Bearing fault classification method and system based on decision tree algorithm full-analog circuit

Abstract

The invention discloses a bearing fault classification method based on a decision tree algorithm full-analog circuit, and the method comprises the steps: enabling various bearing fault signals to pass through two layers of analog filters in sequence, and enabling the difference between the root mean square values of a low-pass output signal and a high-pass output signal of each layer of analog filter to serve as a decision condition, classifying and coding various bearing fault signals to obtain simulation signal codes; the currently collected bearing fault signal is successively introduced into two layers of programmable control filters with the same parameters as the two layers of analog filters, the difference between root mean square values of a low-pass output signal and a high-pass output signal of each layer of programmable control filter is used as a decision condition, and the current bearing fault signal is coded to obtain a current signal code; and comparing the current signal code with the simulation signal code to determine the current bearing fault signal type. According to the invention, the original continuous vibration signals collected on the motor can be directly classified, and the advantages of more convenient operation, faster classification speed, lower energy consumption and the like can be realized.

Description

Technical Field

[0001] The present invention relates to the field of bearing fault classification, and particularly to a bearing fault classification method and system based on a decision tree algorithm for a full analog circuit. Background Art

[0002] In the field of bearing fault diagnosis, vibration signals are the most commonly used signals for diagnosing bearing faults. Vibration signals are generally converted into voltage signals by vibration sensors. At this time, the continuous analog signals output by the sensors, that is, continuous voltage signals, will change with the magnitude of the vibration amplitude. The fault signals of bearings can also be reflected by current signals, and the fluctuations of the current signals also reflect different bearing faults.

[0003] Signals often have complex non-linear characteristics and may be affected by noise. Traditional fault diagnosis methods usually rely on digital calculations and feature extraction. Although these methods are very effective in many cases, they usually require complex algorithms and high-performance computing devices (computers cannot directly process continuous analog signals, so continuous signals need to be sampled into discrete signals for processing), which will have certain limitations in scenarios requiring real-time performance and energy consumption.

[0004] Analog circuits are an important technical means capable of realizing specific signal processing and computing tasks. They can be widely applied in multiple fields, such as signal processing, control systems, and fault diagnosis. Analog circuits have the advantages of fast response speed, low power consumption, and simple implementation of non-linear characteristics, and have gradually been applied to the field of fault diagnosis in recent years. Using an analog circuit to implement the function of a decision tree can directly process signals to achieve feature extraction and classification, thereby realizing real-time processing and decision classification tasks, and greatly reducing the complexity and computing delay of the system.

[0005] Although the application of analog circuits in fault diagnosis has great potential, most existing studies focus on the processing of specific types of signals, lacking a general and highly adaptable circuit architecture. In addition, traditional analog circuit implementation methods may be affected by circuit noise and instability when processing high-noise signals or weak fault features, limiting their application scope. Therefore, an effective detection and classification method for complex fault signals remains a major challenge for analog circuits in the field of fault diagnosis.

[0006] Therefore, how to solve the deficiencies of the above existing technologies has become the subject to be studied and solved by the present invention. Summary of the Invention

[0007] The purpose of the present invention is to provide a bearing fault classification method and system based on a decision tree algorithm for a full analog circuit.

[0008] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0009] In the first aspect of the present invention, a bearing fault classification method for a full analog circuit based on a decision tree algorithm is provided. The method includes:

[0010] Step 1: Construct a simulation circuit model using two - layer analog filters; after various bearing fault signals are input into the simulation circuit model, they pass through two - layer analog filters in sequence. The difference between the root - mean - square values of the low - pass output signal and the high - pass output signal of each layer of analog filter is used as a decision condition to classify and encode various bearing fault signals, and a simulation signal encoding corresponding to each bearing fault signal is obtained;

[0011] Step 2: Construct a full analog circuit model using two - layer programmable control filters with the same parameters as the two - layer analog filters; the currently collected bearing fault signals are input into the full analog circuit model and pass through two - layer programmable control filters in sequence. The difference between the root - mean - square values of the low - pass output signal and the high - pass output signal of each layer of programmable control filter is used as a decision condition to encode the currently collected bearing fault signals, and a current signal encoding is obtained;

[0012] Step 3: Compare the current signal encoding with the simulation signal encoding to determine the type of bearing fault signal corresponding to the current signal encoding.

[0013] Preferably, the bearing fault signal is a voltage signal or a current signal.

[0014] Preferably, the analog filter in Step 1 is a filter with optimized parameters, and the parameter is the cut - off frequency;

[0015] The optimization method of the parameter includes:

[0016] Superimpose various bearing fault signals and input them into the first - layer analog filter. After low - pass and high - pass filtering, a first low - pass analog signal and a first high - pass analog signal are output respectively. Calculate the difference between the first root - mean - square values of the first low - pass analog signal and the first high - pass analog signal, and optimize the parameters of the first - layer analog filter with this difference between the first root - mean - square values to obtain a first - layer optimized analog filter;

[0017] Use the difference between the first root - mean - square values as a decision condition to classify and encode various bearing fault signals, eliminate bearing fault signals with different encodings, and retain bearing fault signals with the same encoding;

[0018] The first low-pass analog signal and the first high-pass analog signal of the superimposed and retained bearing fault signals are input into the second-layer analog filter. After low-pass and high-pass filtering, the second low-pass analog signal and the second high-pass analog signal are respectively output. Calculate the difference between the second analog root-mean-square values of the second low-pass analog signal and the second high-pass analog signal, and optimize the parameters of the second-layer analog filter with this difference between the second analog root-mean-square values to obtain the second-layer optimized analog filter.

[0019] Preferably, the parameters of both the first-layer analog filter and the second-layer analog filter are optimized using a genetic algorithm:

[0020] Take the absolute value of the difference between the root-mean-square values as the objective function, take the cut-off frequency of the filter as the variable, and obtain the minimum absolute value through optimization. The cut-off frequency corresponding to this minimum absolute value is the optimal parameter of the filter.

[0021] Preferably, the method of using the difference between the root-mean-square values as a decision condition to classify and encode various bearing fault signals in step one and step two includes:

[0022] When the difference between the root-mean-square values of the low-pass output signal and the high-pass output signal is greater than zero, set the signal encoding of the corresponding bearing fault signal as a; when the difference between the root-mean-square values of the low-pass output signal and the high-pass output signal is less than zero, set the signal encoding of the corresponding bearing fault signal as b.

[0023] Preferably, both the simulation signal encoding and the current signal encoding are combinations of the two signal encodings obtained by classifying and encoding the bearing fault signal through two layers of filters.

[0024] Preferably, before the currently collected bearing fault signal in step two passes through the second-layer programmable control filter, an adder module is used to add the low-pass output signal and the high-pass output signal of the first-layer programmable control filter, and then input it into the second-layer programmable control filter.

[0025] Preferably, the root-mean-square values of the low-pass output signal and the high-pass output signal of each layer of programmable control filter in step two are calculated using a root-mean-square value calculation module.

[0026] Preferably, the root-mean-square values of the low-pass output signal and the high-pass output signal of each layer of programmable control filter in step two are output to an oscilloscope, and the difference between the root-mean-square values is determined according to the magnitudes of the waveforms displayed on each channel of the oscilloscope.

[0027] The second aspect of the present invention provides a bearing fault classification system based on a decision tree algorithm full analog circuit, and this bearing fault classification system is used to implement the above full analog circuit model.

[0028] The working principle and advantages of the present invention are as follows:

[0029] The all-analog circuit of the present invention can implement the idea of the decision tree machine learning algorithm. Different filtering methods of two layers of filters are used to replace the decision conditions on different branches of the decision tree, that is, the difference in the root mean square values obtained by filtering and calculating the bearing fault signal through each layer is used as the decision condition, and then the bearing fault signal is classified.

[0030] Compared with the traditional method of using a complex neural network for classification, the method of using an all-analog circuit to classify different types of bearing fault signals proposed by the present invention is as follows: The traditional method relying on neural network classification needs to collect vibration signals into discrete signals through a data acquisition card and perform complex preprocessing on the signals before using them as the input of the network for classification. The method of using an all-analog circuit classification proposed by the present invention can directly classify the original continuous vibration analog signals collected on the motor. During the transmission and classification process of the vibration analog signals in the all-analog circuit, they are all transmitted in the form of analog signals, without the need to collect continuous signals into discrete signals and then perform processing and classification. Therefore, it can achieve the advantages of more convenient operation, faster classification speed, and lower energy consumption.

[0031] The all-analog circuit model proposed by the present invention has a simple structure. For different working modes of each layer of filter, only one parameter needs to be adjusted, making parameter optimization simpler, with higher optimization efficiency, and it is easier to make the circuit model work in the best state.

[0032] All functions of the all-analog circuit of the present invention are implemented in a modular manner, and there are fewer peripheral circuits involved, so the stability is stronger and it is less affected by circuit noise and instability. Description of the Drawings

[0033] Appendix Figure 1 is the flowchart of the bearing fault signal classification method of the present invention;

[0034] Appendix Figure 2 is the flowchart of the encoding of the present invention;

[0035] Appendix Figure 3 is the flowchart of the analog filter parameter optimization of the present invention;

[0036] Appendix Figure 4 (a), (b), and (c) are respectively the time domain diagrams of the signals of a brushless DC motor in normal condition, inner ring 2mm fault, and outer ring 2mm fault;

[0037] Appendix Figure 5 is the simulation result diagram of the present invention;

[0038] Appendix Figure 6 is the implementation flowchart of the all-analog circuit of the present invention. Detailed Embodiments

[0039] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0040] Embodiment: The present case will be clearly described below with diagrams and detailed descriptions. After any person skilled in the art understands the embodiments of the present case, the techniques taught by the present case can be changed and modified without departing from the spirit and scope of the present case.

[0041] The terms used herein are only for describing specific embodiments and are not intended to limit the present case. Singular forms such as "a", "this", "this", "the present", and "the" also include plural forms as used herein.

[0042] Regarding the use of "first", "second", etc. in this article, it does not particularly refer to the meaning of order or sequence, nor is it used to limit the present case. It is only used to distinguish components or operations described with the same technical terms.

[0043] Regarding the use of "connected" or "positioned" in this article, it can refer to two or more components or devices making direct physical contact with each other, or making indirect physical contact with each other. It can also refer to two or more components or devices operating or acting on each other.

[0044] Regarding the use of "comprising", "including", "having", etc. in this article, they are all open-ended terms, that is, they mean including but not limited to.

[0045] Regarding the terms used in this article, unless otherwise specified, they generally have the ordinary meaning of each term used in this field, in the context of the present case, and in the context of special content. Certain terms used to describe the present case will be discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art regarding the description of the present case.

[0046] See the attached Figure 1 As shown, the first aspect of the present invention provides a bearing fault classification method based on a decision tree algorithm for a full analog circuit. Currently, the fault detection of bearings generally uses vibration sensors or current sensors, etc. Therefore, in this embodiment, the bearing fault signal is the voltage signal output by the vibration sensor, and in other embodiments, the bearing fault signal can be the current signal output by the current sensor.

[0047] In this embodiment, various bearing fault signals include three different types, namely normal bearing signal, inner ring fault 2mm signal, and outer ring fault 2mm signal.

[0048] The bearing fault signal classification method includes:

[0049] Step 1: Use a two-layer analog filter to construct a simulation circuit model. The analog filter can be a Butterworth filter.

[0050] In this embodiment, the analog filter is a filter with optimized parameters, and the parameter is the cut-off frequency. See the appendix Figure 3 As shown, the optimization method of the parameter includes:

[0051] Superimpose three types of bearing fault signals and input them into the first-layer analog filter. After low-pass and high-pass filtering, three pairs of first low-pass analog signals and first high-pass analog signals are respectively output. Calculate the difference between the first analog root mean square values of each pair of first low-pass analog signals and first high-pass analog signals, and use the genetic algorithm to optimize the parameters of the first-layer analog filter with this difference between the first analog root mean square values to obtain the first-layer optimized analog filter;

[0052] Use the difference between the first analog root mean square values as the decision condition to classify and code various bearing fault signals, eliminate the bearing fault signals with different codes, and retain the bearing fault signals with the same code;

[0053] Superimpose the first low-pass analog signals and first high-pass analog signals of the retained bearing fault signals and input them into the second-layer analog filter. After low-pass and high-pass filtering, second low-pass analog signals and second high-pass analog signals are respectively output. Calculate the difference between the second analog root mean square values of the second low-pass analog signals and second high-pass analog signals, and use the genetic algorithm to optimize the parameters of the second-layer analog filter with this difference between the second analog root mean square values to obtain the second-layer optimized analog filter.

[0054] In this embodiment, the calculation formula of the root mean square value is:

[0055]

[0056] In the formula, V OUT is the output signal of the filter. First, take the average of the output signal, then perform a square operation, and finally take the square root to obtain the root mean square value of the output signal.

[0057] In this embodiment, the method of using the genetic algorithm to optimize the parameters of the first-layer analog filter and the second-layer analog filter is: take the absolute value of the difference between the root mean square values as the objective function, take the cut-off frequency of the filter as the variable, and obtain the minimum absolute value through optimization. The cut-off frequency corresponding to this minimum absolute value is the optimal parameter of the filter. The specific model is:

[0058] Error = |RMS High -RMS Low |

[0059] In the formula, RMS High is the root mean square value of the output signal of the signal passing through the high-pass filter, RMS Low is the root mean square value of the output signal of the signal passing through the low-pass filter, and Error is the absolute value of the difference between the two.

[0060] After the three types of bearing fault signals are input into the simulation circuit model, they pass through two layers of optimized analog filters successively. The difference between the root mean square values of the low-pass output signal and the high-pass output signal of each layer of optimized analog filter is used as the decision condition to classify and encode various bearing fault signals, and a simulation signal encoding corresponding to each type of bearing fault signal is obtained. See the appendix Figure 2 As shown, the specific method is as follows:

[0061] The three types of bearing fault signals are respectively input into the first layer of optimized analog filter, and three pairs of first low-pass simulation signals and first high-pass simulation signals are respectively output after low-pass and high-pass filtering. Calculate the difference between the first simulation root mean square values of each pair of first low-pass simulation signals and first high-pass simulation signals, and use this difference between the first simulation root mean square values to perform the first encoding on various bearing fault signals to obtain the first simulation signal encoding;

[0062] The three pairs of the first low-pass simulation signals and first high-pass simulation signals are superimposed and input into the second layer of optimized analog filter, and three pairs of second low-pass simulation signals and second high-pass simulation signals are respectively output after low-pass and high-pass filtering. Calculate the difference between the second simulation root mean square values of each pair of second low-pass simulation signals and second high-pass simulation signals, and use this difference between the second simulation root mean square values to perform the second encoding on various bearing fault signals to obtain the second simulation signal encoding; As Figure 4 shown are the output waveforms of three different types of bearing fault voltage signals input into this simulation circuit model.

[0063] Combine the first simulation signal encoding and the second simulation signal encoding to obtain a simulation signal encoding corresponding to each type of bearing fault signal, and this simulation signal encoding is used to classify various bearing fault signals.

[0064] In this embodiment, the method of using the difference between the root mean square values as the decision condition to classify and encode various bearing fault signals includes:

[0065] When the difference between the root mean square values of the low-pass output signal and the high-pass output signal is greater than zero, set the signal encoding of the corresponding bearing fault signal as a; when the difference between the root mean square values of the low-pass output signal and the high-pass output signal is less than zero, set the signal encoding of the corresponding bearing fault signal as b.

[0066] In this embodiment, a can be 10 and b can be 01; therefore, the encoding truth table of the output signal after each layer of filtering is as follows:

[0067]

[0068] See the appendix Figure 5As shown, after filtering by two layers of filters, each signal will correspond to a unique code. Different signals can be classified according to different coding methods. The bearing signals of three different fault types of the brushless DC motor are respectively input into this simulation circuit model, and the codes of the output signals are obtained after combination: the simulation signal code of the normal signal is 0101; the simulation signal code of the inner ring fault 2mm signal is 1001; the simulation signal code of the outer ring fault 2mm signal is 1010. The coding values are shown in the following table:

[0069]

[0070] It can be seen from this table that in the parameter optimization step, the signal codes output by the first layer of analog filter are 01, 10, and 10 respectively. Among them, 01 is a different code. Therefore, the normal signal is eliminated, and the inner ring fault 2mm signal and the outer ring fault 2mm signal are retained and superimposed and input into the second layer of analog filter to optimize the parameters of the second layer of analog filter.

[0071] The above simulation circuit models all rely on computer software to complete the simulation.

[0072] Step 2: Construct a full analog circuit model using two layers of MAX261 programmable control filters with the same parameters as the two layers of analog filters respectively; the currently collected bearing fault signal is input into the full analog circuit model and passes through two layers of programmable control filters in sequence. The root mean square value difference between the low-pass output signal and the high-pass output signal of each layer of programmable control filter is used as the decision condition to encode the currently collected bearing fault signal to obtain the current signal code. The specific method is as follows:

[0073] Input the currently collected bearing fault signal into the first programmable control filter. The first programmable control filter includes a first layer of MAX261 low-pass filtering module and a first layer of MAX261 high-pass filtering module. The currently collected bearing fault signal is low-pass filtered by the first layer of MAX261 low-pass filtering module to output a first low-pass signal, and high-pass filtered by the first layer of MAX261 high-pass filtering module to output a first high-pass signal. The root mean square value calculation module calculates the first root mean square value of the first low-pass signal and the first high-pass signal and outputs the root mean square value to the oscilloscope. Determine the root mean square value difference according to the magnitudes of the waveforms displayed on each channel of the oscilloscope, and use this first root mean square value difference to perform the first encoding on various bearing fault signals to obtain the first actual signal code;

[0074] Since in the actual full analog circuit, the entire process of classifying the above three different bearing signals is analog signal input and analog signal output, an adder module is required to add the low-pass output signal and the high-pass output signal together after the output of the first layer of programmable control filter to restore the characteristics of the signal in the entire frequency band and avoid affecting the second layer of filtering output.

[0075] Add the low-pass output signal and the high-pass output signal of the first programmable control filter, and then input the result into the second programmable control filter. The second programmable control filter includes a second MAX261 low-pass filtering module and a second MAX261 high-pass filtering module. The added signal is low-pass filtered by the second MAX261 low-pass filtering module to output a second low-pass signal, and is high-pass filtered by the second MAX261 high-pass filtering module to output a second high-pass signal. The root mean square (RMS) value calculation module calculates the second RMS value of the second low-pass signal and the second high-pass signal and outputs the RMS value to the oscilloscope. Determine the difference in RMS values based on the magnitudes of the waveforms displayed on each channel of the oscilloscope, and use this difference in the second RMS value to perform a second encoding on various bearing fault signals to obtain a second actual signal encoding.

[0076] Combine the first actual signal encoding and the second actual signal encoding to obtain the current signal encoding. The signal encoding method in this step is the same as the encoding method applied in the simulation circuit model.

[0077] In this embodiment, the RMS value calculation module uses an AD637 module. The AD637 module directly outputs the calculated RMS value to the oscilloscope, and the zero scale points of each channel of the oscilloscope need to be adjusted to be consistent. The adder module is built based on an LM741 operational amplifier.

[0078] Step 3: Compare the current signal encoding and the simulation signal encoding to determine the type of bearing fault signal corresponding to the current signal encoding.

[0079] See the appendix Figure 6 As shown, in the second aspect of the present invention, a bearing fault classification system based on a decision tree algorithm full analog circuit is provided. This bearing fault classification system is used to implement the above full analog circuit model. This bearing fault classification system includes a first programmable control filter, a second programmable control filter, an RMS value calculation module (AD637 module), an adder module, and an oscilloscope.

[0080] The first programmable control filter includes a first MAX261 low-pass filtering module and a first MAX261 high-pass filtering module. The second programmable control filter includes a second MAX261 low-pass filtering module and a second MAX261 high-pass filtering module.

[0081] The output ends of the first MAX261 low-pass filtering module, the first MAX261 high-pass filtering module, the second MAX261 low-pass filtering module, and the second MAX261 high-pass filtering module are all connected to the AD637 module, and the output end of the AD637 module is connected to the oscilloscope.

[0082] The output terminals of the first - layer MAX261 low - pass filter module and the first - layer MAX261 high - pass filter module are connected to the input terminals of the adder module, and the output terminal of the adder module is connected to the second - layer MAX261 low - pass filter module and the second - layer MAX261 high - pass filter module.

[0083] The above - mentioned modules are connected to form a full - analog circuit. The original continuous vibration analog signal collected from the motor is transmitted in the form of an analog signal throughout the full - analog circuit without the need to sample the continuous signal into a discrete signal and then perform processing and classification. Therefore, it can achieve the advantages of more convenient operation, faster classification speed, and lower energy consumption.

[0084] The present invention can implement the idea of the decision - tree machine - learning algorithm using the above - mentioned full - analog circuit. Different filtering methods of the two - layer filters are used to replace the decision conditions on different branches of the decision tree. That is, the difference in the root - mean - square values obtained by filtering and calculating the bearing fault signal through each layer is used as the decision condition, so as to classify the bearing fault signal.

[0085] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly, and should not be used to limit the protection scope of the present invention. All equivalent changes or modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.

Claims

1. A bearing fault classification method based on a decision tree algorithm full analog circuit, characterized in that: The method comprises: Step 1: Use two layers of analog filters to construct a simulation circuit model; after various bearing fault signals are passed into the simulation circuit model, they pass through two layers of analog filters in succession, and the root mean square value difference between the low-pass output signal and the high-pass output signal of each layer of analog filters is used as a decision condition to classify and encode various bearing fault signals, and obtain simulation signal codes corresponding to various bearing fault signals one by one; Step 2: Use two layers of programmable control filters with the same parameters as the two layers of analog filters to construct a full analog circuit model; the currently collected bearing fault signal is passed into the full analog circuit model and then passes through the two layers of programmable control filters in succession, and the root mean square value difference between the low-pass output signal and the high-pass output signal of each layer of programmable control filters is used as a decision condition to encode the current bearing fault signal to obtain the current signal code; Step three: compare the current signal code with the simulation signal code to determine the bearing fault signal type corresponding to the current signal code.

2. According to claim 1, a bearing fault classification method based on a decision tree algorithm full analog circuit is characterized in that: The bearing fault signal is a voltage signal or a current signal.

3. The bearing fault classification method based on decision tree algorithm full analog circuit according to claim 1 is characterized by: The analog filter described in step 1 is a filter after parameter optimization, and the parameter is the cutoff frequency; The parameter optimization method includes: Various bearing fault signals are superimposed and passed into the first layer of analog filter, and a first low-pass analog signal and a first high-pass analog signal are outputted respectively after low-pass and high-pass filtering, and a difference between the first analog root mean square value of the first low-pass analog signal and the first high-pass analog signal is calculated, and the parameters of the first layer of analog filter are optimized by the difference of the first analog root mean square value to obtain a first layer of optimized analog filter; Using the difference of the first simulated RMS value as a decision condition, classifying and encoding various types of bearing fault signals, eliminating bearing fault signals with different codes, and retaining bearing fault signals with the same code; The first low-pass analog signal and the first high-pass analog signal of the superimposed and retained bearing fault signal are passed into the second-layer analog filter, and the second low-pass analog signal and the second high-pass analog signal are output respectively after low-pass and high-pass filtering, and the difference between the second analog root mean square values ​​of the second low-pass analog signal and the second high-pass analog signal is calculated, and the parameters of the second-layer analog filter are optimized by the difference between the second analog root mean square values ​​to obtain the second-layer optimized analog filter.

4. The bearing fault classification method based on decision tree algorithm full analog circuit according to claim 3 is characterized by: The parameters of the first layer analog filter and the second layer analog filter are optimized by genetic algorithm: The absolute value of the difference between the RMS values ​​is used as the objective function, and the cutoff frequency of the filter is used as a variable. The minimum absolute value is obtained through optimization, and the cutoff frequency corresponding to the minimum absolute value is the optimal parameter of the filter.

5. The bearing fault classification method based on decision tree algorithm full analog circuit according to claim 1 is characterized by: The method described in step 1 and step 2 for classifying and encoding various types of bearing fault signals by taking the difference of the root mean square value as a decision condition includes: When the difference between the root mean square values ​​of the low-pass output signal and the high-pass output signal is greater than zero, the signal code of the corresponding bearing fault signal is set to a; when the difference between the root mean square values ​​of the low-pass output signal and the high-pass output signal is less than zero, the signal code of the corresponding bearing fault signal is set to b.

6. The bearing fault classification method based on decision tree algorithm full analog circuit according to claim 5 is characterized by: The simulation signal code and the current signal code are both combinations of two signal codes obtained by classifying and coding the bearing fault signal through two layers of filters.

7. The bearing fault classification method based on decision tree algorithm full analog circuit according to claim 1 is characterized by: In step 2, before the currently collected bearing fault signal passes through the second layer of programmable control filter, an adder module is used to add the low-pass output signal and the high-pass output signal of the first layer of programmable control filter, and then the signal is passed into the second layer of programmable control filter.

8. The bearing fault classification method based on decision tree algorithm full analog circuit according to claim 1 is characterized by: In step 2, the root mean square value of the low-pass output signal and the high-pass output signal of each layer of the programmable control filter is calculated using a root mean square value calculation module.

9. The bearing fault classification method based on decision tree algorithm full analog circuit according to claim 8 is characterized by: In step 2, the root mean square values ​​of the low-pass output signal and the high-pass output signal of each layer of the programmable control filter are output to the oscilloscope, and the difference in the root mean square values ​​is determined according to the size of the waveform displayed by each channel of the oscilloscope.

10. A bearing fault classification system based on a decision tree algorithm full analog circuit, characterized in that: The bearing fault classification system is used to implement the full analog circuit model described in any one of claims 1-9.

Images