Fault monitoring method and system for motor carbon brush

Abstract

The invention discloses a fault monitoring method and system for a motor carbon brush. The fault monitoring method comprises the steps that a temperature sensor device, a current sensor device and a pressure sensor device are arranged in a brush holder corresponding to the carbon brush; a sound sensor device and a timing device are arranged in the motor shell; calculating data obtained by the sensor device to generate a first characteristic parameter, a second characteristic parameter, a third characteristic parameter and a fourth characteristic parameter; inputting a feature vector composed of the first feature parameter, the second feature parameter, the third feature parameter and the fourth feature parameter into the trained multivariate Gaussian distribution model, and calculating and generating a probability density function value; the probability density function value is compared with a preset fault judgment threshold value, whether the motor carbon brush breaks down or not is judged, the fault monitoring method and system for the motor carbon brush are achieved, and the problem that a method and a related system capable of conducting real-time fault monitoring on the motor carbon brush do not exist at present is solved.

Description

Technical Field

[0001] The invention relates to the technical field of carbon brush fault monitoring, and in particular to a method and system for monitoring the fault of a motor carbon brush. Background Art

[0002] Carbon brush is a kind of sliding contact part, which is widely used in many motors and generators. It is mainly made of graphite. It transfers energy or signals between the fixed part and the rotor of the motor or generator. It is generally cubic in shape, stuck on the brush holder and pressed by a spring. When the motor rotates, the electrical energy is transmitted to the coil through the commutator. Because its main component is carbon, it is called a carbon brush. It is a consumable that is easy to wear and should be regularly maintained and replaced, and carbon deposits should be cleaned.

[0003] For complex motor equipment or large motor equipment, real-time fault monitoring of motor carbon brushes is required. However, there are currently no methods, related equipment, or systems on the market that can achieve real-time fault monitoring of motor carbon brushes. In addition, if the independent characteristics of the motor carbon brushes are used for fault monitoring, the overall fault condition of the motor carbon brushes cannot be comprehensively determined, which will limit the accuracy of the motor carbon brush fault monitoring. Summary of the invention

[0004] In view of the above-mentioned technical deficiencies, the purpose of the present invention is to provide a method and system for fault monitoring of motor carbon brushes, aiming to solve the problem that there is currently no method and related system that can perform real-time fault monitoring of motor carbon brushes, and that fault detection is performed using the independent characteristics of the motor carbon brushes, and the overall fault condition of the motor carbon brushes cannot be comprehensively determined, resulting in insufficient accuracy in fault monitoring of the motor carbon brushes.

[0005] In view of the above problems, the present application provides a method and system for monitoring faults of motor carbon brushes.

[0006] In a first aspect disclosed in the present application, a method for monitoring a motor carbon brush fault is provided, the method comprising the following steps: Step 1: a temperature sensor device, a current sensor device and a pressure sensor device are arranged in the brush holder corresponding to the carbon brush, wherein the temperature sensor device is used to obtain in real time the temperature of the friction position between the carbon brush and the rotor during the operation of the motor, the current sensor device is used to obtain in real time the current intensity flowing through the carbon brush during the operation of the motor, and the pressure sensor device is used to obtain in real time the elastic pressure of the spring on the carbon brush during the operation of the motor; Step 2: A sound sensor device and a timing device are arranged in the motor housing, wherein the sound sensor device is used to obtain the noise amplitude of the motor in real time during operation, and the timing device is used to obtain the usage time of the current carbon brush in real time, and the timestamp is reset to zero and the timing is restarted after each replacement of the carbon brush; Step 3: Generate a first characteristic parameter by calculating the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the current intensity flowing through the carbon brush during the operation of the motor; generate a second characteristic parameter by calculating the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the elastic pressure of the spring on the carbon brush during the operation of the motor; generate a third characteristic parameter by calculating the noise amplitude during the operation of the motor and the current use time of the carbon brush; and generate a fourth characteristic parameter by calculating the current use time of the carbon brush; Step 4: Input the feature vector composed of the first feature parameter, the second feature parameter, the third feature parameter and the fourth feature parameter into the trained multivariate Gaussian distribution model to calculate and generate a probability density function value; Step 5: Compare the probability density function value with the preset fault judgment threshold to determine whether the motor carbon brush is faulty.

[0007] Preferably, the first characteristic parameter is calculated and generated by the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the current intensity flowing through the carbon brush during the operation of the motor, including: Using formula (1), first calculate the current intensity flowing through the carbon brush during the operation of the motor: The maximum value of the motor carbon brush current The ratio between the carbon brush and the rotor is calculated by adding 4 to the ratio and inputting it into the natural exponential function. The natural exponential function outputs the current reference value and then calculates the temperature of the friction position between the carbon brush and the rotor during the operation of the motor. and the maximum motor rotor temperature The ratio between Then input the cosine function, the cosine function outputs the temperature reference value, and finally multiply the current reference value by the tenth root of the temperature reference value to generate the first characteristic parameter : Formula (1).

[0008] Preferably, the second characteristic parameter is calculated and generated by the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the elastic pressure of the spring on the carbon brush during the operation of the motor, including: Using formula (2), first calculate the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the maximum motor rotor temperature The ratio between Then input the cosine function, the cosine function outputs the temperature reference value, and then the tenth root of the temperature reference value is compared with the elastic pressure of the spring on the carbon brush during the operation of the motor. Multiply to generate the second characteristic parameter : Formula (2).

[0009] Preferably, the third characteristic parameter is calculated and generated by the noise amplitude of the motor during operation and the current usage time of the carbon brush, including: Using formula (3), firstly calculate the current carbon brush usage time The opposite number is input into the natural exponential function, and the output result of the natural exponential function is added by 1 to generate a time reference value, and then the noise amplitude of the motor during operation is calculated. Input the natural exponential function, the natural exponential function outputs the amplitude reference value, and finally calculate the ratio of the time reference value to the amplitude reference value to generate the third characteristic parameter : Formula (3).

[0010] Preferably, the calculation and generation of the fourth characteristic parameter by using the current usage time of the carbon brush comprises: Using formula (4), first set the maximum use time of the carbon brush The usage time of the current carbon brush The difference between the two is input into the natural logarithm function, and then the opposite number of the output result of the natural logarithm function is input into the natural exponential function. Finally, the output result of the natural exponential function is added by 1 and the reciprocal is taken to generate the fourth characteristic parameter. : Formula (4).

[0011] Preferably, the training of the multivariate Gaussian distribution model comprises the following steps: Obtain 1,000 sets of motor carbon brush data for motors that are operating normally and have no carbon brush faults. Each set of motor carbon brush data includes: the temperature of the friction position between the carbon brush and the rotor during the operation of the motor, the current intensity flowing through the carbon brush during the operation of the motor, the elastic pressure of the spring on the carbon brush during the operation of the motor, the noise amplitude during the operation of the motor, and the current use time of the carbon brush; The first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter corresponding to each group of motor carbon brush data are calculated by using formula (1), formula (2), formula (3) and formula (4) to form a characteristic vector corresponding to each group of motor carbon brush data; Calculate the average value of the eigenvectors corresponding to 1000 sets of motor carbon brush data and the covariance matrix ,average value and the covariance matrix The multivariate Gaussian distribution model is constructed.

[0012] Preferably, the step of inputting a feature vector composed of the first feature parameter, the second feature parameter, the third feature parameter and the fourth feature parameter into a trained multivariate Gaussian distribution model to calculate and generate a probability density function value comprises: The first characteristic parameter , the second characteristic parameter , the third characteristic parameter and the fourth characteristic parameter Composition feature vector , input the trained multivariate Gaussian distribution model, and the multivariate Gaussian distribution model uses formula (5) to calculate the probability density function value, where p is used to represent the probability density function value: Formula (5).

[0013] The second aspect disclosed in the present application provides a motor carbon brush fault monitoring system, the system is used for the above-mentioned motor carbon brush fault monitoring method, the system comprises: A first acquisition module, wherein the first acquisition module is used to set a temperature sensor device, a current sensor device and a pressure sensor device in a brush holder corresponding to the carbon brush, wherein the temperature sensor device is used to obtain in real time the temperature of the friction position between the carbon brush and the rotor during the operation of the motor, the current sensor device is used to obtain in real time the current intensity flowing through the carbon brush during the operation of the motor, and the pressure sensor device is used to obtain in real time the elastic pressure of the spring on the carbon brush during the operation of the motor; A second acquisition module, wherein the second acquisition module is used to set a sound sensor device and a timing device in the motor housing, wherein the sound sensor device is used to obtain the noise amplitude of the motor in real time during operation, and the timing device is used to obtain the use time of the current carbon brush in real time, and reset the timestamp to zero and restart the timing after each replacement of the carbon brush; A parameter generation module, the parameter generation module is used to calculate and generate a first characteristic parameter by using the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the current intensity flowing through the carbon brush during the operation of the motor, calculate and generate a second characteristic parameter by using the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the elastic pressure of the spring on the carbon brush during the operation of the motor, calculate and generate a third characteristic parameter by using the noise amplitude during the operation of the motor and the current use time of the carbon brush, and calculate and generate a fourth characteristic parameter by using the current use time of the carbon brush; A calculation module, wherein the calculation module is used to input a feature vector composed of the first feature parameter, the second feature parameter, the third feature parameter and the fourth feature parameter into the trained multivariate Gaussian distribution model, and calculate and generate a probability density function value; The determination module is used to compare the probability density function value with a preset fault determination threshold value to determine whether the motor carbon brush has a fault.

[0014] The beneficial effects of the present invention are: (1) A method and system for fault monitoring of motor carbon brushes is implemented, solving the problem that there is currently no method and related system for real-time fault monitoring of motor carbon brushes.

[0015] (2) The first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter are generated by nonlinear processing of the data, and the various characteristics of the motor carbon brush are integrated to perform fault judgment, thereby solving the problem that the overall fault condition of the motor carbon brush cannot be comprehensively judged by using the independent characteristics of the motor carbon brush for fault monitoring, resulting in insufficient monitoring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 The present invention is an overall flow chart of a method for monitoring faults of motor carbon brushes.

[0018] Figure 2 Schematic diagram of the tenth root function curve of the temperature reference value.

[0019] Figure 3 It is a schematic diagram of the function curve of the fourth characteristic parameter.

[0020] Figure 4 The figure is an overall structural diagram of a motor carbon brush fault monitoring system. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] like Figure 1 As shown, an embodiment of the present application provides a method for monitoring a motor carbon brush fault, the method comprising the following steps: Step 1: a temperature sensor device, a current sensor device and a pressure sensor device are arranged in the brush holder corresponding to the carbon brush, wherein the temperature sensor device is used to obtain in real time the temperature of the friction position between the carbon brush and the rotor during the operation of the motor, the current sensor device is used to obtain in real time the current intensity flowing through the carbon brush during the operation of the motor, and the pressure sensor device is used to obtain in real time the elastic pressure of the spring on the carbon brush during the operation of the motor; Step 2: A sound sensor device and a timing device are arranged in the motor housing, wherein the sound sensor device is used to obtain the noise amplitude of the motor in real time during operation, and the timing device is used to obtain the usage time of the current carbon brush in real time, and the timestamp is reset to zero and the timing is restarted after each replacement of the carbon brush; Step 3: Generate a first characteristic parameter by calculating the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the current intensity flowing through the carbon brush during the operation of the motor; generate a second characteristic parameter by calculating the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the elastic pressure of the spring on the carbon brush during the operation of the motor; generate a third characteristic parameter by calculating the noise amplitude during the operation of the motor and the current use time of the carbon brush; and generate a fourth characteristic parameter by calculating the current use time of the carbon brush; Step 4: Input the feature vector composed of the first feature parameter, the second feature parameter, the third feature parameter and the fourth feature parameter into the trained multivariate Gaussian distribution model to calculate and generate a probability density function value; Step 5: Compare the probability density function value with the preset fault judgment threshold to determine whether the motor carbon brush is faulty.

[0023] Furthermore, the first characteristic parameter is calculated and generated by the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the current intensity flowing through the carbon brush during the operation of the motor, including: Using formula (1), first calculate the current intensity flowing through the carbon brush during the operation of the motor: The maximum value of the motor carbon brush current The ratio between the carbon brush and the rotor is calculated by adding 4 to the ratio and inputting it into the natural exponential function. The natural exponential function outputs the current reference value and then calculates the temperature of the friction position between the carbon brush and the rotor during the operation of the motor. and the maximum motor rotor temperature The ratio between Then input the cosine function, the cosine function outputs the temperature reference value, and finally multiply the current reference value by the tenth root of the temperature reference value to generate the first characteristic parameter : Formula (1).

[0024] Specifically, assuming that the maximum value of the motor rotor temperature is 500 temperature units, the tenth root function curve of the temperature reference value is as follows: Figure 2 As shown, when the temperature of the friction position between the carbon brush and the rotor during the operation of the motor approaches the maximum temperature of the motor rotor, the value of the tenth root of the temperature reference value will decay rapidly, causing the first characteristic parameter to deviate from the normal value range.

[0025] In addition, the change amplitude of the current intensity flowing through the carbon brush during the operation of the motor is usually small. By inputting a natural exponential function and utilizing the exponential explosion effect of the exponential function, this change amplitude can be amplified, making the change of the first characteristic parameter more sensitive.

[0026] Furthermore, the second characteristic parameter is calculated and generated by the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the elastic pressure of the spring on the carbon brush during the operation of the motor, including: Using formula (2), first calculate the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the maximum motor rotor temperature The ratio between Then input the cosine function, the cosine function outputs the temperature reference value, and then the tenth root of the temperature reference value is compared with the elastic pressure of the spring on the carbon brush during the operation of the motor. Multiply to generate the second characteristic parameter : Formula (2).

[0027] Furthermore, the third characteristic parameter is calculated and generated by the noise amplitude of the motor during operation and the current use time of the carbon brush, including: Using formula (3), firstly calculate the current carbon brush usage time The opposite number is input into the natural exponential function, and the output result of the natural exponential function is added by 1 to generate a time reference value, and then the noise amplitude of the motor during operation is calculated. Input the natural exponential function, the natural exponential function outputs the amplitude reference value, and finally calculate the ratio of the time reference value to the amplitude reference value to generate the third characteristic parameter : Formula (3).

[0028] Furthermore, the calculation and generation of the fourth characteristic parameter by using the current usage time of the carbon brush includes: Using formula (4), first set the maximum use time of the carbon brush The usage time of the current carbon brush The difference between the two is input into the natural logarithm function, and then the opposite number of the output result of the natural logarithm function is input into the natural exponential function. Finally, the output result of the natural exponential function is added by 1 and the reciprocal is taken to generate the fourth characteristic parameter. : Formula (4).

[0029] Specifically, assuming that the maximum use time of the carbon brush is 50 time units, the curve of the fourth characteristic parameter function is as follows: Figure 3 As shown, when the current usage time of the carbon brush is close to the maximum usage time of the carbon brush, the value of the fourth characteristic parameter will quickly tend to 0, causing the fourth characteristic parameter to deviate from the normal value range. This operation allows the present invention to directly determine that the carbon brush that has reached the maximum usage time is faulty, thereby improving the accuracy of the present invention.

[0030] Furthermore, the training of the multivariate Gaussian distribution model includes the following steps: Obtain 1,000 sets of motor carbon brush data for motors that are operating normally and have no carbon brush faults. Each set of motor carbon brush data includes: the temperature of the friction position between the carbon brush and the rotor during the operation of the motor, the current intensity flowing through the carbon brush during the operation of the motor, the elastic pressure of the spring on the carbon brush during the operation of the motor, the noise amplitude during the operation of the motor, and the current use time of the carbon brush; The first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter corresponding to each group of motor carbon brush data are calculated by using formula (1), formula (2), formula (3) and formula (4) to form a characteristic vector corresponding to each group of motor carbon brush data; Calculate the average value of the eigenvectors corresponding to 1000 sets of motor carbon brush data and the covariance matrix ,average value and the covariance matrix The multivariate Gaussian distribution model is constructed.

[0031] Furthermore, the step of inputting the feature vector composed of the first feature parameter, the second feature parameter, the third feature parameter and the fourth feature parameter into the trained multivariate Gaussian distribution model to calculate and generate the probability density function value includes: The first characteristic parameter , the second characteristic parameter , the third characteristic parameter and the fourth characteristic parameter Composition feature vector , input the trained multivariate Gaussian distribution model, and the multivariate Gaussian distribution model uses formula (5) to calculate the probability density function value, where p is used to represent the probability density function value: Formula (5).

[0032] Specifically, the feature vectors corresponding to 1000 sets of motor carbon brush data are input into the trained multivariate Gaussian distribution model, and the minimum value of all the probability density function values ​​generated is the preset fault judgment threshold described in step 5.

[0033] In summary, the motor carbon brush fault monitoring method provided by the embodiment of the present application has the following technical effects: (1) A method and system for fault monitoring of motor carbon brushes is implemented, solving the problem that there is currently no method and related system for real-time fault monitoring of motor carbon brushes.

[0034] (2) The first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter are generated by nonlinear processing of the data, and the various characteristics of the motor carbon brush are integrated to perform fault judgment, thereby solving the problem that the overall fault condition of the motor carbon brush cannot be comprehensively judged by using the independent characteristics of the motor carbon brush for fault monitoring, resulting in insufficient monitoring accuracy.

[0035] Based on the same inventive concept as the method for monitoring the fault of a motor carbon brush in the aforementioned embodiment, Figure 4 As shown, the present application provides a motor carbon brush fault monitoring system, the system comprising: A first acquisition module, wherein the first acquisition module is used to set a temperature sensor device, a current sensor device and a pressure sensor device in a brush holder corresponding to the carbon brush, wherein the temperature sensor device is used to obtain in real time the temperature of the friction position between the carbon brush and the rotor during the operation of the motor, the current sensor device is used to obtain in real time the current intensity flowing through the carbon brush during the operation of the motor, and the pressure sensor device is used to obtain in real time the elastic pressure of the spring on the carbon brush during the operation of the motor; A second acquisition module, wherein the second acquisition module is used to set a sound sensor device and a timing device in the motor housing, wherein the sound sensor device is used to obtain the noise amplitude of the motor in real time during operation, and the timing device is used to obtain the use time of the current carbon brush in real time, and reset the timestamp to zero and restart the timing after each replacement of the carbon brush; A parameter generation module, the parameter generation module is used to calculate and generate a first characteristic parameter by using the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the current intensity flowing through the carbon brush during the operation of the motor, calculate and generate a second characteristic parameter by using the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the elastic pressure of the spring on the carbon brush during the operation of the motor, calculate and generate a third characteristic parameter by using the noise amplitude during the operation of the motor and the current use time of the carbon brush, and calculate and generate a fourth characteristic parameter by using the current use time of the carbon brush; A calculation module, wherein the calculation module is used to input a feature vector composed of the first feature parameter, the second feature parameter, the third feature parameter and the fourth feature parameter into the trained multivariate Gaussian distribution model, and calculate and generate a probability density function value; The determination module is used to compare the probability density function value with a preset fault determination threshold value to determine whether the motor carbon brush has a fault.

[0036] Through the above-mentioned detailed description of a motor carbon brush fault monitoring method in this specification, those skilled in the art can clearly know a motor carbon brush fault monitoring system in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0037] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0038] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring the fault of a motor carbon brush, characterized in that: The method comprises the following steps: Step 1: a temperature sensor device, a current sensor device and a pressure sensor device are arranged in the brush holder corresponding to the carbon brush, wherein the temperature sensor device is used to obtain in real time the temperature of the friction position between the carbon brush and the rotor during the operation of the motor, the current sensor device is used to obtain in real time the current intensity flowing through the carbon brush during the operation of the motor, and the pressure sensor device is used to obtain in real time the elastic pressure of the spring on the carbon brush during the operation of the motor; Step 2: A sound sensor device and a timing device are arranged in the motor housing, wherein the sound sensor device is used to obtain the noise amplitude of the motor in real time during operation, and the timing device is used to obtain the usage time of the current carbon brush in real time, and the timestamp is reset to zero and the timing is restarted after each replacement of the carbon brush; Step 3: Generate a first characteristic parameter by calculating the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the current intensity flowing through the carbon brush during the operation of the motor; generate a second characteristic parameter by calculating the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the elastic pressure of the spring on the carbon brush during the operation of the motor; generate a third characteristic parameter by calculating the noise amplitude during the operation of the motor and the current use time of the carbon brush; and generate a fourth characteristic parameter by calculating the current use time of the carbon brush; Step 4: Input the feature vector composed of the first feature parameter, the second feature parameter, the third feature parameter and the fourth feature parameter into the trained multivariate Gaussian distribution model to calculate and generate a probability density function value; Step 5: Compare the probability density function value with the preset fault judgment threshold to determine whether the motor carbon brush is faulty.

2. A method for monitoring a motor carbon brush fault as claimed in claim 1, characterized in that: The first characteristic parameter is generated by calculating the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the current intensity flowing through the carbon brush during the operation of the motor, including: Using formula (1), first calculate the current intensity flowing through the carbon brush during the operation of the motor: Maximum value of motor carbon brush current The ratio between the carbon brush and the rotor is calculated by adding 4 to the ratio and inputting it into the natural exponential function. The natural exponential function outputs the current reference value and then calculates the temperature of the friction position between the carbon brush and the rotor during the operation of the motor. and the maximum motor rotor temperature The ratio between Then input the cosine function, the cosine function outputs the temperature reference value, and finally multiply the current reference value by the tenth root of the temperature reference value to generate the first characteristic parameter : Formula (1).

3. A method for monitoring a motor carbon brush fault as claimed in claim 2, characterized in that: The second characteristic parameter is calculated and generated by the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the elastic pressure of the spring on the carbon brush during the operation of the motor, including: Using formula (2), first calculate the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the maximum motor rotor temperature The ratio between Then input the cosine function, the cosine function outputs the temperature reference value, and then the tenth root of the temperature reference value is compared with the elastic pressure of the spring on the carbon brush during the operation of the motor. Multiply to generate the second characteristic parameter : Formula (2).

4. A method for monitoring a motor carbon brush fault as claimed in claim 3, characterized in that: The third characteristic parameter is generated by calculating the noise amplitude of the motor during operation and the current use time of the carbon brush, including: Using formula (3), firstly calculate the current carbon brush usage time The opposite number is input into the natural exponential function, and the output result of the natural exponential function is added by 1 to generate a time reference value, and then the noise amplitude of the motor during operation is calculated. Input the natural exponential function, the natural exponential function outputs the amplitude reference value, and finally calculate the ratio of the time reference value to the amplitude reference value to generate the third characteristic parameter : Formula (3).

5. A method for monitoring a motor carbon brush fault as claimed in claim 4, characterized in that: The fourth characteristic parameter is generated by calculating the current usage time of the carbon brush, including: Using formula (4), first set the maximum use time of the carbon brush The usage time of the current carbon brush The difference between the two is input into the natural logarithm function, and then the opposite number of the output result of the natural logarithm function is input into the natural exponential function. Finally, the output result of the natural exponential function is added by 1 and the reciprocal is taken to generate the fourth characteristic parameter. : Formula (4).

6. A method for monitoring a motor carbon brush fault as claimed in claim 5, characterized in that: The training of the multivariate Gaussian distribution model comprises the following steps: Obtain 1,000 sets of motor carbon brush data for motors that are operating normally and have no carbon brush faults. Each set of motor carbon brush data includes: the temperature of the friction position between the carbon brush and the rotor during the operation of the motor, the current intensity flowing through the carbon brush during the operation of the motor, the elastic pressure of the spring on the carbon brush during the operation of the motor, the noise amplitude during the operation of the motor, and the current use time of the carbon brush; The first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter corresponding to each group of motor carbon brush data are calculated by using formula (1), formula (2), formula (3) and formula (4) to form a characteristic vector corresponding to each group of motor carbon brush data; Calculate the average value of the eigenvectors corresponding to 1000 sets of motor carbon brush data and the covariance matrix ,average value and the covariance matrix The multivariate Gaussian distribution model is constructed.

7. A method for monitoring a motor carbon brush fault as claimed in claim 6, characterized in that: The step of inputting a feature vector composed of the first feature parameter, the second feature parameter, the third feature parameter and the fourth feature parameter into the trained multivariate Gaussian distribution model and calculating and generating a probability density function value comprises: The first characteristic parameter , the second characteristic parameter , the third characteristic parameter and the fourth characteristic parameter Composition feature vector , input the trained multivariate Gaussian distribution model, and the multivariate Gaussian distribution model uses formula (5) to calculate the probability density function value, where p is used to represent the probability density function value: Formula (5).

8. A motor carbon brush fault monitoring system, the system comprising: A first acquisition module, wherein the first acquisition module is used to set a temperature sensor device, a current sensor device and a pressure sensor device in a brush holder corresponding to the carbon brush, wherein the temperature sensor device is used to obtain in real time the temperature of the friction position between the carbon brush and the rotor during the operation of the motor, the current sensor device is used to obtain in real time the current intensity flowing through the carbon brush during the operation of the motor, and the pressure sensor device is used to obtain in real time the elastic pressure of the spring on the carbon brush during the operation of the motor; A second acquisition module, wherein the second acquisition module is used to set a sound sensor device and a timing device in the motor housing, wherein the sound sensor device is used to obtain the noise amplitude of the motor in real time during operation, and the timing device is used to obtain the use time of the current carbon brush in real time, and reset the timestamp to zero and restart the timing after each replacement of the carbon brush; A parameter generation module, the parameter generation module is used to calculate and generate a first characteristic parameter by using the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the current intensity flowing through the carbon brush during the operation of the motor, calculate and generate a second characteristic parameter by using the temperature of the friction position between the carbon brush and the rotor during the operation of the motor and the elastic pressure of the spring on the carbon brush during the operation of the motor, calculate and generate a third characteristic parameter by using the noise amplitude during the operation of the motor and the current use time of the carbon brush, and calculate and generate a fourth characteristic parameter by using the current use time of the carbon brush; A calculation module, wherein the calculation module is used to input a feature vector composed of the first feature parameter, the second feature parameter, the third feature parameter and the fourth feature parameter into the trained multivariate Gaussian distribution model, and calculate and generate a probability density function value; The determination module is used to compare the probability density function value with a preset fault determination threshold value to determine whether the motor carbon brush has a fault.

Images