Intelligent electromechanical comprehensive diagnosis, monitoring method and system based on industrial Internet
Through the comprehensive analysis of motor audio and temperature data, a comprehensive fault evaluation index is generated, which solves the problem of narrow motor fault diagnosis and analysis in the existing technology, and comprehensive monitoring and diagnosis of motor faults is achieved, and the accuracy of fault detection is improved. .
Patent Information
- Application Number
- CN202410934961.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-12
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-07-12
AI Technical Summary
The prior art only relies on excitation current data analysis in motor fault diagnosis, with a narrow analysis surface, which cannot comprehensively monitor various fault conditions of the motor, and lacks comprehensive considerations for temperature and audio changes.
By collecting the audio time domain signal and temperature data of the motor, preprocessing and correlation analysis are performed, the motor audio fault index and temperature fault evaluation coefficient are generated, and the two are combined to generate a comprehensive fault evaluation index, output the fault confidence, and realize the motor failure Comprehensive monitoring and diagnosis.
It realizes multi-faceted monitoring and diagnosis of motor faults, improves the accuracy and reliability of fault detection, and can detect and warn of abnormal motor conditions earlier.
Smart Images

Figure CN118503926B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of electromechanical monitoring technology, and specifically to an intelligent electromechanical comprehensive diagnosis and monitoring method and system based on the Industrial Internet. Background Art
[0002] In industry, a motor is a device that converts electrical energy into mechanical energy. It uses the principle of electromagnetic induction to drive the rotor to move, thereby achieving mechanical movement. In order to ensure the normal operation of the motor, industry needs to perform fault diagnosis and monitoring on the motor, usually manually using detection tools to detect whether the motor status is abnormal.
[0003] The Chinese invention patent with the authorization number CN111650509B discloses a method, device, computer equipment and medium for judging the fault of a brushless excitation motor. The method includes: obtaining the excitation current data in the stator excitation winding of the brushless excitation motor; performing Fourier analysis on the excitation current data, and calculating the first effective value I1 and the second effective value I2 at different preset harmonic frequencies; judging whether a fault occurs at the grounding point of the stator excitation winding of the brushless excitation motor based on the first effective value I1 and the second effective value I2. The embodiment of the present invention performs Fourier analysis on the excitation current data to obtain the first effective value and the second effective value of the current stator excitation resistance at different preset harmonic frequencies, and judges whether a fault occurs at the grounding point of the stator excitation winding based on the two effective values. The embodiment of the present invention has the characteristics of simple calculation and intuitive judgment, and ensures the safety of the brushless excitation motor. It only obtains the motor's excitation current data for analysis to determine the motor's fault condition, and the analysis scope is relatively narrow. When the motor is working, various faults may occur, including broken rotor bars, rotor misalignment, rotor imbalance, base fault, stator winding fault, stator core fault, bearing fault, etc. Faults caused by deformation of the appearance will cause changes in the motor audio, and circuit failures will cause changes in heat generation. Therefore, it is very necessary to combine temperature and audio monitoring and analysis of the motor.
[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0005] The purpose of the present invention is to provide an intelligent electromechanical comprehensive diagnosis and monitoring method and system based on the Industrial Internet to solve the problems raised in the above-mentioned background technology.
[0006] To achieve the above object, the present invention provides the following technical solutions:
[0007] The intelligent electromechanical comprehensive diagnosis and monitoring method based on the industrial Internet includes the following specific steps:
[0008] S1, collecting motor audio time domain signal;
[0009] S2, preprocessing the audio time domain signal to generate a characteristic signal, wherein the characteristic signal highlights the high-frequency component part of the audio time domain signal;
[0010] S3, perform windowing and frame processing on the characteristic signal to generate a detection signal, and generate the first The amplitude of the sampling point in the frame detection signal is analyzed for correlation between the amplitudes of the detection signal and the detection signal to generate the mean amplitude of the sampling point in the detection signal and the standard deviation of the amplitude of the sampling point in the detection signal, and the mean amplitude of the sampling point in the detection signal and the standard deviation of the amplitude of the sampling point in the detection signal are preprocessed to generate a motor audio fault index, which reflects the proportion of abnormal sound signals;
[0011] S4, collecting the fault-free motor temperature and the fault-free ambient temperature, pre-processing the fault-free motor temperature, generating the fault-free motor stable temperature and the fault-free motor temperature rise coefficient, wherein the fault-free motor temperature rise coefficient reflects the motor temperature rise rate when the motor is working normally;
[0012] S5, collecting the working motor temperature and the working environment temperature, pre-processing the working motor temperature, generating the working motor stable temperature and the working motor temperature increase coefficient, wherein the working motor temperature increase coefficient reflects the temperature increase rate when the monitoring motor is working;
[0013] S6, pre-processing the stable temperature of the fault-free motor, the temperature rise coefficient of the fault-free motor, the stable temperature of the working motor and the temperature rise coefficient of the working motor to generate a motor temperature fault evaluation coefficient, wherein the motor temperature fault evaluation coefficient reflects the abnormal temperature of the monitored motor when it is working;
[0014] S7. Preprocess the motor temperature fault evaluation coefficient and the motor audio fault index to generate a motor comprehensive fault evaluation index, compare the motor comprehensive fault evaluation index with the motor fault threshold, and output the motor fault confidence. The motor comprehensive fault evaluation index reflects the comprehensive fault degree of the monitored motor, and the motor fault confidence reflects the confidence degree of the motor fault.
[0015] Furthermore, the audio time domain signal is used Said that The audio time domain signal of sampling points is used Indicates that the number of sampling points is Analyze the audio time domain signal and generate sampling point characteristic signal , the formula based on is The characteristic signal of the sampling point Perform analysis and generate characteristic signals , the formula based on is ;
[0016] Among them, T is the transpose of the matrix, and the characteristic signal The high-frequency component part in the audio time domain signal is highlighted, making the spectrogram of the audio signal flat, reducing the loss of effective components in the signal, and facilitating subsequent signal feature extraction.
[0017] Furthermore, in S3, the audio signal sampling rate used in the frame processing is 10500 Hz, the frame length of each frame is 262, and the frame shift is 157.
[0018] Furthermore, in S3, the windowing process adopts a Hamming window function formula.
[0019] Further, in said S3, Frame detection signal express, The value range of is 1, 2, 3, ..., p, the first Frame No. The amplitude of the detection signal at each sampling point is expressed as Indicates the amplitude of the sampling point in the detection signal Perform correlation analysis to generate The average amplitude of the sampling points in the frame detection signal , the formula based on is: ;
[0020] For The average amplitude of the sampling points in the frame detection signal and Frame No. The amplitude of the detection signal at each sampling point Perform correlation analysis to generate Standard deviation of the sampling point amplitude in the frame detection signal , the formula based on is: .
[0021] Furthermore, for Standard deviation of the sampling point amplitude in the frame detection signal , No. The average amplitude of the sampling points in the frame detection signal , No. Frame detection signal Perform correlation analysis to generate a motor audio fault index , the formula based on is: ;
[0022] The motor audio fault index Reflects the proportion of abnormal sound signals. If the threshold range is exceeded, it indicates that the device is faulty.
[0023] Further, the fault-free motor temperature is Indicates that, where the subscript is the fault-free motor working time in seconds, The value range of is 1, 2, 3, ..., k, where , the trouble-free ambient temperature is used express;
[0024] For fault-free motor temperature Perform correlation analysis to generate Trouble-free motor temperature change rate in seconds , the formula based on is:
[0025] ;
[0026] The first record value range is Ten consecutive groups of , and for ten consecutive groups Perform averaging to obtain the stable temperature of the fault-free motor , the ten consecutive groups Arranged from smallest to largest in terms of time, the first group The corresponding time is , for time and trouble-free ambient temperature , trouble-free motor stable temperature Perform correlation analysis to generate fault-free motor temperature rise coefficients , the formula based on is:
[0027] ;
[0028] in, is the working environment temperature weight factor, and its value range is , the fault-free motor temperature rise coefficient It reflects the rate of increase of motor temperature during normal motor operation.
[0029] Furthermore, the working motor temperature is Indicates that, where the subscript is the working time of the working motor, in seconds, The value range of is 1, 2, 3, ..., k, where , the working environment temperature is express;
[0030] Working motor temperature Perform correlation analysis to generate Operating motor temperature change rate in seconds , the formula based on is:
[0031] ;
[0032] The first record value range is Ten consecutive groups of , and for ten consecutive groups Perform averaging to obtain the stable temperature of the working motor , the ten consecutive groups Arranged from smallest to largest in terms of time, the first group The corresponding time is , for time and operating environment temperature , Working motor stable temperature Perform correlation analysis to generate the operating motor temperature rise coefficient , the formula based on is:
[0033] ;
[0034] The working motor temperature rise coefficient It reflects the temperature rise rate when the monitored motor is working;
[0035] Temperature rise coefficient of working motor , Fault-free motor temperature rise coefficient , trouble-free motor stable temperature And the working motor stable temperature Perform correlation analysis to generate motor temperature fault evaluation coefficients , the formula based on is: ;
[0036] The motor temperature fault evaluation coefficient It reflects the abnormal temperature of the monitored motor when it is working.
[0037] Furthermore, the motor temperature fault evaluation coefficient and the motor audio fault index are preprocessed to generate the motor comprehensive fault evaluation index , the formula based on is: ;
[0038] The motor comprehensive fault evaluation index It reflects the comprehensive fault degree of the monitored motor.
[0039] Furthermore, the motor fault threshold is ,when When the output motor fault confidence is above 95%, it means that the monitoring motor is abnormal; when When the output motor fault confidence is 80%, it means that the monitoring motor needs manual confirmation to see if there is a fault; when When the output motor fault confidence is less than 10%, it means that the monitored motor is working normally.
[0040] Furthermore, the present invention also provides an intelligent electromechanical integrated diagnosis and monitoring system based on the industrial Internet, which is used to perform an intelligent electromechanical integrated diagnosis and monitoring method based on the industrial Internet, including:
[0041] An audio acquisition module, wherein the audio acquisition module is used to acquire an audio time domain signal of the motor;
[0042] An audio analysis module, which analyzes, windows, and frames the audio time domain signal of the motor to generate a detection signal, and analyzes the detection signal to generate a motor audio fault index;
[0043] A fault-free motor temperature acquisition module, wherein the fault-free motor temperature acquisition module is used to collect temperature data of the fault-free motor when it is working and fault-free environment temperature data;
[0044] A first temperature analysis module, the first temperature analysis module is used to analyze the temperature data of the fault-free motor when it is working and the fault-free environmental temperature data, and generate the fault-free motor stable temperature and the fault-free motor temperature rise coefficient;
[0045] A working motor temperature acquisition module, wherein the working motor temperature acquisition module is used to acquire the working motor temperature and the working environment temperature;
[0046] A second temperature analysis module, the second temperature analysis module is used to analyze the temperature data of the working motor when it is working and the working environment temperature data, and generate the working motor stable temperature and the working motor temperature rise coefficient;
[0047] A temperature comprehensive analysis module, the temperature comprehensive analysis module is used to perform correlation analysis on the fault-free motor stable temperature, the fault-free motor temperature rise coefficient, the working motor stable temperature and the working motor temperature rise coefficient generated by the first temperature analysis module and the second temperature analysis module, and generate a motor temperature fault evaluation coefficient;
[0048] An evaluation and analysis module, wherein the evaluation and analysis module is used to perform a correlation analysis on a motor temperature fault evaluation coefficient and a motor audio fault index to generate a motor comprehensive fault evaluation index;
[0049] A comparison module is used to compare the motor audio fault index with the motor fault threshold and output the motor fault confidence.
[0050] Compared with the prior art, the present invention has the following beneficial effects:
[0051] The present invention monitors and analyzes the motor audio and temperature of an intelligent electromechanical device for the first time, collects and preprocesses audio time domain signals, generates a motor audio fault index, quantifies the abnormality in the audio, and also collects motor temperature data of the intelligent electromechanical device, uses the temperature data of a fault-free motor as a comparison quantity, performs correlation analysis with the temperature of the monitored motor, generates a motor temperature fault evaluation coefficient, combines the motor temperature fault evaluation coefficient and the motor audio fault index, generates a motor comprehensive fault evaluation index that reflects the comprehensive fault state of the motor, and outputs the motor fault confidence level, thereby enabling monitoring and diagnosis of whether the motor has failed. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] Figure 1 It is a schematic diagram of the overall method flow of the present invention;
[0053] Figure 2 It is a schematic diagram of the overall system flow of the present invention. DETAILED DESCRIPTION
[0054] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.
[0055] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0056] Example:
[0057] See also Figure 1 , the present invention provides a technical solution:
[0058] The intelligent electromechanical comprehensive diagnosis and monitoring method based on the industrial Internet. In industry, the operation of intelligent electromechanical often requires the movement of various components, and most of these components are realized by motors. Therefore, the motors often need to be repaired and maintained in industry. The present invention aims to monitor and diagnose the motors of intelligent electromechanical, output whether the motors are faulty, and help the staff better understand the motor status of intelligent electromechanical. The specific steps include:
[0059] Step 1: Collect the audio time domain signal of the motor; use an audio sensor to collect the audio time domain signal of the motor to be monitored. When the motor fails and the physical structure changes, it often causes the audio to change, so the motor audio time domain signal is collected for analysis;
[0060] Step 2: Preprocess the audio time domain signal to generate a characteristic signal;
[0061] The audio time domain signal is used Said that The audio time domain signal of sampling points is used Indicates that the number of sampling points is Analyze the audio time domain signal and generate sampling point characteristic signal , the formula based on is The characteristic signal of the sampling point Perform analysis and generate characteristic signals , the formula based on is ;
[0062] Among them, T is the transpose of the matrix, and the characteristic signal Highlights the high-frequency components in the audio time domain signal, flattens the spectrogram of the audio signal, reduces the loss of effective components in the signal, and facilitates subsequent signal feature extraction;
[0063] Step 3: Perform windowing and frame processing on the characteristic signal to generate a detection signal, and generate the first The amplitude of the sampling point in the frame detection signal is analyzed for correlation between the amplitude of the detection signal and the detection signal to generate the mean amplitude of the sampling point in the detection signal and the standard deviation of the amplitude of the sampling point in the detection signal, and the mean amplitude of the sampling point in the detection signal and the standard deviation of the amplitude of the sampling point in the detection signal are preprocessed to generate the motor audio fault index;
[0064] Feature extraction is performed on short-term stable signals. Therefore, non-stationary signals need to be processed to obtain relatively stable signals, that is, the feature signals need to be framed. The audio signal of the motor is a non-stationary signal, but in a very short time region, the audio signal is relatively stable. By dividing the sampling points under the sampling time into multiple segments, the audio signal is analyzed segment by segment to extract its parameters. The audio signal sampling rate used in the frame processing is 10500Hz, the frame length of each frame is 262, and the frame shift is 157;
[0065] In order to ensure the reliability of the characteristic signal, the characteristic signal is processed by using a windowing method, and the windowing process adopts a Hamming window function formula;
[0066] No. Frame detection signal express, The value range of is 1, 2, 3, ..., p, the first Frame No. The amplitude of the detection signal at each sampling point is expressed as Indicates the amplitude of the sampling point in the detection signal Perform correlation analysis to generate The average amplitude of the sampling points in the frame detection signal , the formula based on is: ;
[0067] For The average amplitude of the sampling points in the frame detection signal and Frame No. The amplitude of the detection signal at each sampling point Perform correlation analysis to generate Standard deviation of the sampling point amplitude in the frame detection signal , the formula based on is: .
[0068] For Standard deviation of the sampling point amplitude in the frame detection signal , No. The average amplitude of the sampling points in the frame detection signal , No. Frame detection signal Perform correlation analysis to generate a motor audio fault index , the formula based on is: ;
[0069] The motor audio fault index Reflects the proportion of abnormal sound signals. If the threshold value is exceeded, it means that the device is faulty. The larger the value, the more serious the fault. The size of the motor audio fault index will change according to the proportion of abnormal amplitude components in the audio signal, which can indicate that the equipment has a fault. The larger the motor audio fault index value, the more serious the corresponding fault.
[0070] When the motor has a circuit fault, its physical temperature will be abnormal due to the change of the running circuit. Therefore, the present invention also analyzes the motor temperature and uses a temperature sensor to collect the motor temperature data.
[0071] The temperature sensor and the audio sensor of the present invention are both connected to the Internet to achieve data transmission.
[0072] Step 4: Collect the fault-free motor temperature and the fault-free ambient temperature, pre-process the fault-free motor temperature, and generate the fault-free motor stable temperature and the fault-free motor temperature rise coefficient;
[0073] The fault-free motor temperature is Indicates that, where the subscript is the fault-free motor working time in seconds, The value range of is 1, 2, 3, ..., k, where , the trouble-free ambient temperature is used express;
[0074] For fault-free motor temperature Perform correlation analysis to generate Trouble-free motor temperature change rate in seconds , the formula based on is:
[0075] ;
[0076] The first record value range is Ten consecutive groups of , and for ten consecutive groups Perform averaging to obtain the stable temperature of the fault-free motor , the ten consecutive groups Arranged from smallest to largest in terms of time, the first group The corresponding time is , for time and trouble-free ambient temperature , trouble-free motor stable temperature Perform correlation analysis to generate fault-free motor temperature rise coefficients , the formula based on is:
[0077] ;
[0078] The first record value range is Ten consecutive groups of , and for ten consecutive groups Perform averaging to obtain the stable temperature of the fault-free motor , the ten consecutive groups Arranged from smallest to largest in terms of time, the first group The corresponding time is , for time and trouble-free ambient temperature , trouble-free motor stable temperature Perform correlation analysis to generate fault-free motor temperature rise coefficients , the formula based on is:
[0079] ;
[0080] in, is the working environment temperature weight factor, and its value range is , the fault-free motor temperature rise coefficient It reflects the rate of increase of motor temperature during normal motor operation.
[0081] Step 5: Collect the working motor temperature and the working environment temperature, pre-process the working motor temperature, and generate the working motor stable temperature and the working motor temperature rise coefficient;
[0082] The working motor temperature is Indicates that, where the subscript is the working time of the working motor, in seconds, The value range of is 1, 2, 3, ..., k, where , the working environment temperature is express;
[0083] Working motor temperature Perform correlation analysis to generate Operating motor temperature change rate in seconds , the formula based on is:
[0084] ;
[0085] The first record value range is Ten consecutive groups of , and for ten consecutive groups Perform averaging to obtain the stable temperature of the working motor , the ten consecutive groups Arranged from smallest to largest in terms of time, the first group The corresponding time is , for time and operating environment temperature , Working motor stable temperature Perform correlation analysis to generate the operating motor temperature rise coefficient , the formula based on is:
[0086] ;
[0087] The working motor temperature rise coefficient It reflects the temperature rise rate when the monitored motor is working;
[0088] Step 6: Preprocess the stable temperature of the fault-free motor, the temperature rise coefficient of the fault-free motor, the stable temperature of the working motor and the temperature rise coefficient of the working motor to generate a motor temperature fault evaluation coefficient;
[0089] Temperature rise coefficient of working motor , Fault-free motor temperature rise coefficient , trouble-free motor stable temperature And the working motor stable temperature Perform correlation analysis to generate motor temperature fault evaluation coefficients , the formula based on is: ;
[0090] The motor temperature fault evaluation coefficient It reflects the abnormal temperature of the monitored motor when it is working;
[0091] Step 7: Preprocess the motor temperature fault evaluation coefficient and the motor audio fault index to generate a motor comprehensive fault evaluation index, compare the motor comprehensive fault evaluation index with the motor fault threshold, and output the motor fault confidence.
[0092] Preprocess the motor temperature fault evaluation coefficient and motor audio fault index to generate the motor comprehensive fault evaluation index , the formula based on is: ;
[0093] The motor comprehensive fault evaluation index Reflects the comprehensive fault degree of the monitored motor;
[0094] The motor fault threshold is , The value of is 2.69. When the output motor fault confidence is above 95%, it means that the monitoring motor is abnormal; when When the output motor fault confidence is 80%, it means that the monitoring motor needs manual confirmation to see if there is a fault; when When the output motor fault confidence is less than 10%, it means that the monitored motor is working normally.
[0095] Reference Figure 2 The present invention also provides an intelligent electromechanical comprehensive diagnosis and monitoring system based on the industrial Internet, which is used to perform an intelligent electromechanical comprehensive diagnosis and monitoring method based on the industrial Internet, including:
[0096] An audio acquisition module, wherein the audio acquisition module is used to acquire an audio time domain signal of the motor;
[0097] An audio analysis module, which analyzes, windows, and frames the audio time domain signal of the motor to generate a detection signal, and analyzes the detection signal to generate a motor audio fault index;
[0098] A fault-free motor temperature acquisition module, wherein the fault-free motor temperature acquisition module is used to collect temperature data of the fault-free motor when it is working and fault-free environment temperature data;
[0099] A first temperature analysis module, the first temperature analysis module is used to analyze the temperature data of the fault-free motor when it is working and the fault-free environmental temperature data, and generate the fault-free motor stable temperature and the fault-free motor temperature rise coefficient;
[0100] A working motor temperature acquisition module, wherein the working motor temperature acquisition module is used to acquire the working motor temperature and the working environment temperature;
[0101] A second temperature analysis module, the second temperature analysis module is used to analyze the temperature data of the working motor when it is working and the working environment temperature data, and generate the working motor stable temperature and the working motor temperature rise coefficient;
[0102] A temperature comprehensive analysis module, the temperature comprehensive analysis module is used to perform correlation analysis on the fault-free motor stable temperature, the fault-free motor temperature rise coefficient, the working motor stable temperature and the working motor temperature rise coefficient generated by the first temperature analysis module and the second temperature analysis module, and generate a motor temperature fault evaluation coefficient;
[0103] An evaluation and analysis module, wherein the evaluation and analysis module is used to perform a correlation analysis on a motor temperature fault evaluation coefficient and a motor audio fault index to generate a motor comprehensive fault evaluation index;
[0104] A comparison module is used to compare the motor audio fault index with the motor fault threshold and output the motor fault confidence.
[0105] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0106] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.
[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0108] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. An intelligent electromechanical comprehensive diagnosis and monitoring method based on the industrial Internet, characterized in that: The specific steps include: S1, collecting motor audio time domain signal; S2, preprocessing the audio time domain signal to generate a characteristic signal, wherein the characteristic signal highlights the high-frequency component part of the audio time domain signal; S3, perform windowing and frame processing on the characteristic signal to generate a detection signal, and generate the first The amplitude of the sampling point in the frame detection signal is analyzed for correlation between the amplitudes of the detection signal and the detection signal to generate the mean amplitude of the sampling point in the detection signal and the standard deviation of the amplitude of the sampling point in the detection signal, and the mean amplitude of the sampling point in the detection signal and the standard deviation of the amplitude of the sampling point in the detection signal are preprocessed to generate a motor audio fault index, which reflects the proportion of abnormal sound signals; S4, collecting the fault-free motor temperature and the fault-free ambient temperature, pre-processing the fault-free motor temperature, generating the fault-free motor stable temperature and the fault-free motor temperature rise coefficient, wherein the fault-free motor temperature rise coefficient reflects the motor temperature rise rate when the motor is working normally; S5, collecting the working motor temperature and the working environment temperature, pre-processing the working motor temperature, generating the working motor stable temperature and the working motor temperature increase coefficient, wherein the working motor temperature increase coefficient reflects the temperature increase rate when the monitoring motor is working; S6, pre-processing the stable temperature of the fault-free motor, the temperature rise coefficient of the fault-free motor, the stable temperature of the working motor and the temperature rise coefficient of the working motor to generate a motor temperature fault evaluation coefficient, wherein the motor temperature fault evaluation coefficient reflects the abnormal temperature of the monitored motor when it is working; S7, pre-processing the motor temperature fault evaluation coefficient and the motor audio fault index to generate a motor comprehensive fault evaluation index, comparing the motor comprehensive fault evaluation index with the motor fault threshold, and outputting the motor fault confidence, wherein the motor comprehensive fault evaluation index reflects the degree of comprehensive fault of the monitored motor, and the motor fault confidence reflects the confidence degree of the motor fault; The audio time domain signal is used Said that The audio time domain signal of sampling points is used Indicates that the number of sampling points is Analyze the audio time domain signal and generate sampling point characteristic signal , the formula based on is The characteristic signal of the sampling point Perform analysis and generate characteristic signals , the formula based on is Among them, T is the transpose of the matrix, and the characteristic signal Highlights the high-frequency components in the audio time domain signal; In S3, Frame detection signal express, The value range of is 1, 2, 3, ..., p, the first Frame No. The amplitude of the detection signal at each sampling point is expressed as Indicates the amplitude of the sampling point in the detection signal Perform correlation analysis to generate The average amplitude of the sampling points in the frame detection signal , the formula based on is: ; For The average amplitude of the sampling points in the frame detection signal and Frame No. The amplitude of the detection signal at each sampling point Perform correlation analysis to generate Standard deviation of the sampling point amplitude in the frame detection signal , the formula based on is: ; For Standard deviation of the sampling point amplitude in the frame detection signal , No. The average amplitude of the sampling points in the frame detection signal , No. Frame detection signal Perform correlation analysis to generate a motor audio fault index , the formula based on is: The motor audio fault index Reflects the proportion of abnormal sound signals. If the threshold range is exceeded, it means that the device is faulty; The fault-free motor temperature is Indicates that, where the subscript is the fault-free motor working time in seconds, The value range of is 1, 2, 3, ..., k, where , the trouble-free ambient temperature is used express; For fault-free motor temperature Perform correlation analysis to generate Trouble-free motor temperature change rate in seconds , the formula based on is: The first value range of the record is Ten consecutive groups of , and for ten consecutive groups Perform averaging to obtain the stable temperature of the fault-free motor , the ten consecutive groups Arranged from smallest to largest in terms of time, the first group The corresponding time is , for time and trouble-free ambient temperature , trouble-free motor stable temperature Perform correlation analysis to generate fault-free motor temperature rise coefficients , the formula based on is: in, is the working environment temperature weight factor, and its value range is , the fault-free motor temperature rise coefficient It reflects the rate of increase of motor temperature during normal motor operation; The working motor temperature is Indicates that, where the subscript is the working time of the working motor, in seconds, The value range of is 1, 2, 3, ..., k, where , the working environment temperature is express; Working motor temperature Perform correlation analysis to generate Operating motor temperature change rate in seconds , the formula based on is: The first record value range is Ten consecutive groups of , and for ten consecutive groups Perform averaging to obtain the stable temperature of the working motor , the ten consecutive groups Arranged from smallest to largest in terms of time, the first group The corresponding time is , for time and operating environment temperature , Working motor stable temperature Perform correlation analysis to generate the operating motor temperature rise coefficient , the formula based on is: The working motor temperature rise coefficient It reflects the temperature rise rate when the monitored motor is working; Temperature rise coefficient of working motor , Fault-free motor temperature rise coefficient , trouble-free motor stable temperature And the working motor stable temperature Perform correlation analysis to generate motor temperature fault evaluation coefficients , the formula based on is: The motor temperature fault evaluation coefficient It reflects the abnormal temperature of the monitored motor when it is working; Preprocess the motor temperature fault evaluation coefficient and motor audio fault index to generate the motor comprehensive fault evaluation index , the formula based on is: The motor comprehensive fault evaluation index Reflects the comprehensive fault degree of the monitored motor; The motor fault threshold is ,when When the output motor fault confidence is above 95%, it means that the monitoring motor is abnormal; when When the output motor fault confidence is 80%, it means that the monitoring motor needs manual confirmation to see if there is a fault; when When the output motor fault confidence is less than 10%, it means that the monitored motor is working normally.
2. The intelligent electromechanical comprehensive diagnosis and monitoring method based on the industrial Internet according to claim 1 is characterized in that: In S3, the audio signal sampling rate is 10500 Hz, the frame length of each frame is 262, and the frame shift is 157 during the frame processing.
3. The intelligent electromechanical comprehensive diagnosis and monitoring method based on the industrial Internet according to claim 1 is characterized in that: In S3, the windowing process uses a Hamming window function formula.
4. An intelligent electromechanical integrated diagnosis and monitoring system based on the industrial Internet, used to execute the intelligent electromechanical integrated diagnosis and monitoring method based on the industrial Internet as claimed in claim 1, characterized in that: include: An audio acquisition module, wherein the audio acquisition module is used to acquire an audio time domain signal of the motor; An audio analysis module, which analyzes, windows, and frames the audio time domain signal of the motor to generate a detection signal, and analyzes the detection signal to generate a motor audio fault index; A fault-free motor temperature acquisition module, wherein the fault-free motor temperature acquisition module is used to collect temperature data of the fault-free motor when it is working and fault-free environment temperature data; A first temperature analysis module, the first temperature analysis module is used to analyze the temperature data of the fault-free motor when it is working and the fault-free environmental temperature data, and generate the fault-free motor stable temperature and the fault-free motor temperature rise coefficient; A working motor temperature acquisition module, wherein the working motor temperature acquisition module is used to acquire the working motor temperature and the working environment temperature; A second temperature analysis module, the second temperature analysis module is used to analyze the temperature data of the working motor when it is working and the working environment temperature data, and generate the working motor stable temperature and the working motor temperature rise coefficient; A temperature comprehensive analysis module, the temperature comprehensive analysis module is used to perform correlation analysis on the fault-free motor stable temperature, the fault-free motor temperature rise coefficient, the working motor stable temperature and the working motor temperature rise coefficient generated by the first temperature analysis module and the second temperature analysis module, and generate a motor temperature fault evaluation coefficient; An evaluation and analysis module, wherein the evaluation and analysis module is used to perform a correlation analysis on a motor temperature fault evaluation coefficient and a motor audio fault index to generate a motor comprehensive fault evaluation index; A comparison module is used to compare the motor audio fault index with the motor fault threshold and output the motor fault confidence.
