CN115656700B - Detection method, training method, electric appliance, monitoring system and storage medium - Google Patents
Detection method, training method, electric appliance, monitoring system and storage medium Download PDFInfo
- Publication number
- CN115656700B CN115656700B CN202211578164.3A CN202211578164A CN115656700B CN 115656700 B CN115656700 B CN 115656700B CN 202211578164 A CN202211578164 A CN 202211578164A CN 115656700 B CN115656700 B CN 115656700B
- Authority
- CN
- China
- Prior art keywords
- vibration
- detection
- electric appliance
- information
- rotating speed
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 217
- 238000012549 training Methods 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012544 monitoring process Methods 0.000 title claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 37
- 230000002159 abnormal effect Effects 0.000 claims abstract description 20
- 238000005070 sampling Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 11
- 238000012423 maintenance Methods 0.000 description 9
- 230000005856 abnormality Effects 0.000 description 7
- 230000001133 acceleration Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000006073 displacement reaction Methods 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/89—Arrangement or mounting of control or safety devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H1/00—Measuring characteristics of vibrations in solids by using direct conduction to the detector
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B40/00—Technologies aiming at improving the efficiency of home appliances, e.g. induction cooking or efficient technologies for refrigerators, freezers or dish washers
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Mechanical Engineering (AREA)
- Data Mining & Analysis (AREA)
- Combustion & Propulsion (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Thermal Sciences (AREA)
Abstract
The application relates to the technical field of electric appliance detection, and discloses a detection method, a training method, an electric appliance, a monitoring system and a storage medium. The detection method comprises the steps of obtaining vibration signals collected by vibration sensors arranged on the electric appliance, wherein the vibration sensors comprise a plurality of vibration sensors which are arranged at different preset positions of the electric appliance, and the vibration rules of the different preset positions are different; processing the vibration signal to obtain vibration information; and respectively inputting the vibration information of each vibration sensor to the detection model corresponding to each vibration sensor so as to output a detection result, wherein the detection result comprises whether each preset position is abnormal or not. The vibration sensor is used for acquiring vibration signals of the electric appliance, processing the vibration signals to obtain vibration information, inputting the vibration information into the detection model, and judging whether the electric appliance is abnormal or not according to a detection result output by the detection model, so that a user can know whether the electric appliance is abnormal or not in time, and the electric appliance can be checked and maintained in time.
Description
Technical Field
The present application relates to the field of electrical appliance detection technologies, and in particular, to a detection method, a training method, an electrical appliance, a monitoring system, and a computer-readable storage medium.
Background
Along with the development of the times, the demand of people on electrical appliances is continuously increased, the electrical appliances become necessary equipment in people's lives, and because the electrical appliances are provided with shells, the internal operation conditions of the electrical appliances cannot be visually seen at work, so that a user can find out that the electrical appliances have faults only when the electrical appliances have faults which affect the normal operation of the electrical appliances seriously, and the electrical appliances cannot be maintained in time.
Disclosure of Invention
The embodiment of the application provides a detection method, a training method, an electric appliance, a monitoring system and a computer readable storage medium.
The detection method comprises the steps of obtaining vibration signals collected by vibration sensors arranged on an electric appliance, wherein the vibration sensors comprise a plurality of vibration sensors which are arranged at different preset positions of the electric appliance, and the vibration rules of the different preset positions are different; processing the vibration signal to obtain vibration information; and respectively inputting the vibration information of each vibration sensor to a detection model corresponding to each vibration sensor so as to output a detection result, wherein the detection result comprises whether each preset position is abnormal or not.
The training method comprises the steps of obtaining historical vibration signals collected by vibration sensors arranged on an electric appliance, wherein the vibration sensors comprise a plurality of vibration sensors which are arranged at different preset positions of the electric appliance, and the vibration rules of the different preset positions are different; processing the historical vibration signal to obtain a plurality of training samples; training a detection model corresponding to each vibration sensor according to a plurality of training samples corresponding to each vibration sensor so that the detection model corresponding to each vibration sensor is converged, wherein the detection model is an unsupervised model.
The electric appliance comprises a first processor, wherein the first processor is used for acquiring vibration signals acquired by vibration sensors arranged on the electric appliance, the vibration sensors are arranged at different preset positions of the electric appliance, and the vibration laws at the different preset positions are different; processing the vibration signal to obtain vibration information; and respectively inputting the vibration information of each vibration sensor to a detection model corresponding to each vibration sensor so as to output a detection result, wherein the detection result comprises whether each preset position is abnormal or not.
The monitoring system comprises an electric appliance, wherein a first processor of the electric appliance is used for acquiring vibration signals acquired by vibration sensors arranged on the electric appliance and uploading the vibration signals to a cloud server, the vibration sensors comprise a plurality of vibration sensors, the plurality of vibration sensors are arranged at different preset positions of the electric appliance, and the vibration rules of the different preset positions are different; the second processor of the cloud server is used for processing the vibration signal to obtain vibration information; and respectively inputting the vibration information of each vibration sensor to a detection model corresponding to each vibration sensor so as to output a detection result, wherein the detection result comprises whether each preset position is abnormal or not.
In the detection method, the training method, the electric appliance, the monitoring system and the computer-readable storage medium according to the embodiment of the application, the vibration sensor is arranged on the electric appliance to collect vibration signals in real time, and the collected vibration signals are processed to obtain vibration information. The extracted vibration information is input into a preset detection model, and whether the electrical appliance is abnormal or not is judged according to a detection result output by the detection model, so that a user can know whether the electrical appliance is abnormal or not in time, the electrical appliance can be checked and maintained in time, the slight fault of the electrical appliance can be prevented from being evolved into a serious fault, and compared with the maintenance of the serious fault which affects the operation of the electrical appliance, the maintenance cost is high, the maintenance time is long, and the maintenance cost and the maintenance time can be reduced by timely maintaining the slight fault. In addition, because the vibration rules of the vibration sensors arranged at different preset positions of the electric appliance are different, each vibration sensor performs abnormality detection through the corresponding detection model, the abnormality detection accuracy of each vibration sensor can be improved, and the position of the abnormal vibration sensor can be accurately positioned, so that the position of a possible fault in the electric appliance can be accurately positioned, and the accurate detection of the fault is realized.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow diagram of a detection method according to certain embodiments of the present application;
FIG. 2 is a schematic structural diagram of an appliance in accordance with certain embodiments of the present application;
FIG. 3 is a schematic flow chart of a detection method according to certain embodiments of the present application;
FIG. 4 is a schematic flow chart of a detection method according to certain embodiments of the present application;
FIG. 5 is a schematic flow chart of a detection method according to certain embodiments of the present application;
FIG. 6 is a schematic flow chart of a detection method according to certain embodiments of the present application;
FIG. 7 is a graphical representation of the reliability of an appliance at different rotational speeds for the detection method of certain embodiments of the present application;
FIG. 8 is a schematic flow chart of a detection method according to certain embodiments of the present application;
FIG. 9 is a schematic structural diagram of an appliance in accordance with certain embodiments of the present application;
FIG. 10 is a schematic flow chart of a detection method according to certain embodiments of the present application;
FIG. 11 is a schematic flow chart diagram of a training method according to some embodiments of the present application;
FIG. 12 is a schematic flow chart diagram of a training method according to some embodiments of the present application;
FIG. 13 is a schematic flow chart diagram of a training method according to some embodiments of the present application;
FIG. 14 is a schematic diagram of a training method according to certain embodiments of the present application;
FIG. 15 is a schematic diagram of a connection between a first processor and a second processor in some embodiments of the present application;
FIG. 16 is a schematic diagram of a storage medium coupled to a first processor and a second processor in accordance with certain embodiments of the present application;
FIG. 17 is a block schematic diagram of a detection device according to certain embodiments of the present application;
FIG. 18 is a block diagram of an exercise device according to some embodiments of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of explaining the embodiments of the present application, and are not to be construed as limiting the embodiments of the present application.
Referring to fig. 1 to 2, the detection method of the present embodiment is applied to an electrical appliance 100, and the detection method includes the following steps:
011: the vibration sensor 30 of the electric appliance 100 is used for acquiring vibration signals collected, the vibration sensors 30 comprise a plurality of vibration sensors, the plurality of vibration sensors 30 are arranged at different preset positions of the electric appliance 100, and the vibration rules of the different preset positions are different.
Specifically, the electric appliance 100 is provided with a plurality of vibration sensors 30, each vibration sensor 30 is used for collecting a vibration signal (the vibration signal at least comprises an acceleration) of the electric appliance 100, the number of the vibration sensors 30 can be determined according to actual conditions, and each vibration sensor 30 can be arranged at any position where the vibration signal of the electric appliance 100 can be extracted, so that the vibration sensor 30 can timely collect the vibration signal of the electric appliance 100, and when the vibration signal of the electric appliance 100 needs to be obtained, the vibration sensor 30 can collect the vibration signal of the electric appliance 100. It should be noted that the electric appliance 100 may be a refrigeration device such as an air conditioner or a refrigerator; the vibration sensor 30 may be a sensor capable of obtaining acceleration, such as an acceleration sensor or a displacement sensor, and the vibration signal may be an acceleration signal when the vibration sensor 30 is an acceleration sensor, or a displacement signal when the vibration sensor 30 is a displacement sensor, and the acceleration signal may be obtained by integrating the displacement signal.
012: and processing the vibration signal to obtain vibration information.
Specifically, when the vibration sensor 30 collects the vibration signal of the electric appliance 100, the collected vibration signal may be processed, such as calculating the vibration intensity, the vibration kurtosis, and the first-order vibration information of the collected vibration signal.
Optionally, the collected vibration signals may be subjected to a detrending term processing and a denoising processing.
Specifically, a least square method can be used to eliminate the trend term contained in the zero point drift of the vibration signal and remove the vibration signal beyond the threshold of the collected vibration signal, such as 0.5 meter per square second (m/s) of the vibration signal 2 ) To 0.7m/s 2 The collected vibration signals are respectively 0.45m/s 2 、0.6m/s 2 And 0.55m/s 2 In this case, it is necessary to set the ratio to 0.45m/s 2 The vibration signal of (2) is removed. Therefore, the accuracy of the acquired vibration signal is ensured.
013: the vibration information of each vibration sensor 30 is respectively input to the detection model 80 corresponding to each vibration sensor 30 to output a detection result including whether there is an abnormality at each preset position.
Specifically, the obtained vibration information of each vibration sensor 30 is input into the corresponding detection model 80, the detection model 80 automatically detects the input vibration information and outputs a detection result, the detection result at least includes information about whether each preset position is abnormal or not to indicate whether each preset position is possibly faulty or not, and when the detection result indicates that the preset position is abnormal, it indicates that the preset position is possibly faulty or needs to be overhauled.
It should be noted that the detection model 80 is preset in advance, and in this example, the detection model 80 used is taken as the detection model 80 based on the isolated forest algorithm for example. Of course, the detection model 80 of the present application is not limited to the detection model 80 based on the isolated forest algorithm, but only needs to be an unsupervised model based on the unsupervised algorithm, and is not described one by one here.
According to the detection method, the vibration sensors 30 are arranged at a plurality of preset positions of the electric appliance 100 to collect vibration signals of the electric appliance 100, and then the collected vibration signals are processed to obtain vibration information (the vibration signals can be vibration intensity, vibration kurtosis and first-order vibration information). And then, inputting the extracted vibration information into a preset detection model 80 for detection, outputting a detection result, determining whether each preset position of the electric appliance 100 is abnormal or not by judging the result output by the detection model 80, and sending the detection result to a user so that the user can timely check and maintain the electric appliance 100, thereby being beneficial to preventing slight faults of the electric appliance 100 from being evolved into serious faults, and being higher in maintenance cost and longer in maintenance time compared with the maintenance of serious faults affecting the operation of the electric appliance 100, and being capable of reducing the maintenance cost and time by timely maintaining the slight faults. In addition, because the vibration rules of the vibration sensors 30 disposed at different preset positions of the electrical apparatus 100 are different, if there is attenuation due to vibration, the vibration information on the bearings can be extracted to obtain vibration intensity, vibration kurtosis and first-order vibration information, the revolving body (such as the bearings) has the first-order vibration information, but the shell cannot obtain the first-order vibration information, therefore, each vibration sensor 30 needs to establish a corresponding detection model 80 for abnormal detection, which not only can improve the accuracy of abnormal detection on each vibration sensor 30, but also can accurately locate the position of the abnormal vibration sensor 30, thereby accurately locating the position where there is a possible fault in the electrical apparatus 100, and realizing accurate detection of the fault.
Referring to fig. 2, in some example embodiments, the vibration sensor 30 is disposed at a position where the bearing portion 40 of the electric appliance 100 is located.
Specifically, the appliance 100 includes a bearing portion 40. The vibration sensor 30 must be installed at a position where it can acquire a vibration signal of the bearing portion 40 of the electric appliance 100. Such as the housing portion corresponding to the bearing portion 40, provided in the housing 50 of the electrical apparatus 100, enables the vibration sensor 30 to timely acquire the vibration signal of the bearing portion 40.
Referring to fig. 3, in some example embodiments, step 011: obtain the vibration signal who sets up the vibration sensor 30 collection at electrical apparatus 100, vibration sensor 30 includes a plurality ofly, and a plurality of vibration sensor 30 set up the different preset position at electrical apparatus 100, and the vibration law of the different preset position is different, includes following step:
0111: a preset number of vibration signals are acquired within a preset time period based on the sampling frequency of the vibration sensor 30.
Specifically, the vibration sensor 30 collects the vibration signal according to its sampling frequency, and the collection frequency is preset in advance. And the user can set a preset time length based on the acquisition frequency of the vibration sensor 30, thereby acquiring a preset number of vibration signals. If the sampling frequency of the vibration sensor 30 is 1 second to collect 1024 vibration signals, and the sampling time is required to be 1 minute to sample the vibration signals of the electric appliance 100, the vibration sensor can collect 60 groups of 1024 vibration signals in 1 minute, that is, the vibration sensor can collect 61440 vibration signals in total.
Referring to fig. 4, in some example embodiments, the vibration information includes vibration intensity and vibration kurtosis, step 012: the vibration signal is processed to obtain vibration information, and the method comprises the following steps:
0121: and processing the preset number of vibration signals to obtain the vibration intensity and the vibration kurtosis.
Wherein, the vibration intensity represents the intensity of the vibration of the electric appliance 100, and can be used for measuring the magnitude of the vibration intensity of the electric appliance 100; the vibration kurtosis is a numerical statistic that reflects the distribution characteristics of vibration signals, and is one of important features for determining whether the electrical appliance 100 is abnormal.
Specifically, the vibration information obtained after processing the vibration signals includes vibration intensity and vibration kurtosis, and the vibration intensity and the vibration kurtosis are obtained by processing a preset number of vibration signals obtained within a preset time period.
The vibration intensity can be obtained according to the following formula:
wherein M is the vibration intensity, k +1 represents the number of vibration signals contained in the sample, and if 1024 vibration signals collected within 1s are taken as one sample, the vibration intensity of each sample can be obtained,
representing the ith vibration signal.
The vibration kurtosis can be obtained according to the following formula:
wherein Z is the vibration kurtosis, n is the number of vibration signals contained in the sample, then the vibration kurtosis vibration signal of each sample can be obtained, x i For the (i) th vibration signal,
is the mean of the vibration signals contained by the sample.
Referring to fig. 5, the detection method according to the embodiment of the present application further includes the following steps:
014: acquiring the rotating speed of the electric appliance 100 and synchronizing the vibration signals and the rotating speed to acquire the rotating speed corresponding to each vibration signal;
the vibration information also includes vibration first order information, step 012: processing the vibration signal to obtain vibration information, comprising:
0122: carrying out Fourier transform on a preset number of vibration signals to obtain frequencies and amplitudes corresponding to the frequencies;
0123: acquiring a target frequency with a value equal to a target rotating speed, wherein the target frequency is any one of a plurality of frequencies, and the target rotating speed is the maximum value of the rotating speeds corresponding to a preset number of vibration signals;
0124: and obtaining the amplitude corresponding to the target frequency to be used as first-order vibration information.
Specifically, the acceleration signal of the electric appliance 100 is acquired by the vibration sensor 30, the rotational speed of the electric appliance 100 is acquired by the encoder 60, and then the acquisition time of each vibration signal is synchronized with the acquisition time of each rotational speed, so as to acquire the rotational speed at which each vibration signal is synchronized, for example, the vibration signal with the smallest difference in the acquisition time is synchronized with the rotational speed, so that each vibration signal has a rotational speed corresponding to one another. In addition, the vibration information also includes first-order vibration information (one of important features reflecting whether the bearing portion 40 of the electrical appliance 100 is abnormal), a preset number of vibration signals are subjected to fourier transform, so that a frequency and an amplitude corresponding to the frequency are obtained, and the amplitude corresponding to the target frequency is used as the first-order vibration information.
It should be noted that the value of the target frequency is equal to the target rotation speed corresponding to the preset number of vibration signals, and the target rotation speed is the maximum value of the rotation speeds corresponding to the preset number of vibration signals, for example, the vibration signals include vibration signal A1, vibration signal A2, vibration signal A3, and vibration signal A4, the rotation speed corresponding to vibration signal A1 is 150rps, the rotation speed corresponding to vibration signal A2 is 160rps, the rotation speed corresponding to vibration signal A3 is 100rps, and the rotation speed corresponding to vibration signal A4 is 200rps, at this time, the maximum value of the rotation speeds corresponding to vibration signal A1, vibration signal A2, vibration signal A3, and vibration signal A4 is taken as the target rotation speed, that is, the maximum rotation speed 200rps is taken as the target rotation speed of vibration signal A1, vibration signal A2, vibration signal A3, and vibration signal A4. After the target frequency is determined, the amplitude corresponding to the target frequency can be obtained, so that the amplitude corresponding to the target frequency is determined to be used as first-order vibration information; for another example, the number of the vibration signals collected by the vibration sensor is 1000 within 1 second, and the rotation speeds of the electric appliance 100 appearing in the second are 60 revolutions per second (rps), 100rps and 200rps, respectively, so that the target rotation speed can be determined to be 200rps.
The vibration first order information can be obtained according to the following formula:
L=f(r/1), wherein L is first order information of vibration, r is rotational speed, and the unit is revolutions per second (rps); f (x) is the amplitude of the signal at frequency x.
Referring to fig. 6, in some exemplary embodiments, the detection model 80 corresponding to each vibration sensor 30 includes a plurality of detection models 80, and the plurality of detection models 80 correspond to a plurality of rotation speed ranges, respectively, in step 013: the method for inputting the vibration information of each vibration sensor 30 to the detection model 80 corresponding to each vibration sensor 30 to output the detection result comprises the following steps:
0131: the vibration information of each vibration sensor 30 is input to the target detection model corresponding to each vibration sensor 30, which is any one of the plurality of detection models 80, to output the detection result, and the target detection model is the detection model 80 corresponding to the rotation speed range in which the target rotation speed is located.
Specifically, the detection pattern 80 corresponding to each vibration sensor 30 may include one or more, and each detection pattern 80 corresponds to a rotation speed range. The rotation speed ranges are divided according to the change of the stability indexes of the electric appliance 100 at different rotation speeds, for example, fig. 7 shows the reliability of the electric appliance 100 at different rotation speeds, and fig. 7 shows that the rotation speed ranges a, B and C are known, and the rotation speed ranges a, B and C are divided into three rotation speed ranges because the trend of the change of the stability indexes is different, and each rotation speed range has one corresponding detection model 80, so that the vibration information of the detection model 80 in the rotation speed range corresponding to the detected target rotation speed is more accurate.
After the vibration signal of each vibration sensor 30 is processed to obtain vibration information, the vibration information of each vibration sensor is input into a corresponding target detection model for detection, so as to obtain a detection result. The target detection model is any one of the plurality of detection models 80, and the target detection model is the detection model 80 corresponding to the rotation speed range in which the target rotation speed is located. Therefore, the accuracy of the detected detection result can be ensured. If the detection pattern 80 includes the detection pattern Y1, the detection pattern Y2, and the detection pattern Y3. The method comprises the steps that the detection range of the rotating speed corresponding to a detection model Y1 is (200rps, 400rps), the detection range of the rotating speed corresponding to a detection model Y2 is (400rps, 600rps), the detection range of the rotating speed corresponding to a detection model Y3 is (600rps, 800rps), 3 groups of vibration signals are collected by a vibration sensor, the 3 groups of vibration signals are processed respectively to obtain vibration information Y1, vibration information Y2 and vibration information Y3, firstly, the maximum value of the rotating speed corresponding to a preset number of vibration signals corresponding to the vibration information Y1 is determined, the maximum value of the rotating speed corresponding to the vibration information Y1 is determined, the target rotating speed corresponding to the vibration information Y2 is determined, the target rotating speed corresponding to the vibration information Y3 is determined, the target rotating speed corresponding to the vibration information Y1 is determined to be 330 s, the target rotating speed corresponding to the vibration information Y2 is determined, the target rotating speed corresponding to the vibration information Y3 is input into the detection model Y2, and then the detection result of the vibration information Y1 is input into the detection model Y2, and the detection model Y3.
Referring to fig. 8, in some exemplary embodiments, the vibration sensor 30 includes a plurality of vibration sensors 30, and the plurality of vibration sensors 30 are disposed at different predetermined positions of the electrical appliance 100, step 011: the method for acquiring the vibration signals collected by the vibration sensors 30 arranged on the electric appliance 100 comprises the following steps that:
0112: acquiring a vibration signal acquired by the vibration sensor 30 at each preset position;
step 012: processing the vibration signal to obtain vibration information, comprising the steps of:
0125: processing the vibration signals collected by each vibration sensor 30 to obtain vibration information corresponding to each vibration sensor 30;
step 013: the method for inputting the vibration information of each vibration sensor 30 to the corresponding detection model 80 of each vibration sensor 30 to output the detection result comprises the following steps:
0132: the vibration information of each vibration sensor 30 is respectively input to the detection model 80 corresponding to each vibration sensor 30 to output a detection result including whether there is an abnormality at each preset position.
Specifically, as shown in fig. 9, a plurality of vibration sensors 30 may be disposed on the electric appliance 100, each vibration sensor 30 is disposed at a different preset position of the electric appliance 100, the specific preset position depends on the actual acquisition requirement of the electric appliance 100, and each vibration sensor 30 may be disposed at any position where a vibration signal of the electric appliance 100 can be extracted, so that the vibration sensor 30 can timely acquire the vibration signal of the electric appliance 100. When vibration signals of a plurality of preset positions of the electric appliance 100 need to be acquired, the vibration sensors 30 arranged at each preset position are used for acquiring the vibration signals of the plurality of preset positions, then the vibration signals acquired by each vibration sensor 30 are processed, vibration information corresponding to each vibration sensor 30 is obtained, finally the obtained vibration information is input into the detection model 80 corresponding to each vibration sensor 30 for detection, a detection result is output, and whether the preset position arranged by each vibration sensor 30 is normal or not is determined according to the detection result. It should be noted that there are one or more detection models 80 corresponding to different rotation speed ranges for each vibration sensor 30, and the vibration sensors 30 disposed at different preset positions cannot share one detection model 80.
Referring to fig. 10, the detection method according to the embodiment of the present application further includes the following steps:
015: and generating push information according to the detection result, and pushing the push information to the terminal related to the electric appliance 100.
Specifically, after the detection model 80 detects the vibration information, the detection result is output, and push information (the push information may include the detection result of the electrical appliance 100) is generated according to the detection result and is pushed to the terminal associated with the electrical appliance 100, so that the user can know the state of the electrical appliance 100 in time. The terminal associated with the electric appliance 100 may be a device capable of communicating, such as a mobile phone and a tablet.
Referring to fig. 11, an embodiment of the present application further provides a training method, including the following steps:
021: acquiring historical vibration signals acquired by a plurality of vibration sensors 30 arranged on the electric appliance 100, wherein the plurality of vibration sensors 30 are arranged at different preset positions of the electric appliance 100, and the vibration rules of the different preset positions are different;
022: processing the historical vibration signal to obtain a plurality of training samples;
023: the detection model 80 corresponding to each vibration sensor 30 is trained according to a plurality of training samples corresponding to each vibration sensor 30, so that the detection model 80 corresponding to each vibration sensor 30 converges, and the detection model 80 is an unsupervised model.
Specifically, a historical vibration signal acquired by the vibration sensor 30 provided on the electric appliance 100 is acquired, and then the historical vibration signal is processed to obtain a plurality of training samples, and the detection model 80 corresponding to each vibration sensor 30 is trained according to the obtained plurality of training samples corresponding to each vibration sensor 30, so that the detection model 80 corresponding to each vibration sensor 30 converges. It should be noted that the vibration sensor 30 includes a plurality of vibration sensors 30, and the plurality of vibration sensors 30 are disposed at different preset positions of the electric appliance 100; the detection model 80 is an unsupervised model, such as the detection model 80 based on an isolated forest algorithm; the expected effect that the detection model 80 needs to achieve is preset, and it can be set according to the actual situation that the historical vibration signal can include the vibration signal collected by the vibration sensor 30 of the electric appliance 100 for a specific duration, such as the vibration signal collected in the past hour; another example includes vibration signals collected over the past minute; and for example, vibration signals collected over the past second. In this way, the detection model 80 can ensure the detection effect of the detection model after being trained to converge through the training samples.
It can be understood that, for the detection model 80 corresponding to the rotation speed range of each vibration sensor 30, training needs to be performed according to the training sample obtained from the historical vibration signal collected by the vibration sensor 30, so as to obtain the converged detection model 80 corresponding to the rotation speed range of each vibration sensor 30.
Referring to fig. 12, in some example implementations, step 022: processing the historical vibration signal to obtain a plurality of training samples, comprising the steps of:
0221: sequentially acquiring historical vibration signals in each preset duration by taking the preset duration as a step length to generate a plurality of vibration signal groups;
0222: and processing each vibration signal group to obtain a training sample corresponding to each vibration signal group.
Specifically, the plurality of vibration signal sets are generated by sequentially acquiring the historical vibration signals collected by the vibration sensor 30 within each preset time length with the preset time length as a step length. And processing each vibration signal group to obtain a training sample corresponding to each vibration signal group. The vibration signal group includes a plurality of vibration signals. If historical vibration signals collected by the vibration sensor within one hour are obtained, and the preset time duration of 1 second(s) is taken as the step length, 3600 vibration signal groups can be generated at the moment, namely 3600 corresponding training samples can be obtained after the 3600 vibration signal groups are processed; if historical vibration signals collected by the vibration sensor within one hour are obtained, and the preset time duration of 1 minute (min) is taken as the step length, 60 vibration signal groups can be generated at the moment, namely, after the 60 vibration signal groups are processed, 60 corresponding training samples can be obtained.
Referring to fig. 13, in some example embodiments, the detection model 80 corresponding to each vibration sensor 30 includes a plurality of detection models 80, and the plurality of detection models 80 respectively correspond to a plurality of rotation speed ranges, and the training method further includes the following steps:
024: acquiring historical rotating speed of the electric appliance 100 and synchronizing the historical vibration signals and the historical rotating speed to acquire the historical rotating speed corresponding to each historical vibration signal;
025: determining the maximum rotating speed in a plurality of different historical rotating speeds of the vibration signal group as the target rotating speed of the training sample corresponding to the vibration signal group;
026: dividing the training sample into a plurality of training sets according to the target rotating speed and the rotating speed range of the training sample, wherein the plurality of training sets correspond to the plurality of detection models 80 one by one;
step 023: training the detection model 80 corresponding to each vibration sensor 30 according to a plurality of training samples corresponding to each vibration sensor 30 so that the detection model 80 corresponding to each vibration sensor 30 converges, comprising the steps of:
0231: the detection model 80 corresponding to each training set is trained on the basis of each training set so that the plurality of detection models 80 corresponding to each vibration sensor 30 converge.
Specifically, the detection model 80 corresponding to each vibration sensor 30 includes a plurality of models, and the plurality of detection models 80 correspond to a plurality of rotation speed ranges, respectively. The historical rotation speed of the electric appliance 100 can be obtained through the encoder 60 and is synchronized with the historical vibration signal, so that the historical rotation speed corresponding to the historical vibration signal can be obtained, and when the historical vibration signal of the vibration signal group corresponds to a plurality of different historical rotation speeds, the maximum rotation speed in the corresponding plurality of different historical rotation speeds is taken as the target rotation speed of the training sample corresponding to the vibration signal group. According to the target rotating speed and the rotating speed range of the training samples, the training samples are divided into a plurality of training sets, and it should be noted that the training sets correspond to the detection models 80 one to one. And the detection model 80 corresponding to each training set is trained based on each training set so that the plurality of detection models 80 corresponding to each vibration sensor 30 converge. In this way, multiple detection models 80 can be trained simultaneously to meet the requirements of practical applications. For example, as shown in fig. 14, 2 vibration sensors 30 are preset in the electrical appliance 100 as a vibration sensor K1 and a vibration sensor K2, the detection model 80 includes a detection model X1 (rotation speed range (40rps, 100rps)), a detection model X2 (rotation speed range (100rps, 200rps)), and a detection model X3 (rotation speed range (200rps, 300rps)), wherein the detection model 80 corresponding to the vibration sensor K1 includes the detection model X1 and the detection model X2, the detection model 80 corresponding to the vibration sensor K2 includes the detection model X3, the training samples include training samples B1 to B3600, the target rotation speeds corresponding to B1 to B1200 are 200rps, the target rotation speeds corresponding to B1201 to B2400 are 90s, the target rotation speeds corresponding to B2401 to B3600 are 250 s, the training set includes training sets J1 to J3, the training samples B to B1201 to B1, B200 to B1201 s are generated into the training set, the training set is generated into the training set through the training samples B1 to B2, and the detection model X1 to B1200 is detected through the training set by the training set X1 to B2, and the training model X1 to B2, and then the detection model X1 to B1200.
Referring to fig. 2 again, the electric appliance 100 according to the embodiment of the present application includes a first processor 70, the first processor 70 is configured to acquire a vibration signal collected by a plurality of vibration sensors 30 disposed on the electric appliance 100, and the plurality of vibration sensors 30 are disposed at different preset positions of the electric appliance 100; processing the vibration signal to obtain vibration information; the vibration information of each vibration sensor 30 is input to the detection model 80 corresponding to each vibration sensor 30, respectively, to output a detection result including whether there is an abnormality at each preset position.
In some embodiments, the first processor 70 is further configured to perform the detection method of any of the above embodiments.
In order to facilitate better implementing the detection method and the training method of the embodiments of the present application, the embodiments of the present application further provide a monitoring system 300, please refer to fig. 2 and fig. 15, where the monitoring system 300 may include:
the electric appliance 100, the first processor 70 of the electric appliance 100 is configured to acquire a vibration signal acquired by a vibration sensor 30 disposed on the electric appliance 100, and upload the vibration signal to the cloud server 310, where the plurality of vibration sensors 30 are disposed at different preset positions of the electric appliance 100, and vibration laws at the different preset positions are different;
the second processor 311 of the cloud server 310 is configured to process the vibration signal to obtain vibration information; the vibration information of each vibration sensor 30 is respectively input to the detection model 80 corresponding to each vibration sensor 30 to output a detection result including whether there is an abnormality at each preset position.
In some embodiments, the second processor 311 is configured to perform the training method or the detection method of any of the above embodiments.
Referring to fig. 16, the present embodiment further provides a computer-readable storage medium 400 (which can be read by a computer) having a computer program 401 stored thereon, where the steps of the detection method according to any of the above embodiments are implemented when the computer program 401 is executed by the first processor 70, and the steps of the training method according to any of the above embodiments are implemented when the computer program 401 is executed by the second processor 311, and are not described herein again for brevity.
In order to facilitate better implementation of the detection method of the embodiment of the present application, the embodiment of the present application further provides a detection device 10. Referring to fig. 17, the detecting device may include:
the first obtaining module 11 is configured to obtain a vibration signal collected by a vibration sensor 30 disposed in the electrical appliance 100.
The first obtaining module 11 is further specifically configured to obtain a preset number of vibration signals within a preset time period based on the sampling frequency of the vibration sensor 30; acquiring a vibration signal acquired by the vibration sensor 30 at each preset position;
the first processing module 12 is configured to process the vibration signal to obtain vibration information.
The first processing module 12 is specifically configured to process a preset number of vibration signals to obtain vibration intensity and vibration kurtosis; carrying out Fourier transform on preset number of vibration signals to obtain frequencies and amplitudes corresponding to the frequencies; acquiring a target frequency of target rotating speeds such as numerical values, wherein the target frequency is any one of a plurality of frequencies, and the target rotating speed is the maximum value of the rotating speeds corresponding to a preset number of vibration signals; obtaining an amplitude corresponding to the target frequency as first-order vibration information; the vibration signals collected by each vibration sensor 30 are processed to obtain vibration information corresponding to each vibration sensor 30.
The detecting module 13 is configured to input vibration information of each vibration sensor 30 to the corresponding detection model 80 of each vibration sensor 30, respectively, so as to output a detection result, where the detection result includes whether there is an abnormality at each preset position.
The detecting module 13 is specifically further configured to input vibration information of each vibration sensor 30 into a target detection model corresponding to each vibration sensor 30, so as to output a detection result, where the target detection model is any one of the multiple detection models 80, and the target detection model is the detection model 80 corresponding to a rotation speed range in which the target rotation speed is located.
The second obtaining module 14 is configured to obtain a rotation speed of the electrical appliance 100 and synchronize the vibration signals and the rotation speed to obtain a rotation speed corresponding to each vibration signal.
And the generating module 15 is configured to generate push information according to the detection result, and push the push information to a terminal associated with the electrical appliance 100.
The modules in the detection apparatus 10 can be implemented in whole or in part by software, hardware, and a combination thereof. The modules may be embedded in hardware or independent of the first processor 70, so that the first processor 70 can call and execute the operations corresponding to the modules.
In order to facilitate better implementation of the training method according to the embodiment of the present application, the embodiment of the present application further provides a training device 20. Referring to fig. 18, the training apparatus may include:
the third obtaining module 21 is configured to obtain historical vibration signals collected by the vibration sensors 30 of the electrical appliance 100, where the vibration sensors 30 include a plurality of vibration sensors 30, the plurality of vibration sensors 30 are disposed at different preset positions of the electrical appliance 100, and the vibration rules at the different preset positions are different.
And a second processing module 22, configured to process the historical vibration signal to obtain a plurality of training samples.
The second processing module 22 is further specifically configured to sequentially obtain the historical vibration signals within each preset duration by taking the preset duration as a step length, so as to generate a plurality of vibration signal groups; and processing each vibration signal group to obtain a training sample corresponding to each vibration signal group.
The training module 23 is configured to train the detection model 80 corresponding to each vibration sensor 30 according to a plurality of training samples corresponding to each vibration sensor 30, so that the detection model 80 corresponding to each vibration sensor 30 converges, where the detection model 80 is an unsupervised model.
The training module 23 is further configured to train the detection model 80 corresponding to each training set according to each training set, so that the plurality of detection models 80 corresponding to each vibration sensor 30 converge.
And the fourth obtaining module 24 is configured to obtain a historical rotation speed of the electrical appliance 100 and synchronize the historical vibration signals and the historical rotation speed to obtain a historical rotation speed corresponding to each historical vibration signal.
And the determining module 25 is configured to determine a maximum rotation speed of the plurality of different historical rotation speeds of the vibration signal group as a target rotation speed of the training sample corresponding to the vibration signal group.
The third processing module 26 is configured to divide the training samples into a plurality of training sets according to the target rotation speed and the rotation speed range of the training samples, where the plurality of training sets correspond to the plurality of detection models 80 one to one.
The various modules in the exercise device 20 described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules may be embedded in the second processor 311 or independent of the second processor 311 in a hardware manner, so that the second processor 311 calls to execute operations corresponding to the modules.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specified otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following technologies, which are well known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware that is related to instructions of a program, and the program may be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (9)
1. A method of detection, comprising:
acquiring a preset number of vibration signals within a preset time length based on the sampling frequency of a plurality of vibration sensors, wherein the plurality of vibration sensors are arranged at different preset positions of an electric appliance, and the vibration rules of the different preset positions are different;
acquiring the rotating speed of the electric appliance and synchronizing the vibration signals and the rotating speed to acquire the rotating speed corresponding to each vibration signal;
processing the vibration signal to obtain vibration information;
respectively inputting the vibration information of each vibration sensor to a detection model corresponding to each vibration sensor to output a detection result, wherein the detection result comprises whether each preset position is abnormal or not;
the vibration information further includes vibration first-order information, the processing the vibration signal to obtain vibration information includes:
carrying out Fourier transform on a preset number of vibration signals to obtain frequencies and amplitudes corresponding to the frequencies;
acquiring a target frequency with a value equal to a target rotating speed, wherein the target frequency is any one of the plurality of frequencies, and the target rotating speed is the maximum value of the rotating speeds corresponding to a preset number of the vibration signals; and
and acquiring the amplitude corresponding to the target frequency to serve as the first-order vibration information.
2. The method of claim 1, wherein the vibration sensor is disposed at a location where a bearing portion of the appliance is located.
3. The detection method according to claim 1, wherein the vibration information includes vibration intensity and vibration kurtosis, and the processing the vibration signal to obtain vibration information includes:
and processing a preset number of the vibration signals to obtain the vibration intensity and the vibration kurtosis.
4. The detecting method according to claim 1, wherein the detecting model corresponding to each of the vibration sensors includes a plurality of detecting models corresponding to a plurality of rotation speed ranges, respectively, and the inputting the vibration information of each of the vibration sensors to the detecting model corresponding to each of the vibration sensors to output the detecting result includes:
the vibration information of each vibration sensor is input to a target detection model corresponding to each vibration sensor to output the detection result, the target detection model is any one of the detection models, and the target detection model is the detection model corresponding to the rotation speed range in which the target rotation speed is located.
5. The detection method according to claim 1, further comprising:
and generating push information according to the detection result, and pushing the push information to the terminal associated with the electric appliance.
6. A method of training, comprising:
acquiring historical vibration signals acquired by vibration sensors arranged on an electric appliance, wherein the vibration sensors comprise a plurality of vibration sensors which are arranged at different preset positions of the electric appliance, and the vibration rules of the different preset positions are different;
processing the historical vibration signal to obtain a plurality of training samples;
respectively training a detection model corresponding to each vibration sensor according to a plurality of training samples corresponding to each vibration sensor so as to make the detection model corresponding to each vibration sensor converge, wherein the detection model is an unsupervised model;
the processing the historical vibration signal to obtain a plurality of training samples includes:
sequentially acquiring the historical vibration signals in each preset duration by taking the preset duration as a step length to generate a plurality of vibration signal groups;
processing each vibration signal group to obtain the training sample corresponding to each vibration signal group;
the detection model corresponding to each vibration sensor comprises a plurality of detection models, the plurality of detection models respectively correspond to a plurality of rotating speed ranges, and the training method further comprises the following steps:
acquiring historical rotating speed of the electric appliance and synchronizing the historical vibration signals and the historical rotating speed to acquire the historical rotating speed corresponding to each historical vibration signal;
determining a maximum rotation speed in a plurality of different historical rotation speeds of the vibration signal group as a target rotation speed of the training sample corresponding to the vibration signal group;
dividing the training samples into a plurality of training sets according to the target rotating speed and the rotating speed range of the training samples, wherein the plurality of training sets correspond to the plurality of detection models one to one;
the training a detection model corresponding to each of the vibration sensors according to a plurality of training samples corresponding to each of the vibration sensors so that the detection model corresponding to each of the vibration sensors converges includes:
and training the detection model corresponding to each training set according to each training set so as to enable the plurality of detection models corresponding to each vibration sensor to be converged.
7. The electric appliance is characterized by comprising a first processor, wherein the first processor is used for acquiring a preset number of vibration signals within a preset time length based on the sampling frequency of a plurality of vibration sensors, the plurality of vibration sensors are arranged at different preset positions of the electric appliance, and the vibration rules of the different preset positions are different; acquiring the rotating speed of the electric appliance and synchronizing the vibration signals and the rotating speed to acquire the rotating speed corresponding to each vibration signal; processing the vibration signal to obtain vibration information; respectively inputting the vibration information of each vibration sensor to a detection model corresponding to each vibration sensor to output a detection result, wherein the detection result comprises whether each preset position is abnormal or not;
the vibration information further includes vibration first-order information, the processing the vibration signal to obtain vibration information includes:
carrying out Fourier transform on a preset number of vibration signals to obtain frequencies and amplitudes corresponding to the frequencies;
acquiring a target frequency with a value equal to a target rotating speed, wherein the target frequency is any one of the plurality of frequencies, and the target rotating speed is the maximum value of the rotating speeds corresponding to a preset number of the vibration signals; and
and acquiring the amplitude corresponding to the target frequency to serve as the first-order vibration information.
8. A monitoring system, comprising:
the system comprises an electric appliance and a plurality of vibration sensors, wherein a first processor of the electric appliance is used for acquiring a preset number of vibration signals within a preset time length based on the sampling frequency of the vibration sensors and uploading the vibration signals to a cloud server, the plurality of vibration sensors are arranged at different preset positions of the electric appliance, and the vibration rules of the different preset positions are different;
the second processor of the cloud server is used for acquiring the rotating speed of the electric appliance and synchronizing the vibration signals and the rotating speed so as to acquire the rotating speed corresponding to each vibration signal; processing the vibration signal to obtain vibration information; respectively inputting the vibration information of each vibration sensor to a detection model corresponding to each vibration sensor to output a detection result, wherein the detection result comprises whether each preset position is abnormal or not;
the vibration information further includes vibration first-order information, processing the vibration signal to obtain vibration information includes:
carrying out Fourier transform on a preset number of vibration signals to obtain frequencies and amplitudes corresponding to the frequencies;
acquiring a target frequency with a value equal to a target rotating speed, wherein the target frequency is any one of the plurality of frequencies, and the target rotating speed is the maximum value of the rotating speeds corresponding to a preset number of the vibration signals; and
and acquiring the amplitude corresponding to the target frequency to serve as the first-order vibration information.
9. A computer-readable storage medium, comprising a computer program which, when executed by one or more processors, implements the detection method of any one of claims 1-5 or the training method of claim 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211578164.3A CN115656700B (en) | 2022-12-09 | 2022-12-09 | Detection method, training method, electric appliance, monitoring system and storage medium |
| PCT/CN2023/125236 WO2024120018A1 (en) | 2022-12-09 | 2023-10-18 | Detection method, training method, electrical appliance, monitoring system, storage medium, and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211578164.3A CN115656700B (en) | 2022-12-09 | 2022-12-09 | Detection method, training method, electric appliance, monitoring system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115656700A CN115656700A (en) | 2023-01-31 |
| CN115656700B true CN115656700B (en) | 2023-04-14 |
Family
ID=85017976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211578164.3A Active CN115656700B (en) | 2022-12-09 | 2022-12-09 | Detection method, training method, electric appliance, monitoring system and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115656700B (en) |
| WO (1) | WO2024120018A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115656700B (en) * | 2022-12-09 | 2023-04-14 | 广东美的暖通设备有限公司 | Detection method, training method, electric appliance, monitoring system and storage medium |
Family Cites Families (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3725799B2 (en) * | 2001-03-30 | 2005-12-14 | 大日本スクリーン製造株式会社 | Failure location determination method and failure location determination device |
| JP3912230B2 (en) * | 2002-08-30 | 2007-05-09 | 井関農機株式会社 | Vibration detector |
| CN101796238B (en) * | 2007-09-04 | 2012-08-22 | 松下电器产业株式会社 | Washing machine, and method for controlling drum rotation speed |
| CN102175409B (en) * | 2011-02-01 | 2012-08-29 | 华北电力大学 | Real-time identification method for oil whirl fault of turbo generator set |
| CN103884482B (en) * | 2012-12-21 | 2017-03-08 | 珠海格力电器股份有限公司 | A kind of method for testing vibration based on compressor and system |
| CN103743477B (en) * | 2013-12-27 | 2016-01-13 | 柳州职业技术学院 | A kind of mechanical fault detection diagnostic method and equipment thereof |
| CN107796507A (en) * | 2017-09-18 | 2018-03-13 | 洛阳双瑞精铸钛业有限公司 | A kind of heat-exchange unit Vibration Condition Monitoring platform |
| CN110836516B (en) * | 2019-10-18 | 2020-11-13 | 珠海格力电器股份有限公司 | Heating and ventilation equipment control method and device and heating and ventilation system |
| JP6918893B2 (en) * | 2019-10-29 | 2021-08-11 | 株式会社川本製作所 | Anomaly detection device |
| CN111027426B (en) * | 2019-11-28 | 2023-10-20 | 中国航空工业集团公司西安航空计算技术研究所 | Method for calculating fundamental frequency amplitude of vibration signal of aero-engine |
| CN111046541B (en) * | 2019-11-28 | 2023-05-09 | 中国航空工业集团公司西安航空计算技术研究所 | Self-adaptive solving method and system for variation of fundamental frequency vibration amplitude of engine along with rotation speed |
| DE102020206626B3 (en) * | 2020-05-27 | 2021-06-24 | Ziehl-Abegg Se | Method for determining a vibration behavior of an electric motor and electric motor and fan, each designed to carry out the method |
| JP6995969B1 (en) * | 2020-12-22 | 2022-01-17 | 株式会社クボタ | Diagnostic device for rotating equipment |
| DE102021203932B3 (en) * | 2021-04-20 | 2022-07-14 | Ziehl-Abegg Se | Method for evaluating the vibration behavior of an electric motor and the corresponding electric motor and fan |
| DE102021204463A1 (en) * | 2021-05-04 | 2022-11-10 | Ziehl-Abegg Se | Method for determining the vibration behavior of an electric motor and/or its installation environment, as well as the corresponding electric motor and fan |
| CN113627017A (en) * | 2021-08-11 | 2021-11-09 | 观为监测技术无锡股份有限公司 | Vibration monitoring model multiplexing method, device, equipment and storage medium |
| CN114659785A (en) * | 2021-12-27 | 2022-06-24 | 三一重能股份有限公司 | Fault detection method and device for transmission chain of wind driven generator |
| CN114636554A (en) * | 2022-03-15 | 2022-06-17 | 联合汽车电子有限公司 | Electric drive system bearing fault monitoring method and device |
| CN115270896B (en) * | 2022-09-28 | 2023-04-07 | 西华大学 | Intelligent diagnosis method for identifying loosening fault of main bearing of aircraft engine |
| CN115656700B (en) * | 2022-12-09 | 2023-04-14 | 广东美的暖通设备有限公司 | Detection method, training method, electric appliance, monitoring system and storage medium |
-
2022
- 2022-12-09 CN CN202211578164.3A patent/CN115656700B/en active Active
-
2023
- 2023-10-18 WO PCT/CN2023/125236 patent/WO2024120018A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024120018A1 (en) | 2024-06-13 |
| CN115656700A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11561127B2 (en) | Apparatus for analysing the condition of a machine having a rotating part | |
| US11460005B2 (en) | Condition monitoring system and wind turbine generation apparatus | |
| CN109520738B (en) | Rotating machinery rolling bearing fault diagnosis method based on order spectrum and envelope spectrum | |
| CN110226140B (en) | State monitoring method and state monitoring device | |
| CN104136896B (en) | For the system for the vibration signal for obtaining rotation motor | |
| US20190162748A1 (en) | Pump assembly, method and computer program | |
| CN110160765A (en) | A kind of shock characteristic recognition methods and system based on sound or vibration signal | |
| CN115656700B (en) | Detection method, training method, electric appliance, monitoring system and storage medium | |
| CN110057583A (en) | A kind of bearing fault recognition methods, device and computer equipment | |
| EP2135144B1 (en) | Machine condition monitoring using pattern rules | |
| US20190332102A1 (en) | Machine health monitoring of rotating machinery | |
| CN103116032A (en) | Method and device for acquiring rotating speed of wind generating set | |
| CN114739667A (en) | Multi-mode information fusion bearing lubrication state monitoring device and method | |
| CN116226719A (en) | Bearing fault diagnosis method based on multidimensional steady-state vibration characteristics and related components | |
| CN110411730B (en) | Fault judgment method and system for rotating equipment and readable storage medium | |
| CN115859210B (en) | Intelligent detection method and system for power-off tail sound of power-on equipment | |
| JP2015114224A (en) | Vibration inspection system using portable terminal, and server thereof | |
| CN110749443A (en) | Rolling bearing fault diagnosis method and system based on high-order origin moment | |
| KR101752298B1 (en) | Health monitoring apparatus based on configuration information and method thereof | |
| JP2002139376A (en) | Failure diagnosis system and failure diagnosis server | |
| CN107436244B (en) | Equipment fault alarm method based on frequency segmentation vibration data acquisition | |
| CN118150857B (en) | Rotational speed estimation system and method based on vibration sensor | |
| CN109444622A (en) | A kind of shaft angle sends system failure automatic testing method, system and device | |
| JP2019086349A (en) | Condition monitoring device and abnormality diagnostic method for bearing | |
| CN112268688B (en) | Error data identification method and device |
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 |