Proximity sensor self-learning identification system based on multi-dimensional signal processing

Abstract

The invention discloses a proximity sensor self-learning recognition system based on multi-dimensional signal processing, and relates to the field of data analysis, and the main scheme is as follows: taking vibration data, electric energy quality data, sound data, operation data, wear data and magnetic field data of equipment in a normal operation state and different fault type operation states as input; and the comprehensive index # imgabs0 # of the equipment and the corresponding fault type label are taken as output, and the fault identification self-learning model is trained, so that the problems of poor model training effect and low identification accuracy caused by single data acquisition type and neglect of the relation among various types of data are solved, and the fault identification self-learning model is obtained. And judging whether the training data needs to be updated or not according to the fault index deviation value # imgabs1 # and the fault index deviation threshold value # imgabs2 #, thereby solving the problems that the distribution of the motor operation data may change along with time lapse and environment change, and the model performance declines if updating is not carried out in time.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a proximity sensor self-learning recognition system based on multi-dimensional signal processing. Background Art

[0002] In the field of motor fault identification, the proximity sensor self-learning identification system integrates data from multiple sensors and combines advanced signal processing technology and machine learning algorithms to effectively monitor and analyze the operating status of equipment, thereby realizing automatic identification of potential fault types. This not only provides strong support for equipment maintenance, but also helps to improve the safety and efficiency of industrial production.

[0003] The traditional method for the identification system to determine the fault type is to monitor the vibration signal of the motor equipment through a proximity sensor, input the collected vibration signal into a trained self-learning identification model, and the model automatically outputs the judgment result of the equipment fault type.

[0004] The existing technology still has the following shortcomings: the data collection type is single, and the connection between different types of data is ignored, resulting in poor model training effect, thereby reducing recognition accuracy. At the same time, with the passage of time and environmental changes, the distribution of motor operation data may change. If it is not updated in time, the model performance will decline. Summary of the invention

[0005] 1. Technical problems solved: In view of the shortcomings of the prior art, the present invention provides a proximity sensor self-learning recognition system based on multi-dimensional signal processing, which takes the vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment in normal operation state and different fault types as input, and converts the comprehensive index of the equipment into And the corresponding fault type label as output, the fault identification self-learning model is trained, which solves the problem of single data collection type and ignoring the connection between different types of data, resulting in poor model training effect and reduced recognition accuracy. and fault indicator deviation threshold Determining whether the training data for this fault type needs to be updated solves the problem that the distribution of motor operation data may change over time and due to environmental changes. If it is not updated in time, the model performance will deteriorate.

[0006] (II) Technical solution: To achieve the above objectives, the present invention is implemented through the following technical solutions: A proximity sensor self-learning recognition system based on multi-dimensional signal processing, comprising: A data acquisition module is used to collect vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment under normal operation and different fault types; Index calculation module, which can calculate vibration deviation index based on vibration data , calculate the power quality deviation index based on the power quality data , according to the vibration deviation index and power quality deviation index Calculating the Electrical-Vibration Correlation Index ; Calculate sound anomaly index based on sound data , based on operating data and abnormal sound indicators Calculating Sound-Operation Coupling Indicators ; Calculate wear distribution index based on wear data , calculate the magnetic field-power quality deviation index based on the magnetic field data and power quality data , according to the wear distribution index and magnetic field-power quality deviation index Calculation performance degradation index ; According to the electrical-vibration correlation index , Sound-Operation Coupling Index and performance degradation indicators Calculate composite index ; The model judgment module can build a fault identification self-learning model through the support vector machine learning model, taking the vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment under normal operation and different fault types as input, and converting the comprehensive indicators of the equipment into The corresponding fault type label is used as output to train the fault identification self-learning model; the current vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment are input into the trained fault identification self-learning model, and the model outputs comprehensive indicators and the corresponding fault type; Update module to obtain comprehensive indicators output in model judgment module And the comprehensive index of the corresponding fault type , and based on comprehensive indicators And the comprehensive index of the corresponding fault type Calculate the fault index deviation value ; Preset fault indicator deviation threshold , according to the fault index deviation value and fault indicator deviation threshold Determine whether the training data for this fault type needs to be updated.

[0007] In the preferred solution of the proximity sensor self-learning recognition system based on multi-dimensional signal processing: calculating the vibration deviation index The method is: Vibration data including vibration acceleration signals , vibration peak , RMS normal value and normal peak maximum ; Calculate vibration deviation index from vibration data , the formula based on is: ; in, For equipment Vibration deviation index under various operating conditions, It is the serial number corresponding to different operating states of the equipment, and its value is a positive integer; For equipment In the first operating state The vibration acceleration signal corresponding to each sampling point; is the serial number corresponding to different sampling points, and its value is ; is the total number of sampling points, which is a positive integer; For equipment The vibration peak value under various operating conditions.

[0008] In the preferred solution of the proximity sensor self-learning identification system based on multi-dimensional signal processing: calculating the power quality deviation index The method is: Power quality data including active power , reactive power , rated power factor , harmonic voltage effective value , Fundamental voltage effective value , Maximum voltage per unit time , minimum voltage per unit time and rated voltage ; Calculate power quality deviation index based on power quality data , the formula based on is: ;

[0009] in, For equipment Power quality deviation indicators under various operating conditions; For equipment Active power under various operating conditions; For equipment Reactive power under various operating conditions; For equipment The effective value of the fundamental voltage under the operating state; For equipment The maximum voltage per unit time under the operating state; For equipment The minimum voltage per unit time under the operating state; For equipment In the first operating state The effective value of the subharmonic voltage, is the serial number corresponding to different harmonic voltages, and its value is ; For equipment The total number of harmonic voltages under this operating state, which is a positive integer greater than 1.

[0010] In the preferred solution of the proximity sensor self-learning recognition system based on multi-dimensional signal processing: calculating the electrical-vibration correlation index The method is: According to the vibration deviation index and power quality deviation index Calculating the Electrical-Vibration Correlation Index , the formula based on is: ;

[0011] in, For equipment Electrical-vibration correlation index under various operating conditions; For equipment Vibration deviation index under different operating conditions The weight coefficient is between 0.3 and 0.7; For equipment Power quality deviation indicators under various operating conditions The weight coefficient is between 0.3 and 0.7; and .

[0012] In the preferred solution of the proximity sensor self-learning recognition system based on multi-dimensional signal processing: calculating the sound abnormality index The method is: Sound data including actual sound pressure , reference sound pressure , fundamental frequency amplitude of sound signal , sound signal harmonic amplitude , Band signal-to-noise ratio , upper limit of normal range of signal-to-noise ratio The lower limit of the normal range of signal-to-noise ratio ; Calculate sound anomaly index based on sound data , the formula based on is: ;

[0013] in, For equipment Abnormal sound index under various operating conditions; actual sound pressure For equipment The actual sound pressure under various operating conditions; For equipment The fundamental frequency amplitude of the sound signal under the various operating conditions; For equipment The first sound signal in the operating state The amplitude of the harmonics, is the serial number corresponding to different harmonics in the sound signal, and its value is ; For equipment The total number of harmonics in the sound signal under this operating state, which is a positive integer greater than 1; For equipment In the first operating state The signal-to-noise ratio value of the frequency band, is the serial number corresponding to different frequency bands, and its value is ; For equipment The total number of frequency bands in this operating state, which is a positive integer.

[0014] In the preferred embodiment of the proximity sensor self-learning recognition system based on multi-dimensional signal processing: calculating the sound-operation coupling index The method is: Operating data including actual operating temperature , Normal operating temperature , actual speed and rated speed ; According to the operation data and abnormal sound indicators Calculating Sound-Operation Coupling Indicators , the formula based on is: ;

[0015] in, For equipment Sound-operation coupling index under various operating conditions; For equipment The actual operating temperature under the operating conditions; For equipment Normal operating temperature under the operating state; For equipment The actual speed under various operating conditions.

[0016] In the preferred solution of the proximity sensor self-learning recognition system based on multi-dimensional signal processing: calculating the wear distribution index The method is: Wear data including average wear particle diameter , the number of wear particles and the total number of wear particles under normal conditions ; Calculate wear distribution index based on wear data , the formula based on is: ;

[0017] in, For equipment Wear distribution index under various operating conditions; For equipment In the first operating state Average diameter of wear particles within the size range, is the serial number corresponding to different size ranges, and its value is ; is the total number of different size ranges; For equipment In the first operating state The number of wear particles in a certain size range; For equipment The weight coefficient of the wear particle size index under the operating conditions is 0.4 to 0.6; For equipment The weight coefficient of the wear particle distribution entropy under the operating state is 0.4 to 0.6; and .

[0018] In the preferred solution of the proximity sensor self-learning recognition system based on multi-dimensional signal processing: calculating the performance degradation index The method is: Magnetic field data including actual magnetic field strength and normal magnetic field strength ; Power quality data also includes actual insulation resistance And normal insulation resistance ; Calculate the magnetic field-power quality deviation index based on the magnetic field data and power quality data , the formula based on is: ;

[0019] in, For equipment Magnetic field-power quality deviation index under various operating conditions; For equipment The actual magnetic field strength under various operating conditions; For equipment The actual insulation resistance under various operating conditions; According to the wear distribution index and magnetic field-power quality deviation index Calculation performance degradation index , the formula based on is: ;

[0020] in, For equipment Performance degradation indicators under various operating conditions.

[0021] In the preferred solution of the proximity sensor self-learning recognition system based on multi-dimensional signal processing: calculating the comprehensive index The method is: According to the electrical-vibration correlation index , Sound-Operation Coupling Index and performance degradation indicators Calculate composite index , the formula based on is: ;

[0022] in, For equipment Comprehensive indicators under various operating conditions; For equipment Electrical-vibration correlation index under various operating conditions The weight coefficient is 0.3 to 0.5; For equipment Sound-operation coupling index under various operating conditions The weight coefficient is between 0.2 and 0.5; For equipment Performance degradation indicators under various operating conditions The weight coefficient is between 0.2 and 0.5; and .

[0023] In the preferred solution of the proximity sensor self-learning recognition system based on multi-dimensional signal processing, the method for determining whether the training data needs to be updated is: According to comprehensive indicators And the comprehensive index of the corresponding fault type Calculate the fault index deviation value , the formula based on is: ;

[0024] in, For the Fault indicator deviation value of each fault type; According to the fault index deviation value and fault indicator deviation threshold The criteria for determining whether the training data for this fault type needs to be updated are: .

[0025] (III) Beneficial effects: The present invention provides a proximity sensor self-learning recognition system based on multi-dimensional signal processing, which has the following beneficial effects: (1) By collecting vibration data, power quality data, sound data, operation data, wear data, and magnetic field data under normal operating conditions and different fault types of equipment, multi-dimensional data can be provided for training the model to improve model accuracy.

[0026] (2) Calculate the electrical-vibration correlation index based on vibration data and power quality data , reflects the coordinated working of the electrical and mechanical parts of the equipment, helps to identify potential faults, and calculates the sound-operation coupling index based on sound data and operation data , which can more comprehensively reflect the operating status of the equipment, provide a basis for optimizing and adjusting the equipment operating parameters, and calculate the performance degradation index based on wear data, magnetic field data and power quality data , can more keenly detect early signs of faults, provide a basis for fault location and diagnosis, according to the electrical-vibration correlation index , Sound-Operation Coupling Index and performance degradation indicators Calculate composite index , which can evaluate the equipment from multiple dimensions and reflect the equipment operation characteristics more comprehensively.

[0027] (3) The vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment under normal operation and different fault types are used as input to calculate the comprehensive index of the equipment. And the corresponding fault type label is used as the output to train the fault recognition self-learning model, which solves the problem of single data collection type and ignoring the connection between different types of data, resulting in poor model training effect and thus reduced recognition accuracy.

[0028] (4) According to the fault index deviation value and fault indicator deviation threshold Determining whether the training data for this fault type needs to be updated solves the problem that the distribution of motor operation data may change over time and due to environmental changes. If it is not updated in time, the model performance will deteriorate. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a structural schematic diagram of the proximity sensor self-learning recognition system based on multi-dimensional signal processing of the present invention.

[0030] Figure 2 Calculate the electrical-vibration correlation index in the proximity sensor self-learning recognition system based on multi-dimensional signal processing of the present invention Parameter relationship structure diagram.

[0031] Figure 3 The present invention is a method for calculating the performance degradation index in the proximity sensor self-learning recognition system based on multi-dimensional signal processing. Parameter relationship structure diagram. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] See also Figure 1-Figure 3 The present invention provides a proximity sensor self-learning recognition system based on multi-dimensional signal processing, comprising: The data acquisition module is used to collect vibration data, power quality data, sound data, operation data, wear data and magnetic field data under normal operation status and different fault type operation status of the equipment.

[0034] In the above scheme, by collecting vibration data, power quality data, sound data, operation data, wear data and magnetic field data under normal operating conditions and different fault types of equipment, multi-dimensional data can be provided for the training model to improve the accuracy of the model.

[0035] Index calculation module, which can calculate vibration deviation index based on vibration data , calculate the power quality deviation index based on the power quality data , according to the vibration deviation index and power quality deviation index Calculating the Electrical-Vibration Correlation Index ; Calculate sound anomaly index based on sound data , based on operating data and abnormal sound indicators Calculating Sound-Operation Coupling Indicators ; Calculate wear distribution index based on wear data , calculate the magnetic field-power quality deviation index based on the magnetic field data and power quality data , according to the wear distribution index and magnetic field-power quality deviation index Calculation performance degradation index ; According to the electrical-vibration correlation index , Sound-Operation Coupling Index and performance degradation indicators Calculate composite index .

[0036] Specifically, the vibration deviation index is calculated The method is: Vibration data including vibration acceleration signals , vibration peak , RMS normal value and normal peak maximum .

[0037] It should be noted that the vibration acceleration signal It is a physical quantity that describes the vibration state of the equipment. It reflects the speed of the equipment during the vibration process and is measured by an acceleration sensor. It refers to the maximum value reached by the vibration acceleration signal during the vibration of the equipment, reflecting the strongest instantaneous vibration intensity during the vibration process. The acquisition method is: the vibration acceleration signal obtained by measuring the acceleration sensor Import the data into MATLAB software, write a program to traverse the data sequence, and find the maximum value in the data as the vibration peak . RMS normal value It is a measure of the energy of the vibration acceleration signal. The acquisition method is: during the normal operation of the equipment, collect the vibration acceleration signal within a unit time, such as hours, days or weeks, where the unit time depends on the operation cycle and stability of the equipment. Then, square the signal value of each sampling point, add these square values ​​and divide them by the number of sampling points to get the average value, and finally square the average value to get the root mean square normal value. . Normal peak maximum It refers to the maximum value of the vibration peak value that may occur during normal operation of the equipment. It is used to distinguish normal vibration fluctuations from abnormal vibrations that may indicate a fault. It is obtained by referring to the equipment manual.

[0038] Calculate vibration deviation index from vibration data , the formula based on is: ;

[0039] in, For equipment Vibration deviation index under various operating conditions, It is the serial number corresponding to different operating states of the equipment, and its value is a positive integer; For equipment In the first operating state The vibration acceleration signal corresponding to each sampling point; is the serial number corresponding to different sampling points, and its value is ; is the total number of sampling points, which is a positive integer; For equipment The vibration peak value under various operating conditions.

[0040] It should be noted that the operating principle of this formula is: It is used to measure the deviation between the actual RMS value and the normal RMS value. Used to measure the actual value of the vibration peak and the maximum value of the normal peak The formula comprehensively considers the influence of the above two aspects to obtain the vibration deviation index. .

[0041] Specifically, the power quality deviation index is calculated The method is: Power quality data including active power , reactive power , rated power factor , harmonic voltage effective value , Fundamental voltage effective value , Maximum voltage per unit time , minimum voltage per unit time and rated voltage .

[0042] It should be noted that active power Reactive power refers to the electrical energy actually used to do work in a device per unit time. It is a physical quantity used to measure the rate at which electrical energy is converted into other forms of energy. It can be measured using a power analyzer. It is the electrical energy used to establish and maintain the electric and magnetic fields in an AC circuit and can be measured using a power analyzer. It refers to the ratio of active power to apparent power of the equipment under rated operating conditions, which reflects the efficiency of the equipment in utilizing electric energy. It can be obtained by checking the equipment nameplate or product manual. It refers to the effective value of the harmonic voltage component. Harmonics refer to other frequency components besides the fundamental frequency component. These frequencies are integer multiples of the fundamental frequency and are called harmonics. The effective value of the harmonic voltage Obtained through spectrum analyzer measurement. Fundamental voltage RMS value It refers to the effective value of the fundamental frequency voltage component. It is an important indicator for measuring the size of AC voltage and is measured using a spectrum analyzer. The maximum voltage per unit time It refers to the maximum amplitude of the voltage signal in a specific time period and the minimum voltage per unit time. It refers to the minimum amplitude of the voltage signal in the same time period and the maximum voltage per unit time. And the minimum voltage per unit time The determination method is: use voltage sensors, power parameter testers and other data acquisition equipment to collect voltage signals, import the collected voltage data sequence into MATLAB software, write a program to traverse the data sequence, find the maximum and minimum values ​​in the data, and use them as the maximum voltage per unit time. And the minimum voltage per unit time . Rated voltage It refers to the standard voltage value when the equipment is operating normally. It represents the voltage range that the equipment can adapt to under normal working conditions. It can be obtained by checking the equipment nameplate or product manual.

[0043] Calculate power quality deviation index based on power quality data , the formula based on is: ;

[0044] in, For equipment Power quality deviation indicators under various operating conditions; For equipment Active power under various operating conditions; For equipment Reactive power under various operating conditions; For equipment The effective value of the fundamental voltage under the operating state; For equipment The maximum voltage per unit time under the operating state; For equipment The minimum voltage per unit time under the operating state; For equipment In the first operating state The effective value of the subharmonic voltage, is the serial number corresponding to different harmonic voltages, and its value is ; For equipment The total number of harmonic voltages under this operating state, which is a positive integer greater than 1.

[0045] It should be noted that the operating principle of this formula is: It is used to measure the deviation between the actual power factor and the rated power factor. Used to measure the degree of deviation of harmonic voltage. Used to measure voltage fluctuations, this formula comprehensively considers the influence of three aspects to obtain the power quality deviation index .

[0046] Specifically, the electrical-vibration correlation index is calculated The method is: According to the vibration deviation index and power quality deviation index Calculating the Electrical-Vibration Correlation Index , the formula based on is: ;

[0047] in, For equipment Electrical-vibration correlation index under various operating conditions; For equipment Vibration deviation index under different operating conditions The weight coefficient is 0.3 to 0.7, depending on the vibration deviation index under different operating conditions. Electrical-vibration correlation index Determine the extent of impact; For equipment Power quality deviation indicators under various operating conditions The weight coefficient is 0.3 to 0.7, depending on the power quality deviation index under different operating conditions. Electrical-vibration correlation index The extent of the impact is determined; and .

[0048] It should be noted that this formula takes into account the vibration deviation index through a weighted method. and power quality deviation index The influence of electrical-vibration correlation index is obtained .

[0049] Specifically, the sound anomaly index is calculated The method is: Sound data including actual sound pressure , reference sound pressure , fundamental frequency amplitude of sound signal , sound signal harmonic amplitude , Band signal-to-noise ratio , upper limit of normal range of signal-to-noise ratio The lower limit of the normal range of signal-to-noise ratio .

[0050] It should be noted that the actual sound pressure It refers to the pressure fluctuation value corresponding to the sound waves actually existing in the surrounding air due to equipment vibration and other reasons during the operation of the equipment. It reflects the intensity of the sound generated when the equipment is running. It is measured by a sound pressure meter and the unit is Pa. It is a reference value used to compare and measure the intensity of sound. The sound pressure value corresponding to the weakest sound that can be heard by the human ear is usually defined as the reference sound pressure. pa. Fundamental frequency amplitude of sound signal It refers to the amplitude corresponding to the fundamental frequency in the sound signal, which reflects the main vibration frequency and intensity of the equipment. The fundamental frequency is the basic frequency of the vibration and the main frequency in the sound frequency component. The amplitude of the fundamental frequency of the sound signal Obtained through spectrum analyzer measurement. Sound signal harmonic amplitude It refers to the amplitude corresponding to the harmonic frequency. The change of harmonic amplitude can reflect whether the equipment is abnormal. It is measured by spectrum analyzer. It refers to the ratio of signal power to noise power within a certain frequency bandwidth. It is used to measure the degree to which the device sound signal is interfered with by noise within a specific frequency range. It is measured using professional acoustic measurement instruments such as audio analyzers or signal-to-noise ratio testers. The lower limit of the normal range of signal-to-noise ratio It is a reference value used to judge whether the quality of the sound signal of the equipment is normal. The method of obtaining it is as follows: when the equipment is operating normally, use a signal-to-noise ratio tester to measure the signal-to-noise ratio data of the equipment multiple times, calculate the average value and standard deviation of these signal-to-noise ratio data, and calculate the value of the average value plus twice the standard deviation as the upper limit of the normal range of the signal-to-noise ratio value. Calculate the value of the mean minus two times the standard deviation as the lower limit of the normal range of the signal-to-noise ratio .

[0051] Calculate sound anomaly index based on sound data , the formula based on is: ;

[0052] in, For equipment Abnormal sound index under various operating conditions; actual sound pressure For equipment The actual sound pressure under various operating conditions; For equipment The fundamental frequency amplitude of the sound signal under the various operating conditions; For equipment The first sound signal in the operating state The amplitude of the harmonics, is the serial number corresponding to different harmonics in the sound signal, and its value is ; For equipment The total number of harmonics in the sound signal under this operating state, which is a positive integer greater than 1; For equipment In the first operating state The signal-to-noise ratio value of the frequency band, is the serial number corresponding to different frequency bands, and its value is ; For equipment The total number of frequency bands in this operating state, which is a positive integer.

[0053] It should be noted that the operating principle of this formula is: Used to measure the sound pressure level of equipment. It is used to measure the degree of deviation of harmonics in sound signals. Used to measure sound clarity, this formula takes into account three factors to obtain the sound abnormality index: ,in, is the base of the natural logarithm in the exponential function.

[0054] Specifically, the sound-operation coupling index is calculated The method is: Operating data including actual operating temperature , Normal operating temperature , actual speed and rated speed .

[0055] It should be noted that the actual operating temperature It refers to the actual temperature reached by the equipment during operation. The method of obtaining it is: use an infrared thermometer to measure the temperature values ​​of different parts of the equipment, such as transformers and windings, and add up the temperature values ​​of different parts and divide them by the number of data to obtain the actual operating temperature. Normal operating temperature It refers to the temperature range in which the equipment can operate stably for a long time under ideal working conditions without adversely affecting the performance and life of the equipment. The method of obtaining it is: refer to the equipment's operating manual, technical specification or product manual to obtain the normal operating temperature range, and calculate (temperature range upper limit + temperature range lower limit) / 2 to get the actual operating temperature . Actual speed It refers to the actual number of revolutions per minute or per second of rotating parts such as the motor rotor or machine tool spindle during the operation of the equipment. It reflects the operating speed of the equipment. The method of obtaining the speed is as follows: the measuring head of the tachometer is in contact with the rotating shaft of the equipment. The measuring head transmits the rotation speed of the equipment to the meter head through transmission mechanisms such as gears and friction wheels. The meter head displays the speed value mechanically or electronically. This value is the actual speed. . Rated speed It refers to the rotation speed that the equipment should reach under rated load and rated working conditions, which can be obtained by checking the nameplate of the equipment.

[0056] According to the operation data and abnormal sound indicators Calculating Sound-Operation Coupling Indicators , the formula based on is: ;

[0057] in, For equipment Sound-operation coupling index under various operating conditions; For equipment The actual operating temperature under the operating conditions; For equipment Normal operating temperature under the operating state; For equipment The actual speed under various operating conditions.

[0058] It should be noted that the operating principle of this formula is: The operating data deviation index is obtained by calculating the deviation between the actual operating temperature of the equipment and the normal operating temperature, as well as the deviation between the actual speed and the rated speed. This formula takes into account the abnormal sound index. and the operation data deviation index to obtain the sound-operation coupling index .

[0059] Specifically, the wear distribution index is calculated The method is: Wear data including average wear particle diameter , the number of wear particles and the total number of wear particles under normal conditions .

[0060] It should be noted that the average diameter of wear particles It refers to the average size of wear particles in different size ranges generated by friction between parts during equipment operation. The size ranges include 0-10μm, 0-50μm, 50-100μm, etc. The acquisition method is: collect equipment lubricating oil samples, use centrifugal separation to extract wear particles from the samples, use the measurement software provided by the electron microscope to measure the diameter of the observed wear particles, record the diameter of each wear particle and classify them according to the size range, for each size range, add up the diameters of all particles in the range, and then divide by the number of particles to obtain the average wear particle diameter. . Number of wear particles It refers to the number of particles in different size ranges among the wear particles generated by the equipment. By counting the number of particles in different size ranges, we can understand the specific situation of equipment wear in more detail. The acquisition method is: collect equipment lubricant samples, use centrifugal separation to extract wear particles from the samples, use the measurement software provided by the electron microscope to measure the diameter of the observed wear particles, record the diameter of each wear particle and classify them according to the size range, and count the number of particles in each size range as the wear particle number. The total number of wear particles under normal conditions It refers to the range of the number of wear particles contained in a certain volume of lubricating oil or lubricating medium under normal operating conditions of the equipment. It is used to determine whether the equipment is in a normal wear state. The acquisition method is: in the early stage of equipment commissioning or when the equipment is operating normally, lubricating oil samples are collected regularly, and the number of wear particles in the lubricating oil samples is measured using the measurement software provided by the electron microscope. The number of wear particles in all samples is accumulated and divided by the number of samples, which is the total number of wear particles under normal conditions. .

[0061] Calculate wear distribution index based on wear data , the formula based on is: ;

[0062] in, For equipment Wear distribution index under various operating conditions; For equipment In the first operating state Average diameter of wear particles within the size range, is the serial number corresponding to different size ranges, and its value is ; is the total number of different size ranges; For equipment In the first operating state The number of wear particles in a certain size range; For equipment The weight coefficient of the wear particle size index under different operating conditions is 0.4 to 0.6. The wear distribution index is calculated based on the wear particle size index under different operating conditions. Determine the importance of For equipment The weight coefficient of the wear particle distribution entropy under different operating conditions is 0.4-0.6. The wear distribution index is calculated based on the wear particle distribution entropy under different operating conditions. The importance of .

[0063] It should be noted that the operating principle of this formula is: For equipment The wear particle size index under a certain operating condition is used to measure the influence of the size and quantity of wear particles on the distribution of wear particles. For equipment The wear particle distribution entropy under the operating state is used to measure the uniformity of wear particle distribution. The formula uses a weighted method to comprehensively consider the wear particle size index and the wear particle distribution entropy to obtain the wear distribution index. .

[0064] Specifically, the performance degradation index is calculated The method is: Magnetic field data including actual magnetic field strength and normal magnetic field strength .

[0065] It should be noted that the actual magnetic field strength It refers to the strength of the actual magnetic field generated by the device when it is running. It is measured using a Hall effect sensor. The specific method is: place the Hall effect sensor at the location where the magnetic field strength needs to be measured, connect the magnetic field strength meter to the Hall effect sensor, and obtain the actual magnetic field strength by reading the value displayed by the magnetic field strength meter. . Normal magnetic field strength It refers to the range of magnetic field strength that the equipment should generate under normal operating conditions, which can be obtained by referring to the equipment's operating manual, technical specification sheet or product brochure.

[0066] Power quality data also includes actual insulation resistance and normal insulation resistance .

[0067] It should be noted that the actual insulation resistance It refers to the resistance value of the insulation part of the equipment under actual operation, which reflects the ability of the equipment insulation material to prevent current leakage. It is measured by a digital insulation resistance tester. It refers to the range of insulation resistance values ​​that the equipment should have under ideal, trouble-free operating conditions. It is an important reference standard for judging whether the insulation status of the equipment is good. It can be obtained by referring to the equipment's operating manual, technical specification or product manual.

[0068] Calculate the magnetic field-power quality deviation index based on the magnetic field data and power quality data , the formula based on is: ;

[0069] in, For equipment Magnetic field-power quality deviation index under various operating conditions; For equipment The actual magnetic field strength under various operating conditions; For equipment The actual insulation resistance under various operating conditions.

[0070] It should be noted that the operating principle of this formula is: Used to measure the actual magnetic field strength and normal magnetic field strength The degree of deviation, Used to measure actual insulation resistance And normal insulation resistance The formula comprehensively considers the degree of deviation of the magnetic field and the degree of deviation of the insulation resistance to obtain the magnetic field-power quality deviation index. .

[0071] According to the wear distribution index and magnetic field-power quality deviation index Calculation performance degradation index , the formula based on is: ;

[0072] in, For equipment Performance degradation indicators under various operating conditions.

[0073] It should be noted that the operating principle of this formula is: By taking the square root of the square, the effect of the smaller of the two indicators is magnified. By taking the natural logarithm, the influence of the larger value of the two indicators is amplified. The formula takes into account the wear distribution indicators and magnetic field-power quality deviation index The two aspects of influence, get the performance degradation index .in, is the natural logarithm function.

[0074] Specifically, the calculation of the composite index The method is: According to the electrical-vibration correlation index , Sound-Operation Coupling Index and performance degradation indicators Calculate composite index , the formula based on is: ;

[0075] in, For equipment Comprehensive indicators under various operating conditions; For equipment Electrical-vibration correlation index under various operating conditions The weight coefficient is 0.3 to 0.5, according to the electrical-vibration correlation index under different operating conditions. For comprehensive indicators Determine the extent of impact; For equipment Sound-operation coupling index under various operating conditions The weight coefficient is 0.2 to 0.5, depending on the sound-operation coupling index under different operating conditions. For comprehensive indicators Determine the extent of impact; For equipment Performance degradation indicators under various operating conditions The weight coefficient is 0.2 to 0.5, depending on the performance degradation index under different operating conditions. For comprehensive indicators The extent of the impact is determined; and .

[0076] It should be noted that this formula takes into account the electrical-vibration correlation index through a weighted method. , Sound-Operation Coupling Index and performance degradation indicators Three aspects of influence, use at the same time Function, maps the final result into a bounded range to obtain a comprehensive index .

[0077] In the above scheme, the electrical-vibration correlation index is calculated based on vibration data and power quality data , reflects the coordinated working of the electrical and mechanical parts of the equipment, helps to identify potential faults, and calculates the sound-operation coupling index based on sound data and operation data , which can more comprehensively reflect the operating status of the equipment, provide a basis for optimizing and adjusting the equipment operating parameters, and calculate the performance degradation index based on wear data, magnetic field data and power quality data , can more keenly detect early signs of faults, provide a basis for fault location and diagnosis, according to the electrical-vibration correlation index , Sound-Operation Coupling Index and performance degradation indicators Calculate composite index , which can evaluate the equipment from multiple dimensions and reflect the equipment operation characteristics more comprehensively.

[0078] The model judgment module can build a fault identification self-learning model through the support vector machine learning model. The vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment under normal operation and different fault types are used as input to calculate the comprehensive index of the equipment. The corresponding fault type label is used as output to train the fault identification self-learning model; the current vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment are input into the trained fault identification self-learning model, and the model outputs comprehensive indicators and the corresponding fault type.

[0079] It should be noted that different fault types include stator winding fault, rotor winding fault, electrical connection fault, bearing fault, rotor imbalance fault and ventilation fault, etc.

[0080] In the above scheme, the vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment under normal operation and different fault types are taken as input, and the comprehensive index of the equipment is And the corresponding fault type label is used as the output to train the fault identification self-learning model, which solves the problem of single data collection type and ignoring the connection between different types of data, resulting in poor model training effect and thus reduced recognition accuracy.

[0081] Update module to obtain comprehensive indicators output in model judgment module And the comprehensive index of the corresponding fault type , and based on comprehensive indicators And the comprehensive index of the corresponding fault type Calculate the fault index deviation value ; Preset fault indicator deviation threshold , according to the fault index deviation value and fault indicator deviation threshold Determine whether the training data for this fault type needs to be updated.

[0082] Specifically, the method to determine whether the training data needs to be updated is: According to comprehensive indicators And the comprehensive index of the corresponding fault type Calculate the fault index deviation value , the formula based on is: ;

[0083] It should be noted that this formula calculates the comprehensive index And the comprehensive index of the corresponding fault type The distance between them is used to obtain the fault index deviation value. .

[0084] in, For the Fault indicator deviation value of the fault type.

[0085] According to the fault index deviation value and fault indicator deviation threshold The criteria for determining whether the training data for this fault type needs to be updated are: ;

[0086] It should be noted that the fault indicator deviation threshold The determination method is as follows: obtain the historical comprehensive index value output by the fault identification self-learning model, calculate the comprehensive index of the historical comprehensive index value and its corresponding fault type The fault indicator deviation value between the two is selected, and the lower 50% data is selected and the average value is calculated as the fault indicator deviation threshold. reference value.

[0087] In the above scheme, according to the fault indicator deviation value and fault indicator deviation threshold Determining whether the training data for this fault type needs to be updated solves the problem that the distribution of motor operation data may change over time and due to environmental changes. If it is not updated in time, the model performance will deteriorate.

[0088] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill 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 in electronic hardware or in combination with computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0089] 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, that is, they 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.

[0090] 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. A proximity sensor self-learning recognition system based on multi-dimensional signal processing, characterized by: include: A data acquisition module is used to collect vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment under normal operation and different fault types; Index calculation module, which can calculate vibration deviation index based on vibration data , calculate the power quality deviation index based on the power quality data , according to the vibration deviation index and power quality deviation index Calculating the Electrical-Vibration Correlation Index ; Calculate sound anomaly index based on sound data , based on operating data and abnormal sound indicators Calculating Sound-Operation Coupling Indicators ; Calculate wear distribution index based on wear data , calculate the magnetic field-power quality deviation index based on the magnetic field data and power quality data , according to the wear distribution index and magnetic field-power quality deviation index Calculation performance degradation index ; According to the electrical-vibration correlation index , Sound-Operation Coupling Index and performance degradation indicators Calculate composite index ; The model judgment module can build a fault identification self-learning model through the support vector machine learning model, taking the vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment under normal operation and different fault types as input, and converting the comprehensive indicators of the equipment into The corresponding fault type label is used as output to train the fault identification self-learning model; the current vibration data, power quality data, sound data, operation data, wear data and magnetic field data of the equipment are input into the trained fault identification self-learning model, and the model outputs comprehensive indicators and the corresponding fault type; Update module to obtain comprehensive indicators output in model judgment module And the comprehensive index of the corresponding fault type , and based on comprehensive indicators And the comprehensive index of the corresponding fault type Calculate the fault index deviation value ; Preset fault indicator deviation threshold , according to the fault index deviation value and fault indicator deviation threshold Determine whether the training data for this fault type needs to be updated.

2. The proximity sensor self-learning recognition system based on multi-dimensional signal processing according to claim 1, characterized in that: Calculating vibration deviation index The method is: Vibration data including vibration acceleration signals , vibration peak , RMS normal value and normal peak maximum ; Calculate vibration deviation index from vibration data , the formula based on is: ； in, For equipment Vibration deviation index under various operating conditions, It is the serial number corresponding to different operating states of the equipment, and its value is a positive integer; For equipment In the first operating state The vibration acceleration signal corresponding to each sampling point; is the serial number corresponding to different sampling points, and its value is ; is the total number of sampling points, which is a positive integer; For equipment The vibration peak value under various operating conditions.

3. The proximity sensor self-learning recognition system based on multi-dimensional signal processing according to claim 2 is characterized in that: Calculate power quality deviation index The method is: Power quality data including active power , reactive power , rated power factor , harmonic voltage effective value , Fundamental voltage effective value , Maximum voltage per unit time , minimum voltage per unit time and rated voltage ; Calculate power quality deviation index based on power quality data , the formula based on is: ； in, For equipment Power quality deviation indicators under various operating conditions; For equipment Active power under various operating conditions; For equipment Reactive power under various operating conditions; For equipment The effective value of the fundamental voltage under the operating state; For equipment The maximum voltage per unit time under the operating state; For equipment The minimum voltage per unit time under the operating state; For equipment In the first operating state The effective value of the subharmonic voltage, is the serial number corresponding to different harmonic voltages, and its value is ; For equipment The total number of harmonic voltages under this operating state, which is a positive integer greater than 1.

4. The proximity sensor self-learning recognition system based on multi-dimensional signal processing according to claim 3 is characterized in that: Calculating the Electrical-Vibration Correlation Index The method is: According to the vibration deviation index and power quality deviation index Calculating the Electrical-Vibration Correlation Index , the formula based on is: ； in, For equipment Electrical-vibration correlation index under various operating conditions; For equipment Vibration deviation index under different operating conditions The weight coefficient is between 0.3 and 0.7; For equipment Power quality deviation indicators under various operating conditions The weight coefficient is between 0.3 and 0.7; and .

5. The proximity sensor self-learning recognition system based on multi-dimensional signal processing according to claim 4 is characterized in that: Calculate the sound anomaly index The method is: Sound data including actual sound pressure , reference sound pressure , fundamental frequency amplitude of sound signal , sound signal harmonic amplitude , Band signal-to-noise ratio , upper limit of normal range of signal-to-noise ratio The lower limit of the normal range of signal-to-noise ratio ; Calculate sound anomaly index based on sound data , the formula based on is: ； in, For equipment Abnormal sound index under various operating conditions; actual sound pressure For equipment The actual sound pressure under various operating conditions; For equipment The fundamental frequency amplitude of the sound signal under the various operating conditions; For equipment The first sound signal in the operating state The amplitude of the harmonics, is the serial number corresponding to different harmonics in the sound signal, and its value is ; For equipment The total number of harmonics in the sound signal under this operating state, which is a positive integer greater than 1; For equipment In the first operating state The signal-to-noise ratio value of the frequency band, is the serial number corresponding to different frequency bands, and its value is ; For equipment The total number of frequency bands in this operating state, which is a positive integer.

6. The proximity sensor self-learning recognition system based on multi-dimensional signal processing according to claim 5, characterized in that: Calculating Sound-Operation Coupling Indicators The method is: Operating data including actual operating temperature , Normal operating temperature , actual speed and rated speed ; According to the operation data and abnormal sound indicators Calculating Sound-Operation Coupling Indicators , the formula based on is: ； in, For equipment Sound-operation coupling index under various operating conditions; For equipment The actual operating temperature under the operating conditions; For equipment Normal operating temperature under the operating state; For equipment The actual speed under various operating conditions.

7. The proximity sensor self-learning recognition system based on multi-dimensional signal processing according to claim 6, characterized in that: Calculate wear distribution index The method is: Wear data including average wear particle diameter , the number of wear particles and the total number of wear particles under normal conditions ; Calculate wear distribution index based on wear data , the formula based on is: ； in, For equipment Wear distribution index under various operating conditions; For equipment In the first operating state Average diameter of wear particles within the size range, is the serial number corresponding to different size ranges, and its value is ; is the total number of different size ranges; For equipment In the first operating state The number of wear particles in a certain size range; For equipment The weight coefficient of the wear particle size index under the operating state is 0.4 to 0.6; For equipment The weight coefficient of the wear particle distribution entropy under the operating state is 0.4 to 0.6; and .

8. The proximity sensor self-learning recognition system based on multi-dimensional signal processing according to claim 7, characterized in that: Calculation performance degradation index The method is: Magnetic field data including actual magnetic field strength and normal magnetic field strength ; Power quality data also includes actual insulation resistance And normal insulation resistance ; Calculate the magnetic field-power quality deviation index based on the magnetic field data and power quality data , the formula based on is: ； in, For equipment Magnetic field-power quality deviation index under various operating conditions; For equipment The actual magnetic field strength under various operating conditions; For equipment The actual insulation resistance under various operating conditions; According to the wear distribution index and magnetic field-power quality deviation index Calculation performance degradation index , the formula based on is: ； in, For equipment Performance degradation indicators under various operating conditions.

9. The proximity sensor self-learning recognition system based on multi-dimensional signal processing according to claim 8, characterized in that: Calculate composite index The method is: According to the electrical-vibration correlation index , Sound-Operation Coupling Index and performance degradation indicators Calculate composite index , the formula based on is: ； in, For equipment Comprehensive indicators under various operating conditions; For equipment Electrical-vibration correlation index under various operating conditions The weight coefficient is 0.3 to 0.5; For equipment Sound-operation coupling index under various operating conditions The weight coefficient is between 0.2 and 0.5; For equipment Performance degradation indicators under various operating conditions The weight coefficient is between 0.2 and 0.5; and .

10. The proximity sensor self-learning recognition system based on multi-dimensional signal processing according to claim 9, characterized in that: The method to determine whether the training data needs to be updated is: According to comprehensive indicators And the comprehensive index of the corresponding fault type Calculate the fault index deviation value , the formula based on is: ； in, For the Fault indicator deviation value of each fault type; According to the fault index deviation value and fault indicator deviation threshold The criteria for determining whether the training data for this fault type needs to be updated are: 。

Images