A method and system for monitoring faults of motor carbon brushes

Abstract

The present invention discloses a fault monitoring method and system for a motor carbon brush, comprising: arranging a temperature sensor device, a current sensor device and a pressure sensor device in a brush holder corresponding to the carbon brush; arranging a sound sensor device and a timing device in a motor housing; generating a first characteristic parameter, a second characteristic parameter, a third characteristic parameter and a fourth characteristic parameter by calculating data obtained by the above-mentioned sensor devices; inputting a characteristic vector composed of the first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter into a trained multivariate Gaussian distribution model to calculate and generate a probability density function value; comparing the probability density function value with a preset fault judgment threshold to determine whether the motor carbon brush has a fault. The present invention realizes a fault monitoring method and system for a motor carbon brush, and solves the problem that there is currently no method and related system for real-time fault monitoring of motor carbon brushes.

Description

Technical Field

[0001] The present 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] A carbon brush is a sliding contact part that is widely used in many motors and generators. It is mainly made of graphite and transmits 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 item that is easy to wear and should be maintained and replaced regularly, and carbon deposits should be cleaned.

[0003] For complex or large motor equipment, real-time fault monitoring of the 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 individual 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 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 each motor carbon brush, but it is impossible to comprehensively determine the overall fault condition of the motor carbon brush, which will cause the problem of insufficient accuracy of fault monitoring of the motor carbon brushes.

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

[0006] The present application discloses a first aspect, which provides a method for monitoring a motor carbon brush fault, comprising the following steps:

[0007] Step 1: Install a temperature sensor device, a current sensor device, and a pressure sensor device in the brush holder corresponding to the carbon brush. The temperature sensor device is used to obtain the temperature of the friction position between the carbon brush and the rotor in real time during the operation of the motor. The current sensor device is used to obtain the current intensity flowing through the carbon brush in real time during the operation of the motor. The pressure sensor device is used to obtain the elastic pressure of the spring on the carbon brush in real time during the operation of the motor.

[0008] Step 2: Install a sound sensor device and a timing device in the motor housing. 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 current carbon brush usage time in real time. After each carbon brush replacement, the timestamp is reset to zero and the timing is restarted.

[0009] Step 3: Calculate and generate a first characteristic parameter based on the temperature of the friction point 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 based on the temperature of the friction point 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 based on the noise amplitude during the operation of the motor and the current usage time of the carbon brush; and calculate and generate a fourth characteristic parameter based on the current usage time of the carbon brush;

[0010] 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;

[0011] Step 5: Compare the probability density function value with the preset fault judgment threshold to determine whether the motor carbon brush is faulty.

[0012] Preferably, the first characteristic parameter is calculated based on 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, and includes:

[0013] Using formula (1), first calculate the current intensity flowing through the carbon brush during the operation of the motor and 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 :

[0014] Formula (1).

[0015] Preferably, the second 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 elastic pressure of the spring on the carbon brush during the operation of the motor, including:

[0016] 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 :

[0017] Formula (2).

[0018] Preferably, the calculation and generation of the third characteristic parameter by using the noise amplitude during the operation of the motor and the current usage time of the carbon brush includes:

[0019] Using formula (3), first calculate the current carbon brush usage time The opposite number is input into the natural exponential function, and the output 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 :

[0020] Formula (3).

[0021] Preferably, the calculation and generation of the fourth characteristic parameter based on the current carbon brush usage time includes:

[0022] Using formula (4), first set the maximum service life of the carbon brush to 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. :

[0023] Formula (4).

[0024] Preferably, the training of the multivariate Gaussian distribution model comprises the following steps:

[0025] Obtain 1000 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 brush-rotor friction point during motor operation, the current intensity flowing through the brush during motor operation, the elastic pressure of the spring on the brush during motor operation, the noise amplitude during motor operation, and the current usage time of the brush;

[0026] The first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter corresponding to each set of motor carbon brush data are calculated using formula (1), formula (2), formula (3) and formula (4) to form a characteristic vector corresponding to each set of motor carbon brush data;

[0027] 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.

[0028] 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 the trained multivariate Gaussian distribution model to calculate and generate a probability density function value comprises:

[0029] 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:

[0030] Formula (5).

[0031] A second aspect disclosed in the present application provides a motor carbon brush fault monitoring system, which is used in the above-mentioned motor carbon brush fault monitoring method, and includes:

[0032] a first acquisition module, wherein the first acquisition module is configured 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 configured to obtain in real time the temperature of the friction position between the carbon brush and the rotor during operation of the motor, the current sensor device is configured to obtain in real time the current intensity flowing through the carbon brush during operation of the motor, and the pressure sensor device is configured to obtain in real time the elastic pressure of the spring on the carbon brush during operation of the motor;

[0033] a second acquisition module, wherein the second acquisition module is configured to set a sound sensor device and a timing device in the motor housing, wherein the sound sensor device is configured to obtain the noise amplitude of the motor in real time during operation, and the timing device is configured to obtain the usage time of the current carbon brush in real time, and reset the timestamp to zero and restart the timing after each carbon brush replacement;

[0034] a parameter generation module, the parameter generation module being configured to calculate and generate a first characteristic parameter based on a temperature at a friction point between the carbon brush and the rotor during operation of the motor and an intensity of a current flowing through the carbon brush during operation of the motor; calculate and generate a second characteristic parameter based on a temperature at a friction point between the carbon brush and the rotor during operation of the motor and an elastic pressure of a spring on the carbon brush during operation of the motor; calculate and generate a third characteristic parameter based on a noise amplitude during operation of the motor and a current usage time of the carbon brush; and calculate and generate a fourth characteristic parameter based on the current usage time of the carbon brush;

[0035] a calculation module, the calculation module being configured to input a feature vector consisting 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;

[0036] The determination module is used to compare the probability density function value with a preset fault determination threshold to determine whether the motor carbon brush has a fault.

[0037] The beneficial effects of the present invention are:

[0038] (1) A fault monitoring method and system for motor carbon brushes are implemented, solving the problem that there are currently no methods and related systems that can perform real-time fault monitoring on motor carbon brushes.

[0039] (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

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0041] Figure 1 The figure is an overall flow chart of a method for monitoring faults of motor carbon brushes.

[0042] Figure 2 Schematic diagram of the tenth root function curve of the temperature reference value.

[0043] Figure 3 Schematic diagram of the function curve of the fourth characteristic parameter.

[0044] Figure 4This is the overall structure diagram of a motor carbon brush fault monitoring system. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0046] like Figure 1 As shown, an embodiment of the present application provides a method for monitoring faults of a motor carbon brush, the method comprising the following steps:

[0047] Step 1: Install a temperature sensor device, a current sensor device, and a pressure sensor device in the brush holder corresponding to the carbon brush. The temperature sensor device is used to obtain the temperature of the friction position between the carbon brush and the rotor in real time during the operation of the motor. The current sensor device is used to obtain the current intensity flowing through the carbon brush in real time during the operation of the motor. The pressure sensor device is used to obtain the elastic pressure of the spring on the carbon brush in real time during the operation of the motor.

[0048] Step 2: Install a sound sensor device and a timing device in the motor housing. 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 current carbon brush usage time in real time. After each carbon brush replacement, the timestamp is reset to zero and the timing is restarted.

[0049] Step 3: Calculate and generate a first characteristic parameter based on the temperature of the friction point 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 based on the temperature of the friction point 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 based on the noise amplitude during the operation of the motor and the current usage time of the carbon brush; and calculate and generate a fourth characteristic parameter based on the current usage time of the carbon brush;

[0050] 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;

[0051] Step 5: Compare the probability density function value with the preset fault judgment threshold to determine whether the motor carbon brush is faulty.

[0052] Furthermore, the calculation of the first characteristic parameter based on 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 includes:

[0053] Using formula (1), first calculate the current intensity flowing through the carbon brush during the operation of the motor and 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 :

[0054] Formula (1).

[0055] 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.

[0056] 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.

[0057] Furthermore, the second 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 elastic pressure of the spring on the carbon brush during the operation of the motor, including:

[0058] 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 :

[0059] Formula (2).

[0060] Furthermore, the calculation of the third characteristic parameter based on the noise amplitude during the operation of the motor and the current usage time of the carbon brush includes:

[0061] Using formula (3), first calculate the current carbon brush usage time The opposite number is input into the natural exponential function, and the output 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 :

[0062] Formula (3).

[0063] Furthermore, the calculation and generation of the fourth characteristic parameter based on the current carbon brush usage time includes:

[0064] Using formula (4), first set the maximum service life of the carbon brush to 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. :

[0065] Formula (4).

[0066] Specifically, assuming that the maximum service life 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 carbon brush usage time is close to the maximum usage time of the carbon brush, the value of the fourth characteristic parameter will quickly approach 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.

[0067] Furthermore, the training of the multivariate Gaussian distribution model includes the following steps:

[0068] Obtain 1000 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 brush-rotor friction point during motor operation, the current intensity flowing through the brush during motor operation, the elastic pressure of the spring on the brush during motor operation, the noise amplitude during motor operation, and the current usage time of the brush;

[0069] The first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter corresponding to each set of motor carbon brush data are calculated using formula (1), formula (2), formula (3) and formula (4) to form a characteristic vector corresponding to each set of motor carbon brush data;

[0070] 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.

[0071] 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 a probability density function value includes:

[0072] 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:

[0073] Formula (5).

[0074] 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.

[0075] In summary, the motor carbon brush fault monitoring method provided by the embodiment of the present application has the following technical effects:

[0076] (1) A fault monitoring method and system for motor carbon brushes are implemented, solving the problem that there are currently no methods and related systems that can perform real-time fault monitoring on motor carbon brushes.

[0077] (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.

[0078] Based on the same inventive concept as the fault monitoring method of a motor carbon brush in the above embodiment, Figure 4 As shown, the present application provides a motor carbon brush fault monitoring system, the system comprising:

[0079] a first acquisition module, wherein the first acquisition module is configured 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 configured to obtain in real time the temperature of the friction position between the carbon brush and the rotor during operation of the motor, the current sensor device is configured to obtain in real time the current intensity flowing through the carbon brush during operation of the motor, and the pressure sensor device is configured to obtain in real time the elastic pressure of the spring on the carbon brush during operation of the motor;

[0080] a second acquisition module, wherein the second acquisition module is configured to set a sound sensor device and a timing device in the motor housing, wherein the sound sensor device is configured to obtain the noise amplitude of the motor in real time during operation, and the timing device is configured to obtain the usage time of the current carbon brush in real time, and reset the timestamp to zero and restart the timing after each carbon brush replacement;

[0081] a parameter generation module, the parameter generation module being configured to calculate and generate a first characteristic parameter based on a temperature at a friction point between the carbon brush and the rotor during operation of the motor and an intensity of a current flowing through the carbon brush during operation of the motor; calculate and generate a second characteristic parameter based on a temperature at a friction point between the carbon brush and the rotor during operation of the motor and an elastic pressure of a spring on the carbon brush during operation of the motor; calculate and generate a third characteristic parameter based on a noise amplitude during operation of the motor and a current usage time of the carbon brush; and calculate and generate a fourth characteristic parameter based on the current usage time of the carbon brush;

[0082] a calculation module, the calculation module being configured to input a feature vector consisting 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;

[0083] The determination module is used to compare the probability density function value with a preset fault determination threshold to determine whether the motor carbon brush has a fault.

[0084] Through the detailed description of the fault monitoring method of a motor carbon brush in the foregoing specification, those skilled in the art can clearly understand the fault monitoring system of a motor carbon brush in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For relevant details, please refer to the method section.

[0085] The technical features of the above embodiments can 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.

[0086] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one 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 is not limited to the embodiments shown herein, but is intended to 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: Install a temperature sensor device, a current sensor device, and a pressure sensor device in the brush holder corresponding to the carbon brush. The temperature sensor device is used to obtain the temperature of the friction position between the carbon brush and the rotor in real time during the operation of the motor. The current sensor device is used to obtain the current intensity flowing through the carbon brush in real time during the operation of the motor. The pressure sensor device is used to obtain the elastic pressure of the spring on the carbon brush in real time during the operation of the motor. Step 2: Install a sound sensor device and a timing device in the motor housing. 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 current carbon brush usage time in real time. After each carbon brush replacement, the timestamp is reset to zero and the timing is restarted. Step 3: Calculate and generate a first characteristic parameter based on the temperature of the friction point 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 based on the temperature of the friction point 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 based on the noise amplitude during the operation of the motor and the current usage time of the carbon brush; and calculate and generate a fourth characteristic parameter based on the current usage time of the carbon brush; in: 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 and 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); The second 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 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); The third characteristic parameter is generated by calculating the noise amplitude during the operation of the motor and the current usage time of the carbon brush, including: Using formula (3), first calculate the current carbon brush usage time The opposite number is input into the natural exponential function, and the output 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); The calculation and generation of the fourth characteristic parameter based on the current carbon brush usage time includes: Using formula (4), first set the maximum service life of the carbon brush to 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); 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 motor carbon brush fault monitoring method according to claim 1, characterized in that: The training of the multivariate Gaussian distribution model includes the following steps: Obtain 1000 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 brush-rotor friction point during motor operation, the current intensity flowing through the brush during motor operation, the elastic pressure of the spring on the brush during motor operation, the noise amplitude during motor operation, and the current usage time of the brush; The first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter corresponding to each set of motor carbon brush data are calculated using formula (1), formula (2), formula (3) and formula (4) to form a characteristic vector corresponding to each set 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.

3. A method for monitoring a motor carbon brush fault as claimed in claim 2, 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).

4. A motor carbon brush fault monitoring system, the system comprising: a first acquisition module, wherein the first acquisition module is configured 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 configured to obtain in real time the temperature of the friction position between the carbon brush and the rotor during operation of the motor, the current sensor device is configured to obtain in real time the current intensity flowing through the carbon brush during operation of the motor, and the pressure sensor device is configured to obtain in real time the elastic pressure of the spring on the carbon brush during operation of the motor; a second acquisition module, wherein the second acquisition module is configured to set a sound sensor device and a timing device in the motor housing, wherein the sound sensor device is configured to obtain the noise amplitude of the motor in real time during operation, and the timing device is configured to obtain the usage time of the current carbon brush in real time, and reset the timestamp to zero and restart the timing after each carbon brush replacement; a parameter generation module, the parameter generation module being configured to calculate and generate a first characteristic parameter based on a temperature at a friction point between the carbon brush and the rotor during operation of the motor and an intensity of a current flowing through the carbon brush during operation of the motor; calculate and generate a second characteristic parameter based on a temperature at a friction point between the carbon brush and the rotor during operation of the motor and an elastic pressure of a spring on the carbon brush during operation of the motor; calculate and generate a third characteristic parameter based on a noise amplitude during operation of the motor and a current usage time of the carbon brush; and calculate and generate a fourth characteristic parameter based on the current usage time of the carbon brush; in: 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 and 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); The second 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 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); The third characteristic parameter is generated by calculating the noise amplitude during the operation of the motor and the current usage time of the carbon brush, including: Using formula (3), first calculate the current carbon brush usage time The opposite number is input into the natural exponential function, and the output 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); The calculation and generation of the fourth characteristic parameter based on the current carbon brush usage time includes: Using formula (4), first set the maximum service life of the carbon brush to 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); a calculation module, the calculation module being configured to input a feature vector consisting 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 to determine whether the motor carbon brush has a fault.

Images