过以下方式建立像素坐标系,包括:通过摄像模块获取空调器室外机电器箱体内部的初始图像。以初始图像的左上角为原点,水平向右为x轴,x轴为横轴。竖直向下为y轴,y轴为纵轴,建立像素坐标系。其中,像素坐标系中的坐标用于表征图像中像素点的像素坐标。定位计算模块通过以下方式建立物体实际坐标系,包括:以初始图像对应的实际物体的左上角为原点。水平向右为u轴,u轴为横轴。竖直向下为v轴,v轴为纵轴,建立实际物体坐标系。其中,实际物体坐标系中的坐标用于表征物体的实际坐标。实际物体坐标系的u轴与像素坐标系的x轴相重合,实际物体坐标系的v轴与像素坐标系的y轴相重合。像素坐标系和实际物体坐标系可以相互转化。In some embodiments, the positioning calculation module is configured to establish a pixel coordinate system and an actual coordinate system of the object. The positioning calculation module establishes the pixel coordinate system in the following manner, including: obtaining an initial image of the interior of the electrical box of the air conditioner outdoor unit through the camera module. Taking the upper left corner of the initial image as the origin, horizontally to the right is the x-axis, and the x-axis is the horizontal axis. Vertically downward is the y-axis, and the y-axis is the vertical axis, and a pixel coordinate system is established. Among them, the coordinates in the pixel coordinate system are used to characterize the pixel coordinates of the pixel points in the image. The positioning calculation module establishes the actual coordinate system of the object in the following manner, including: taking the upper left corner of the actual object corresponding to the initial image as the origin. Horizontally to the right is the u-axis, and the u-axis is the horizontal axis. Vertically downward is the v-axis, and the v-axis is the vertical axis, and a real object coordinate system is established. Among them, the coordinates in the real object coordinate system are used to characterize the real coordinates of the object. The u-axis of the real object coordinate system coincides with the x-axis of the pixel coordinate system, and the v-axis of the real object coordinate system coincides with the y-axis of the pixel coordinate system. The pixel coordinate system and the real object coordinate system can be converted into each other.
在一些实施例中,已识别电器元件包括图像中已识别电器元件的名称。电器元件识别模块将已识别电器元件发送给定位计算模块。像素坐标计算模块对获取的图像进行处理,获得图像中各像素点的像素坐标,并将图像中各像素点的像素坐标发送给定位计算模块。定位计算模块根据图像中各像素点的像素坐标和已识别电器元件的名称,确定出已识别电 器元件的像素坐标。利用像素坐标系和物体实际坐标系这两个可以转换的坐标系来确定出已识别电器元件的实际坐标。In some embodiments, the identified electrical component includes the name of the identified electrical component in the image. The electrical component identification module sends the identified electrical component to the positioning calculation module. The pixel coordinate calculation module processes the acquired image to obtain the pixel coordinates of each pixel in the image, and sends the pixel coordinates of each pixel in the image to the positioning calculation module. The positioning calculation module determines the identified electrical component based on the pixel coordinates of each pixel in the image and the name of the identified electrical component. The actual coordinates of the identified electrical components are determined by using the pixel coordinate system and the object's actual coordinate system, two coordinate systems that can be converted.
结合图7所示,图7为控制装置4的结构示意图,控制装置4包括:控制模块14、数据处理模块15、显示模块16和第一控制单元17。其中,第一控制单元17分别连接控制模块14、数据处理模块15和显示模块16。控制模块14连接第二控制单元6、第三控制单元8和第四控制单元13。数据处理模块15连接显示模块16。As shown in FIG. 7 , FIG. 7 is a schematic diagram of the structure of the control device 4, and the control device 4 includes: a control module 14, a data processing module 15, a display module 16, and a first control unit 17. Among them, the first control unit 17 is connected to the control module 14, the data processing module 15, and the display module 16 respectively. The control module 14 is connected to the second control unit 6, the third control unit 8, and the fourth control unit 13. The data processing module 15 is connected to the display module 16.
通过控制装置的控制模块14分别向温升监测装置的第二控制单元6、电器元件识别装置的第三控制单元8和定位装置的第四控制单元13发送控制温升监测装置、电器元件识别装置和定位装置开启的指令。The control module 14 of the control device sends instructions for controlling the temperature rise monitoring device, the electrical component identification device and the positioning device to start up, respectively, to the second control unit 6 of the temperature rise monitoring device, the third control unit 8 of the electrical component identification device and the fourth control unit 13 of the positioning device.
数据处理模块15连接温度识别模块7和定位计算模块11。定位计算模块将确定出的已识别电器元件的实际坐标发送给数据处理模块。温度识别模块将识别出的目标温升点及对应的温度值发送给数据处理模块。The data processing module 15 is connected to the temperature identification module 7 and the positioning calculation module 11. The positioning calculation module sends the actual coordinates of the identified electrical components to the data processing module. The temperature identification module sends the identified target temperature rise point and the corresponding temperature value to the data processing module.
定位装置的像素坐标计算模块被配置为获取第一像素坐标和第二像素坐标,并将第一像素坐标和第二像素坐标发送给定位计算模块。定位计算模块将各第一像素坐标与各第二像素坐标进行匹配,获得匹配结果,将匹配结果发送给控制装置。其中,第一像素坐标为已识别电器元件的像素坐标,第二像素坐标为目标温升点的像素坐标。控制装置的数据处理模块被配置为在匹配结果为存在第二像素坐标与第一像素坐标匹配的情况下,根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温升情况。The pixel coordinate calculation module of the positioning device is configured to obtain the first pixel coordinate and the second pixel coordinate, and send the first pixel coordinate and the second pixel coordinate to the positioning calculation module. The positioning calculation module matches each first pixel coordinate with each second pixel coordinate, obtains a matching result, and sends the matching result to the control device. Among them, the first pixel coordinate is the pixel coordinate of the identified electrical component, and the second pixel coordinate is the pixel coordinate of the target temperature rise point. The data processing module of the control device is configured to determine the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate when the matching result is that the second pixel coordinate matches the first pixel coordinate.
在一些实施例中,图像中的各已识别电器元件分别对应有一个或多个像素坐标。定位计算模块将各第二像素坐标分别与各已识别电器元件的第一像素坐标进行匹配,获得匹配结果。其中,匹配结果包括:存在第二像素坐标与第一像素坐标匹配,或,不存在第二像素坐标与第一像素坐标匹配。其中,存在一个或多个第二像素坐标被包含于第一像素坐标中,即确定存在第二像素坐标与第一像素坐标匹配。第一像素坐标中没有包含第二像素坐标,即确定不存在第二像素坐标与第一像素坐标匹配。In some embodiments, each identified electrical component in the image corresponds to one or more pixel coordinates. The positioning calculation module matches each second pixel coordinate with the first pixel coordinate of each identified electrical component to obtain a matching result. The matching result includes: there is a second pixel coordinate that matches the first pixel coordinate, or there is no second pixel coordinate that matches the first pixel coordinate. There are one or more second pixel coordinates included in the first pixel coordinate, that is, it is determined that there is a second pixel coordinate that matches the first pixel coordinate. The first pixel coordinate does not include the second pixel coordinate, that is, it is determined that there is no second pixel coordinate that matches the first pixel coordinate.
可选地,数据处理模块通过以下方式根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温升情况,包括:根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温度值,将已识别电器元件的温度值确定为已识别电器元件的温升情况。这样,实现了对图像中所有电器元件的温升情况的获取,提高了对室外机电器元件温升检测的覆盖率。Optionally, the data processing module determines the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate in the following manner, including: determining the temperature value of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate, and determining the temperature value of the identified electrical component as the temperature rise of the identified electrical component. In this way, the temperature rise of all electrical components in the image is obtained, and the coverage of temperature rise detection of outdoor unit electrical components is improved.
可选地,数据处理模块通过以下方式根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温升情况,包括:根据第二像素坐标对应的温度值确定第一像 素坐标对应的已识别电器元件的温度值,将已识别电器元件的温度值与环境温度作差,获得已识别电器元件的温升情况。这样,实现了对图像中所有电器元件的温升情况的获取,提高了对室外机电器元件温升检测的覆盖率。Optionally, the data processing module determines the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate in the following manner, including: determining the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate The temperature value of the identified electrical component corresponding to the pixel coordinate is obtained by subtracting the temperature value of the identified electrical component from the ambient temperature to obtain the temperature rise of the identified electrical component. In this way, the temperature rise of all electrical components in the image is obtained, and the coverage of temperature rise detection of outdoor unit electrical components is improved.
可选地,数据处理模块通过以下方式根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温度值,包括:在已识别电器元件的第一像素坐标中包含有多个第二像素坐标的情况下,将被包含的第二像素坐标对应的温度值中的最大温度值,或,最小温度值,或,随机选取一个温度值作为第一像素坐标对应的已识别电器元件的温度值。Optionally, the data processing module determines the temperature value of the identified electrical component corresponding to the first pixel coordinate based on the temperature value corresponding to the second pixel coordinate in the following manner, including: when the first pixel coordinate of the identified electrical component contains multiple second pixel coordinates, the maximum temperature value or the minimum temperature value among the temperature values corresponding to the included second pixel coordinates, or a randomly selected temperature value as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
可选地,数据处理模块通过以下方式根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温度值,包括:在已识别电器元件的第一像素坐标中包含有多个第二像素坐标的情况下,计算被包含的第二像素坐标对应的温度值的平均值,将该平均值作为第一像素坐标对应的已识别电器元件的温度值。Optionally, the data processing module determines the temperature value of the identified electrical component corresponding to the first pixel coordinate based on the temperature value corresponding to the second pixel coordinate in the following manner, including: when the first pixel coordinate of the identified electrical component contains multiple second pixel coordinates, calculating the average value of the temperature values corresponding to the included second pixel coordinates, and using the average value as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
可选地,数据处理模块通过以下方式根据第二像素坐标对应的温度值确定第一像素坐标对应的已识别电器元件的温度值,包括:在已识别电器元件的第一像素坐标中只包含一个第二像素坐标的情况下,将该第二像素坐标对应的温度值作为第一像素坐标对应的已识别电器元件的温度值。Optionally, the data processing module determines the temperature value of the identified electrical component corresponding to the first pixel coordinate based on the temperature value corresponding to the second pixel coordinate in the following manner, including: when the first pixel coordinate of the identified electrical component contains only one second pixel coordinate, the temperature value corresponding to the second pixel coordinate is used as the temperature value of the identified electrical component corresponding to the first pixel coordinate.
可选地,数据处理模块将已识别电器元件的实际坐标和该已识别电器元件的温升情况发送给显示模块。显示模块被配置为对已识别电器元件的实际坐标和该已识别电器元件的温升情况进行显示。Optionally, the data processing module sends the actual coordinates of the identified electrical component and the temperature rise of the identified electrical component to the display module. The display module is configured to display the actual coordinates of the identified electrical component and the temperature rise of the identified electrical component.
可选地,用于空调器温升检测的系统,还包括:供电装置和通信装置。供电装置被配置为为空调器温升检测的系统供电。通信装置被配置为实现温升监测装置、定位装置、电器元件识别装置和控制装置之间的通信连接。Optionally, the system for detecting temperature rise of an air conditioner further comprises: a power supply device and a communication device. The power supply device is configured to supply power to the system for detecting temperature rise of the air conditioner. The communication device is configured to realize communication connection among the temperature rise monitoring device, the positioning device, the electrical component identification device and the control device.
在一些实施例中,在空调器室外机处于工作的状态下,用户通过控制模块向温升监测装置的第二控制单元发送控制指令,第二控制单元控制摄像模块进行图像采集,并将包含电器元件的图像发送给温升监测装置的温度识别模块、电器元件识别装置和定位装置。温升监测装置的温度识别模块利用预先训练好的卷积神经网络对包含电器元件的图像进行温度识别,获得目标温升点。并将目标温升点及对应的温度值发送至控制装置和定位装置。电器元件识别装置对包含电器元件的图像进行电器元件识别,获得已识别的电器元件。将已识别的电器元件发送给定位装置和控制装置。定位装置的像素坐标计算模块获取包含电器元件的图像中各像素点的像素坐标。将图像中各像素点的像素坐标发送给定位计算模块。定位装置的定位计算模块根据已识别的电器元件和图像中各像素点的像素坐标确定出已识别的电器元件的像素坐标。定位装置的定位计算模块根据目标温升点和图像中各像素点 的像素坐标确定出目标温升点的像素坐标。定位计算模块将已识别电器元件的像素坐标和目标温升点的像素坐标进行匹配,将匹配结果发送给控制装置。控制装置的数据处理模块在接收到的匹配结果为存在电器元件的像素坐标与目标温升点的像素坐标匹配的情况下,根据目标温升点的像素坐标对应的温度值确定已识别电器元件的温升情况,并将已识别电器元件的温度值发送给显示模块进行显示。这样,通过室外机内电器元件的图像来检测各电器元件的温升情况,能够对图像中包含的所有电器元件的温升情况进行检测,从而提高了对室外机内的电器元件进行温升检测的覆盖率。In some embodiments, when the air conditioner outdoor unit is in operation, the user sends a control instruction to the second control unit of the temperature rise monitoring device through the control module, and the second control unit controls the camera module to collect images and sends the image containing the electrical components to the temperature recognition module, electrical component recognition device and positioning device of the temperature rise monitoring device. The temperature recognition module of the temperature rise monitoring device uses a pre-trained convolutional neural network to perform temperature recognition on the image containing the electrical components to obtain the target temperature rise point. The target temperature rise point and the corresponding temperature value are sent to the control device and the positioning device. The electrical component recognition device performs electrical component recognition on the image containing the electrical components to obtain the recognized electrical components. The recognized electrical components are sent to the positioning device and the control device. The pixel coordinate calculation module of the positioning device obtains the pixel coordinates of each pixel in the image containing the electrical components. The pixel coordinates of each pixel in the image are sent to the positioning calculation module. The positioning calculation module of the positioning device determines the pixel coordinates of the recognized electrical components based on the recognized electrical components and the pixel coordinates of each pixel in the image. The positioning calculation module of the positioning device determines the pixel coordinates of the recognized electrical components based on the target temperature rise point and the pixel coordinates of each pixel in the image. The pixel coordinates of the target temperature rise point are determined by the pixel coordinates of the identified electrical component. The positioning calculation module matches the pixel coordinates of the target temperature rise point and sends the matching result to the control device. When the data processing module of the control device receives the matching result that the pixel coordinates of the electrical component match the pixel coordinates of the target temperature rise point, it determines the temperature rise of the identified electrical component according to the temperature value corresponding to the pixel coordinates of the target temperature rise point, and sends the temperature value of the identified electrical component to the display module for display. In this way, the temperature rise of each electrical component is detected through the image of the electrical component in the outdoor unit, and the temperature rise of all electrical components contained in the image can be detected, thereby improving the coverage rate of temperature rise detection of the electrical components in the outdoor unit.
本公开实施例提供了一种计算机程序,当所述计算机程序被计算机执行时,使所述计算机实现上述用于空调器温升检测的方法。The embodiment of the present disclosure provides a computer program, which, when executed by a computer, enables the computer to implement the above-mentioned method for detecting temperature rise of an air conditioner.
本公开实施例提供了一种计算机程序产品,所述计算机程序产品包括存储在计算机可读存储介质上的计算机指令,当所述程序指令被计算机执行时,使所述计算机实现上述用于空调器温升检测的方法。An embodiment of the present disclosure provides a computer program product, which includes computer instructions stored on a computer-readable storage medium. When the program instructions are executed by a computer, the computer implements the above-mentioned method for detecting temperature rise of an air conditioner.
以上描述和附图充分地示出了本公开的实施例,以使本领域的技术人员能够实践它们。其他实施例可以包括结构的、逻辑的、电气的、过程的以及其他的改变。实施例仅代表可能的变化。除非明确要求,否则单独的部件和功能是可选的,并且操作的顺序可以变化。一些实施例的部分和特征可以被包括在或替换其他实施例的部分和特征。而且,本申请中使用的用词仅用于描述实施例并且不用于限制权利要求。如在实施例以及权利要求的描述中使用的,除非上下文清楚地表明,否则单数形式的“一个”(a)、“一个”(an)和“所述”(the)旨在同样包括复数形式。类似地,如在本申请中所使用的术语“和/或”是指包含一个或一个以上相关联的列出的任何以及所有可能的组合。另外,当用于本申请中时,术语“包括”(comprise)及其变型“包括”(comprises)和/或包括(comprising)等指陈述的特征、整体、步骤、操作、元素,和/或组件的存在,但不排除一个或一个以上其它特征、整体、步骤、操作、元素、组件和/或这些的分组的存在或添加。在没有更多限制的情况下,由语句“包括一个…”限定的要素,并不排除在包括所述要素的过程、方法或者设备中还存在另外的相同要素。本文中,每个实施例重点说明的可以是与其他实施例的不同之处,各个实施例之间相同相似部分可以互相参见。对于实施例公开的方法、产品等而言,如果其与实施例公开的方法部分相对应,那么相关之处可以参见方法部分的描述。The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and/or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variants "comprises" and/or including (comprising) refer to the existence of stated features, wholes, steps, operations, elements, and/or components, but do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and/or these groups. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same or similar parts between the embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.
本领域技术人员可以意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行,可以取决于技术方案的特定应用和设计约束条件。所述技术人员可以对每个特定的应用来使用不同方法以实现所描述的功能,但是这种实现不应认为超出本 公开实施例的范围。所述技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document. The technical personnel can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices and units can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.
附图中的流程图和框图显示了根据本公开实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分,所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个连续的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这可以依所涉及的功能而定。在附图中的流程图和框图所对应的描述中,不同的方框所对应的操作或步骤也可以以不同于描述中所披露的顺序发生,有时不同的操作或步骤之间不存在特定的顺序。例如,两个连续的操作或步骤实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这可以依所涉及的功能而定。框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或动作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。 The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the system, method and computer program product according to the embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each box in the block diagram and/or flowchart, and the combination of boxes in the block diagram and/or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

Claims (12)

  1. 一种用于空调器温升检测的方法,其特征在于,包括:A method for detecting temperature rise of an air conditioner, characterized by comprising:
    获取包含电器元件的图像,所述电器元件位于空调器室外机内;Acquire an image containing an electrical component, wherein the electrical component is located in an outdoor unit of an air conditioner;
    对所述图像进行电器元件识别,获得已识别电器元件;Performing electrical component recognition on the image to obtain recognized electrical components;
    识别所述图像中的目标温升点,所述目标温升点为所述图像中满足预设条件的像素点;Identifying a target temperature rise point in the image, wherein the target temperature rise point is a pixel point in the image that meets a preset condition;
    根据所述目标温升点和所述已识别电器元件确定已识别电器元件的温升情况。The temperature rise of the identified electrical component is determined according to the target temperature rise point and the identified electrical component.
  2. 根据权利要求1所述的方法,其特征在于,所述对所述图像进行电器元件识别,包括:The method according to claim 1, characterized in that the step of performing electrical component recognition on the image comprises:
    将所述图像输入预设的电器元件识别模型进行电器元件识别,获得已识别电器元件。The image is input into a preset electrical component recognition model to perform electrical component recognition to obtain recognized electrical components.
  3. 根据权利要求1或2所述的方法,其特征在于,所述识别所述图像中的目标温升点,包括:The method according to claim 1 or 2, characterized in that the identifying the target temperature rise point in the image comprises:
    将所述图像输入预设的温度识别模型进行温度识别,获得所述图像上各像素点对应的温度值;Input the image into a preset temperature recognition model for temperature recognition, and obtain the temperature value corresponding to each pixel point on the image;
    将满足预设条件的温度值对应的像素点确定为目标温升点。The pixel point corresponding to the temperature value that meets the preset conditions is determined as the target temperature rise point.
  4. 根据权利要求3所述的方法,其特征在于,将满足预设条件的温度值对应的像素点确定为目标温升点,包括:The method according to claim 3 is characterized in that determining the pixel point corresponding to the temperature value that meets the preset condition as the target temperature rise point comprises:
    将大于第一预设阈值的温度值对应的像素点确定为目标温升点。The pixel point corresponding to the temperature value greater than the first preset threshold is determined as the target temperature rise point.
  5. 根据权利要求3所述的方法,其特征在于,所述根据所述目标温升点和所述已识别电器元件确定已识别电器元件的温升情况,包括:The method according to claim 3, characterized in that the step of determining the temperature rise of the identified electrical component according to the target temperature rise point and the identified electrical component comprises:
    获取第一像素坐标和第二像素坐标;所述第一像素坐标为所述已识别电器元件的像素坐标,所述第二像素坐标为所述目标温升点的像素坐标;Acquire a first pixel coordinate and a second pixel coordinate; the first pixel coordinate is the pixel coordinate of the identified electrical component, and the second pixel coordinate is the pixel coordinate of the target temperature rise point;
    将各所述第一像素坐标与各所述第二像素坐标进行匹配,获得匹配结果;Matching each of the first pixel coordinates with each of the second pixel coordinates to obtain a matching result;
    在所述匹配结果为存在第二像素坐标与第一像素坐标匹配的情况下,根据所述第二像素坐标对应的温度值确定所述第一像素坐标对应的已识别电器元件的温升情况。When the matching result is that the second pixel coordinate matches the first pixel coordinate, the temperature rise of the identified electrical component corresponding to the first pixel coordinate is determined according to the temperature value corresponding to the second pixel coordinate.
  6. 一种用于空调器温升检测的系统,其特征在于,包括:A system for detecting temperature rise of an air conditioner, characterized by comprising:
    温升监测装置,被配置为获取包含电器元件的图像,所述电器元件位于空调器室外机内;识别所述图像中的目标温升点,所述目标温升点为所述图像中满足预设条件的像素点;The temperature rise monitoring device is configured to obtain an image containing an electrical component, wherein the electrical component is located in an outdoor unit of an air conditioner; identify a target temperature rise point in the image, wherein the target temperature rise point is a pixel point in the image that meets a preset condition;
    电器元件识别装置,被配置为对所述图像进行电器元件识别,获得已识别电器元 件;The electrical component recognition device is configured to recognize the electrical components of the image and obtain the recognized electrical components. Item;
    控制装置,被配置为根据所述目标温升点和所述已识别电器元件确定已识别电器元件的温升情况。The control device is configured to determine the temperature rise of the identified electrical component based on the target temperature rise point and the identified electrical component.
  7. 根据权利要求6所述的系统,其特征在于,所述电器元件识别装置包括:电器元件识别模块,被配置为将所述图像输入预设的电器元件识别模型进行电器元件识别,获得已识别电器元件。The system according to claim 6 is characterized in that the electrical component identification device comprises: an electrical component identification module configured to input the image into a preset electrical component identification model to perform electrical component identification and obtain an identified electrical component.
  8. 根据权利要求6或7所述的系统,其特征在于,所述温升监测装置,包括:温度识别模块,被配置为将所述图像输入预设的温度识别模型进行温度识别,获得所述图像上各像素点对应的温度值;The system according to claim 6 or 7 is characterized in that the temperature rise monitoring device comprises: a temperature recognition module configured to input the image into a preset temperature recognition model for temperature recognition, and obtain a temperature value corresponding to each pixel point on the image;
    将满足预设条件的温度值对应的像素点确定为目标温升点。The pixel point corresponding to the temperature value that meets the preset conditions is determined as the target temperature rise point.
  9. 根据权利要求8所述的系统,其特征在于,所述温度识别模块被配置为通过以下方式将满足预设条件的温度值对应的像素点确定为目标温升点:The system according to claim 8, characterized in that the temperature recognition module is configured to determine the pixel point corresponding to the temperature value that meets the preset condition as the target temperature rise point in the following manner:
    将大于或等于第一预设阈值的温度值对应的像素点确定为目标温升点。The pixel point corresponding to the temperature value greater than or equal to the first preset threshold is determined as the target temperature rise point.
  10. 根据权利要求8所述的系统,其特征在于,还包括:The system according to claim 8, further comprising:
    定位装置,被配置为获取第一像素坐标和第二像素坐标;将各所述第一像素坐标与各所述第二像素坐标进行匹配,获得匹配结果;将所述匹配结果发送给所述控制装置;其中,所述第一像素坐标为所述已识别电器元件的像素坐标,所述第二像素坐标为所述目标温升点的像素坐标;A positioning device, configured to obtain a first pixel coordinate and a second pixel coordinate; match each of the first pixel coordinates with each of the second pixel coordinates to obtain a matching result; and send the matching result to the control device; wherein the first pixel coordinate is the pixel coordinate of the identified electrical component, and the second pixel coordinate is the pixel coordinate of the target temperature rise point;
    所述控制装置,被配置为在所述匹配结果为存在第二像素坐标与第一像素坐标匹配的情况下,根据所述第二像素坐标对应的温度值确定所述第一像素坐标对应的已识别电器元件的温升情况。The control device is configured to determine the temperature rise of the identified electrical component corresponding to the first pixel coordinate according to the temperature value corresponding to the second pixel coordinate when the matching result is that the second pixel coordinate matches the first pixel coordinate.
  11. 一种计算机程序,当所述计算机程序被计算机执行时,使所述计算机实现如权利要求1至5任一项所述的用于空调器温升检测的方法。A computer program, when executed by a computer, enables the computer to implement the method for detecting temperature rise of an air conditioner as claimed in any one of claims 1 to 5.
  12. 一种计算机程序产品,所述计算机程序产品包括存储在计算机可读存储介质上的计算机指令,当所述程序指令被计算机执行时,使所述计算机实现如权利要求1至5任一项所述的用于空调器温升检测的方法。 A computer program product, comprising computer instructions stored on a computer-readable storage medium, wherein when the program instructions are executed by a computer, the computer implements the method for detecting temperature rise of an air conditioner as described in any one of claims 1 to 5.
PCT/CN2023/099817 2022-10-17 2023-06-13 Method and system for temperature rise detection of air conditioner WO2024082658A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211267738.5 2022-10-17
CN202211267738.5A CN117906211A (en) 2022-10-17 2022-10-17 Method and system for detecting temperature rise of air conditioner

Publications (1)

Publication Number Publication Date
WO2024082658A1 true WO2024082658A1 (en) 2024-04-25

Family

ID=90682527

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/099817 WO2024082658A1 (en) 2022-10-17 2023-06-13 Method and system for temperature rise detection of air conditioner

Country Status (2)

Country Link
CN (1) CN117906211A (en)
WO (1) WO2024082658A1 (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0755227A (en) * 1993-08-20 1995-03-03 Kumagai Gumi Co Ltd Hot heat environment control system utilizing infrared ray imaging device
CN103336224A (en) * 2013-07-03 2013-10-02 同济大学 Complex information based insulator temperature rise fault comprehensive diagnosis method
CN106979820A (en) * 2017-03-14 2017-07-25 西安电子科技大学 Infrared temperature rise element method for detecting abnormality based on similarity measurement factor
CN110487414A (en) * 2019-08-16 2019-11-22 云南电网有限责任公司电力科学研究院 Breaker temperature monitoring method and system based on infrared image technology
CN113418617A (en) * 2021-07-15 2021-09-21 西安华控智能系统工程有限公司 Three-dimensional temperature field measuring and diagnosing method for box type transformer of wind power plant
CN113776670A (en) * 2021-08-09 2021-12-10 邹平市供电有限公司 Power equipment monitoring system and method based on infrared image
CN113866536A (en) * 2021-09-07 2021-12-31 深圳Tcl数字技术有限公司 Temperature rise detection method and device and temperature rise detection system
CN114119518A (en) * 2021-11-16 2022-03-01 国网重庆市电力公司电力科学研究院 Method and system for detecting temperature abnormal point in infrared image of current transformer

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0755227A (en) * 1993-08-20 1995-03-03 Kumagai Gumi Co Ltd Hot heat environment control system utilizing infrared ray imaging device
CN103336224A (en) * 2013-07-03 2013-10-02 同济大学 Complex information based insulator temperature rise fault comprehensive diagnosis method
CN106979820A (en) * 2017-03-14 2017-07-25 西安电子科技大学 Infrared temperature rise element method for detecting abnormality based on similarity measurement factor
CN110487414A (en) * 2019-08-16 2019-11-22 云南电网有限责任公司电力科学研究院 Breaker temperature monitoring method and system based on infrared image technology
CN113418617A (en) * 2021-07-15 2021-09-21 西安华控智能系统工程有限公司 Three-dimensional temperature field measuring and diagnosing method for box type transformer of wind power plant
CN113776670A (en) * 2021-08-09 2021-12-10 邹平市供电有限公司 Power equipment monitoring system and method based on infrared image
CN113866536A (en) * 2021-09-07 2021-12-31 深圳Tcl数字技术有限公司 Temperature rise detection method and device and temperature rise detection system
CN114119518A (en) * 2021-11-16 2022-03-01 国网重庆市电力公司电力科学研究院 Method and system for detecting temperature abnormal point in infrared image of current transformer

Also Published As

Publication number Publication date
CN117906211A (en) 2024-04-19

Similar Documents

Publication Publication Date Title
CN106991395B (en) Information processing method and device and electronic equipment
TWI497247B (en) Data processing device and method for regulating the lighting power of a display
KR101603017B1 (en) Gesture recognition device and gesture recognition device control method
CN110174174A (en) Detection terminal and its application method based on infrared heat and visual light imaging
CN113066195A (en) Power equipment inspection method and device, AR glasses and storage medium
CN103063314A (en) Thermal imaging device and thermal imaging shooting method
CN102142240A (en) Data processing equipment and method for realizing brightness adjustment
US8295313B2 (en) Video instant messaging system and method thereof
CN111881867A (en) Video analysis method and device and electronic equipment
CN110765289A (en) Method for rapidly acquiring building crack opening degree at low cost
WO2024082658A1 (en) Method and system for temperature rise detection of air conditioner
KR102366396B1 (en) RGB-D Data and Deep Learning Based 3D Instance Segmentation Method and System
WO2015096824A1 (en) Analysis device and analysis method
CN109685775B (en) Filter screen filth blockage identification method and device, intelligent equipment and readable storage medium
CN111563726A (en) Enterprise rectification supervision method, device, equipment and computer readable storage medium
CN113808107B (en) Image recommendation method, device, electronic equipment and storage medium
KR101348951B1 (en) The Management System and Method for Vehicle Customers
EP3906528A1 (en) Anthropometric data portable acquisition device and method of collecting anthropometric data
CN116134480A (en) Image processing device, image processing method, and program
CN112052706B (en) Electronic device and face recognition method
CN113420686A (en) Power transmission line inspection method, device and system
JP5985327B2 (en) Display device
TWM528432U (en) Heat inspection apparatus and system including the same
CN106846302B (en) Detection method for correctly taking tool and examination table based on method
CN104748863A (en) Infrared analysis area setting device and infrared analysis area setting method