CN117576800A - Automatic inspection method and device for thermal power plant, inspection robot and storage medium - Google Patents
Automatic inspection method and device for thermal power plant, inspection robot and storage medium Download PDFInfo
- Publication number
- CN117576800A CN117576800A CN202311400389.4A CN202311400389A CN117576800A CN 117576800 A CN117576800 A CN 117576800A CN 202311400389 A CN202311400389 A CN 202311400389A CN 117576800 A CN117576800 A CN 117576800A
- Authority
- CN
- China
- Prior art keywords
- inspection
- target
- thermal power
- power plant
- equipment
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 238
- 238000000034 method Methods 0.000 title claims abstract description 59
- 239000007788 liquid Substances 0.000 claims description 100
- 238000001514 detection method Methods 0.000 claims description 53
- 238000004519 manufacturing process Methods 0.000 claims description 23
- 230000002159 abnormal effect Effects 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 14
- 230000007613 environmental effect Effects 0.000 claims description 12
- 238000012423 maintenance Methods 0.000 abstract description 12
- 238000010248 power generation Methods 0.000 abstract description 2
- 239000003550 marker Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/54—Extraction of image or video features relating to texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/185—Electrical failure alarms
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Manipulator (AREA)
Abstract
The application discloses an automatic inspection method, an automatic inspection device, an inspection robot and a storage medium of a thermal power plant, and relates to the field of thermal power generation. It can be understood that in this embodiment, the inspection robot is used to carry out manual inspection or carry out part of manual inspection, so that the working strength of the operation and maintenance personnel is reduced, the number of times that the operation and maintenance personnel go to the site is reduced, the safety risk of the operation and maintenance personnel is reduced, and the personal safety guarantee is improved.
Description
Technical Field
The application relates to the technical field of thermal power generation, in particular to an automatic inspection method and device for a thermal power plant, an inspection robot and a storage medium.
Background
At present, in the thermal power industry, inspection of production equipment is mainly based on inspection of operation and maintenance personnel. I.e. the equipment is checked by the operation and maintenance personnel going to the production site. However, in the production field environment of the thermal power plant, the environment is mostly dangerous, and the risk factors such as high temperature, noise, dust and high altitude fall exist. Therefore, the traditional manual inspection mode has a large safety risk.
Disclosure of Invention
The main aim of the application is to provide an automatic inspection method, device, inspection robot and storage medium for a thermal power plant, and aims to solve the technical problem that a traditional manual inspection mode has a large safety risk.
In order to achieve the above purpose, the application provides an automatic inspection method of a thermal power plant, which is applied to an inspection robot, wherein the inspection robot is configured with an inspection route, and the automatic inspection method of the thermal power plant comprises the following steps:
moving on the production site of the thermal power plant based on the routing inspection route;
After the equipment abuts against the inspection node in the inspection route, acquiring equipment information of equipment corresponding to the inspection node based on data acquisition attitude parameters configured by the inspection node;
and determining the equipment state of the equipment based on the equipment information, and outputting prompt information under the condition that the equipment state is not consistent with the rated equipment state.
Optionally, the device information includes a device image, the inspection node is further configured with a meter object, the meter object corresponds to a preset target shape feature, and the step of determining the device state of the device based on the device information includes:
extracting a preset target shape feature from the device image;
extracting target texture features from the region where the target shape features are located;
generating an instrument value of the instrument object according to the relative position of the target texture feature in the target shape feature;
and taking the instrument value as the equipment state.
Optionally, the step of extracting the target texture feature from the region in which the target shape feature is located includes:
extracting linear features from the region where the target shape features are located based on a linear detection algorithm;
If the number of the linear features is a preset number, the linear features are used as target texture features;
if the number of the straight line features is not the preset number, extracting target color features from the range of the target shape features;
if the number of the target color features is two, taking a boundary between the two color features as the target texture feature;
and if the number of the target color features is one, taking the preset upper and lower limit boundaries of the target shape features as the target texture features.
Optionally, the inspection robot is configured with a camera, the data acquisition gesture parameter is determined based on a positional relationship between the inspection node and the corresponding device, and the step of acquiring the device information of the equipment corresponding to the inspection node based on the data acquisition gesture parameter configured on the inspection node includes:
adjusting the height of the camera and the shooting direction of the camera based on the data acquisition posture parameters;
and acquiring an equipment image of the equipment in the current shooting direction through the camera.
Optionally, the camera is a depth camera, and the automatic inspection method of the thermal power plant further comprises:
Acquiring an environment image in real time in the moving process of the thermal power plant production site based on the routing inspection route;
determining a ground area on the environmental image based on depth information in the environmental image;
performing liquid target detection based on the ground area;
and outputting liquid leakage risk information based on the detection result of the liquid target detection.
Optionally, the step of detecting the liquid target based on the ground area includes:
detecting a communication area in which depth information is missing in the ground area;
determining whether the color value average value of the color values of each position in the connected region is in a preset dark color value range;
and if the color value is not within the preset range of the dark color value, taking the communication area as the liquid target.
Optionally, the step of outputting the liquid leakage risk information based on the detection result of the liquid target detection includes:
if a liquid target is detected from the ground area, determining a target history detection record based on the current position;
judging whether a historical liquid target exists in the target historical detection record;
if the historical liquid target exists and is normal, marking the environment image as normal;
If the historical liquid target does not exist or is abnormal, marking the environment image as abnormal;
and outputting the environment image marked as abnormal as liquid leakage risk information.
In addition, for realizing above-mentioned purpose, this application still provides an automatic inspection device of thermal power plant, is applied to inspection robot, inspection robot disposes the route of patrolling and examining, automatic inspection device of thermal power plant includes:
the moving module is used for moving on the production site of the thermal power plant based on the routing inspection route;
the acquisition module is used for acquiring equipment information of equipment corresponding to the routing inspection node based on the data acquisition attitude parameters configured by the routing inspection node after the routing inspection node in the routing inspection route is reached;
and the determining module is used for determining the equipment state of the equipment based on the equipment information and outputting prompt information under the condition that the equipment state is not consistent with the rated equipment state.
In addition, in order to realize above-mentioned purpose, this application still provides a robot of patrolling and examining, the robot of patrolling and examining includes: the automatic inspection method for the thermal power plant comprises a memory, a processor and an automatic inspection program of the thermal power plant, wherein the automatic inspection program of the thermal power plant is stored in the memory and can run on the processor, and the automatic inspection program of the thermal power plant is executed by the processor to realize the steps of the automatic inspection method for the thermal power plant.
In addition, in order to achieve the above objective, the present application further provides a storage medium, where the storage medium is a computer readable storage medium, and an automatic inspection program of a thermal power plant is stored on the storage medium, and the automatic inspection program of the thermal power plant implements the steps of the automatic inspection method of the thermal power plant when being executed by a processor.
The embodiment of the application provides an automatic inspection method and device for a thermal power plant, an inspection robot and a storage medium. In the embodiment of the application, the automatic inspection method of the thermal power plant is applied to an inspection robot, the inspection robot is provided with an inspection route, and the inspection robot moves on a production site of the thermal power plant based on the inspection route; after the equipment abuts against the inspection node in the inspection route, acquiring equipment information of equipment corresponding to the inspection node based on data acquisition attitude parameters configured by the inspection node; and determining the equipment state of the equipment based on the equipment information, and outputting prompt information under the condition that the equipment state is not consistent with the rated equipment state. That is, the inspection nodes are arranged on the inspection route of the inspection robot, the inspection robot collects equipment information of equipment nearby the inspection nodes on the inspection nodes, the equipment state of the equipment is determined from the equipment information, whether the equipment state is consistent with the rated equipment state is judged based on the equipment state, and if the equipment state is not consistent with the rated equipment state, prompt information is output to carry out alarm prompt. It can be understood that in this embodiment, the inspection robot is used to carry out manual inspection or carry out part of manual inspection, so that the working strength of the operation and maintenance personnel is reduced, the number of times that the operation and maintenance personnel go to the site is reduced, the safety risk of the operation and maintenance personnel is reduced, and the personal safety guarantee is improved.
Drawings
Fig. 1 is a schematic structural diagram of a patrol robot in a hardware running environment according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a first embodiment of an automatic inspection method of a thermal power plant according to the present application;
FIG. 3 is a schematic flow chart of a second embodiment of the automatic inspection method of a thermal power plant according to the present application;
FIG. 4 is a schematic flow chart of a third embodiment of an automatic inspection method of a thermal power plant according to the present application;
fig. 5 is a schematic diagram of an automatic inspection device of a thermal power plant in the automatic inspection method of the thermal power plant.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a patrol robot in a hardware running environment according to an embodiment of the present application.
As shown in fig. 1, the inspection robot may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Optionally, the inspection robot may further include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. The terminal may also be configured with other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., which are not described in detail herein. It will be appreciated by those skilled in the art that the inspection robot configuration shown in fig. 1 is not limiting of the inspection robot and may include more or fewer components than illustrated, or may combine certain components, or may be arranged in a different arrangement of components.
It will be appreciated by those skilled in the art that the inspection robot configuration shown in fig. 1 is not limiting of the inspection robot and may include more or fewer components than illustrated, or may combine certain components, or may be arranged in a different arrangement of components.
Further, as shown in fig. 1, an operating system, a network communication module, a user interface module, and an automatic inspection program of a thermal power plant may be included in the memory 1005 as one type of computer storage medium.
In the inspection robot shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call an automatic inspection program of a thermal power plant stored in the memory 1005, and perform the following operations:
Moving on the production site of the thermal power plant based on the routing inspection route;
after the equipment abuts against the inspection node in the inspection route, acquiring equipment information of equipment corresponding to the inspection node based on data acquisition attitude parameters configured by the inspection node;
and determining the equipment state of the equipment based on the equipment information, and outputting prompt information under the condition that the equipment state is not consistent with the rated equipment state.
In a possible implementation, the processor 1001 may call the automatic inspection program of the thermal power plant stored in the memory 1005, and further perform the following operations:
the device information includes a device image, the inspection node is further configured with an instrument object, the instrument object corresponds to a preset target shape feature, and the step of determining a device state of the device based on the device information includes:
extracting a preset target shape feature from the device image;
extracting target texture features from the region where the target shape features are located;
generating an instrument value of the instrument object according to the relative position of the target texture feature in the target shape feature;
and taking the instrument value as the equipment state.
In a possible implementation, the processor 1001 may call the automatic inspection program of the thermal power plant stored in the memory 1005, and further perform the following operations:
the step of extracting the target texture feature from the region where the target shape feature is located includes:
extracting linear features from the region where the target shape features are located based on a linear detection algorithm;
if the number of the linear features is a preset number, the linear features are used as target texture features;
if the number of the straight line features is not the preset number, extracting target color features from the range of the target shape features;
if the number of the target color features is two, taking a boundary between the two color features as the target texture feature;
and if the number of the target color features is one, taking the preset upper and lower limit boundaries of the target shape features as the target texture features.
In a possible implementation, the processor 1001 may call the automatic inspection program of the thermal power plant stored in the memory 1005, and further perform the following operations:
the inspection robot is configured with a camera, the data acquisition gesture parameters are determined based on the position relationship between the inspection node and the corresponding equipment, and the step of acquiring equipment information of the equipment corresponding to the inspection node based on the data acquisition gesture parameters configured on the inspection node comprises the following steps:
Adjusting the height of the camera and the shooting direction of the camera based on the data acquisition posture parameters;
and acquiring an equipment image of the equipment in the current shooting direction through the camera.
In a possible implementation, the processor 1001 may call the automatic inspection program of the thermal power plant stored in the memory 1005, and further perform the following operations:
the camera is a depth camera, and the automatic inspection method of the thermal power plant further comprises the following steps:
acquiring an environment image in real time in the moving process of the thermal power plant production site based on the routing inspection route;
determining a ground area on the environmental image based on depth information in the environmental image;
performing liquid target detection based on the ground area;
and outputting liquid leakage risk information based on the detection result of the liquid target detection.
In a possible implementation, the processor 1001 may call the automatic inspection program of the thermal power plant stored in the memory 1005, and further perform the following operations:
the step of detecting the liquid target based on the ground area comprises the following steps:
detecting a communication area in which depth information is missing in the ground area;
determining whether the color value average value of the color values of each position in the connected region is in a preset dark color value range;
And if the color value is not within the preset range of the dark color value, taking the communication area as the liquid target.
In a possible implementation, the processor 1001 may call the automatic inspection program of the thermal power plant stored in the memory 1005, and further perform the following operations:
the step of outputting the liquid leakage risk information based on the detection result of the liquid target detection includes:
if a liquid target is detected from the ground area, determining a target history detection record based on the current position;
judging whether a historical liquid target exists in the target historical detection record;
if the historical liquid target exists and is normal, marking the environment image as normal;
if the historical liquid target does not exist or is abnormal, marking the environment image as abnormal;
and outputting the environment image marked as abnormal as liquid leakage risk information.
Referring to fig. 2, a first embodiment of an automatic inspection method of a thermal power plant is applied to a cloud end and an inspection robot, wherein the inspection robot is configured with an inspection route, and the automatic inspection method of the thermal power plant comprises the following steps:
step S10, moving on the production site of the thermal power plant based on the routing inspection route;
It should be noted that, the automatic inspection method of the thermal power plant is applied to an inspection robot, an inspection route is configured on the inspection robot, and in practical application, the inspection robot moves according to the inspection route and completes inspection work of a production site of the thermal power plant. That is, in this embodiment, the inspection robot is used to replace manual inspection, so that the situation that the operation and maintenance personnel enter the field is reduced, and the safety risk of manual inspection is reduced.
By way of example, the inspection robot moves the inspection route in the electronic map on the generating site of the thermal power plant, and it can be understood that at present, the autonomous navigation movement scheme of the robot is mature, which will not be described here again. The inspection route can be set by related technicians according to the positions of equipment which needs to be inspected on the production site, so that the inspection robot can pass through each equipment which needs to be inspected according to the inspection route. Meanwhile, routing inspection nodes can be arranged on the routing inspection route, for example, routing inspection nodes are arranged for key equipment, routing inspection nodes can also be arranged for each equipment needing to be inspected, one equipment can be correspondingly provided with one or more routing inspection nodes, for example, one equipment possibly has information acquisition points at different positions, and correspondingly, a plurality of routing inspection nodes are required to be arranged.
Step S20, after the inspection nodes in the inspection route are abutted, acquiring equipment information of equipment corresponding to the inspection nodes based on data acquisition attitude parameters configured by the inspection nodes;
it should be noted that, the inspection nodes are set in the inspection route. The inspection robot can judge whether the robot reaches the position of the inspection node in the inspection route or not according to the position of the robot in the electronic map and the position of the inspection node marked on the inspection route in the electronic map. In addition, a marker can be set on an actual inspection node in the production field for the inspection robot to judge whether the inspection robot reaches the inspection node, for example, the marker can be a cursor or a two-dimensional code, etc., it can be understood that setting the marker in the production field can provide a relatively accurate positioning basis for the inspection robot, so that the inspection node in the production field is preferably provided with the marker for the inspection robot to judge whether the inspection node is reached. After reaching the inspection node, acquiring equipment information of equipment corresponding to the node based on data acquisition gesture parameters configured on the inspection node, for example, a vision sensor can be configured on an inspection robot, and the data acquisition gesture parameters are position parameters of the vision sensor.
In a possible implementation manner, the inspection robot is configured with a camera, the data acquisition gesture parameter is determined based on a positional relationship between the inspection node and the corresponding device, and the step of acquiring device information of the device corresponding to the inspection node based on the data acquisition gesture parameter configured on the inspection node includes:
step S201, adjusting the height of the camera and the shooting direction of the camera based on the data acquisition gesture parameters;
step S202, collecting device images of devices in the current shooting direction through the camera.
It should be noted that, in this embodiment, the above-mentioned configurable camera of the robot and the data acquisition gesture parameter are determined based on the positional relationship between the inspection node and the corresponding device, for example, in practical application, the camera configured by the inspection robot may be connected to the inspection robot through a mechanical arm, the inspection robot may control the position of the camera through the mechanical arm, when determining the data acquisition gesture, a technician may manually move the camera to a specific position, for example, a position where an instrument image of the device needs to be captured, the specific position may be a position where an instrument front image of the device may be captured, and the specific position may be set by the technician, after the technician manually moves the camera to the characteristic position, the inspection robot may record various joint parameters of the mechanical arm, for example, a position progress parameter, an angle progress parameter, and the like, and may be used as the above-mentioned data acquisition gesture parameter. It can be understood that after the inspection robot arrives at the inspection node, the height of the camera and the shooting direction of the camera are adjusted according to the configuration data acquisition gesture parameters on the inspection node, so that the camera can arrive at a specific position used when the data acquisition gesture parameters are generated, and a front image of the equipment instrument, namely the equipment image, can be shot at the specific position. After the adjustment is completed, the camera can acquire the device image of the device in the current shooting direction, and the device image is the device information.
And step S30, determining the equipment state of the equipment based on the equipment information, and outputting prompt information when the equipment state is not consistent with the rated equipment state.
The device information may be, for example, a device image, and the value of the meter is acquired from the device image based on the image recognition technology, and is taken as the device state. And outputting prompt information when the equipment state is not consistent with the rated equipment state. For example, the value of the instrument is out of the preset rated equipment value range (namely the rated equipment state), so that the possible failure of the equipment can be judged, and prompt information can be output to the centralized control center.
It can be appreciated that in this embodiment, the automatic inspection method of the thermal power plant is applied to an inspection robot, the inspection robot is configured with an inspection route, and the inspection robot moves on a production site of the thermal power plant based on the inspection route; after the equipment abuts against the inspection node in the inspection route, acquiring equipment information of equipment corresponding to the inspection node based on data acquisition attitude parameters configured by the inspection node; and determining the equipment state of the equipment based on the equipment information, and outputting prompt information under the condition that the equipment state is not consistent with the rated equipment state. That is, the inspection nodes are arranged on the inspection route of the inspection robot, the inspection robot collects equipment information of equipment nearby the inspection nodes on the inspection nodes, the equipment state of the equipment is determined from the equipment information, whether the equipment state is consistent with the rated equipment state is judged based on the equipment state, and if the equipment state is not consistent with the rated equipment state, prompt information is output to carry out alarm prompt. It can be understood that in this embodiment, the inspection robot is used to carry out manual inspection or carry out part of manual inspection, so that the working strength of the operation and maintenance personnel is reduced, the number of times that the operation and maintenance personnel go to the site is reduced, the safety risk of the operation and maintenance personnel is reduced, and the personal safety guarantee is improved.
In a possible embodiment, the device information includes a device image, the inspection node is further configured with a meter object, the meter object corresponds to a preset target shape feature, and the step of determining the device state of the device based on the device information includes:
step S210, extracting preset target shape features from the equipment image;
step S220, extracting target texture features from the region where the target shape features are located;
step S230, generating the instrument value of the instrument object according to the relative position of the target texture feature in the target shape feature;
and step S240, taking the instrument value as the equipment state.
It should be noted that, besides being configured with data acquisition gesture parameters, the inspection node may also be configured with an instrument object, where the instrument object is an instrument of the equipment corresponding to the inspection node. For example, the device may be an auxiliary device, and in a thermal power plant, the types of auxiliary devices are correspondingly more, and for example, the meters may be pressure gauges, temperature gauges, level gauges and the like, wherein the level gauges may be divided into oil level gauges and water level gauges, and the oil level gauges or the level gauges are different in form on different auxiliary devices. In this embodiment, different meters are distinguished by different shape features. Typically, the shape of the meter is generally circular or elongated, and the predetermined target shape features are circular or elongated.
Illustratively, a preset target shape feature is extracted from the device image, for example, a circle and a bar. It can be understood that, since the position of acquiring the device image is predetermined (the data acquisition posture parameter is fixed), the position of acquiring the device image can exclude a part of the interference screen from entering the device image when setting. Meanwhile, the preset target shape features are simpler, so that the target shape features can be extracted through a traditional target detection algorithm. And extracting the target texture features from the region where the target shape features are located. It will be appreciated that the instrument is typically a pointer and level indicator to indicate a particular value. The target texture feature is the texture corresponding to the pointer and the liquid level in the area where the target shape feature is located. The target texture feature is typically a straight line. And generating the instrument value of the instrument object according to the relative position of the target texture feature in the target shape feature. Taking a liquid level gauge as an example for illustration, the liquid level in the liquid level gauge is mapped to the height of the liquid in the corresponding device. Correspondingly, the preset target shape feature corresponds to the liquid level meter, the target texture feature corresponds to the liquid level in the liquid level meter, the measuring range of one liquid level meter is set to be 0-100, and if the target texture feature is positioned in the middle of the preset target shape feature, the instrument value can be obtained at the moment to be 50, namely 100×0.5=50. Based on the same method, the circular instrument panel can also obtain a specific instrument value, for example, according to the angle duty ratio pointed by the target texture feature in the circular effective range area and the range of the instrument panel, wherein the circular effective range area can be preset, and is usually a fixed area in a circular shape. The obtained instrument value can be used as the set equipment state.
In a possible embodiment, the step of extracting the target texture feature from the region where the target shape feature is located includes:
step S221, extracting linear features from the region where the target shape features are located based on a linear detection algorithm;
step S222, if the number of the straight line features is a preset number, the straight line features are used as target texture features;
step S223, if the number of the straight line features is not the preset number, extracting target color features from the range of the target shape features;
step S224, if the number of the target color features is two, using a boundary between the two color features as the target texture feature;
step S225, if the number of the target color features is one, taking the preset upper and lower limit boundaries of the target shape features as the target texture features.
For example, a straight line feature may be extracted from the region where the target shape feature is located based on a straight line detection algorithm. It can be understood that the straight line feature extraction is also simpler, for example, the straight line can be extracted by gray processing, binarization, expansion, corrosion and other operations based on the straight line detection algorithm. Of course, the straight line detection algorithm may be an object detection algorithm that targets a straight line.
Furthermore, it should be noted that the level gauge typically displays the level of the liquid by the level of the liquid in the gauge. However, the magnetic plate type liquid level meter is different, for example, red and white (or silver) are respectively present on two sides of the turning plate in the magnetic plate type liquid level meter, the turning plate corresponding position displaying red is set to indicate that liquid is present, the turning plate corresponding position displaying white is set to indicate that liquid is not present, so the turning plate below the liquid level of the magnetic plate type liquid level meter is red, the turning plate above the liquid level is white, and it is understood that the edge of the turning plate can be considered as a straight line because the liquid level of the magnetic plate type liquid level meter is displayed through one turning plate, the number of the extracted straight line features is more, and the fact that which straight line feature represents the texture feature between targets cannot be determined. Therefore, in this embodiment, after the straight line features are extracted, the number of the straight line features is determined.
For example, the preset number is generally set to 1, and if the number of extracted linear features is 1, the linear features may be directly used as the target texture features. And if the number of the straight line features is not 1, extracting the target color features from the range of the target shape features. In general, the target color features are two kinds, and for example, based on the above example, the target color features include red and white, and then a boundary between red and white is taken as a target texture feature. If the number of the target color features is one, for example, if only red is extracted, the liquid level reaches an upper limit, and correspondingly, the preset upper boundary of the target shape feature is taken as the target texture feature, and if only white is extracted, the liquid level reaches a lower limit, and the preset lower boundary of the target shape feature is taken as the target texture feature.
Referring to fig. 3, in order to propose a second embodiment of the present application based on the first embodiment of the present application, in this embodiment, the same or similar parts as those of the above embodiment may be referred to the above, and will not be described herein again. The camera is a depth camera, and the automatic inspection method of the thermal power plant further comprises the following steps:
step A10, acquiring an environment image in real time in the process of moving on the production site of the thermal power plant based on the routing inspection route;
step A20, determining a ground area on the environment image based on depth information in the environment image;
step A30, detecting a liquid target based on the ground area;
and step A40, outputting liquid leakage risk information based on the detection result of the liquid target detection.
In addition to determining the status of each device during inspection, another important task is to determine whether leakage occurs in the field. Leakage may occur anywhere, so that the inspection robot needs to acquire an environmental image in real time during the movement of the inspection robot at the production site of the thermal power plant based on the inspection route. Leakage defects are typically manifested in liquid at the surface, so the acquired environmental image is typically directed toward the surface to find liquid at the surface.
It is understood that in the present embodiment, the camera configured on the inspection robot may be a depth camera. The acquired ambient image may include depth information. A ground area on the ambient image is determined from the depth information. It will be appreciated that the coordinate data of each point bit on the ambient image can be obtained from the depth information. For example, first, coordinate data of each point on the environmental image in the camera coordinate system is obtained by internal parameters of the camera, and the coordinate data in the camera coordinate system is converted into data in the world coordinate system (when the camera position changes, the coordinate conversion matrix can be regenerated by the change amount of the camera position). The current coordinate system conversion method is mature, so that no further description is given here. The ground plane may be marked in advance in the ground coordinate system, so that the determination of the ground area may be determined by the distance between the coordinate data of each point on the environmental image and the marked ground plane, for example, a point with a distance from the ground plane smaller than a preset distance threshold is taken as a point on the ground plane, and then the area formed by the points determined to be on the ground plane is taken as the ground area. And then carrying out liquid target detection on the ground area. The detection of the liquid target can be realized by a target detection algorithm, and the description is omitted here. If the detection result shows that the liquid exists, outputting information that the liquid leakage risk exists at the current position.
In a possible embodiment, the step of detecting the liquid target based on the ground area includes:
step A310, detecting a connected region in which depth information is missing in the ground region;
step A320, determining whether the color value average value of the color values of each position in the connected region is within a preset dark color value range;
and step A330, if the color value is not within the preset range of the dark color value, taking the connected area as the liquid target.
It should be noted that, because the surface of the liquid is smoother, the infrared light emitted by the depth camera is reflected, so that the depth information of the area corresponding to the ground liquid is lost. Therefore, the connected region formed by the point where the depth information is missing in the ground area is searched for. In addition, considering that the dark color (such as black) also causes the depth information to be lost, it is further determined whether the color value average value of the color values of each position in the connected region is within the preset dark color value range, and if not, it is determined that the connected region is a liquid target. On the contrary, if the color value is within the range of the dark color value, it can be determined that the connected region is not a liquid target or the connected region is suspected.
Referring to fig. 4, in order to propose a third embodiment of the present application based on the first embodiment and the second embodiment of the present application, in this embodiment, the same or similar parts as those of the above embodiment may be referred to the above, and will not be repeated here. The step of outputting the liquid leakage risk information based on the detection result of the liquid target detection includes:
Step B10, if the liquid target is detected from the ground area, determining a target history detection record based on the current position;
step B20, judging whether a historical liquid target exists in the target historical detection record;
step B30, if a historical liquid target exists and the historical liquid target is normal, marking the environment image as normal;
step B40, marking the environment image as abnormal if the historical liquid target does not exist or is abnormal;
and step B50, outputting the environment image marked as abnormal as liquid leakage risk information.
For example, if a liquid target is detected from a ground area, repeated judgment is repeated to avoid erroneous judgment, a target history detection record (history environment image) associated with the current position is acquired. Judging whether a historical liquid target exists in the target historical detection record, if the historical liquid target does not exist, marking the environment image as abnormal, and outputting the current position and the environment image marked as abnormal as liquid leakage risk information. If the historical liquid target exists and is normal, the situation image is indicated to be normal, namely the liquid target at the moment is probably normal water stain.
Referring to fig. 5, in addition, the embodiment of the present application further provides an automatic inspection device 100 of a thermal power plant, which is applied to an inspection robot, wherein the inspection robot is configured with an inspection route, and the automatic inspection device 100 of the thermal power plant includes:
a moving module 10 for moving at a production site of the thermal power plant based on the inspection route;
the acquiring module 20 is configured to acquire device information of a device corresponding to the routing inspection node based on the data acquisition gesture parameter configured by the routing inspection node after the routing inspection node in the routing inspection route is reached;
and the determining module 30 is used for determining the equipment state of the equipment based on the equipment information and outputting prompt information when the equipment state is not consistent with the rated equipment state.
Optionally, the device information includes a device image, the inspection node is further configured with a meter object, and the meter object corresponds to a preset target shape feature, and the determining module 30 is further configured to:
extracting a preset target shape feature from the device image;
extracting target texture features from the region where the target shape features are located;
generating an instrument value of the instrument object according to the relative position of the target texture feature in the target shape feature;
And taking the instrument value as the equipment state.
Optionally, the determining module 30 is further configured to:
extracting linear features from the region where the target shape features are located based on a linear detection algorithm;
if the number of the linear features is a preset number, the linear features are used as target texture features;
if the number of the straight line features is not the preset number, extracting target color features from the range of the target shape features;
if the number of the target color features is two, taking a boundary between the two color features as the target texture feature;
and if the number of the target color features is one, taking the preset upper and lower limit boundaries of the target shape features as the target texture features.
Optionally, the inspection robot is configured with a camera, the data acquisition gesture parameter is determined based on a positional relationship between the inspection node and the corresponding device, and the acquiring module 20 is further configured to:
adjusting the height of the camera and the shooting direction of the camera based on the data acquisition posture parameters;
and acquiring an equipment image of the equipment in the current shooting direction through the camera.
Optionally, the camera is a depth camera, and the automatic inspection device 100 for a thermal power plant further includes a liquid detection module 40, where the liquid detection module 40 is configured to:
Acquiring an environment image in real time in the moving process of the thermal power plant production site based on the routing inspection route;
determining a ground area on the environmental image based on depth information in the environmental image;
performing liquid target detection based on the ground area;
and outputting liquid leakage risk information based on the detection result of the liquid target detection.
Optionally, the liquid detection module 40 is further configured to:
detecting a communication area in which depth information is missing in the ground area;
determining whether the color value average value of the color values of each position in the connected region is in a preset dark color value range;
and if the color value is not within the preset range of the dark color value, taking the communication area as the liquid target.
Optionally, the liquid detection module 40 is further configured to:
if a liquid target is detected from the ground area, determining a target history detection record based on the current position;
judging whether a historical liquid target exists in the target historical detection record;
if the historical liquid target exists and is normal, marking the environment image as normal;
if the historical liquid target does not exist or is abnormal, marking the environment image as abnormal;
And outputting the environment image marked as abnormal as liquid leakage risk information.
The application provides an automatic inspection device of thermal power plant adopts the automatic inspection method of thermal power plant among the above-mentioned embodiment, aims at solving the mode that traditional manual work was patrolled and examined, has great security risk's technical problem. Compared with the prior art, the beneficial effects of the automatic inspection device for the thermal power plant provided by the embodiment of the application are the same as those of the automatic inspection method for the thermal power plant provided by the embodiment, and other technical features in the automatic inspection device for the thermal power plant are the same as those disclosed by the method of the embodiment, so that redundant description is omitted.
In addition, in order to realize above-mentioned purpose, this application still provides a robot of patrolling and examining, the robot of patrolling and examining includes: the automatic inspection method for the thermal power plant comprises a memory, a processor and an automatic inspection program for the thermal power plant, wherein the automatic inspection program is stored in the memory and can run on the processor, and the automatic inspection program for the thermal power plant realizes the steps of the automatic inspection method for the thermal power plant when being executed by the processor.
The specific implementation manner of the inspection robot is basically the same as the above embodiments of the automatic inspection method of the thermal power plant, and will not be described herein.
In addition, in order to achieve the above purpose, the present application further provides a storage medium, where an automatic inspection program of a thermal power plant is stored on the storage medium, and the automatic inspection program of the thermal power plant implements the steps of the automatic inspection method of the thermal power plant when being executed by a processor.
The specific implementation manner of the storage medium is basically the same as that of each embodiment of the automatic inspection method of the thermal power plant, and is not repeated here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above, including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in the embodiments of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
Claims (10)
1. The automatic inspection method for the thermal power plant is characterized by being applied to an inspection robot, wherein the inspection robot is provided with an inspection route, and the automatic inspection method for the thermal power plant comprises the following steps of:
moving on the production site of the thermal power plant based on the routing inspection route;
after the equipment abuts against the inspection node in the inspection route, acquiring equipment information of equipment corresponding to the inspection node based on data acquisition attitude parameters configured by the inspection node;
and determining the equipment state of the equipment based on the equipment information, and outputting prompt information under the condition that the equipment state is not consistent with the rated equipment state.
2. The automatic inspection method of a thermal power plant according to claim 1, wherein the equipment information includes equipment images, the inspection node is further configured with an instrument object corresponding to a preset target shape feature, and the step of determining the equipment state of the equipment based on the equipment information includes:
Extracting a preset target shape feature from the device image;
extracting target texture features from the region where the target shape features are located;
generating an instrument value of the instrument object according to the relative position of the target texture feature in the target shape feature;
and taking the instrument value as the equipment state.
3. The automatic inspection method of a thermal power plant according to claim 2, wherein the step of extracting the target texture feature from the region where the target shape feature is located comprises:
extracting linear features from the region where the target shape features are located based on a linear detection algorithm;
if the number of the linear features is a preset number, the linear features are used as target texture features;
if the number of the straight line features is not the preset number, extracting target color features from the range of the target shape features;
if the number of the target color features is two, taking a boundary between the two color features as the target texture feature;
and if the number of the target color features is one, taking the preset upper and lower limit boundaries of the target shape features as the target texture features.
4. The automatic inspection method of a thermal power plant according to claim 3, wherein the inspection robot is configured with a camera, the data acquisition posture parameter is determined based on a positional relationship between the inspection node and the corresponding device, and the step of acquiring device information of the inspection node corresponding device based on the data acquisition posture parameter configured on the inspection node comprises:
Adjusting the height of the camera and the shooting direction of the camera based on the data acquisition posture parameters;
and acquiring an equipment image of the equipment in the current shooting direction through the camera.
5. The automatic inspection method of a thermal power plant according to claim 4, wherein the camera is a depth camera, the automatic inspection method of a thermal power plant further comprising:
acquiring an environment image in real time in the moving process of the thermal power plant production site based on the routing inspection route;
determining a ground area on the environmental image based on depth information in the environmental image;
performing liquid target detection based on the ground area;
and outputting liquid leakage risk information based on the detection result of the liquid target detection.
6. The automatic inspection method of a thermal power plant according to claim 5, wherein the step of performing liquid target detection based on the ground area comprises:
detecting a communication area in which depth information is missing in the ground area;
determining whether the color value average value of the color values of each position in the connected region is in a preset dark color value range;
and if the color value is not within the preset range of the dark color value, taking the communication area as the liquid target.
7. The automatic inspection method of a thermal power plant according to claim 5, wherein the step of outputting the liquid leakage risk information based on the detection result of the liquid target detection includes:
if a liquid target is detected from the ground area, determining a target history detection record based on the current position;
judging whether a historical liquid target exists in the target historical detection record;
if the historical liquid target exists and is normal, marking the environment image as normal;
if the historical liquid target does not exist or is abnormal, marking the environment image as abnormal;
and outputting the environment image marked as abnormal as liquid leakage risk information.
8. The utility model provides an automatic device of patrolling and examining of thermal power plant, its characterized in that is applied to the robot of patrolling and examining, the robot of patrolling and examining is furnished with the route of patrolling and examining, the automatic device of patrolling and examining of thermal power plant includes:
the moving module is used for moving on the production site of the thermal power plant based on the routing inspection route;
the acquisition module is used for acquiring equipment information of equipment corresponding to the routing inspection node based on the data acquisition attitude parameters configured by the routing inspection node after the routing inspection node in the routing inspection route is reached;
And the determining module is used for determining the equipment state of the equipment based on the equipment information and outputting prompt information under the condition that the equipment state is not consistent with the rated equipment state.
9. The utility model provides a robot patrols and examines, its characterized in that, the robot patrols and examines includes memory, treater and storage and can be on the automatic procedure of patrolling and examining of thermal power plant on the treater, wherein: the steps of the automatic inspection method of a thermal power plant according to any one of claims 1 to 7 are realized when the automatic inspection program of the thermal power plant is executed by the processor.
10. A storage medium, characterized in that the storage medium is a computer readable storage medium, and the storage medium stores an automatic inspection program of a thermal power plant, and the automatic inspection program of the thermal power plant realizes the steps of the automatic inspection method of the thermal power plant according to any one of claims 1 to 7 when being executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311400389.4A CN117576800B (en) | 2023-10-25 | 2023-10-25 | Automatic inspection method and device for thermal power plant, inspection robot and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311400389.4A CN117576800B (en) | 2023-10-25 | 2023-10-25 | Automatic inspection method and device for thermal power plant, inspection robot and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117576800A true CN117576800A (en) | 2024-02-20 |
| CN117576800B CN117576800B (en) | 2024-09-10 |
Family
ID=89863398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311400389.4A Active CN117576800B (en) | 2023-10-25 | 2023-10-25 | Automatic inspection method and device for thermal power plant, inspection robot and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117576800B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951900A (en) * | 2017-04-13 | 2017-07-14 | 杭州申昊科技股份有限公司 | A kind of automatic identifying method of arrester meter reading |
| US20180253619A1 (en) * | 2017-03-06 | 2018-09-06 | Intelligent Security Systems Corporation | Systems and methods for evaluating readings of gauge dials |
| CN112183369A (en) * | 2020-09-29 | 2021-01-05 | 国网上海市电力公司 | Pointer instrument reading identification method for transformer substation unmanned inspection |
| CN113326787A (en) * | 2021-06-02 | 2021-08-31 | 武汉理工大学 | Automatic identification method, system and equipment for reading of pointer instrument |
| CN113727022A (en) * | 2021-08-30 | 2021-11-30 | 杭州申昊科技股份有限公司 | Inspection image acquisition method and device, electronic equipment and storage medium |
| CN215177415U (en) * | 2021-08-02 | 2021-12-14 | 陈忠艺 | Position indication structure of actuator |
| WO2023110210A1 (en) * | 2021-12-13 | 2023-06-22 | Ispark | Robust remote instrument reading |
-
2023
- 2023-10-25 CN CN202311400389.4A patent/CN117576800B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180253619A1 (en) * | 2017-03-06 | 2018-09-06 | Intelligent Security Systems Corporation | Systems and methods for evaluating readings of gauge dials |
| CN106951900A (en) * | 2017-04-13 | 2017-07-14 | 杭州申昊科技股份有限公司 | A kind of automatic identifying method of arrester meter reading |
| CN112183369A (en) * | 2020-09-29 | 2021-01-05 | 国网上海市电力公司 | Pointer instrument reading identification method for transformer substation unmanned inspection |
| CN113326787A (en) * | 2021-06-02 | 2021-08-31 | 武汉理工大学 | Automatic identification method, system and equipment for reading of pointer instrument |
| CN215177415U (en) * | 2021-08-02 | 2021-12-14 | 陈忠艺 | Position indication structure of actuator |
| CN113727022A (en) * | 2021-08-30 | 2021-11-30 | 杭州申昊科技股份有限公司 | Inspection image acquisition method and device, electronic equipment and storage medium |
| WO2023110210A1 (en) * | 2021-12-13 | 2023-06-22 | Ispark | Robust remote instrument reading |
Non-Patent Citations (1)
| Title |
|---|
| 周泓;徐海儿;耿晨歌;: "基于HSI模型和Hough变换的指针式汽车仪表自动校验", 浙江大学学报(工学版), no. 06, 15 June 2010 (2010-06-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117576800B (en) | 2024-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109325520B (en) | Method, device and system for checking petroleum leakage | |
| US20180247121A1 (en) | Systems and methods for surface and subsurface damage assessments, patch scans, and visualization | |
| JP2020118484A (en) | System for automatically reading indicated value of indicator of analog meter and method for automatic reading | |
| CN104316033A (en) | Visual inspection system for automobile parts | |
| CN115808324B (en) | Light safety management monitoring method and system for small and medium span bridges | |
| CN113379712A (en) | Steel bridge bolt disease detection method and system based on computer vision | |
| CN112484655A (en) | Large tank type equipment structure deformation online detection and applicability evaluation system and method | |
| CN115063017A (en) | Monitoring and evaluating system and method for small and medium-span bridge structure | |
| CN113865712A (en) | JP regulator cubicle temperature monitoring system | |
| Liu et al. | An approach for auto bridge inspection based on climbing robot | |
| CN104316530A (en) | Part detection method and application | |
| CN115993366A (en) | Workpiece surface detection method and system based on sensing equipment | |
| CN113778091A (en) | Method for inspecting equipment of wind power plant booster station | |
| CN114486132A (en) | Bridge body vertical displacement measuring device | |
| CN117576800B (en) | Automatic inspection method and device for thermal power plant, inspection robot and storage medium | |
| CN116678368B (en) | BIM technology-based intelligent acquisition method for assembled steel structure data | |
| CN117853295A (en) | Safety environmental protection emergency system based on industry interconnection and digital panorama | |
| CN109879170B (en) | Crane jib sidewise bending displacement real-time detection system | |
| CN106123808B (en) | A method of it is measured for the deflection of automobile rearview mirror specular angle degree | |
| CN116818233A (en) | High-precision bridge state monitoring method and system adopting laser and machine vision | |
| CN115857536A (en) | Unmanned aerial vehicle intelligent inspection method, device, equipment and medium for workshop equipment | |
| CN111678438B (en) | Scale body displacement early warning method and system | |
| CN110231152B (en) | Unmanned aerial vehicle-based derrick detection method and equipment | |
| US11886897B2 (en) | Personal digital assistant and inspection support system | |
| CN118362058B (en) | Tunnel deformation detection method, device, equipment, storage medium and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |