Fault detection method for driving chip of photoelectric accelerometer

Abstract

The invention discloses a photoelectric accelerometer driving chip fault detection method, and belongs to the technical field of electrical variable measurement. According to the method, output signals of all modules of a driving chip are divided according to a zero crossing point, positive and negative half-wave sets are obtained, and then a waveform symmetric value and a waveform symmetric stable value are extracted. Converting the positive and negative half-wave sets into a frequency domain and dividing the frequency domain into important frequency and clutter frequency to generate four frequency sets; by calculating the difference of the adjacent modules on four frequency sets, the positive half-wave frequency variation value and the negative half-wave frequency variation value of the adjacent modules are obtained, and meanwhile the waveform symmetry difference value and the waveform stability difference value of the adjacent modules are obtained according to the difference value of the waveform symmetry value and the waveform symmetry stability value of the adjacent modules. And finally, the characteristic values of the adjacent modules are used as samples to be input into the convolutional neural network, so that the fault value of the driving chip is accurately obtained, and the fault detection precision is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of measuring electrical variables, and in particular to a method for detecting faults of a photoelectric accelerometer driver chip. Background Art

[0002] The modules in the driver chip of the photoelectric accelerometer include: a signal generation module, an operational amplifier module and a coupling circuit module. The signal generation module generates a sinusoidal modulation signal, amplifies the modulation signal through the operational amplifier module, and the coupling circuit module couples the amplified signal and applies it to the photoelectric accelerometer.

[0003] Traditional driver chip fault detection methods mainly rely on the measurement of simple electrical parameters, such as measuring the voltage, current, and resistance of the circuit. However, this detection method has obvious limitations for the complex fault modes of various modules inside the chip, especially when the fault manifests as a slight change in the signal waveform or an abnormal frequency characteristic. For example, if the sine wave modulation signal generated by the signal generation module has an asymmetric waveform or increased harmonic components, it is difficult to detect it only by measuring electrical parameters. Therefore, the existing driver chip fault detection method has the problem of low fault detection accuracy. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, a method for detecting faults in a photoelectric accelerometer driver chip provided by the present invention solves the problem of low fault detection accuracy in the prior driver chip.

[0005] In order to achieve the above-mentioned invention object, the technical solution adopted by the present invention is: a method for detecting faults of a photoelectric accelerometer driver chip, comprising: The output signals of each module in the driver chip are divided according to the zero crossing point to obtain a positive half-wave set and a negative half-wave set; For the positive half-wave set and the negative half-wave set of each module, extract the waveform symmetry value and the waveform symmetry stability value; The positive half-wave set and the negative half-wave set are converted into the frequency domain, and the frequency domain information is divided into important frequencies and clutter frequencies, so as to obtain four frequency sets, wherein the four frequency sets include: a positive half-wave important frequency set, a positive half-wave clutter frequency set, a negative half-wave important frequency set and a negative half-wave clutter frequency set; According to the gaps between adjacent modules in the driver chip in the four frequency sets, the positive half-wave frequency variation value and the negative half-wave frequency variation value of the adjacent modules are obtained; According to the differences in waveform symmetry values ​​and waveform symmetry stability values ​​of adjacent modules in the driver chip, the waveform symmetry difference and waveform stability difference of adjacent modules are obtained; The positive half-wave frequency variation value, negative half-wave frequency variation value, waveform symmetry difference and waveform stability difference of each adjacent module are input into the convolutional neural network as samples to obtain the fault value of the driver chip.

[0006] Furthermore, the process of extracting the waveform symmetry value is: For each positive half-wave in the positive half-wave set, calculate the positive half-wave area; For each negative half-wave in the negative half-wave set, calculate the negative half-wave area; The positive half-wave area and the positive half-wave peak value are used as elements to form a positive half-wave eigenvector; The negative half-wave area and the absolute value of the peak value of the negative half-wave are used as elements to form a negative half-wave eigenvector; Calculate the similarity between the positive half-wave eigenvector and the negative half-wave eigenvector of the same period; The similarity of each cycle is averaged to obtain the waveform symmetry value.

[0007] Furthermore, the formula for calculating the waveform symmetry stability value is: , where γ is the waveform symmetry stability value and σ is the standard deviation of the similarity of each cycle.

[0008] Furthermore, each positive half-wave in the positive half-wave set and each negative half-wave in the negative half-wave set are respectively converted in time-to-frequency mode to obtain positive half-wave frequency domain information and negative half-wave frequency domain information, and each frequency domain information is divided into an important frequency set and a clutter frequency set to obtain a positive half-wave important frequency set, a positive half-wave clutter frequency set, a negative half-wave important frequency set and a negative half-wave clutter frequency set.

[0009] Furthermore, the process of obtaining the positive half-wave important frequency set and the positive half-wave clutter frequency set is: Perform time-frequency conversion on each positive half-wave in the positive half-wave set to obtain frequency domain information of the positive half-wave; The amplitude greater than the amplitude threshold in the frequency domain information of the positive half-wave is regarded as the important amplitude of the positive half-wave, and the other amplitudes are regarded as the positive half-wave clutter amplitude; The frequencies corresponding to the important amplitudes of the positive half-waves of all cycles are arranged in sequence to construct a set of important frequencies of the positive half-waves; The frequencies corresponding to the positive half-wave clutter amplitudes of all cycles are arranged in sequence to construct a positive half-wave clutter frequency set; Alternatively, the process of obtaining the negative half-wave important frequency set and the negative half-wave clutter frequency set is: Performing time-frequency conversion on each negative half-wave in the negative half-wave set respectively to obtain frequency domain information of the negative half-wave, and taking the absolute value of the amplitude in the frequency domain information of the negative half-wave; The amplitude greater than the amplitude threshold in the frequency domain information of the negative half-wave is regarded as the important amplitude of the negative half-wave, and the other amplitudes are regarded as the clutter amplitude of the negative half-wave; The frequencies corresponding to the important amplitudes of the negative half-waves of all cycles are arranged in sequence to construct a set of important frequencies of the negative half-waves; The frequencies corresponding to the negative half-wave clutter amplitudes of all cycles are arranged in sequence to construct a negative half-wave clutter frequency set.

[0010] Furthermore, the process of obtaining the positive half-wave frequency variation value of the adjacent module and the negative half-wave frequency variation value of the adjacent module includes: According to the difference between adjacent modules in the driver chip in the positive half-wave important frequency set, the first variation coefficient of the positive half-wave is obtained; according to the difference between adjacent modules in the driver chip in the negative half-wave important frequency set, the first variation coefficient of the negative half-wave is obtained; According to the difference between the adjacent modules in the driver chip in the positive half-wave noise frequency set, the second variation coefficient of the positive half-wave is obtained; according to the difference between the adjacent modules in the driver chip in the negative half-wave noise frequency set, the second variation coefficient of the negative half-wave is obtained; The first variation coefficient of the positive half-wave and the second variation coefficient of the positive half-wave are weighted to obtain the frequency variation value of the positive half-wave of the adjacent modules; The first variation coefficient of the negative half-wave and the second variation coefficient of the negative half-wave are weighted to obtain the frequency variation value of the negative half-wave of the adjacent modules.

[0011] Furthermore, the process of obtaining the first coefficient of variation includes: Take the intersection of the important frequency sets of adjacent modules to obtain the important frequency intersection; Eliminate the intersection of important frequencies from the important frequency set of the subsequent module in the adjacent module to obtain the newly added important frequency; Calculate the first coefficient of variation based on the newly added important frequencies; Alternatively, the process of obtaining the second coefficient of variation includes: Taking the intersection of the clutter frequency sets of adjacent modules to obtain the clutter frequency intersection; Eliminate the intersection of clutter frequencies from the clutter frequency set of the subsequent module in the adjacent module to obtain the newly added clutter frequency; The second coefficient of variation is calculated based on the newly added clutter frequency.

[0012] Furthermore, the formula for calculating the first coefficient of variation is: , where μ 1 is the first coefficient of variation, f z,i is the i-th newly added important frequency, f z,avg is the frequency mean of the important frequency set of the previous module in the adjacent module, i is a positive integer, N z is the number of newly added important frequencies, and D is the denominator parameter; The formula for calculating the second coefficient of variation is: , where μ 2 is the second coefficient of variation, fs,i is the ith new clutter frequency, f s,avg is the frequency mean of the clutter frequency set of the previous module in the adjacent module, N s is the number of newly added clutter frequencies.

[0013] Further, the waveform symmetry difference of adjacent modules is equal to the difference between the waveform symmetry value of the preceding module in the adjacent modules and the waveform symmetry value of the following module in the adjacent modules; The waveform stability difference between adjacent modules is equal to the difference between the waveform symmetry stability value of the preceding module in the adjacent modules and the waveform symmetry stability value of the following module in the adjacent modules.

[0014] Furthermore, the convolutional neural network includes: a first convolutional layer, a second convolutional layer, a third convolutional layer, a fourth convolutional layer, a first Concat layer, a second Concat layer, a first fully connected layer, a second fully connected layer and a weighted layer; The input end of the first convolution layer is used to input the first sample, the input end of the second convolution layer is used to input the first sample, the input end of the third convolution layer is used to input the second sample, and the input end of the fourth convolution layer is used to input the second sample, wherein the positive half-wave frequency variation value, the negative half-wave frequency variation value, the waveform symmetry difference value and the waveform stability difference value of the signal generation module and the operational amplifier module together constitute the first sample, and the positive half-wave frequency variation value, the negative half-wave frequency variation value, the waveform symmetry difference value and the waveform stability difference value of the operational amplifier module and the coupling circuit module together constitute the second sample; The input end of the first Concat layer is connected to the output end of the first convolutional layer and the output end of the third convolutional layer respectively; the input end of the second Concat layer is connected to the output end of the second convolutional layer and the output end of the fourth convolutional layer respectively; the input end of the first fully connected layer is connected to the output end of the first Concat layer; the input end of the second fully connected layer is connected to the output end of the second Concat layer; the input end of the weighted layer is connected to the output end of the first fully connected layer and the output end of the second fully connected layer respectively, and its output end is used to output the fault value of the driver chip.

[0015] The beneficial effects of the present invention are as follows: the present invention captures the subtle features of the signal through zero-crossing division and half-wave analysis, and then uses waveform symmetry analysis and frequency domain conversion to deeply explore the signal features, and highlights the abnormal features through comparative analysis of adjacent modules. Finally, a convolutional neural network is used to process the positive half-wave frequency variation value, negative half-wave frequency variation value, waveform symmetry difference and waveform stability difference of adjacent modules to obtain the driver chip fault value. The present invention divides the output signal to obtain a positive half-wave and a negative half-wave, and highlights the fault features from the symmetry of the waveform and the frequency domain features between adjacent modules, so that the fault features are significant, easy to identify, and the fault detection accuracy is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of a method for detecting faults of a photoelectric accelerometer driver chip; Figure 2 It is a schematic diagram of the structure of the driver chip; Figure 3 Schematic diagram of the structure of a convolutional neural network. DETAILED DESCRIPTION

[0017] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

[0018] like Figure 1 As shown, a method for detecting faults in a photoelectric accelerometer driver chip comprises: The output signals of each module in the driver chip are divided according to the zero crossing point to obtain a positive half-wave set and a negative half-wave set; For the positive half-wave set and the negative half-wave set of each module, extract the waveform symmetry value and the waveform symmetry stability value; The positive half-wave set and the negative half-wave set are converted into the frequency domain, and the frequency domain information is divided into important frequencies and clutter frequencies, so as to obtain four frequency sets, wherein the four frequency sets include: a positive half-wave important frequency set, a positive half-wave clutter frequency set, a negative half-wave important frequency set and a negative half-wave clutter frequency set; According to the gaps between adjacent modules in the driver chip in the four frequency sets, the positive half-wave frequency variation value and the negative half-wave frequency variation value of the adjacent modules are obtained; According to the differences in waveform symmetry values ​​and waveform symmetry stability values ​​of adjacent modules in the driver chip, the waveform symmetry difference and waveform stability difference of adjacent modules are obtained; The positive half-wave frequency variation value, negative half-wave frequency variation value, waveform symmetry difference and waveform stability difference of each adjacent module are input into the convolutional neural network as samples to obtain the fault value of the driver chip.

[0019] The present invention marks the points where the output signals of each module in the driving chip are 0 to obtain zero-crossing points, and divides the output signal of each module according to the positions of the zero-crossing points, so that the parts of the signal segments greater than 0 constitute a positive half-wave set, and the parts of the signal segments less than 0 constitute a negative half-wave set.

[0020] like Figure 2As shown, the modules in the driver chip include in sequence: a signal generating module, an operational amplifier module and a coupling circuit module; in the present invention, the signal generating module and the operational amplifier module are adjacent modules, the signal generating module is the front module, and the operational amplifier module is the rear module; the operational amplifier module and the coupling circuit module are adjacent modules, the operational amplifier module is the front module, and the coupling circuit module is the rear module.

[0021] In this embodiment, the process of extracting the waveform symmetry value is: For each positive half-wave in the positive half-wave set, calculate the positive half-wave area; For each negative half-wave in the negative half-wave set, calculate the negative half-wave area; The positive half-wave area and the positive half-wave peak value are used as elements to form a positive half-wave eigenvector; The negative half-wave area and the absolute value of the peak value of the negative half-wave are used as elements to form a negative half-wave eigenvector; Calculate the similarity between the positive half-wave eigenvector and the negative half-wave eigenvector of the same period; The similarity of each cycle is averaged to obtain the waveform symmetry value.

[0022] In a normally functioning photoelectric accelerometer driver chip, the energy carried by the positive half-wave and negative half-wave of the signal is relatively stable and symmetrical. For example, in an ideal sinusoidal signal, the energy of the positive half-wave and the negative half-wave are equal. When the chip fails, such as gain changes or nonlinear distortion, the energy distribution of the positive half-wave and the negative half-wave will be unbalanced. By calculating the area, this change in energy distribution can be quantified and used as an important feature for fault detection.

[0023] The positive half-wave eigenvector and the negative half-wave eigenvector contain two important signal features: area and peak value. Calculating their similarity is actually measuring the consistency of the positive half-wave and the negative half-wave in energy distribution and amplitude characteristics. The higher the similarity, the more symmetrical the positive half-wave and the negative half-wave are; otherwise, it indicates that the signal is asymmetric, which may be caused by chip failure.

[0024] In this embodiment, the formula for calculating the waveform symmetry stability value is: , where γ is the waveform symmetry stability value and σ is the standard deviation of the similarity of each cycle.

[0025] The standard deviation σ is an indicator to measure the degree of data dispersion. The standard deviation of the similarity of each period can reflect the fluctuation of the waveform symmetry in different periods. The larger the standard deviation σ, the smaller the waveform symmetry stability value.

[0026] In this embodiment, , , where A + is the positive half-wave area, A- is the negative half-wave area, f + (t) is the positive half wave, f - (t) is the negative half-wave, d is the differential sign, t is time, | | is the absolute value, T + is the length of the positive half-wave, T - is the length of the negative half-wave.

[0027] In this embodiment, each positive half-wave in the positive half-wave set and each negative half-wave in the negative half-wave set are respectively converted in time-frequency to obtain positive half-wave frequency domain information and negative half-wave frequency domain information, and each frequency domain information is divided into an important frequency set and a clutter frequency set to obtain a positive half-wave important frequency set, a positive half-wave clutter frequency set, a negative half-wave important frequency set and a negative half-wave clutter frequency set.

[0028] In this embodiment, the process of obtaining the positive half-wave important frequency set and the positive half-wave clutter frequency set is as follows: Perform time-frequency conversion on each positive half-wave in the positive half-wave set to obtain frequency domain information of the positive half-wave; The amplitude greater than the amplitude threshold in the frequency domain information of the positive half-wave is regarded as the important amplitude of the positive half-wave, and the other amplitudes are regarded as the positive half-wave clutter amplitude; The frequencies corresponding to the important amplitudes of the positive half-waves of all cycles are arranged in sequence to construct a set of important frequencies of the positive half-waves; The frequencies corresponding to the positive half-wave clutter amplitudes of all cycles are arranged in sequence to construct a positive half-wave clutter frequency set; Alternatively, the process of obtaining the negative half-wave important frequency set and the negative half-wave clutter frequency set is: Performing time-frequency conversion on each negative half-wave in the negative half-wave set respectively to obtain frequency domain information of the negative half-wave, and taking the absolute value of the amplitude in the frequency domain information of the negative half-wave; The amplitude greater than the amplitude threshold in the frequency domain information of the negative half-wave is regarded as the important amplitude of the negative half-wave, and the other amplitudes are regarded as the clutter amplitude of the negative half-wave; The frequencies corresponding to the important amplitudes of the negative half-waves of all cycles are arranged in sequence to construct a set of important frequencies of the negative half-waves; The frequencies corresponding to the negative half-wave clutter amplitudes of all cycles are arranged in sequence to construct a negative half-wave clutter frequency set.

[0029] In the present invention, the amplitude threshold can be set to 0.707 times the maximum value (that is, -3dB), and the maximum amplitude is found from the positive half-wave frequency domain information, and the corresponding amplitude threshold is 0.707 times the maximum amplitude; the maximum amplitude is found from the negative half-wave frequency domain information after taking the absolute value, and the corresponding amplitude threshold is 0.707 times the maximum amplitude.

[0030] In the actual operation of the photoelectric accelerometer driver chip, when the chip is operating normally, the frequency components of the output signal have a certain stability. When the chip fails, such as circuit parameter changes, component damage, etc., the amplitude of certain frequency components in the signal will change abnormally. By obtaining the important frequency set and the clutter frequency set, these abnormal frequency characteristics can be highlighted.

[0031] In this embodiment, the process of obtaining the positive half-wave frequency variation value of the adjacent module and the negative half-wave frequency variation value of the adjacent module includes: According to the difference between adjacent modules in the driver chip in the positive half-wave important frequency set, the first variation coefficient of the positive half-wave is obtained; according to the difference between adjacent modules in the driver chip in the negative half-wave important frequency set, the first variation coefficient of the negative half-wave is obtained; According to the difference between the adjacent modules in the driver chip in the positive half-wave noise frequency set, the second variation coefficient of the positive half-wave is obtained; according to the difference between the adjacent modules in the driver chip in the negative half-wave noise frequency set, the second variation coefficient of the negative half-wave is obtained; The first variation coefficient of the positive half-wave and the second variation coefficient of the positive half-wave are weighted to obtain the frequency variation value of the positive half-wave of the adjacent modules; The first variation coefficient of the negative half-wave and the second variation coefficient of the negative half-wave are weighted to obtain the frequency variation value of the negative half-wave of the adjacent modules.

[0032] In this embodiment, when weighting the first coefficient of variation and the second coefficient of variation, the first coefficient of variation is given priority. Therefore, a larger weight is set for the first coefficient of variation. For example, the weight of the first coefficient of variation can be set to 0.6, and the weight of the second coefficient of variation can be set to 0.4.

[0033] In this embodiment, the process of obtaining the first coefficient of variation includes: Take the intersection of the important frequency sets of adjacent modules to obtain the important frequency intersection; Eliminate the intersection of important frequencies from the important frequency set of the subsequent module in the adjacent module to obtain the newly added important frequency; Based on the newly added important frequencies, calculate the first coefficient of variation.

[0034] Furthermore, the process of obtaining the first coefficient of variation of the positive half-wave includes: The intersection of the positive half-wave important frequency sets of adjacent modules is taken to obtain the intersection of the positive half-wave important frequencies; Eliminate the intersection of the positive half-wave important frequencies from the positive half-wave important frequency set of the subsequent module in the adjacent module to obtain the newly added important frequencies of the positive half-wave; According to the newly added important frequencies of the positive half-wave, the first coefficient of variation of the positive half-wave is calculated.

[0035] Furthermore, the process of obtaining the first coefficient of variation of the negative half-wave includes: Taking the intersection of the negative half-wave important frequency sets of adjacent modules to obtain the intersection of the negative half-wave important frequencies; Eliminate the intersection of the important frequencies of the negative half-wave from the important frequency set of the negative half-wave of the subsequent module in the adjacent module to obtain the newly added important frequencies of the negative half-wave; According to the newly added important frequencies of the negative half-wave, the first coefficient of variation of the negative half-wave is calculated.

[0036] In this embodiment, the process of obtaining the second coefficient of variation includes: Taking the intersection of the clutter frequency sets of adjacent modules to obtain the clutter frequency intersection; Eliminate the intersection of clutter frequencies from the clutter frequency set of the subsequent module in the adjacent module to obtain the newly added clutter frequency; The second coefficient of variation is calculated based on the newly added clutter frequency.

[0037] Furthermore, the process of obtaining the second coefficient of variation of the positive half-wave includes: The intersection of the positive half-wave clutter frequency sets of adjacent modules is taken to obtain the positive half-wave clutter frequency intersection; Eliminate the intersection of positive half-wave clutter frequencies from the positive half-wave clutter frequency set of the subsequent module in the adjacent module to obtain the newly added clutter frequency of the positive half-wave; According to the newly added clutter frequency of the positive half-wave, the second coefficient of variation of the positive half-wave is calculated.

[0038] Furthermore, the process of obtaining the second coefficient of variation of the negative half-wave includes: Taking the intersection of the negative half-wave clutter frequency sets of adjacent modules to obtain the intersection of negative half-wave clutter frequencies; Eliminate the intersection of negative half-wave clutter frequencies from the negative half-wave clutter frequency set of the subsequent module in the adjacent module to obtain the newly added clutter frequency of the negative half-wave; According to the newly added clutter frequency of the negative half-wave, the second coefficient of variation of the negative half-wave is calculated.

[0039] The frequency set is divided into important frequencies and clutter frequencies, and the corresponding coefficients of variation are calculated respectively, following the principle of distinguishing key signal components from interference components in signal analysis. The important frequency set reflects the key frequency characteristics of the chip when it is working normally, while the clutter frequency set contains interference or abnormal frequency components. The coefficients of variation are calculated and weighted separately, so that when analyzing frequency variation, both the changes in key frequencies and the influence of interference frequencies are taken into account, which can more accurately reflect the changes in the working status of the chip.

[0040] In this embodiment, the formula for calculating the first coefficient of variation is: , where μ 1 is the first coefficient of variation, f z,i is the i-th newly added important frequency, f z,avgis the frequency mean of the important frequency set of the previous module in the adjacent module, i is a positive integer, N z is the number of newly added important frequencies, and D is the denominator parameter.

[0041] In this embodiment, the formula for calculating the second coefficient of variation is: , where μ 2 is the second coefficient of variation, f s,i is the ith new clutter frequency, f s,avg is the frequency mean of the clutter frequency set of the previous module in the adjacent module, N s is the number of newly added clutter frequencies.

[0042] The present invention quantifies the degree of difference between important frequencies or clutter frequencies between adjacent modules by calculating the sum of squares of deviations between the newly added frequencies and the mean frequency of the previous module. The denominator parameter D is a parameter greater than 0, which is used to prevent the denominator from being 0, and at the same time, makes the value range of the first coefficient of variation and the second coefficient of variation between 0 and 1.

[0043] In this embodiment, the waveform symmetry difference of adjacent modules is equal to the difference between the waveform symmetry value of the preceding module in the adjacent modules and the waveform symmetry value of the following module in the adjacent modules; The waveform stability difference between adjacent modules is equal to the difference between the waveform symmetry stability value of the preceding module in the adjacent modules and the waveform symmetry stability value of the following module in the adjacent modules.

[0044] The present invention can intuitively reflect the changing trend of the signal waveform symmetry characteristics and its stability during the transmission process between modules by calculating the difference between the waveform symmetry value and the waveform symmetry stability value of adjacent modules. When each module of the chip works normally, each module remains stable for signal transmission. If a large difference occurs, it means that the waveform symmetry characteristics and stability of the signal have changed abnormally when the signal is transmitted between modules.

[0045] like Figure 3 As shown, the convolutional neural network includes: a first convolutional layer, a second convolutional layer, a third convolutional layer, a fourth convolutional layer, a first Concat layer, a second Concat layer, a first fully connected layer, a second fully connected layer and a weighted layer; The input end of the first convolution layer is used to input the first sample, the input end of the second convolution layer is used to input the first sample, the input end of the third convolution layer is used to input the second sample, and the input end of the fourth convolution layer is used to input the second sample, wherein the positive half-wave frequency variation value, the negative half-wave frequency variation value, the waveform symmetry difference value and the waveform stability difference value of the signal generation module and the operational amplifier module together constitute the first sample, and the positive half-wave frequency variation value, the negative half-wave frequency variation value, the waveform symmetry difference value and the waveform stability difference value of the operational amplifier module and the coupling circuit module together constitute the second sample; The input end of the first Concat layer is connected to the output end of the first convolutional layer and the output end of the third convolutional layer respectively; the input end of the second Concat layer is connected to the output end of the second convolutional layer and the output end of the fourth convolutional layer respectively; the input end of the first fully connected layer is connected to the output end of the first Concat layer; the input end of the second fully connected layer is connected to the output end of the second Concat layer; the input end of the weighted layer is connected to the output end of the first fully connected layer and the output end of the second fully connected layer respectively, and its output end is used to output the fault value of the driver chip.

[0046] In this embodiment, the first convolution layer and the third convolution layer use convolution kernels as The second and fourth convolutional layers use convolution kernels of The first sample of the convolutional layer is to arrange the 4 values ​​into The second sample is to arrange the 4 values ​​into The matrix of .

[0047] The present invention adopts the following method to respectively treat the first sample and the second sample: The convolutional layers of different sizes extract features, the first Concat layer concatenates the extracted features, and the first fully connected layer is used to calculate the first fault component; the first sample and the second sample are then The convolutional layers of different sizes extract features, the second Concat layer concatenates the extracted features, the second fully connected layer is used to calculate the second fault component, and the first fault component and the second fault component are weighted in the weighted layer to obtain the driver chip fault value.

[0048] The present invention adopts and The convolutional layers of different sizes extract features from the first sample and the second sample, and can capture feature information of samples from different scales. The first Concat layer concatenates features at one scale, and the second Concat layer concatenates features at another scale, realizing dual-channel calculation of fault components and improving the accuracy of fault detection.

[0049] In this embodiment, the weighted layer can be implemented using a fully connected layer.

[0050] In this embodiment, the convolutional neural network can be trained using the existing gradient descent method, a data set including the first sample and the second sample is collected, and the actual driver chip fault value (label) corresponding to each sample is recorded. The data set is input into the convolutional neural network, and the mean square error (MSE) loss function is selected for training.

[0051] The present invention captures the subtle features of the signal through zero-crossing division and half-wave analysis, and then uses waveform symmetry analysis and frequency domain conversion to deeply explore the signal features, and highlights the abnormal features through comparative analysis of adjacent modules. Finally, a convolutional neural network is used to process the positive half-wave frequency variation value, negative half-wave frequency variation value, waveform symmetry difference and waveform stability difference of adjacent modules to obtain the driver chip fault value. The present invention divides the output signal to obtain a positive half-wave and a negative half-wave, and highlights the fault features from the symmetry of the waveform and the frequency domain features between adjacent modules, so that the fault features are significant, easy to identify, and the fault detection accuracy is improved.

[0052] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for detecting faults in a photoelectric accelerometer driver chip, characterized in that: include: The output signals of each module in the driver chip are divided according to the zero crossing point to obtain a positive half-wave set and a negative half-wave set; For the positive half-wave set and the negative half-wave set of each module, extract the waveform symmetry value and the waveform symmetry stability value; The positive half-wave set and the negative half-wave set are converted into the frequency domain, and the frequency domain information is divided into important frequencies and clutter frequencies, so as to obtain four frequency sets, wherein the four frequency sets include: a positive half-wave important frequency set, a positive half-wave clutter frequency set, a negative half-wave important frequency set and a negative half-wave clutter frequency set; According to the gaps between adjacent modules in the driver chip in the four frequency sets, the positive half-wave frequency variation value and the negative half-wave frequency variation value of the adjacent modules are obtained; According to the differences in waveform symmetry values ​​and waveform symmetry stability values ​​of adjacent modules in the driver chip, the waveform symmetry difference and waveform stability difference of adjacent modules are obtained; The positive half-wave frequency variation value, negative half-wave frequency variation value, waveform symmetry difference and waveform stability difference of each adjacent module are input into the convolutional neural network as samples to obtain the fault value of the driver chip.

2. The photoelectric accelerometer driver chip fault detection method according to claim 1, characterized in that: The process of extracting the waveform symmetry value is: For each positive half-wave in the positive half-wave set, calculate the positive half-wave area; For each negative half-wave in the negative half-wave set, calculate the negative half-wave area; The positive half-wave area and the positive half-wave peak value are used as elements to form a positive half-wave eigenvector; The negative half-wave area and the absolute value of the peak value of the negative half-wave are used as elements to form a negative half-wave eigenvector; Calculate the similarity between the positive half-wave eigenvector and the negative half-wave eigenvector of the same period; The similarity of each cycle is averaged to obtain the waveform symmetry value.

3. The photoelectric accelerometer driver chip fault detection method according to claim 2, characterized in that: The formula for calculating the waveform symmetry stability value is: , where γ is the waveform symmetry stability value and σ is the standard deviation of the similarity of each cycle.

4. The photoelectric accelerometer driver chip fault detection method according to claim 1, characterized in that: Each positive half-wave in the positive half-wave set and each negative half-wave in the negative half-wave set is converted from time to frequency to obtain positive half-wave frequency domain information and negative half-wave frequency domain information, and each frequency domain information is divided into an important frequency set and a clutter frequency set to obtain a positive half-wave important frequency set, a positive half-wave clutter frequency set, a negative half-wave important frequency set and a negative half-wave clutter frequency set.

5. The photoelectric accelerometer driver chip fault detection method according to claim 1, characterized in that: The process of obtaining the positive half-wave important frequency set and the positive half-wave clutter frequency set is: Perform time-frequency conversion on each positive half-wave in the positive half-wave set to obtain frequency domain information of the positive half-wave; The amplitude greater than the amplitude threshold in the frequency domain information of the positive half-wave is regarded as the important amplitude of the positive half-wave, and the other amplitudes are regarded as the positive half-wave clutter amplitude; The frequencies corresponding to the important amplitudes of the positive half-waves of all cycles are arranged in sequence to construct a set of important frequencies of the positive half-waves; The frequencies corresponding to the positive half-wave clutter amplitudes of all cycles are arranged in sequence to construct a positive half-wave clutter frequency set; Alternatively, the process of obtaining the negative half-wave important frequency set and the negative half-wave clutter frequency set is: Performing time-frequency conversion on each negative half-wave in the negative half-wave set respectively to obtain frequency domain information of the negative half-wave, and taking the absolute value of the amplitude in the frequency domain information of the negative half-wave; The amplitude greater than the amplitude threshold in the frequency domain information of the negative half-wave is regarded as the important amplitude of the negative half-wave, and the other amplitudes are regarded as the clutter amplitude of the negative half-wave; The frequencies corresponding to the important amplitudes of the negative half-waves of all cycles are arranged in sequence to construct a set of important frequencies of the negative half-waves; The frequencies corresponding to the negative half-wave clutter amplitudes of all cycles are arranged in sequence to construct a negative half-wave clutter frequency set.

6. The photoelectric accelerometer driver chip fault detection method according to claim 1, characterized in that: The process of obtaining the positive half-wave frequency variation value of the adjacent module and the negative half-wave frequency variation value of the adjacent module includes: According to the difference between adjacent modules in the driver chip in the positive half-wave important frequency set, the first variation coefficient of the positive half-wave is obtained; according to the difference between adjacent modules in the driver chip in the negative half-wave important frequency set, the first variation coefficient of the negative half-wave is obtained; According to the difference between the adjacent modules in the driver chip in the positive half-wave noise frequency set, the second variation coefficient of the positive half-wave is obtained; according to the difference between the adjacent modules in the driver chip in the negative half-wave noise frequency set, the second variation coefficient of the negative half-wave is obtained; The first variation coefficient of the positive half-wave and the second variation coefficient of the positive half-wave are weighted to obtain the frequency variation value of the positive half-wave of the adjacent modules; The first variation coefficient of the negative half-wave and the second variation coefficient of the negative half-wave are weighted to obtain the frequency variation value of the negative half-wave of the adjacent modules.

7. The photoelectric accelerometer driver chip fault detection method according to claim 6, characterized in that: The process of obtaining the first coefficient of variation includes: Take the intersection of the important frequency sets of adjacent modules to obtain the important frequency intersection; Eliminate the intersection of important frequencies from the important frequency set of the subsequent module in the adjacent module to obtain the newly added important frequency; Calculate the first coefficient of variation based on the newly added important frequencies; Alternatively, the process of obtaining the second coefficient of variation includes: Taking the intersection of the clutter frequency sets of adjacent modules to obtain the clutter frequency intersection; Eliminate the intersection of clutter frequencies from the clutter frequency set of the subsequent module in the adjacent module to obtain the newly added clutter frequency; The second coefficient of variation is calculated based on the newly added clutter frequency.

8. The photoelectric accelerometer driver chip fault detection method according to claim 7, characterized in that: The formula for calculating the first coefficient of variation is: , where μ1 is the first coefficient of variation, f z,i is the i-th newly added important frequency, f z,avg is the frequency mean of the important frequency set of the previous module in the adjacent module, i is a positive integer, N z is the number of newly added important frequencies, and D is the denominator parameter; The formula for calculating the second coefficient of variation is: , where μ2 is the second coefficient of variation, f s,i is the ith new clutter frequency, f s,avg is the frequency mean of the clutter frequency set of the previous module in the adjacent module, N s is the number of newly added clutter frequencies.

9. The photoelectric accelerometer driver chip fault detection method according to claim 1, characterized in that: The waveform symmetry difference of adjacent modules is equal to the difference between the waveform symmetry value of the preceding module in the adjacent modules and the waveform symmetry value of the following module in the adjacent modules; The waveform stability difference between adjacent modules is equal to the difference between the waveform symmetry stability value of the preceding module in the adjacent modules and the waveform symmetry stability value of the following module in the adjacent modules.

10. The photoelectric accelerometer driver chip fault detection method according to claim 1, characterized in that: The convolutional neural network includes: a first convolutional layer, a second convolutional layer, a third convolutional layer, a fourth convolutional layer, a first Concat layer, a second Concat layer, a first fully connected layer, a second fully connected layer and a weighted layer; The input end of the first convolution layer is used to input the first sample, the input end of the second convolution layer is used to input the first sample, the input end of the third convolution layer is used to input the second sample, and the input end of the fourth convolution layer is used to input the second sample, wherein the positive half-wave frequency variation value, the negative half-wave frequency variation value, the waveform symmetry difference value and the waveform stability difference value of the signal generation module and the operational amplifier module together constitute the first sample, and the positive half-wave frequency variation value, the negative half-wave frequency variation value, the waveform symmetry difference value and the waveform stability difference value of the operational amplifier module and the coupling circuit module together constitute the second sample; The input end of the first Concat layer is connected to the output end of the first convolutional layer and the output end of the third convolutional layer respectively; the input end of the second Concat layer is connected to the output end of the second convolutional layer and the output end of the fourth convolutional layer respectively; the input end of the first fully connected layer is connected to the output end of the first Concat layer; the input end of the second fully connected layer is connected to the output end of the second Concat layer; the input end of the weighted layer is connected to the output end of the first fully connected layer and the output end of the second fully connected layer respectively, and its output end is used to output the fault value of the driver chip.

Images