A planetary half-shaft gear detection method

Abstract

The present invention discloses a detection method for planetary half-axle gears, belonging to the technical field of planetary half-axle gear fault detection. In the present invention, vibration sensors are arranged on the differential to collect vibration signals during straight driving and turning at different vehicle speeds; the vibration signals during turning and straight driving at the same speed are subjected to EMD decomposition, and the average envelope is extracted to obtain the turning envelope difference signal; they are added level by level, and the difference energy mean value and impact energy value of the synthesized difference signal at each level are calculated; according to the difference energy mean value and impact energy value of the synthesized difference signal at the same level under multiple speeds, the evolution value is calculated and a feature vector is constructed; finally, a multi-input BP neural network is used to process the feature vector and the evolution value to obtain the fault value of the planetary half-axle gear. The present invention solves the problem of low accuracy of existing fault detection.

Description

Technical Field

[0001] The present invention relates to the technical field of planetary half - shaft gear fault detection, and particularly relates to a planetary half - shaft gear detection method. Background Art

[0002] In modern vehicle drive systems, as a key component, the performance of the planetary half - shaft gear directly affects the power transmission and driving stability of the vehicle. Existing fault detection technologies mainly rely on methods such as vibration analysis, temperature monitoring, and oil analysis. Although these traditional technologies can identify abnormal states of the gear to a certain extent, they often have problems such as insufficient sensitivity, high false alarm rates, and inability to monitor in real - time. Especially under complex working conditions, such as when the vehicle is going straight and turning at different speeds, it is difficult for existing technologies to effectively distinguish normal vibration from fault vibration, resulting in a low accuracy rate of fault detection. Summary of the Invention

[0003] Aiming at the above - mentioned deficiencies in the prior art, a planetary half - shaft gear detection method provided by the present invention solves the problem of low accuracy rate of fault detection in the prior art.

[0004] To achieve the above - mentioned invention object, the technical solution adopted by the present invention is: a planetary half - shaft gear detection method, including the following steps:

[0005] S1. Set vibration sensors on the differential, collect vibration signals when the vehicle is going straight and turning at different speeds, and obtain various straight - line vibration signals and various turning vibration signals;

[0006] S2. At the same speed, perform EMD decomposition on the turning and straight - line vibration signals respectively, extract the average envelope line under each decomposition, and obtain the turning envelope line difference signals of multiple decompositions;

[0007] S3. Add the turning envelope line difference signals of multiple decompositions at the same speed level by level, and calculate the difference energy mean value and impact energy value for each level of synthesized difference signal;

[0008] S4. Calculate the evolution value of each level of synthesized difference signal according to the difference energy mean value and impact energy value of the same - level synthesized difference signals at various speeds;

[0009] S5. Construct a feature vector for each level of synthesized difference signal according to the difference energy mean value and impact energy value of the same - level synthesized difference signals at various speeds;

[0010] S6. Use a multi - input BP neural network to process the feature vectors and evolution values of the multi - level synthesized difference signals to obtain the fault value of the planetary half - shaft gear.

[0011] Further, S2 includes the following sub - steps:

[0012] S21. Decompose the turning vibration signals at each speed by EMD, extract the average envelope line of each decomposition process, and obtain multiple turning average envelope lines;

[0013] S22. Decompose the straight-line vibration signals at each speed by EMD, extract the average envelope line of each decomposition process, and obtain multiple straight-line average envelope lines;

[0014] S23. Subtract the turning average envelope line of the i-th decomposition from the straight-line average envelope line of the i-th decomposition at the same speed to obtain the turning envelope line difference signal of the i-th decomposition, where i is a positive integer.

[0015] Further, S3 includes the following sub-steps:

[0016] S31. Add up the turning envelope line difference signals of the 1st decomposition to the -th decomposition at the same speed to obtain the first-level composite difference signal, where N is the number of turning envelope line difference signals, is the floor operation;

[0017] S32. Add up the turning envelope line difference signals of the -th decomposition to the -th decomposition at the same speed to obtain the second-level composite difference signal;

[0018] S33. Add up the remaining turning envelope line difference signals at the same speed to obtain the third-level composite difference signal;

[0019] S34. Calculate the difference energy mean and impact energy value for each level of composite difference signal.

[0020] Further, S34 includes the following sub-steps:

[0021] S341. Divide each level of composite difference signal into multiple segments, and calculate the difference energy value on each segment;

[0022] S342. Take the mean of the difference energy values of each segment to obtain the difference energy mean;

[0023] S343. Screen out the difference energy values greater than the difference energy mean, and calculate the impact energy value.

[0024] Further, the formula for calculating the difference energy value in S341 is: , where G j is the difference energy value of the j-th segment, g j,m is the m-th amplitude on the j-th segment, j and m are positive integers, | | is the absolute value, and M is the length of a segment of the signal;

[0025] The formula for calculating the impact energy value in S343 is as follows: , where ζ impact is the impact energy value, G impact,n is the difference energy value of the nth one greater than the mean difference energy, G avg is the mean difference energy, n is a positive integer, and L is the number of difference energy values greater than the mean difference energy.

[0026] Furthermore, S4 includes the following sub-steps:

[0027] S41. Calculate the first evolution coefficient according to the ratio of the same-level composite difference signal of the second speed and the first speed on the mean difference energy and the impact energy value, where the second speed is greater than the first speed;

[0028] S42. Calculate the second evolution coefficient according to the ratio of the same-level composite difference signal of the third speed and the second speed on the mean difference energy and the impact energy value, where the third speed is greater than the second speed;

[0029] S43. Add the first evolution coefficient and the second evolution coefficient to obtain the evolution value of the same-level composite difference signal at this level.

[0030] Furthermore, the formula for calculating the first evolution coefficient in S41 is: , where θ 1 is the first evolution coefficient, G avg,2,k is the mean difference energy of the kth-level composite difference signal at the second speed, G avg,1,k is the mean difference energy of the kth-level composite difference signal at the first speed, ζ impact,2,k is the impact energy value of the kth-level composite difference signal at the second speed, ζ impact,1,k is the impact energy value of the kth-level composite difference signal at the first speed, and k is a positive integer;

[0031] The formula for calculating the second evolution coefficient in S42 is: , where θ 2 is the second evolution coefficient, G avg,3,k is the mean difference energy of the kth-level composite difference signal at the third speed, ζ impact,3,k is the impact energy value of the kth-level composite difference signal at the third speed.

[0032] Furthermore, S5 includes the following sub-steps:

[0033] S51. Add the mean difference energies of the same-level composite difference signals at multiple speeds to obtain the first eigenvalue;

[0034] S52. Add the impact energy values of the same-level composite difference signals at multiple speeds to obtain the second eigenvalue;

[0035] S53. Construct a feature vector of the synthetic difference signal at this level with the first eigenvalue and the second eigenvalue as elements.

[0036] Furthermore, the multi-input BP neural network in S6 includes: a first fully connected layer, a second fully connected layer, a third fully connected layer, a multiplier M1, a multiplier M2, a multiplier M3, and a BP neural network.

[0037] The input end of the first fully connected layer is used to input the feature vector of the synthetic difference signal at the 1st level.

[0038] The input end of the second fully connected layer is used to input the feature vector of the synthetic difference signal at the 2nd level.

[0039] The input end of the third fully connected layer is used to input the feature vector of the synthetic difference signal at the 3rd level.

[0040] The first input end of the multiplier M1 is connected to the output end of the first fully connected layer, and its second input end is used to input the evolution value of the synthetic difference signal at the 1st level.

[0041] The first input end of the multiplier M2 is connected to the output end of the second fully connected layer, and its second input end is used to input the evolution value of the synthetic difference signal at the 2nd level.

[0042] The first input end of the multiplier M3 is connected to the output end of the third fully connected layer, and its second input end is used to input the evolution value of the synthetic difference signal at the 3rd level.

[0043] The input ends of the BP neural network are respectively connected to the output ends of the multiplier M1, the multiplier M2, and the multiplier M3, and its output end serves as the output end of the multi-input BP neural network.

[0044] Furthermore, the expressions of the first fully connected layer, the second fully connected layer, and the third fully connected layer are all: , where S is the output of the fully connected layer, C r is the rth eigenvalue input to the fully connected layer, ω r is the weight of C r , b r is the bias of C r , and r is a positive integer taking values from 1 to 2.

[0045] The beneficial effects of the present invention are:

[0046] 1. The present invention collects vibration signals when going straight and turning at different speeds, performs EMD decomposition on the turning and straight vibration signals respectively, extracts the average envelope after each decomposition, subtracts the average envelope of turning from the average envelope of straight running, and obtains a turning envelope difference signal. When the vehicle is going straight and turning, the stress conditions and motion states of the planetary half-shaft gears are different, and the vibration signal characteristics generated are also different. When going straight, the planetary half-shaft gears are stationary relative to the half-shaft gears on the output shaft, and the planetary half-shaft gears do not rotate. Therefore, the complex vibration signal can be decomposed through EMD decomposition to obtain the average envelope. The turning envelope difference signal obtained by subtracting the average envelope after extracting the average envelope can amplify the signal characteristic changes caused by the fault, make the fault characteristics more prominent, and effectively distinguish the fault vibration caused by the planetary half-shaft gears.

[0047] 2. The present invention can analyze signal characteristics from different levels and further explore the fault information hidden in the signal through this hierarchical calculation of energy values. The difference energy mean reflects the overall energy distribution of the signal, while the impact energy value is more sensitive to the impact component in the signal and can highlight the impact characteristics caused by the fault. By calculating and analyzing different energy values, the signal characteristics in normal state and fault state can be more clearly distinguished, thereby improving the accuracy of fault detection and reducing the false alarm rate.

[0048] 3. The present invention calculates the evolution value based on the difference energy mean and impact energy value of the same-level synthetic difference signal at multiple speeds. The evolution value can reflect the state change trend of the planetary axle gear as the vehicle running state changes, and reflects the deterioration of its difference energy mean and impact energy value as the vehicle speed increases.

[0049] 4. The present invention uses a multi-input BP neural network to process the characteristic vectors and evolution values ​​of multi-level synthetic difference signals to obtain fault values, comprehensively considers multiple factors, accurately determines the fault state of the planetary half-shaft gear, and improves the accuracy of fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flow chart of a planetary half-shaft gear detection method;

[0051] Figure 2 This is a schematic diagram of the structure of a multi-input BP neural network. DETAILED DESCRIPTION

[0052] The specific embodiments of the present invention will be described below to facilitate those skilled in the art of the present technology to understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art of the present technology, as long as various changes are within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions made using the concept of the present invention are within the scope of protection.

[0053] As Figure 1 shown, a method for detecting a planetary half shaft gear includes the following steps:

[0054] S1. Set a vibration sensor on the differential, collect vibration signals when the vehicle goes straight and turns at different speeds, and obtain a variety of straight-line vibration signals and a variety of turning vibration signals;

[0055] S2. At the same speed, perform EMD decomposition on the turning and straight-line vibration signals respectively, extract the average envelope line under each decomposition, and obtain the turning envelope line difference signals of multiple decompositions;

[0056] S3. Add the turning envelope line difference signals of multiple decompositions at the same speed level by level, and calculate the difference energy mean value and the impact energy value for each level of synthesized difference signal;

[0057] S4. Calculate the evolution value of each level of synthesized difference signal according to the difference energy mean value and the impact energy value of the same-level synthesized difference signals at multiple speeds;

[0058] S5. Construct the feature vector of each level of synthesized difference signal according to the difference energy mean value and the impact energy value of the same-level synthesized difference signals at multiple speeds;

[0059] S6. Use a multi-input BP neural network to process the feature vector and the evolution value of the multi-level synthesized difference signal, and obtain the fault value of the planetary half shaft gear.

[0060] In this embodiment, the speeds within the same speed range are regarded as the same speed. For example, the first speed range is: 5 km / h to 10 km / h, then any speed within the range of 5 km / h to 10 km / h belongs to the same speed. The second speed range is: 15 km / h to 20 km / h, then any speed within the range of 15 km / h to 20 km / h belongs to the same speed. The third speed range is: 25 km / h to 30 km / h, then any speed within the range of 25 km / h to 30 km / h belongs to the same speed. Therefore, the "same speed" in step S2 refers to the speeds within the same speed range. For example, if the straight-line speed is 5 km / h and the turning speed is 8 km / h, then the two belong to the same speed and the subtraction of the average envelope lines can be performed.

[0061] In this embodiment, S2 includes the following sub-steps:

[0062] S21. Perform EMD decomposition on the turning vibration signals at each speed, extract the average envelope of each decomposition process, and obtain multiple turning average envelopes.

[0063] S22. Perform EMD decomposition on the straight-line vibration signals at each speed, extract the average envelope of each decomposition process, and obtain multiple straight-line average envelopes.

[0064] S23. At the same speed, subtract the turning average envelope of the i-th decomposition from the straight-line average envelope of the i-th decomposition to obtain the turning envelope difference signal of the i-th decomposition, where i is a positive integer, and "subtract" here refers to subtracting the amplitudes at the corresponding time points (or sampling points) of the two average envelopes.

[0065] In the present invention, the average envelope is the average of the upper envelope and the lower envelope during the i-th decomposition.

[0066] The differential includes: planetary half-axle gears, input shafts, half-axle gears (also known as sun gears), output shafts, etc. The half-axle gears are connected to the output shafts, the planetary half-axle gears are connected to the input shafts, and the planetary half-axle gears are placed between the two half-axle gears. During straight driving, the planetary half-axle gears and the half-axle gears rotate as a whole. During turning, the planetary half-axle gears start to rotate self-drivingly to adjust the different rotational speeds of the left and right tires.

[0067] The present invention extracts the average envelope of each decomposition, reflects the extreme value distribution of the turning vibration signal and the straight-line vibration signal, compares the turning and straight-line average envelopes at the same speed, and obtains the difference signal. There is an inherent difference between the two under normal conditions, and the failure of the planetary half-axle gear will change this difference. By this comparison, the signal change caused by the failure can be amplified, making the failure characteristics more prominent, improving the sensitivity to early and subtle failures, and facilitating the timely discovery of potential problems.

[0068] In this embodiment, when the number of decomposition times of the straight-line vibration signal and the turning vibration signal is different, for example, the straight-line vibration signal is decomposed 5 times and the turning vibration signal is decomposed 6 times, only the first 5 average envelopes are used for subtraction.

[0069] In this embodiment, S3 includes the following sub-steps:

[0070] S31. Add up the turning envelope difference signals of the 1st decomposition to the -th decomposition at the same speed to obtain the first-level composite difference signal, where N is the number of turning envelope difference signals, is the floor operation, and "add up" here refers to adding the amplitudes at the corresponding time points (or sampling points) of the two turning envelope difference signals.

[0071] S32. Add the turning envelope difference signals from the th decomposition to the th decomposition at the same speed to obtain the second-level composite difference signal;

[0072] S33. Add the turning envelope difference signals of the remaining decompositions at the same speed to obtain the third-level composite difference signal;

[0073] S34. Calculate the difference energy mean and impact energy value for each level of composite difference signal.

[0074] In the present invention, the turning envelope difference signals obtained from multiple decompositions are divided into three levels. For example, when N is equal to 6, the turning envelope difference signals from the first decomposition and the second decomposition are added to obtain the first-level composite difference signal, the turning envelope difference signals from the third decomposition and the fourth decomposition are added to obtain the second-level composite difference signal, and the turning envelope difference signals from the fifth decomposition and the sixth decomposition are added to obtain the third-level composite difference signal.

[0075] In the present invention, the turning envelope difference signals are added in a hierarchical manner, which can fuse the signal features at different scales. The sensitivity of the composite difference signals at different levels to the fault features is different. By calculating the difference energy mean and impact energy value for each level respectively, the performance of the fault at different scales can be highlighted.

[0076] In this embodiment, S34 includes the following sub-steps:

[0077] S341. Divide each level of composite difference signal into multiple segments, and calculate the difference energy value for each segment;

[0078] S342. Take the mean of the difference energy values of each segment to obtain the difference energy mean;

[0079] S343. Select the difference energy values greater than the difference energy mean, and calculate the impact energy value.

[0080] In this embodiment, the formula for calculating the difference energy value in S341 is: , where G j is the difference energy value of the jth segment, g j,m is the mth amplitude on the jth segment, j and m are positive integers, | | represents taking the absolute value, and M is the length of a segment of the signal;

[0081] The formula for calculating the impact energy value in S343 is: , where ζ impact is the impact energy value, G impact,n is the nth difference energy value greater than the difference energy mean, and G avgis the mean value of the differential energy, n is a positive integer, and L is the number of differential energy values greater than the mean value of the differential energy.

[0082] In the present invention, each stage of the synthesized differential signal is divided into multiple segments and the differential energy values are calculated separately, which can finely capture the energy distribution of the signal in different local areas. During the operation of the planetary half-axle gear, the energy distribution of the vibration signal will change at different times or under different working conditions. By calculating in segments, these changes can be more accurately reflected. For example, when the gear is in the initial stage of wear, it may only show abnormal energy at certain specific time periods or working conditions, and calculating in segments can detect these local abnormalities in a timely manner.

[0083] The present invention calculates the mean value of the differential energy, which reflects the degree of difference in vibration between turning and going straight. The present invention screens out the differential energy values greater than the mean value of the differential energy to calculate the impact energy value. This method can effectively highlight the impact component in the signal. When a fault occurs in the planetary half-axle gear, such as cracks, broken teeth, etc., impact vibrations will be generated, and the energy characteristics thereof are manifested as instantaneous energy peaks, that is, greater than the energy mean value in the normal state. By screening and calculating these larger energy values, the impact information generated by the fault can be captured, and a more accurate judgment of the fault type and severity can be achieved.

[0084] In this embodiment, S4 includes the following sub-steps:

[0085] S41. Calculate the first evolution coefficient according to the ratio of the same-stage synthesized differential signal of the second speed to the first speed in terms of the mean value of the differential energy and the impact energy value, where the second speed is greater than the first speed;

[0086] S42. Calculate the second evolution coefficient according to the ratio of the same-stage synthesized differential signal of the third speed to the second speed in terms of the mean value of the differential energy and the impact energy value, where the third speed is greater than the second speed;

[0087] S43. Add the first evolution coefficient and the second evolution coefficient to obtain the evolution value of the same-stage synthesized differential signal.

[0088] In this embodiment, the formula for calculating the first evolution coefficient in S41 is: , where θ 1 is the first evolution coefficient, G avg,2,k is the mean value of the differential energy of the k-th stage synthesized differential signal at the second speed, G avg,1,k is the mean value of the differential energy of the k-th stage synthesized differential signal at the first speed, ζ impact,2,k is the impact energy value of the k-th stage synthesized differential signal at the second speed, ζ impact,1,k is the impact energy value of the k-th stage synthesized differential signal at the first speed, and k is a positive integer;

[0089] The formula for calculating the second evolution coefficient in S42 is as follows: , where θ 2 is the second evolution coefficient, G avg,3,k is the average difference energy of the k-th stage composite difference signal at the third speed, and ζ impact,3,k is the impact energy value of the k-th stage composite difference signal at the third speed.

[0090] By calculating the ratio of the average difference energy and the impact energy value of the same-stage composite difference signals at different speeds, the present invention can reflect the variation of the planetary half-axle gear fault characteristics with speed. When the vehicle is traveling at different speeds, the force and wear conditions of the gears will be different, and the fault manifestations will also vary. This solution can capture these fault characteristic changes caused by speed changes. For example, at low speeds, there may only be slight energy fluctuations, and at high speeds, the impact energy may increase significantly. The evolution value quantifies this change.

[0091] In this embodiment, S5 includes the following sub-steps:

[0092] S51: Add the average difference energies of the same-stage composite difference signals at multiple speeds to obtain the first eigenvalue;

[0093] S52: Add the impact energy values of the same-stage composite difference signals at multiple speeds to obtain the second eigenvalue;

[0094] S53: Use the first eigenvalue and the second eigenvalue as elements to construct the eigenvector of the same-stage composite difference signal.

[0095] By adding the average difference energy and the impact energy value of the same-stage composite difference signals at multiple speeds respectively to obtain the first eigenvalue and the second eigenvalue, the present invention can comprehensively integrate the fault characteristic information of the planetary half-axle gear under different speed conditions.

[0096] As Figure 2 shown, the multi-input BP neural network in S6 includes: the first fully connected layer, the second fully connected layer, the third fully connected layer, multiplier M1, multiplier M2, multiplier M3, and the BP neural network;

[0097] The input end of the first fully connected layer is used to input the eigenvector of the first-stage composite difference signal;

[0098] The input end of the second fully connected layer is used to input the eigenvector of the second-stage composite difference signal;

[0099] The input end of the third fully connected layer is used to input the eigenvector of the third-stage composite difference signal;

[0100] The first input terminal of multiplier M1 is connected to the output terminal of the first fully connected layer, and its second input terminal is used to input the evolution value of the first-level synthetic difference signal;

[0101] The first input terminal of multiplier M2 is connected to the output terminal of the second fully connected layer, and its second input terminal is used to input the evolution value of the second-level synthetic difference signal;

[0102] The first input terminal of multiplier M3 is connected to the output terminal of the third fully connected layer, and its second input terminal is used to input the evolution value of the third-level synthetic difference signal;

[0103] The input terminals of the BP neural network are respectively connected to the output terminals of multiplier M1, multiplier M2, and multiplier M3, and its output terminal serves as the output terminal of the multi-input BP neural network.

[0104] In this embodiment, the expressions of the first fully connected layer, the second fully connected layer, and the third fully connected layer are all: , where S is the output of the fully connected layer, C r is the r-th eigenvalue input to the fully connected layer, ω r is the weight of C r , b r is the bias of C r , and r is a positive integer taking values from 1 to 2.

[0105] In this embodiment, the weights and biases in the multi-input BP neural network can be obtained by training with the gradient descent method.

[0106] In the present invention, each fully connected layer processes the eigenvector of the synthetic difference signal at one level, and then multiplies the output of the fully connected layer by the evolution value of the corresponding-level synthetic difference signal. The evolution value reflects the characteristic changes of the same-level synthetic difference signal at different speeds, and it contains the fault evolution information of the planetary half-axis gear under different speed conditions. By multiplying with the output of the fully connected layer, the characteristics at different speeds can be weighted and adjusted, so that when the network makes a fault judgment, it not only considers the fault characteristics at the current level, but also considers the change trend of these characteristics with speed. For example, if the evolution value of a certain-level synthetic difference signal is large at a certain speed, it indicates that the fault characteristics at this level show obvious changes when the speed changes. Through the multiplication operation, the network's attention to this characteristic can be enhanced, thereby more accurately judging the correlation between the fault and the speed.

[0107] The present invention collects vibration signals during straight running and turning at different speeds, performs EMD decomposition on the turning and straight-running vibration signals respectively, extracts the average envelope line after each decomposition, subtracts the average envelope line of turning from that of straight running to obtain the turning envelope line difference signal. When the vehicle is running straight and turning, the force conditions and motion states of the planetary half shafts gears are different, and the characteristics of the vibration signals generated by them are also different. When running straight, the planetary half shafts gear is stationary relative to the half shafts gear on the output shaft, and the planetary half shafts gear does not rotate on its own. Therefore, through EMD decomposition, complex vibration signals can be decomposed to obtain the average envelope line. The turning envelope line difference signal obtained by subtracting the average envelope lines after extraction can amplify the change in signal characteristics caused by faults, making the fault characteristics more prominent and effectively distinguishing the fault vibration caused by the planetary half shafts gear.

[0108] By this way of calculating energy values at different levels, the present invention can analyze signal characteristics from different aspects and further explore the fault information hidden in the signals. The mean value of differential energy reflects the overall energy distribution of the signal, while the impact energy value is more sensitive to the impact components in the signal and can highlight the impact characteristics caused by faults. By calculating and analyzing different energy values, the signal characteristics in normal and fault states can be more clearly distinguished, thereby improving the accuracy of fault detection and reducing the false alarm rate.

[0109] The present invention calculates the evolution value based on the mean value of differential energy and the impact energy value of the same-level synthesis difference signals at various speeds. The evolution value can reflect the changing trend of the state of the planetary half shafts gear as the running state of the vehicle changes, and reflect the deterioration of its mean value of differential energy and impact energy value as the vehicle speed increases.

[0110] The present invention uses a multi-input BP neural network to process the feature vectors and evolution values of the multi-level synthesis difference signals to obtain the fault value, comprehensively considers various factors, accurately judges the fault state of the planetary half shafts gear, and improves the accuracy rate of fault detection.

[0111] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A planetary side shaft gear detection method, characterized in that: The following steps are involved: S1. A vibration sensor is arranged on the differential to collect vibration signals of the vehicle when it is traveling straight and turning at different speeds, and obtain a plurality of straight vibration signals and a plurality of turning vibration signals; S2. At the same speed, perform EMD decomposition on the turning and straight-moving vibration signals respectively, extract the average envelope under each decomposition, and obtain the turning envelope difference signal of multiple decompositions; S3, adding the turning envelope difference signals decomposed multiple times at the same speed in different levels, and calculating the difference energy mean and impact energy value of the synthetic difference signals at each level; S4, calculating the evolution value of each level of synthetic difference signal according to the difference energy mean and impact energy value of the same level synthetic difference signal at multiple speeds; S5. constructing a feature vector of each level of synthetic difference signal according to the difference energy mean and impact energy value of the same level synthetic difference signal at multiple speeds; S6. Using a multi-input BP neural network to process the characteristic vector and evolution value of the multi-level synthetic difference signal, the fault value of the planetary half-shaft gear is obtained; The S4 comprises the following sub-steps: S41, calculating a first evolution coefficient according to a ratio of a second speed to a first speed composite difference signal of the same level in terms of difference energy mean and impact energy value, wherein the second speed is greater than the first speed; S42, calculating a second evolution coefficient according to a ratio of the third speed to the second speed in terms of the difference energy mean and the impact energy value of the same-level synthetic difference signal, wherein the third speed is greater than the second speed; S43, adding the first evolution coefficient and the second evolution coefficient to obtain an evolution value of the synthetic difference signal of this level; The formula for calculating the first evolution coefficient in S41 is: , where θ1 is the first evolution coefficient, G avg,2,k is the difference energy mean of the k-th level synthetic difference signal at the second speed, G avg,1,k is the difference energy mean of the k-th level synthetic difference signal at the first speed, ζ impact,2,k is the impact energy value of the k-th level synthetic difference signal at the second speed, ζ impact,1,k is the impact energy value of the k-th level synthetic difference signal at the first speed, k is a positive integer; The formula for calculating the second evolution coefficient in S42 is: , where θ2 is the second evolution coefficient, G avg,3,k is the difference energy mean of the k-th level synthetic difference signal at the third speed, ζ impact,3,k is the impact energy value of the k-th level synthetic difference signal at the third speed; The S5 comprises the following sub-steps: S51, adding the difference energy means of the same-level synthetic difference signals at multiple speeds to obtain a first eigenvalue; S52, adding the impact energy values ​​of the same-level synthetic difference signals at multiple speeds to obtain a second characteristic value; S53: Use the first eigenvalue and the second eigenvalue as elements to construct a eigenvector of the synthetic difference signal of this level.

2. The planetary side gear detection method according to claim 1, characterized in that: The S2 comprises the following sub-steps: S21, performing EMD decomposition on the turning vibration signal at each speed, extracting the average envelope of each decomposition process, and obtaining multiple turning average envelopes; S22, performing EMD decomposition on the straight-moving vibration signal at each speed, extracting the average envelope of each decomposition process, and obtaining multiple straight-moving average envelopes; S23. At the same speed, subtract the average envelope of the turning decomposed for the ith time from the average envelope of the straight line decomposed for the ith time to obtain a difference signal of the turning envelope decomposed for the ith time, where i is a positive integer.

3. The planetary side gear detection method according to claim 1, characterized in that: The S3 comprises the following sub-steps: S31, decompose the first ~ the second The first-order synthetic difference signal is obtained by adding the second-order decomposed turning envelope difference signals, where N is the number of turning envelope difference signals, This is a round down operation; S32, the same speed down Decomposition~ The second-order decomposed turning envelope difference signals are added to obtain a second-order synthetic difference signal; S33, adding the remaining decomposed turning envelope difference signals at the same speed to obtain a third-level synthetic difference signal; S34. Calculate the difference energy mean and impact energy value for each level of synthetic difference signal.

4. The planetary side gear detection method according to claim 3, characterized in that: The S34 comprises the following sub-steps: S341, dividing each level of synthesized difference signal into multiple segments, and calculating the difference energy value on each segment; S342, taking the average of the difference energy values ​​of each segment to obtain the difference energy average; S343. Filter out the difference energy values ​​that are greater than the difference energy mean value, and calculate the impact energy value.

5. The planetary side gear detection method according to claim 4, characterized in that: The formula for calculating the difference energy value in S341 is: , where G j is the difference energy value of the jth segment, g j,m is the mth amplitude on the jth segment, j and m are positive integers, || is the absolute value, and M is the length of a signal segment; The formula for calculating the impact energy value in S343 is: , where ζ impact is the impact energy value, G impact,n is the nth difference energy value greater than the mean difference energy value, G avg is the difference energy mean, n is a positive integer, and L is the number of difference energy values ​​greater than the difference energy mean.

6. The planetary side gear detection method according to claim 1, characterized in that: The multi-input BP neural network in S6 includes: a first fully connected layer, a second fully connected layer, a third fully connected layer, a multiplier M1, a multiplier M2, a multiplier M3 and a BP neural network; The input end of the first fully connected layer is used to input the feature vector of the first-level synthetic difference signal; The input end of the second fully connected layer is used to input the feature vector of the second-level synthetic difference signal; The input end of the third fully connected layer is used to input the feature vector of the third-level synthetic difference signal; The first input terminal of the multiplier M1 is connected to the output terminal of the first fully connected layer, and the second input terminal thereof is used to input the evolution value of the first-level synthetic difference signal; The first input terminal of the multiplier M2 is connected to the output terminal of the second fully connected layer, and the second input terminal thereof is used to input the evolution value of the second-level synthetic difference signal; The first input terminal of the multiplier M3 is connected to the output terminal of the third fully connected layer, and the second input terminal thereof is used to input the evolution value of the third-level synthetic difference signal; The input end of the BP neural network is respectively connected to the output end of the multiplier M1, the output end of the multiplier M2 and the output end of the multiplier M3, and its output end serves as the output end of the multi-input BP neural network.

7. The planetary side gear detection method according to claim 6, characterized in that: The expressions of the first fully connected layer, the second fully connected layer and the third fully connected layer are all: , where S is the output of the fully connected layer, C r is the rth eigenvalue of the fully connected layer input, ω r C r The weight of b r C r The bias of r is used to identify the number of the eigenvalues ​​of the fully connected layer input, and r is a positive integer ranging from 1 to 2.

Images