Variable working condition abnormal data processing system and method for mine car electric wheel speed reducer

Abstract

The invention provides a variable working condition abnormal data processing system and method for a mine car electric wheel speed reducer, and the system comprises a data collection device (100) which is disposed on a mine car electric wheel and is used for collecting the operation state data A of the mine car electric wheel and the working condition data T of the surrounding environment. The data classification device (200) is used for performing time effect classification on the operation state data A and giving a doubt value; the data processing device is used for judging abnormal data F in the processing data B and the processing data C through a GAN network model; and the display device (400) is used for displaying an analysis result to a user. According to the variable working condition abnormal data processing system and method for the mine car electric wheel speed reducer, abnormal data in a variable working condition environment is cleaned, so that the data accuracy is effectively ensured, and the authenticity of fault diagnosis is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal data processing of electric wheel reducers, and in particular to a system and method for processing abnormal data of variable working conditions of electric wheel reducers of mining vehicles. Background Art

[0002] As one of the most important assemblies of a mine car, the electric wheel has a high cost and a high cost for major repairs. The electric wheel reducer is currently monitored by offline regular testing, which has a large gap period. If the major repair is not timely, it is easy to cause serious mechanical accidents such as bearing damage and tooth breaking, resulting in large losses. For safety reasons, the major repair cycle is shortened, which increases costs.

[0003] Changing operating conditions refer to other operating conditions that are not under the design operating conditions. Abnormal data are usually generated during the changing operating conditions, but most of the abnormal data are non-normal data. The generation of such data will interfere with the fault diagnosis of the electric wheel, and in severe cases, misdiagnosis will occur. How to clean these non-normal data in time is crucial to the accuracy of equipment fault diagnosis.

[0004] Application number CN202311060547.6 discloses a method for detecting abnormalities in mechanical rotating equipment under variable working conditions based on feature alignment residual GAN. The method includes: constructing a time-frequency diagram of rotating machinery data, reconstructing the time-frequency diagram using an encoder GE(x) and a decoder GD(x) respectively combined with an autoencoder network of a residual module ResNet, and using a discriminator D to discriminate the authenticity of reconstructed data and source data to determine abnormal data. The network loss function contains adversarial loss Ladv, context loss Lcon of generator reconstruction data error, encoder loss Lenc, and Wasserstein distance loss Lw-gan for constructing ranked parity data classification for feature value alignment. Summary of the invention

[0005] The present invention aims to overcome the technical problem in the prior art that the abnormal data generated by variable operating conditions affect the accuracy of fault diagnosis during the fault diagnosis of an electric wheel reducer, and provides a variable operating condition abnormal data processing system and method for an electric wheel reducer of a mine car. By cleaning the abnormal data under variable operating conditions, the accuracy of the data is effectively guaranteed and the authenticity of the fault diagnosis is improved.

[0006] The present invention provides a variable working condition abnormal data processing system for a mine car electric wheel reducer, comprising:

[0007] Data acquisition device: arranged on the electric wheel of the mine car, used to collect the running state data A of the electric wheel of the mine car and the surrounding environment working condition data T, and used to transmit the running state data A and the working condition data T to the data classification device;

[0008] Data classification device: used for receiving the operation status data A and the working condition data T transmitted by the data acquisition device, used for dividing the operation status data A into the operation data A1 which is not related to the time t change and the time-effect data A2 which is related to the time t according to the time effect, used for assigning the doubtful value S1 to the operation data A1 to generate the processed data B, used for assigning the doubtful value S2 to the operation data A2 to generate the processed data C, used for transmitting the processed data B, the processed data C and the working condition data T to the data processing device; the doubtful value S1 and the doubtful value S2 are calculated as follows:

[0009] S1=f(t)×f(α,E)

[0010] S2=g(t)×g(β,E)

[0011] Among them, f(t) and g(t) are time constant curves, f(α, E) and g(β, E) are functions related to the measured data, E is the measured data value, α and β are the deviation coefficients between the measured data and the theoretical data;

[0012] Data processing device: used for receiving the processed data B, processed data C and operating condition data T transmitted by the data classification device, used for calculating the operating condition parameter curve S according to the operating condition data, used for determining whether a changed operating condition occurs according to the operating condition parameter curve S, used for training the GAN network model through the processed data D whose doubtful value S2 under the changed operating condition is less than a set threshold, used for judging abnormal data F in the processed data B and processed data C through the GAN network model, used for analyzing the abnormal data F and generating an analysis result, and used for transmitting the analysis result to the display device;

[0013] Display device: used to receive the analysis results transmitted by the data processing device and display the analysis results to the user.

[0014] The variable operating condition abnormal data processing system for the electric wheel reducer of a mine car described in the present invention, as a preferred embodiment, the operating data A1 includes the real-time speed, the deviation value between the real-time speed and the set speed, the vibration frequency, the amplitude, and the phase; the time-effect data A2 includes the detection point stroke, the detection point stroke deviation value, the time domain characteristics, the frequency domain characteristics, the time-frequency domain characteristics, and the energy spectrum. The time domain characteristics include the variance, the mean square value, the effective value, the skewness and the kurtosis, the peak index, the margin index, the waveform index, and the pulse index. The frequency domain characteristics include the FFT spectrum, the power spectrum, and the envelope spectrum.

[0015] The present invention provides a method for processing abnormal data of a variable working condition of an electric wheel reducer of a mine car, comprising the following steps:

[0016] S1. Data collection: The data collection device collects the running status data A and working condition data T of the electric wheel of the mine car in real time;

[0017] S2, data classification: the data classification device classifies the operation status data A into operation data A1 that is not related to the time t change and time-effect data A2 that is related to the time t according to the time effect;

[0018] S3, assigning a questionable value: the data classification device assigns a questionable value S1 and a questionable value S2 to the operation data A1 and the timeliness data A2 respectively;

[0019] S4, judgment of changed working condition: the data processing device judges whether the changed working condition behavior occurs according to the working condition data T, and if it is judged to be yes, it proceeds to step S5, and if it is judged to be no, it proceeds to step S7;

[0020] S5, abnormal data judgment: the data processing device screens out abnormal data F through the GAN network model;

[0021] S6. Abnormal data confirmation: The data processing device cleans the abnormal data F according to the doubtful value S of the abnormal data F and generates an analysis report;

[0022] S7. The abnormal data processing system operates normally.

[0023] The method for processing abnormal data of variable working conditions of the electric wheel reducer of a mine car described in the present invention is, as a preferred embodiment, step S4 further comprises the following steps:

[0024] S41, calculating the operating condition parameter curve S according to the operating condition data T

[0025] S=c×f(t)×f(T,P,rh,v)+d

[0026] Among them, f(t) is a function related to time, f(T,P,rh,v) is a function related to temperature, air pressure, humidity and wind speed, c is the influencing factor, and d is the correction deviation;

[0027] S42, judgment of variable working condition behavior: deriving the working condition parameter curve S

[0028]

[0029] If S' is greater than the operating condition change threshold, it is determined that the operating condition change behavior occurs.

[0030] The method for processing abnormal data under variable operating conditions for an electric wheel reducer of a mine car described in the present invention is, as a preferred embodiment, that the data processing device in step S6 can correct the doubtful value S of the abnormal data F according to historical data or data from other monitoring points to determine whether the abnormal data F is true abnormal data.

[0031] The method for processing abnormal data under variable operating conditions for an electric wheel reducer of a mine car described in the present invention is, as a preferred embodiment, a data processing device performs fault diagnosis on real abnormal data and performs data cleaning on non-real abnormal data.

[0032] The method for processing abnormal data of variable working conditions for the electric wheel reducer of a mine car described in the present invention, as a preferred embodiment, further comprises the following steps:

[0033] S8. GAN network model training: Under variable working conditions, normal data E can be used to train the GAN network training model. Normal data E:

[0034] E=DF∪D.

[0035] The advantages of the present invention compared with the prior art are:

[0036] (1) The present invention assigns a doubt value S to the operating status data A to verify the abnormal data screened by the GAN network model, thereby effectively completing data cleaning.

[0037] (2) The present invention combines different historical data and differently collected data under similar working conditions to perform secondary judgment on abnormal data, thereby improving the accuracy of abnormal data cleaning and ensuring the normal operation of the fault diagnosis system.

[0038] (3) The present invention further improves the accuracy of abnormal data screening by training the GAN network model with actual operation data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a composition diagram of a variable working condition abnormal data processing system for a mine car electric wheel reducer;

[0040] Figure 2 This is a schematic diagram of the position of the sensor installed on the outer side of the electric wheel of a variable working condition abnormal data processing system for the electric wheel reducer of a mine car;

[0041] Figure 3 This is a schematic diagram of the position of the sensor installed on the inner side of the electric wheel of a variable working condition abnormal data processing system for the electric wheel reducer of a mine car;

[0042] Figure 4 A schematic diagram of the sensor location for the main generator of a variable operating condition abnormal data processing system for a mine car electric wheel reducer;

[0043] Figure 5 The present invention is a flow chart of a method for processing abnormal data under variable operating conditions of an electric wheel reducer for a mine car.

[0044] Reference numerals:

[0045] 100. Data acquisition device; 200. Data classification device; 300. Data processing device; 400. Display device. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0047] Example 1

[0048] like Figure 1 As shown, a variable working condition abnormal data processing system for a mine car electric wheel reducer comprises:

[0049] The data acquisition device 100 is arranged on the electric wheel of the mine car, and is used to collect the running state data A of the electric wheel of the mine car and the surrounding environment working condition data T, and is used to transmit the running state data A and the working condition data T to the data classification device 200; Figures 2 to 4 As shown, each mining car includes at least 3 collection points, which are respectively arranged on the outside of the motor, the inside of the motor (on the gear box) and the main generator;

[0050] The data classification device 200 is used to receive the operation status data A and the working condition data T transmitted by the data acquisition device 100, and is used to divide the operation status data A into operation data A1 that is independent of the time t change and time-effect data A2 that is related to the time t according to the time effect, and is used to assign the operation data A1 with a questionable value S1 to generate the processed data B, and is used to assign the operation data A2 with a questionable value S2 to generate the processed data C, and is used to transmit the processed data B, the processed data C and the working condition data T to the data processing device 300; the operation data A1 includes the real-time speed, the deviation value between the real-time speed and the set speed, the vibration frequency, the amplitude and the phase; the time-effect data A2 includes the detection point stroke, the detection point stroke deviation value, the time domain characteristics, the frequency domain characteristics, the time-frequency domain characteristics and the energy spectrum; the time domain characteristics include the variance, the mean square value, the effective value, the skewness and the kurtosis, the peak index, the margin index, the waveform index and the pulse index; the frequency domain characteristics include the FFT spectrum, the power spectrum and the envelope spectrum;

[0051] The doubt value S1 and the doubt value S2 are calculated as follows:

[0052] S1=f(t)×f(α,E)

[0053] S2=g(t)×g(β,E)

[0054] Among them, f(t) and g(t) are time constant curves, f(α, E) and g(β, E) are functions related to the measured data, E is the measured data value, α and β are the deviation coefficients between the measured data and the theoretical data;

[0055] The data processing device 300 is used to receive the processed data B, processed data C and operating condition data T transmitted by the data classification device 200, to calculate the operating condition parameter curve S according to the operating condition data, to determine whether a changed operating condition occurs according to the operating condition parameter curve S, to train the GAN network model through the processed data D whose doubtful value S2 under the changed operating condition is less than a set threshold, to determine the abnormal data F in the processed data B and processed data C through the GAN network model, to analyze the abnormal data F and generate an analysis result, and to transmit the analysis result to the display device 400;

[0056] Display device 400: used to receive the analysis results transmitted by data processing device 300 and present the analysis results to the user.

[0057] like Figure 5 As shown, this embodiment provides a method for processing abnormal data of variable working conditions of an electric wheel reducer for a mine car, comprising the following steps:

[0058] S1, data collection: the data collection device 100 collects the running state data A and working condition data T of the electric wheel of the mine car in real time;

[0059] S2, data classification: the data classification device 200 classifies the operation status data A into operation data A1 that is not related to the time t change and time-effect data A2 that is related to the time t according to the time effect;

[0060] S3, assigning a questionable value: the data classification device 200 assigns a questionable value S1 and a questionable value S2 to the operation data A1 and the timeliness data A2 respectively;

[0061] S4, judgment of changed working condition: the data processing device 300 judges whether the changed working condition behavior occurs according to the working condition data T, and if it is judged to be yes, it proceeds to step S5, and if it is judged to be no, it proceeds to step S7; step S4 further includes the following steps:

[0062] S41, calculating the operating condition parameter curve S according to the operating condition data T

[0063] S=c×f(t)×f(T,P,rh,v)+d

[0064] Among them, f(t) is a function related to time, f(T,P,rh,v) is a function related to temperature, air pressure, humidity and wind speed, c is the influencing factor, and d is the correction deviation;

[0065] S42, judgment of variable working condition behavior: deriving the working condition parameter curve S

[0066]

[0067] If S' is greater than the variable operating condition threshold, it is determined that variable operating condition behavior occurs;

[0068] S5, abnormal data judgment: the data processing device 300 screens out abnormal data F through the GAN network model;

[0069] S6. Confirmation of abnormal data: The data processing device 300 cleans the abnormal data F according to the doubtful value S of the abnormal data F and generates an analysis report; the data processing device 300 can correct the doubtful value S of the abnormal data F according to historical data or data from other monitoring points to determine whether the abnormal data F is real abnormal data. The data processing device 300 performs fault diagnosis on real abnormal data and cleans up data on non-real abnormal data;

[0070] S7. The abnormal data processing system operates normally;

[0071] S8. GAN network model training: Under variable working conditions, normal data E can be used to train the GAN network training model. Normal data E:

[0072] E=DF∪D.

[0073] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A variable working condition abnormal data processing system for a mine car electric wheel reducer, characterized in that: include: A data acquisition device (100): arranged on the electric wheel of the mine car, used for collecting the running state data A of the electric wheel of the mine car and the surrounding environment working condition data T, and used for transmitting the running state data A and the working condition data T to the data classification device (200); A data classification device (200): used for receiving the operating status data A and the operating condition data T transmitted by the data acquisition device, used for dividing the operating status data A into operating data A1 that is independent of the time t change and time-effect data A2 that is related to the time t according to the time effect, used for assigning the operating data A1 with a questionable value S1 to generate processed data B, used for assigning the operating data A2 with a questionable value S2 to generate processed data C, and used for transmitting the processed data B, the processed data C and the operating condition data T to a data processing device (300); the questionable value S1 and the questionable value S2 are calculated as follows: S1=f(t)×f(α,E) S2=g(t)×g(β,E) Among them, f(t) and g(t) are time constant curves, f(α, E) and g(β, E) are functions related to the measured data, E is the measured data value, α and β are the deviation coefficients between the measured data and the theoretical data; A data processing device (300): used for receiving the processed data B, the processed data C and the operating condition data T transmitted by the data classification device (200), used for calculating the operating condition parameter curve S according to the operating condition data, used for determining whether a changed operating condition occurs according to the operating condition parameter curve S, used for training a GAN network model through the processed data D in which the doubtful value S2 under the changed operating condition is less than a set threshold, used for judging abnormal data F in the processed data B and the processed data C through the GAN network model, used for analyzing the abnormal data F and generating an analysis result, and used for transmitting the analysis result to a display device (400); Display device (400): used for receiving the analysis result transmitted by the data processing device and presenting the analysis result to the user.

2. The system for processing abnormal data under variable working conditions for electric wheel reducer of a mine car according to claim 1, characterized in that: The operating data A1 includes the real-time speed, the deviation between the real-time speed and the set speed, the vibration frequency, the amplitude, and the phase; the time-effect data A2 includes the detection point stroke, the detection point stroke deviation, the time domain characteristics, the frequency domain characteristics, the time-frequency domain characteristics, and the energy spectrum. The time domain characteristics include the variance, the mean square value, the effective value, the skewness and kurtosis, the peak index, the margin index, the waveform index, and the pulse index. The frequency domain characteristics include the FFT spectrum, the power spectrum, and the envelope spectrum.

3. A method for processing abnormal data of variable working conditions for an electric wheel reducer of a mine car according to any one of claims 1 to 2, characterized in that: The following steps are involved: S1, data collection: the data collection device (100) collects the running state data A and the working condition data T of the electric wheel of the mining vehicle in real time; S2, data classification: the data classification device (200) classifies the operation status data A into the operation data A1 which is independent of the time t change and the time-effect data A2 which is related to the time t according to the time effect; S3, assigning a questionable value: the data classification device (200) assigns a questionable value S1 and a questionable value S2 to the operation data A1 and the timeliness data A2 respectively; S4, judging the changed working condition: the data processing device (300) judges whether the changed working condition behavior occurs according to the working condition data T, and if so, proceeds to step S5, and if not, proceeds to step S7; S5, abnormal data judgment: the data processing device (300) screens out the abnormal data F through the GAN network model; S6, abnormal data confirmation: the data processing device (300) cleans the abnormal data F according to the doubtful value S of the abnormal data F and generates an analysis report; S7. The abnormal data processing system operates normally.

4. The method for processing abnormal data under variable working conditions for a mine car electric wheel reducer according to claim 3, characterized in that: Step S4 further comprises the following steps: S41, calculating the operating condition parameter curve S according to the operating condition data T S=c×f(t)×f(T, P, rh, v)+d Among them, f(t) is a function related to time, f(T,P,rh,v) is a function related to temperature, air pressure, humidity and wind speed, c is the influencing factor, and d is the correction deviation; S42, judging the behavior of the variable working condition: deriving the working condition parameter curve S If S' is greater than the operating condition change threshold, it is determined that the operating condition change behavior occurs.

5. The method for processing abnormal data of variable working conditions for electric wheel reducer of a mine car according to claim 3, characterized in that: In step S6, the data processing device (300) can correct the doubtful value S of the abnormal data F according to historical data or data from other monitoring points to determine whether the abnormal data F is real abnormal data.

6. A method for processing abnormal data under variable working conditions for an electric wheel reducer of a mine car according to claim 5, characterized in that: The data processing device (300) performs fault diagnosis on real abnormal data and performs data cleaning on non-real abnormal data.

7. The method for processing abnormal data under variable working conditions for a mine car electric wheel reducer according to claim 3, characterized in that: The following steps are also included: S8. GAN network model training: Under variable working conditions, normal data E can be used to train the GAN network training model. Normal data E: E=DF∪D.

Images