Motor fault warning method, system, device and storage medium

Abstract

The present invention relates to a motor fault early warning method, which includes the following steps: obtaining the actual working data of the motor, and comparing the actual working data with the rated working parameters to calculate the actual deviation data; calculating the actual output power of the motor according to the actual working data; based on the calculated actual output power value and the power deviation value of the rated output power in the rated working parameters; predicting the power deviation value by self-learning the power deviation value data set based on a preset self-learning algorithm to generate a predicted power deviation value; calculating the actual output power value and the predicted power deviation value to obtain a power fluctuation value, and comparing the power fluctuation value with a preset fluctuation threshold value, if the power fluctuation value reaches the fluctuation threshold value, generating a fault early warning report based on the heat dissipation efficiency detection result and issuing a motor fault early warning prompt. The present application has the effect of improving the timeliness of motor fault early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of motor fault detection, and in particular to a motor fault early warning method, system, equipment and storage medium. Background Art

[0002] As a commonly used power source in the industrial field, electric motors play a very important role in industrial production. Monitoring electric motors and issuing fault warning prompts is an important part of industrial production.

[0003] Existing fault monitoring of electric motors in industrial production includes: vibration analysis (installing vibration sensors and monitoring the vibration characteristics of the motor during operation to detect bearing wear, imbalance, shaft bending and other faults); temperature monitoring (installing temperature sensors and monitoring the temperature changes of various components of the motor to detect insulation aging, overload, cooling system failure and other problems); current and voltage monitoring (monitoring the current and voltage waveforms of the motor to diagnose short circuits, open circuits, phase imbalance and other faults).

[0004] Regarding the above-mentioned related technologies, there are the following defects: the existing motor fault detection methods mainly rely on a single monitoring method, each method has its limitations, and the existing fault monitoring methods are difficult to comprehensively and accurately diagnose various potential faults of the motor, especially in the early stage of the fault or in the case of multiple faults. It is difficult to detect or predict the fault of the motor in time, thereby reducing the timeliness of the motor fault warning, so it needs to be improved. Summary of the invention

[0005] In order to improve the timeliness of motor fault warning, the present application provides a motor fault warning method, system, device and storage medium.

[0006] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions:

[0007] A motor fault early warning method, the method comprising the following steps:

[0008] Acquire real-time heat dissipation data of the motor, and compare the real-time heat dissipation data with preset reference heat dissipation parameters to generate a heat dissipation efficiency detection result;

[0009] Acquiring actual working data of the motor, and comparing the actual working data with the rated working parameters to calculate actual deviation data;

[0010] Calculate the actual output power P of the motor according to the actual working data 实际 , the calculation formula of actual output power is as follows: Among them, P 实际is the actual output power, T is the electromagnetic torque, ω is the angular velocity, m is the power correction factor, and the power correction factor is used to correct the calculated value of the actual output power, C is the preset torque coefficient, Φ is the air gap magnetic flux; I is the current conversion value of the motor circuit, and cosφ is the power factor of the motor circuit;

[0011] According to the calculated actual output power value and the power deviation value of the rated output power in the rated working parameter, and based on the start timestamp and the historical power deviation value association, a power deviation value data set is constructed, and each opening and closing is regarded as a start timestamp cycle;

[0012] The power deviation value data set is input into a preset power deviation value prediction model, and the power deviation value prediction performs self-learning on the power deviation value data set based on a preset self-learning algorithm to generate a predicted power deviation value, and the predicted power deviation value is used as a deviation reference value for subsequent operation of the motor;

[0013] The actual output power value and the predicted power deviation value are calculated to obtain a power fluctuation value, and the power fluctuation value is compared with a preset fluctuation threshold value. If the power fluctuation value reaches the fluctuation threshold value, a fault warning report is generated based on the heat dissipation efficiency detection result and a motor fault warning prompt is issued.

[0014] By adopting the above technical solution, the heat dissipation of the motor is monitored in real time and the heat dissipation efficiency test results are generated, the heat dissipation problem is discovered in time, and the motor is prevented from being damaged or reducing performance due to overheating, which is helpful to improve the reliability and service life of the motor. The actual deviation data is calculated to understand the difference between the actual working state of the motor and the preset rated state. The actual output power of the motor is calculated by the calculation formula of the actual output power. The power size provided by the motor in actual work is calculated from multiple dimensions, and this helps to evaluate the working state and performance of the motor, providing a basis for subsequent fault warning and maintenance. The power fluctuation is obtained by calculating the actual output power value and the predicted power deviation value. The power fluctuation value is used to remind the operator to pay attention to possible faults in the motor. Compared with the existing method of issuing a motor fault warning prompt only when a fault in a certain aspect of the motor is detected, this solution calculates the power fluctuation value through multi-dimensional working data, and compares the power fluctuation value with the preset fluctuation threshold value to achieve real-time monitoring of the motor's working status and fault warning prediction. The subsequent working status of the motor is predicted in advance through the real-time working data of the motor, and it is determined whether there is a risk of failure, which is convenient for operation and maintenance personnel to plan maintenance opportunities in advance to inspect and repair the motor, thereby avoiding production suspension caused by motor failure, reducing the impact of failure on the production process, and thus improving production efficiency.

[0015] In a preferred example, the present application can be further configured as follows: after the actual output power value calculated and the power deviation value of the rated output power in the rated working parameters are associated with the historical power deviation value based on the start timestamp to construct a power deviation value data set, and each start and close is taken as a start timestamp cycle, the actual working data includes actual air gap magnetic flux data, and the rated working parameters include rated air gap magnetic flux parameters, including the following steps:

[0016] Comparing and calculating the actual air gap magnetic flux data with the rated air gap magnetic flux parameters to obtain air gap magnetic flux deviation data;

[0017] Associating the historical air gap magnetic flux deviation data with the power deviation value based on the startup timestamp, and constructing a magnetic flux-power deviation database;

[0018] The preset deviation factor calculation model generates a flux factor based on the flux-power deviation database analysis;

[0019] The preset air gap flux model is analyzed based on the historical actual air gap flux data to generate a predicted air gap flux;

[0020] The power deviation value prediction model generates a first corrected power deviation prediction value based on the magnetic flux factor and the predicted air gap magnetic flux, and the first corrected power deviation prediction value is used to calibrate the predicted power deviation value.

[0021] By adopting the above technical solution, the historical air gap flux deviation data is associated with the corresponding power deviation value according to the startup timestamp, and each opening and closing operation can be regarded as a startup timestamp cycle. The air gap flux deviation data in the cycle is associated with the power deviation value. Through such association, a flux-power deviation database is constructed. By constructing a flux-power deviation database, the relationship between the air gap flux deviation and the power deviation of the motor in different time periods is recorded. This is helpful to analyze the influence of the air gap flux on the power deviation, and provide data support for the subsequent flux factor calculation and power deviation prediction. The deviation factor calculation model is based on the analysis of the flux-power deviation database to calculate the flux factor. The flux factor represents the relationship between the actual air gap flux and the power deviation, which can be used to calibrate the predicted power deviation value. By calculating the flux factor, the influence of the actual air gap flux on the power deviation can be more accurately reflected, thereby improving the prediction accuracy of this scheme and reducing the misjudgment of faults. This scheme makes predictions based on the trend, periodicity or other characteristics of historical data and generates a predicted air gap flux, which can predict the future air gap flux situation to a certain extent and provide more accurate input for the prediction and calibration of the power deviation value.

[0022] In a preferred example, the present application can be further configured as follows: after the actual output power value and the power deviation value of the rated output power in the rated working parameters are calculated and associated with the historical power deviation value based on the start timestamp to construct a power deviation value data set, and each start and close is taken as a start timestamp cycle, the actual working data includes the actual current conversion value, and the rated working parameters include the rated current conversion value, including the following steps:

[0023] Comparing the actual current conversion value with the rated current conversion value to obtain a current fluctuation value;

[0024] Sort the historical current fluctuation values ​​based on the startup timestamp and construct a current fluctuation value database;

[0025] The preset current fluctuation monitoring model analyzes the historical current fluctuation values ​​based on the current fluctuation value database to generate a current correction factor, wherein the current correction factor is used to set the current fluctuation extreme value, and the current fluctuation extreme value is set based on the current correction factor and the rated current conversion value;

[0026] When the current fluctuation value reaches the current fluctuation extreme value, a current fault report is generated and a motor current fault warning is issued.

[0027] By adopting the above technical solution, using the preset current fluctuation monitoring model, analysis is performed based on the current fluctuation value database to calculate the current correction factor, and the current correction factor can be used to set the extreme value of the current fluctuation. By combining with the rated current conversion value, the extreme value range of the current fluctuation is set. By generating the current correction factor and setting the current fluctuation extreme value, the current fluctuation can be monitored more accurately, which helps to timely discover abnormal current fluctuations, warn of potential current faults, and take corresponding maintenance measures to improve the reliability and service life of the motor. The monitored current fluctuation value is compared with the set current fluctuation extreme value. When the current fluctuation value exceeds or reaches the current fluctuation extreme value, a current fault report is generated and a warning signal of the motor current fault is issued. In the embodiment of the present application, a threshold is set and combined with a fault judgment algorithm to determine whether the current fluctuation value exceeds or reaches the current fluctuation extreme value. Through the current fault warning, the abnormal current fluctuation of the motor is discovered in time, and potential current faults are warned in advance.

[0028] In a preferred example, the present application can be further configured as follows: calculating the actual output power P of the motor according to the actual working data 实际 , the calculation formula of actual output power is as follows: This step includes the following steps:

[0029] The power correction factor m is calculated based on the magnetic flux factor and the current correction factor, wherein the calculation formula of the power correction factor m is: Where c is the flux factor and p is the current correction factor.

[0030] By adopting the above technical solution, the power correction factor m is used to quantitatively evaluate the correlation between the magnetic flux factor and the current correction factor, and to verify the correlation between the magnetic flux factor and the current correction factor to determine whether there is a linear or nonlinear relationship between the magnetic flux factor and the current correction factor, and further confirm the degree of influence of the magnetic flux factor and the current correction factor on the actual output power, and whether there is an influence of other factors; thereby improving the accuracy of the actual output power calculation.

[0031] In a preferred example, the present application can be further configured as follows: in the step of obtaining the real-time heat dissipation data of the motor and comparing the real-time heat dissipation data with the preset reference heat dissipation parameters to generate the heat dissipation efficiency detection result, the steps are as follows:

[0032] Acquire external initial image data and external real-time image data of the motor, and compare the external real-time image data with the external initial image data to analyze the real-time thermal insulation status of the motor, and generate a motor housing cleaning warning based on the real-time thermal insulation status.

[0033] By adopting the above technical solution, the initial image data and real-time image data of the motor's exterior are obtained, and comparative analysis is performed through image processing technology to identify the contamination condition and insulation status of the motor casing. When casing contamination is found, a cleaning warning is generated. Compared with the existing manual inspection of the motor's external contamination condition, this solution is real-time, and the automated reminder improves the real-time nature of monitoring, reduces the necessity of worker inspections, and improves the safety of industrial production.

[0034] In a preferred example, the present application can be further configured as follows: in the step of acquiring the external initial image data and the external real-time image data of the motor, and comparing the external real-time image data with the external initial image data to analyze the real-time thermal insulation state of the motor, and generating a motor housing cleaning warning according to the real-time thermal insulation state, the steps are as follows:

[0035] Extracting image features of the external initial image data, and marking parts of the external initial image data according to the image features, wherein the part marking includes marking the housing, exhaust holes and hole positions of the motor;

[0036] Extracting grayscale values ​​of the external initial image data and the external real-time image data, and comparing the grayscale value of the external real-time image data with the grayscale value of the external initial image data to determine whether there is external contamination of the motor;

[0037] If there is external contamination, it is associated with the location mark to generate an early warning for cleaning the motor housing.

[0038] By adopting the above technical solution, the position and characteristics of the motor housing and related components are accurately identified through the image recognition algorithm, the motor is marked according to the image characteristics, and the motor housing, exhaust holes and hole positions are automatically marked. In other embodiments, other parts can be marked according to the motor housing structure to provide accurate basic data for subsequent pollution analysis. When it is determined that there is external pollution, the situation is associated with the previous part marking, the part of the housing where pollution occurs is accurately marked, and a motor housing cleaning warning is generated, so that maintenance personnel can promptly discover the pollution outside the motor and clean it, which helps to maintain the heat dissipation efficiency of the motor and extend the service life of the motor.

[0039] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions:

[0040] A motor fault early warning system, the system comprising:

[0041] A heat dissipation efficiency detection module, used to obtain real-time heat dissipation data of the motor, and compare the real-time heat dissipation data with preset reference heat dissipation parameters to generate a heat dissipation efficiency detection result;

[0042] An actual deviation data calculation module, used for obtaining actual working data of the motor, and comparing the actual working data with the rated working parameters to calculate actual deviation data;

[0043] The actual output power calculation module is used to calculate the actual output power P of the motor according to the actual working data. 实际 , the calculation formula of actual output power is as follows: Among them, P 实际 is the actual output power, T is the electromagnetic torque, ω is the angular velocity, m is the power correction factor, and the power correction factor is used to correct the calculated value of the actual output power, C is the preset torque coefficient, Φ is the air gap magnetic flux; I is the current conversion value of the motor circuit, and cosφ is the power factor of the motor circuit;

[0044] A power deviation value calculation module, used for building a power deviation value data set based on the calculated power deviation value of the actual output power value and the rated output power in the rated working parameters, and associating the power deviation value with the historical power deviation value based on the start timestamp, and taking each start and close as a start timestamp cycle;

[0045] A predicted power deviation value generating module, used for inputting the power deviation value data set into a preset power deviation value prediction model, wherein the power deviation value prediction performs self-learning on the power deviation value data set based on a preset self-learning algorithm to generate a predicted power deviation value, and the predicted power deviation value is used as a deviation reference value for subsequent operation of the motor;

[0046] A power fluctuation value calculation module is used to calculate the actual output power value and the predicted power deviation value to obtain a power fluctuation value, and compare the power fluctuation value with a preset fluctuation threshold value. If the power fluctuation value reaches the fluctuation threshold value, a fault warning report is generated based on the heat dissipation efficiency detection result and a motor fault warning prompt is issued.

[0047] By adopting the above technical solution, the heat dissipation of the motor is monitored in real time and the heat dissipation efficiency test results are generated, the heat dissipation problem is discovered in time, and the motor is prevented from being damaged or reducing performance due to overheating, which is helpful to improve the reliability and service life of the motor. The actual deviation data is calculated to understand the difference between the actual working state of the motor and the preset rated state. The actual output power of the motor is calculated by the calculation formula of the actual output power. The power size provided by the motor in actual work is calculated from multiple dimensions, and this helps to evaluate the working state and performance of the motor, providing a basis for subsequent fault warning and maintenance. The power fluctuation is obtained by calculating the actual output power value and the predicted power deviation value. The power fluctuation value is used to remind the operator to pay attention to possible faults in the motor. Compared with the existing method of issuing a motor fault warning prompt only when a fault in a certain aspect of the motor is detected, this solution calculates the power fluctuation value through multi-dimensional working data, and compares the power fluctuation value with the preset fluctuation threshold value to achieve real-time monitoring of the motor's working status and fault warning prediction. The subsequent working status of the motor is predicted in advance through the real-time working data of the motor, and it is determined whether there is a risk of failure, which is convenient for operation and maintenance personnel to plan maintenance opportunities in advance to inspect and repair the motor, thereby avoiding production suspension caused by motor failure, reducing the impact of failure on the production process, and thus improving production efficiency.

[0048] Preferably, the motor fault early warning system further comprises:

[0049] A current fluctuation value calculation module, used for comparing the actual current conversion value with the rated current conversion value to obtain a current fluctuation value;

[0050] A current fluctuation value database construction module, used to sort the historical current fluctuation values ​​based on the startup timestamp and construct a current fluctuation value database;

[0051] A current fluctuation monitoring module, used for presetting a current fluctuation monitoring model to analyze the historical current fluctuation values ​​based on the current fluctuation value database to generate a current correction factor, wherein the current correction factor is used to set a current fluctuation extreme value, and the current fluctuation extreme value is set based on the current correction factor and the rated current conversion value;

[0052] The current fault report generating module is used to generate a current fault report and issue a motor current fault warning when the current fluctuation value reaches the current fluctuation extreme value.

[0053] By adopting the above technical solution, using the preset current fluctuation monitoring model, analysis is performed based on the current fluctuation value database to calculate the current correction factor, and the current correction factor can be used to set the extreme value of the current fluctuation. By combining with the rated current conversion value, the extreme value range of the current fluctuation is set. By generating the current correction factor and setting the current fluctuation extreme value, the current fluctuation can be monitored more accurately, which helps to timely discover abnormal current fluctuations, warn of potential current faults, and take corresponding maintenance measures to improve the reliability and service life of the motor. The monitored current fluctuation value is compared with the set current fluctuation extreme value. When the current fluctuation value exceeds or reaches the current fluctuation extreme value, a current fault report is generated and a warning signal of the motor current fault is issued. In the embodiment of the present application, a threshold is set and combined with a fault judgment algorithm to determine whether the current fluctuation value exceeds or reaches the current fluctuation extreme value. Through the current fault warning, the abnormal current fluctuation of the motor is discovered in time, and potential current faults are warned in advance.

[0054] On the third aspect, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0055] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned motor fault early warning method when executing the computer program.

[0056] Fourthly, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0057] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned motor fault early warning method are implemented.

[0058] In summary, the present application includes at least one of the following beneficial technical effects:

[0059] 1. Real-time monitoring of the heat dissipation of the motor and generation of heat dissipation efficiency test results, timely detection of heat dissipation problems, avoiding damage or performance degradation of the motor due to overheating, helping to improve the reliability and service life of the motor, calculating the actual deviation data to understand the difference between the actual working state of the motor and the preset rated state, calculating the actual output power of the motor through the calculation formula of the actual output power, calculating the power size provided by the motor in actual work from multiple dimensions, and based on this, it helps to evaluate the working state and performance of the motor, providing a basis for subsequent fault warning and maintenance, calculating the power fluctuation value by the actual output power value and the predicted power deviation value, in order to provide Alert operators to possible motor faults. Compared with the existing method of issuing motor fault warnings only when a motor fault is detected, this solution calculates the power fluctuation value through multi-dimensional working data and compares the power fluctuation value with the preset fluctuation threshold to achieve real-time monitoring of the motor working state and fault warning prediction. The subsequent working state of the motor is predicted in advance through the real-time working data of the motor, and it is determined whether there is a risk of failure, which is convenient for operation and maintenance personnel to plan maintenance opportunities in advance to inspect and repair the motor, thereby avoiding production suspension caused by motor failure, reducing the impact of failure on the production process, and improving production efficiency.

[0060] 2. According to the start timestamp, the historical air gap flux deviation data is associated with the corresponding power deviation value. Each opening and closing operation can be regarded as a start timestamp cycle, and the air gap flux deviation data in the cycle is associated with the power deviation value. Through such association, a flux-power deviation database is constructed. By constructing a flux-power deviation database, the relationship between the air gap flux deviation and the power deviation of the motor in different time periods can be recorded; this helps to analyze the impact of the air gap flux on the power deviation, and provide data support for the subsequent flux factor calculation and power deviation prediction, using the preset deviation factor The calculation model is analyzed based on the magnetic flux-power deviation database to calculate the magnetic flux factor. The magnetic flux factor represents the relationship between the actual air gap magnetic flux and the power deviation, and can be used to calibrate the predicted power deviation value. By calculating the magnetic flux factor, the influence of the actual air gap magnetic flux on the power deviation can be more accurately reflected, and the prediction accuracy of this scheme can be improved, thereby reducing the misjudgment of faults. This scheme is based on the trend, periodicity or other characteristics of historical data for prediction, and generates a predicted air gap magnetic flux, which can predict the future air gap magnetic flux situation to a certain extent, and provide more accurate input for the prediction and calibration of the power deviation value;

[0061] 3. Using the preset current fluctuation monitoring model, the current correction factor is calculated based on the current fluctuation value database for analysis, and the current correction factor can be used to set the extreme value of the current fluctuation. By combining with the rated current conversion value, the extreme value range of the current fluctuation is set. By generating the current correction factor and setting the current fluctuation extreme value, the current fluctuation can be monitored more accurately, which helps to timely discover abnormal current fluctuations, warn of potential current faults, and take corresponding maintenance measures to improve the reliability and service life of the motor. The monitored current fluctuation value is compared with the set current fluctuation extreme value. When the current fluctuation value exceeds or reaches the current fluctuation extreme value, a current fault report is generated and a warning signal of the motor current fault is issued. In the embodiment of the present application, a threshold is set and combined with a fault judgment algorithm to determine whether the current fluctuation value exceeds or reaches the current fluctuation extreme value. Through the current fault warning, the abnormal current fluctuation of the motor is discovered in time, and the potential current fault is warned in advance.

[0062] 4. Obtain the initial image data and real-time image data of the motor's exterior, and compare and analyze them through image processing technology to identify the contamination and insulation status of the motor housing. When the housing is found to be contaminated, a cleaning warning is generated. Compared with the existing manual inspection of the motor's external contamination, this solution is real-time, and the automated reminder improves the real-time monitoring, reduces the necessity of worker inspections, and improves the safety of industrial production. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a flowchart of a motor fault warning method according to an embodiment of the present application;

[0064] Figure 2 is a flowchart of the steps in step S10 in a motor fault early warning method according to an embodiment of the present application;

[0065] Figure 3 This is a flowchart of the implementation after step S40 in a motor fault warning method according to an embodiment of the present application;

[0066] Figure 4 This is a flowchart of the implementation after step S40 in a motor fault warning method according to an embodiment of the present application;

[0067] Figure 5 This is a module principle block diagram of a motor fault early warning system according to an embodiment of the present application;

[0068] Figure 6 It is a schematic diagram of an electronic device in an embodiment of the present application.

[0069] Figure Number:

[0070] 1. Heat dissipation efficiency detection module; 2. Actual deviation data calculation module; 3. Actual output power calculation module; 4. Power deviation value calculation module; 5. Prediction power deviation value generation module; 6. Power fluctuation value calculation module; 7. Current fluctuation value calculation module; 8. Current fluctuation value database construction module; 9. Current fluctuation monitoring module; 10. Current fault report generation module. DETAILED DESCRIPTION

[0071] The present application is further described in detail below in conjunction with the accompanying drawings.

[0072] In one embodiment, a three-phase asynchronous motor is used as an example for explanation. Figure 1-4 As shown, the present application discloses a motor fault early warning method, which specifically includes the following steps:

[0073] S10: acquiring real-time heat dissipation data of the motor, and comparing the real-time heat dissipation data with preset reference heat dissipation parameters to generate a heat dissipation efficiency detection result;

[0074] Specifically, the sensor or monitoring device obtains the real-time heat dissipation data of the motor, including parameters such as the motor body temperature and the speed of the cooling fan in the motor, and compares these real-time heat dissipation data with preset reference heat dissipation parameters, such as the rated temperature, maximum temperature, etc., to evaluate the heat dissipation efficiency of the motor. According to the comparison result, the heat dissipation efficiency test result is generated to determine whether the motor has a heat dissipation problem. The heat dissipation of the motor is monitored in real time and the heat dissipation efficiency test result is generated to detect the heat dissipation problem in time and avoid damage or performance reduction of the motor due to overheating. This helps to improve the reliability and service life of the motor.

[0075] S20: Acquire actual working data of the motor, and compare the actual working data with the rated working parameters to calculate actual deviation data;

[0076] Specifically, the actual working data of the motor is obtained, and the actual working data includes the actual current, the actual voltage, the actual power factor, the actual air gap magnetic flux data, and the actual current conversion value; the rated working parameters include the rated current, the rated voltage, the rated power factor, the rated air gap magnetic flux parameter, and the rated current conversion value. These actual working data are compared with the rated working parameters to calculate the actual deviation data, that is, the difference between the actual working data and the rated working parameters.

[0077] This solution can evaluate whether the motor meets the design requirements in actual operation by comparing the actual working data with the rated working parameters and calculating the actual deviation data. This helps to timely discover the abnormal working of the motor or the deviation from the design requirements, and improve the working stability and reliability of the motor.

[0078] S30: Calculate the actual output power P of the motor according to the actual working data 实际 , the calculation formula of actual output power is as follows:

[0079] Among them, P 实际 is the actual output power, T is the electromagnetic torque, ω is the angular velocity, m is the power correction factor, which is used to correct the calculated value of the actual output power, C is the preset torque coefficient, Φ is the air gap magnetic flux; I is the current conversion value of the motor circuit, and cosφ is the power factor of the motor circuit;

[0080] Specifically, the actual output power of the motor is calculated through the calculation formula of the actual output power, combining the electromagnetic torque, angular velocity, power correction factor, preset torque coefficient, air gap magnetic flux; the current conversion value of the motor circuit and the power factor of the motor circuit. The power provided by the motor in actual work is calculated from multiple dimensions, and this helps to evaluate the working status and performance of the motor, providing a basis for subsequent fault warning and maintenance. The power correction factor is used to eliminate the influence of monitoring noise data on the calculation results, thereby improving the calculation accuracy of the actual output power.

[0081] S40: constructing a power deviation value data set based on the calculated actual output power value and the power deviation value of the rated output power in the rated working parameters and associating the startup timestamp with the historical power deviation value, and taking each opening and closing as a startup timestamp cycle;

[0082] Specifically, the actual output power value is compared with the rated output power in the rated working parameters, the power deviation value is calculated, and the power deviation value is recorded according to the association between the start timestamp and the historical power deviation value, and a power deviation value data set is constructed. It should be noted that each opening and closing operation is regarded as a start timestamp cycle, which means that the start of the motor is the starting point of the start timestamp and the shutdown of the motor is the end point of the start timestamp. For example, if the motor start time is ten minutes, the time length of the start timestamp is ten minutes.

[0083] By constructing a power deviation value dataset, the power deviation of the motor in different time periods can be recorded, which is helpful for analyzing the power fluctuation trend and abnormal changes of the motor and providing data support for fault warning and fault diagnosis.

[0084] S50: inputting the power deviation value data set into a preset power deviation value prediction model, wherein the power deviation value prediction performs self-learning on the power deviation value data set based on a preset self-learning algorithm to generate a predicted power deviation value, and the predicted power deviation value is used as a deviation reference value for subsequent operation of the motor;

[0085] Specifically, the power deviation value data set is input into a preset power deviation value prediction model, and the data set is analyzed and learned using a preset self-learning algorithm. Through the self-learning of the model, a predicted power deviation value can be generated as a deviation reference value for subsequent operation of the motor.

[0086] Furthermore, the preset power deviation value prediction model can adopt a method based on machine learning. In the embodiment of the present application, a support vector regression (SVR) model is adopted. SVR is a supervised learning algorithm used to establish a nonlinear relationship between input features and output targets. By predicting the power deviation value, the power fluctuation trend and deviation of the motor can be predicted in advance, which helps to timely discover the abnormal operation and potential failure of the motor and take corresponding measures for repair and maintenance.

[0087] The training of the dynamic deviation value prediction model includes the following steps:

[0088] Model training: Use the data of the training set to fit the SVR model to the data and establish the relationship between the input features and the output target. The SVR model fits the data by finding an optimal hyperplane to minimize the error between the predicted value and the actual value; Model evaluation: Use the data of the test set to evaluate the performance of the trained SVR model. In the embodiment of the present application, the evaluation indicators include mean squared error (MSE) and root mean square error (RMSE).

[0089] S60: Calculate the actual output power value and the predicted power deviation value to obtain a power fluctuation value, and compare the power fluctuation value with a preset fluctuation threshold value. If the power fluctuation value reaches the fluctuation threshold value, generate a fault warning report based on the heat dissipation efficiency detection result and issue a motor fault warning prompt;

[0090] Specifically, a power fluctuation value is obtained based on the calculation result of the actual output power value and the predicted power deviation value, and the power fluctuation value is compared with a preset fluctuation threshold value. If the power fluctuation value reaches or exceeds the fluctuation threshold value, a motor fault warning report is generated, and a fault warning prompt is issued to remind the operator to pay attention to possible motor faults. Compared with the existing motor fault warning prompt that is only issued when a motor fault is detected, this solution realizes real-time monitoring of the motor's working state and fault warning prediction by comparing the power fluctuation value with a preset fluctuation threshold value. The subsequent working state of the motor is predicted in advance through the real-time working data of the motor, and it is determined whether there is a fault risk, which is convenient for operation and maintenance personnel to plan maintenance opportunities in advance to inspect and repair the motor, thereby avoiding production suspension caused by motor failure, reducing the impact of failure on the production process, and improving production efficiency.

[0091] In step S10: obtaining the real-time heat dissipation data of the motor, and comparing the real-time heat dissipation data with the preset reference heat dissipation parameters to generate the heat dissipation efficiency detection result, the following steps are included:

[0092] S11: acquiring external initial image data and external real-time image data of the motor, and comparing the external real-time image data with the external initial image data to analyze the real-time thermal insulation state of the motor, and generating a motor housing cleaning warning according to the real-time thermal insulation state;

[0093] Specifically, the initial image data and real-time image data of the motor's exterior are obtained, and comparative analysis is performed through image processing technology to identify the contamination condition and insulation status of the motor casing. When casing contamination is found, a cleaning warning is generated. Compared with the existing manual inspection of the motor's external contamination condition, this solution is real-time, and the automated reminder improves the real-time nature of monitoring, reduces the necessity of worker inspections, and improves the safety of industrial production.

[0094] In step S11: obtaining the external initial image data and the external real-time image data of the motor, and comparing the external real-time image data with the external initial image data to analyze the real-time thermal insulation state of the motor, and generating a motor housing cleaning warning according to the real-time thermal insulation state, the following steps are included:

[0095] S111: extracting image features of the external initial image data, and marking parts of the external initial image data according to the image features, wherein the part marking includes marking the housing, exhaust holes and hole positions of the motor;

[0096] Specifically, the position and features of the motor housing and related components are accurately identified through an image recognition algorithm, and the motor is marked according to the image features, and the motor housing, exhaust holes and hole positions are automatically marked. In other embodiments, other parts can also be marked according to the motor housing structure to provide accurate basic data for subsequent pollution analysis.

[0097] S112: extracting grayscale values ​​of the external initial image data and the external real-time image data, and comparing the grayscale values ​​of the external real-time image data with the grayscale values ​​of the external initial image data to determine whether there is external contamination of the motor;

[0098] Specifically, the grayscale values ​​of the external initial image data and the external real-time image data are extracted, and a comparative analysis is performed to determine the grayscale value change in the external real-time image data, thereby determining whether there is pollution outside the motor.

[0099] S113: If there is external contamination, it is associated with the location mark to generate a motor housing cleaning warning;

[0100] Specifically, when external contamination is determined, the situation is associated with the previous part marking, the contaminated shell part is accurately marked, and a motor shell cleaning warning is generated, so that maintenance personnel can promptly discover the contamination of the outside of the motor and clean it, which helps to maintain the heat dissipation efficiency of the motor and extend the service life of the motor.

[0101] In S30: Calculate the actual output power P of the motor according to the actual working data 实际 , the calculation formula of actual output power is as follows: This step includes the following steps:

[0102] S31: Calculate the power correction factor m based on the magnetic flux factor and the current correction factor, wherein the calculation formula of the power correction factor m is: Where c is the flux factor and p is the current correction factor.

[0103] Specifically, the power correction factor m is used to quantitatively evaluate the correlation between the magnetic flux factor and the current correction factor, to verify the correlation between the magnetic flux factor and the current correction factor, to determine whether there is a linear or nonlinear relationship between the magnetic flux factor and the current correction factor, and to further confirm the degree of influence of the magnetic flux factor and the current correction factor on the actual output power, and whether there is an influence of other factors; thereby improving the accuracy of the actual output power calculation.

[0104] At S40: according to the calculated actual output power value and the power deviation value of the rated output power in the rated working parameters, and based on the startup timestamp and the historical power deviation value association, to construct a power deviation value data set, and each opening and closing is taken as a startup timestamp cycle. After this step, the actual working data includes the actual air gap flux data, and the rated working parameters include the rated air gap flux parameters, including the following steps:

[0105] S4001: Compare and calculate the actual air gap magnetic flux data with the rated air gap magnetic flux parameters to obtain air gap magnetic flux deviation data;

[0106] Specifically, actual air gap flux data in the actual working data of the motor is compared and calculated with rated air gap flux parameters in the rated working parameters to obtain deviation data of the air gap flux and understand the degree of difference between the actual air gap flux of the motor and the rated air gap flux.

[0107] S4002: Associating historical air gap magnetic flux deviation data with power deviation values ​​based on a startup timestamp, and constructing a magnetic flux-power deviation database;

[0108] Specifically, according to the startup timestamp, the historical air gap flux deviation data is associated with the corresponding power deviation value. Each opening and closing operation can be regarded as a startup timestamp cycle, and the air gap flux deviation data in the cycle is associated with the power deviation value. Through such association, a flux-power deviation database is constructed. By constructing a flux-power deviation database, the relationship between the air gap flux deviation and the power deviation of the motor in different time periods can be recorded. This helps to analyze the impact of the air gap flux on the power deviation and provide data support for the subsequent flux factor calculation and power deviation prediction.

[0109] S4003: The preset deviation factor calculation model generates a flux factor based on the magnetic flux-power deviation database analysis;

[0110] Specifically, the preset deviation factor calculation model is used to analyze the magnetic flux-power deviation database and calculate the magnetic flux factor. The magnetic flux factor represents the relationship between the actual air gap magnetic flux and the power deviation, and can be used to calibrate the predicted power deviation value. By calculating the magnetic flux factor, the influence of the actual air gap magnetic flux on the power deviation can be more accurately reflected.

[0111] S4004: The preset air gap flux model is analyzed based on historical actual air gap flux data to generate predicted air gap flux;

[0112] Specifically, a preset air gap flux model is used to generate a prediction of future air gap flux by analyzing historical actual air gap flux data.

[0113] This solution makes predictions based on the trend, periodicity or other characteristics of historical data and generates predicted air gap flux, which can predict the future air gap flux conditions to a certain extent and provide more accurate input for the prediction and calibration of dynamic deviation values.

[0114] S4005: The power deviation value prediction model generates a first corrected power deviation prediction value based on the magnetic flux factor and the predicted air gap magnetic flux, where the first corrected power deviation prediction value is used to calibrate the predicted power deviation value;

[0115] Specifically, based on the flux factor and the predicted air gap flux, the power deviation value prediction model generates a first corrected power deviation prediction value. The first corrected power deviation prediction value is used to calibrate the predicted power deviation value, making the prediction more accurate and reliable, which helps to timely discover potential problems of the motor and take corresponding maintenance measures, thereby improving the reliability and service life of the motor.

[0116] At S40: according to the calculated actual output power value and the power deviation value of the rated output power in the rated working parameters, and based on the startup timestamp and the historical power deviation value association, a power deviation value data set is constructed, and each opening and closing is taken as a startup timestamp cycle. After this step, the actual working data includes the actual current conversion value, and the rated working parameters include the rated current conversion value, including the following steps:

[0117] S4011: Compare the actual current conversion value with the rated current conversion value to obtain a current fluctuation value;

[0118] Specifically, the actual current conversion value in the actual working data of the motor is compared with the rated current conversion value in the rated working parameters to obtain the current fluctuation value. In the embodiment of the present application, the current fluctuation value is obtained by calculating the difference between the actual current conversion value and the rated current conversion value, that is, the current fluctuation value = the actual current conversion value = the rated current conversion value, wherein the current fluctuation value is vector data.

[0119] S4012: Sort the historical current fluctuation values ​​based on the startup timestamp and build a current fluctuation value database;

[0120] Specifically, historical current fluctuation values ​​are sorted according to the startup timestamp, and a current fluctuation value database is constructed. Each opening and closing operation is regarded as a startup timestamp cycle, and the current fluctuation values ​​in the cycle are sorted and recorded in the current fluctuation value database.

[0121] S4013: The preset current fluctuation monitoring model analyzes the historical current fluctuation value based on the current fluctuation value database to generate a current correction factor, the current correction factor is used to set the current fluctuation extreme value, and the current fluctuation extreme value is set based on the current correction factor and the rated current conversion value;

[0122] Specifically, a preset current fluctuation monitoring model is used to analyze the current fluctuation value database and calculate the current correction factor. The current correction factor can be used to set the extreme value of the current fluctuation. By combining it with the rated current conversion value, the extreme value range of the current fluctuation is set.

[0123] By generating a current correction factor and setting the current fluctuation extreme value, the current fluctuation can be monitored more accurately, which helps to detect abnormal current fluctuations in time, warn of potential current faults, and take corresponding maintenance measures to improve the reliability and service life of the motor.

[0124] S4014: When the current fluctuation value reaches the current fluctuation extreme value, a current fault report is generated and a motor current fault warning is issued.

[0125] Specifically, the monitored current fluctuation value is compared with the set current fluctuation extreme value. When the current fluctuation value exceeds or reaches the current fluctuation extreme value, a current fault report is generated and a warning signal of a motor current fault is issued. In an embodiment of the present application, a threshold is set and combined with a fault judgment algorithm to determine whether the current fluctuation value exceeds or reaches the current fluctuation extreme value. Through the current fault warning, the abnormal current fluctuation of the motor is discovered in time, and potential current faults are warned in advance.

[0126] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0127] In one embodiment, a motor fault warning system is provided, which corresponds one-to-one to the motor fault warning method in the above embodiment. Figure 5 As shown, the motor fault warning system includes a heat dissipation efficiency detection module 1, an actual deviation data calculation module 2, an actual output power calculation module 3, a power deviation value calculation module 4, a predicted power deviation value generation module 5, a power fluctuation value calculation module 6, a current fluctuation value calculation module 7, a current fluctuation value database construction module 8, a current fluctuation monitoring module 9 and a current fault report generation module 10. The functional modules are described in detail as follows:

[0128] The heat dissipation efficiency detection module 1 is used to obtain the real-time heat dissipation data of the motor, and compare the real-time heat dissipation data with the preset reference heat dissipation parameters to generate a heat dissipation efficiency detection result;

[0129] The actual deviation data calculation module 2 is used to obtain the actual working data of the motor and compare the actual working data with the rated working parameters to calculate the actual deviation data;

[0130] The actual output power calculation module 3 is used to calculate the actual output power of the motor according to the actual working data. The calculation formula of the actual output power is as follows:, wherein, is the actual output power, T is the electromagnetic torque, is the angular velocity, m is the power correction factor, and the power correction factor is used to correct the calculated value of the actual output power, C is the preset torque coefficient, Φ is the air gap magnetic flux; I is the current conversion value of the motor circuit, and cosφ is the power factor of the motor circuit;

[0131] The power deviation value calculation module 4 is used to construct a power deviation value data set based on the calculated actual output power value and the power deviation value of the rated output power in the rated working parameters, and based on the association of the start timestamp and the historical power deviation value, and each opening and closing is regarded as a start timestamp cycle;

[0132] The predicted power deviation value generating module 5 is used to input the power deviation value data set into a preset power deviation value prediction model. The power deviation value prediction performs self-learning on the power deviation value data set based on a preset self-learning algorithm to generate a predicted power deviation value. The predicted power deviation value is used as a deviation reference value for subsequent operation of the motor.

[0133] The power fluctuation value calculation module 6 is used to calculate the actual output power value and the predicted power deviation value to obtain the power fluctuation value, and compare the power fluctuation value with the preset fluctuation threshold value. If the power fluctuation value reaches the fluctuation threshold value, a fault warning report is generated based on the heat dissipation efficiency detection result and a motor fault warning prompt is issued;

[0134] The current fluctuation value calculation module 7 is used to compare the actual current conversion value with the rated current conversion value to obtain the current fluctuation value;

[0135] A current fluctuation value database construction module 8, used to sort the historical current fluctuation values ​​based on the startup timestamp and construct a current fluctuation value database;

[0136] A current fluctuation monitoring module 9 is used to preset a current fluctuation monitoring model to analyze historical current fluctuation values ​​based on a current fluctuation value database to generate a current correction factor, the current correction factor is used to set a current fluctuation extreme value, and the current fluctuation extreme value is set based on the current correction factor and the rated current conversion value;

[0137] The current fault report generating module 10 is used to generate a current fault report and issue a motor current fault warning when the current fluctuation value reaches the current fluctuation extreme value.

[0138] For the specific definition of a motor fault warning system, please refer to the definition of a motor fault warning method above, which will not be repeated here. Each module in the above motor fault warning system can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0139] In one embodiment, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The electronic device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store a database. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a motor fault early warning method is implemented.

[0140] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0141] Acquire real-time heat dissipation data of the motor, and compare the real-time heat dissipation data with preset reference heat dissipation parameters to generate a heat dissipation efficiency detection result;

[0142] Acquiring actual working data of the motor, and comparing the actual working data with rated working parameters to calculate actual deviation data;

[0143] Calculate the actual output power P of the motor according to the actual working data 实际 , the calculation formula of actual output power is as follows: Among them, P 实际 is the actual output power, T is the electromagnetic torque, ω is the angular velocity, m is the power correction factor, and the power correction factor is used to correct the calculated value of the actual output power, C is the preset torque coefficient, Φ is the air gap magnetic flux; I is the current conversion value of the motor circuit, and cosφ is the power factor of the motor circuit;

[0144] According to the calculated actual output power value and the power deviation value of the rated output power in the rated working parameter, and based on the start timestamp and the historical power deviation value association, a power deviation value data set is constructed, and each opening and closing is regarded as a start timestamp cycle;

[0145] The power deviation value data set is input into a preset power deviation value prediction model, and the power deviation value prediction performs self-learning on the power deviation value data set based on a preset self-learning algorithm to generate a predicted power deviation value, and the predicted power deviation value is used as a deviation reference value for subsequent operation of the motor;

[0146] The actual output power value and the predicted power deviation value are calculated to obtain a power fluctuation value, and the power fluctuation value is compared with a preset fluctuation threshold value. If the power fluctuation value reaches the fluctuation threshold value, a fault warning report is generated based on the heat dissipation efficiency detection result and a motor fault warning prompt is issued.

[0147] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0148] Acquire real-time heat dissipation data of the motor, and compare the real-time heat dissipation data with preset reference heat dissipation parameters to generate a heat dissipation efficiency detection result;

[0149] Acquiring actual working data of the motor, and comparing the actual working data with rated working parameters to calculate actual deviation data;

[0150] Calculate the actual output power P of the motor according to the actual working data 实际 , the calculation formula of actual output power is as follows: Among them, P 实际 is the actual output power, T is the electromagnetic torque, ω is the angular velocity, m is the power correction factor, and the power correction factor is used to correct the calculated value of the actual output power, C is the preset torque coefficient, Φ is the air gap magnetic flux; I is the current conversion value of the motor circuit, and cosφ is the power factor of the motor circuit;

[0151] According to the calculated actual output power value and the power deviation value of the rated output power in the rated working parameter, and based on the start timestamp and the historical power deviation value association, a power deviation value data set is constructed, and each opening and closing is regarded as a start timestamp cycle;

[0152] The power deviation value data set is input into a preset power deviation value prediction model, and the power deviation value prediction performs self-learning on the power deviation value data set based on a preset self-learning algorithm to generate a predicted power deviation value, and the predicted power deviation value is used as a deviation reference value for subsequent operation of the motor;

[0153] The actual output power value and the predicted power deviation value are calculated to obtain a power fluctuation value, and the power fluctuation value is compared with a preset fluctuation threshold value. If the power fluctuation value reaches the fluctuation threshold value, a fault warning report is generated based on the heat dissipation efficiency detection result and a motor fault warning prompt is issued.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0155] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0156] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A motor fault early warning method, characterized in that: The method comprises the steps of: acquiring real-time heat dissipation data of the motor, and comparing the real-time heat dissipation data with preset reference heat dissipation parameters to generate a heat dissipation efficiency detection result; Acquiring actual working data of the motor, and comparing the actual working data with rated working parameters to calculate actual deviation data; Calculate the actual output power P of the motor according to the actual working data 实际 , the calculation formula of actual output power is as follows: Among them, P 实际 is the actual output power, T is the electromagnetic torque, ω is the angular velocity, m is the power correction factor, and the power correction factor is used to correct the calculated value of the actual output power, C is the preset torque coefficient, Φ is the air gap magnetic flux; I is the current conversion value of the motor circuit, is the power factor of the motor circuit; According to the calculated actual output power value and the power deviation value of the rated output power in the rated working parameter, and based on the start timestamp and the historical power deviation value association, a power deviation value data set is constructed, and each opening and closing is regarded as a start timestamp cycle; The power deviation value data set is input into a preset power deviation value prediction model, and the power deviation value prediction performs self-learning on the power deviation value data set based on a preset self-learning algorithm to generate a predicted power deviation value, and the predicted power deviation value is used as a deviation reference value for subsequent operation of the motor; The actual output power value and the predicted power deviation value are calculated to obtain a power fluctuation value, and the power fluctuation value is compared with a preset fluctuation threshold value. If the power fluctuation value reaches the fluctuation threshold value, a fault warning report is generated based on the heat dissipation efficiency detection result and a motor fault warning prompt is issued.

2. A motor fault early warning method according to claim 1, characterized in that: After the step of building a power deviation value data set based on the calculated actual output power value and the power deviation value of the rated output power in the rated working parameters and associating the power deviation value with the historical power deviation value based on the start timestamp, and taking each start and close as a start timestamp cycle, the actual working data includes actual air gap magnetic flux data, and the rated working parameters include rated air gap magnetic flux parameters, the steps are as follows: Comparing and calculating the actual air gap magnetic flux data with the rated air gap magnetic flux parameters to obtain air gap magnetic flux deviation data; Associating the historical air gap magnetic flux deviation data with the power deviation value based on the startup timestamp, and constructing a magnetic flux-power deviation database; The preset deviation factor calculation model generates a flux factor based on the flux-power deviation database analysis; The preset air gap flux model is analyzed based on the historical actual air gap flux data to generate a predicted air gap flux; The power deviation value prediction model generates a first corrected power deviation prediction value based on the magnetic flux factor and the predicted air gap magnetic flux, and the first corrected power deviation prediction value is used to calibrate the predicted power deviation value.

3. A motor fault early warning method according to claim 2, characterized in that: After the step of building a power deviation value data set based on the calculated actual output power value and the rated output power in the rated working parameters and associating the power deviation value with the historical power deviation value based on the start timestamp, and taking each start and close as a start timestamp cycle, the actual working data includes the actual current conversion value, and the rated working parameters include the rated current conversion value, the steps include: Comparing the actual current conversion value with the rated current conversion value to obtain a current fluctuation value; Sort the historical current fluctuation values ​​based on the startup timestamp and construct a current fluctuation value database; The preset current fluctuation monitoring model analyzes the historical current fluctuation values ​​based on the current fluctuation value database to generate a current correction factor, wherein the current correction factor is used to set the current fluctuation extreme value, and the current fluctuation extreme value is set based on the current correction factor and the rated current conversion value; When the current fluctuation value reaches the current fluctuation extreme value, a current fault report is generated and a motor current fault warning is issued.

4. A motor fault early warning method according to claim 3, characterized in that: The actual output power P of the motor is calculated according to the actual working data. 实际 , the calculation formula of actual output power is as follows: This step includes the following steps: The power correction factor m is calculated based on the magnetic flux factor and the current correction factor, wherein the calculation formula of the power correction factor m is: Where c is the magnetic flux factor and p is the current correction factor.

5. The motor fault early warning method according to claim 1, characterized in that: The step of obtaining the real-time heat dissipation data of the motor and comparing the real-time heat dissipation data with the preset reference heat dissipation parameters to generate the heat dissipation efficiency detection result includes the following steps: Acquire external initial image data and external real-time image data of the motor, and compare the external real-time image data with the external initial image data to analyze the real-time thermal insulation status of the motor, and generate a motor housing cleaning warning based on the real-time thermal insulation status.

6. A motor fault early warning method according to claim 5, characterized in that: The step of acquiring the external initial image data and the external real-time image data of the motor, and comparing the external real-time image data with the external initial image data to analyze the real-time thermal insulation state of the motor, and generating a motor housing cleaning warning according to the real-time thermal insulation state includes the following steps: Extracting image features of the external initial image data, and marking parts of the external initial image data according to the image features, wherein the part marking includes marking the housing, exhaust holes and hole positions of the motor; Extracting grayscale values ​​of the external initial image data and the external real-time image data, and comparing the grayscale value of the external real-time image data with the grayscale value of the external initial image data to determine whether there is external contamination of the motor; If there is external contamination, it is associated with the location mark to generate an early warning for cleaning the motor housing.

7. A motor fault early warning system, applied to a motor fault early warning method according to any one of claims 1 to 6, characterized in that: It comprises a heat dissipation efficiency detection module (1) for acquiring real-time heat dissipation data of the motor, and generating a heat dissipation efficiency detection result by comparing the real-time heat dissipation data with a preset reference heat dissipation parameter; An actual deviation data calculation module (2) is used to obtain actual working data of the motor and compare the actual working data with the rated working parameters to calculate actual deviation data; The actual output power calculation module (3) is used to calculate the actual output power P of the motor according to the actual working data. 实际 , the calculation formula of actual output power is as follows: Among them, P 实际 is the actual output power, T is the electromagnetic torque, ω is the angular velocity, m is the power correction factor, and the power correction factor is used to correct the calculated value of the actual output power, C is the preset torque coefficient, Φ is the air gap magnetic flux; I is the current conversion value of the motor circuit, is the power factor of the motor circuit; A power deviation value calculation module (4) is used to construct a power deviation value data set based on the calculated actual output power value and the power deviation value of the rated output power in the rated working parameter, and based on the association of the startup timestamp with the historical power deviation value, and each start and close is regarded as a startup timestamp cycle; A predicted power deviation value generating module (5), used for inputting the power deviation value data set into a preset power deviation value prediction model, wherein the power deviation value prediction performs self-learning on the power deviation value data set based on a preset self-learning algorithm to generate a predicted power deviation value, wherein the predicted power deviation value serves as a deviation reference value for subsequent operation of the motor; A power fluctuation value calculation module (6) is used to calculate the actual output power value and the predicted power deviation value to obtain a power fluctuation value, and compare the power fluctuation value with a preset fluctuation threshold value. If the power fluctuation value reaches the fluctuation threshold value, a fault warning report is generated based on the heat dissipation efficiency detection result and a motor fault warning prompt is issued.

8. A motor fault warning system according to claim 7, characterized in that: It also includes a current fluctuation value calculation module (7) for comparing the actual current conversion value with the rated current conversion value to obtain the current fluctuation value; A current fluctuation value database construction module (8), used for sorting historical current fluctuation values ​​based on a startup timestamp and constructing a current fluctuation value database; A current fluctuation monitoring module (9) is used to preset a current fluctuation monitoring model to analyze historical current fluctuation values ​​based on a current fluctuation value database to generate a current correction factor, the current correction factor being used to set a current fluctuation extreme value, and the current fluctuation extreme value is set based on the current correction factor and a rated current conversion value; The current fault report generating module (10) is used to generate a current fault report and issue a motor current fault warning when the current fluctuation value reaches the current fluctuation extreme value.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the motor fault early warning method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a motor fault early warning method as claimed in any one of claims 1 to 6 are implemented.

Images