A method, system, device and storage medium for evaluating the service life of a motor

Abstract

The present invention relates to a method for evaluating the service life of a motor, the method comprising the following steps: obtaining the working data of the motor, and inputting the historical working data into a preset aging model for analysis to generate first aging prediction data; obtaining the working environment data of the motor, and inputting the working environment data into a preset environment judgment model to output an environmental impact factor; correcting the first aging prediction data based on the environmental impact factor to generate second aging prediction data; the preset life prediction model calculates the basic motor service life according to the second aging prediction data; obtaining the historical fault data of the motor, and generating fault life correction data according to the historical fault data; correcting the basic motor service life based on the fault life correction data to generate a corrected service life. The present application has the effect of improving the prediction accuracy of the motor service life.

Description

Technical Field

[0001] The present invention relates to the technical field of motor maintenance, and in particular to a method, system, device and storage medium for evaluating the service life of a motor. Background Art

[0002] At present, electric motors are widely used in industrial automation production, among which DC motors are one of the main types of electric motors. They mainly use commutators and brushes to commutate the armature winding current to achieve normal operation of DC motors. Brushes are made of easily worn materials. As the brushes and commutator rotate and rub, the material temperature rises, plastic deformation occurs, and the friction resistance increases. Carbon brush particles will inevitably fall off, resulting in brush wear. Severe brush wear may cause motor failure and affect the service life of the motor.

[0003] Existing predictions of the service life of DC motors are generally based on historical usage data and experience. The life of new motors is predicted by statistics and analysis of the life of motors under similar working conditions. When the use time of new motors is close to the predicted service life, they are repaired or replaced.

[0004] With respect to the above-mentioned prior art, there are the following problems: prediction of the service life of the motor based on usage experience is usually applicable to similar applications and environments. When the motor has an accidental failure or is damaged by other factors, it is difficult to accurately predict the life of the motor based on experience, which reduces the accuracy of the prediction of the service life of the motor, making it difficult to replace the motor in time, which in turn affects the efficiency of industrial automation production. Therefore, improvement is needed. Summary of the invention

[0005] In order to improve the prediction accuracy of the service life of a motor, the present application provides a method, system, device and storage medium for evaluating the service life of a motor.

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

[0007] A method for evaluating the service life of a motor, the method comprising the following steps:

[0008] Acquire the working data of the motor, and input the historical working data into a preset aging model for analysis to generate first aging prediction data;

[0009] Acquire the working environment data of the motor, input the working environment data into a preset environment judgment model, and output the environmental impact factor;

[0010] Correcting the first aging prediction data based on the environmental influencing factors to generate second aging prediction data;

[0011] The preset life prediction model calculates the basic motor service life according to the second aging prediction data;

[0012] Acquire historical fault data of the motor, and generate fault life correction data according to the historical fault data, wherein the historical fault data includes the fault type and the fault time duration;

[0013] The basic motor service life is corrected based on the fault life correction data to generate corrected service life data, and a motor service life assessment report is generated based on the corrected service life data.

[0014] By adopting the above technical scheme, the first aging prediction data corresponding to the working data is output by the preset aging model, and the aging state of the motor is predicted based on the analysis of the working data of the motor, which helps to identify potential problems of the motor in advance. The environmental impact factor reflects the degree of influence of the environment on the motor. Considering the influence of the working environment on the performance and life of the motor, compared with the existing life assessment of the motor limited to a certain working environment, this scheme adds the dimensional judgment of the working environment on the aging of the motor, and more accurately assesses the life of the motor under specific environmental conditions. By considering environmental factors, the service life of the motor can be more accurately assessed, so as to formulate a more accurate maintenance plan to ensure the reliability and stability of the motor under various environmental conditions. The service life of the basic motor is corrected according to the fault life correction data. The corrected service life can be obtained by adding the fault life correction data to the basic motor service life or applying other correction methods. This step takes into account the impact of historical faults on the life of the motor, and further improves the accuracy of the motor service life assessment.

[0015] In a preferred example, the present application can be further configured as follows: in the step of obtaining the working data of the motor and inputting the historical working data into a preset aging model for analysis to generate first aging prediction data, the working data includes the armature current data and voltage data of the motor, including the following steps:

[0016] Acquire the armature current data and voltage data, and associate the armature current data and voltage data based on a timestamp, and calculate the actual armature resistance value according to the armature current data and voltage data. The specific actual resistance value calculation formula is: Rm=Um / Im, where Rm is the actual resistance value, Um is the voltage data, and Im is the armature current data;

[0017] Recording the actual resistance value in history based on a timestamp, and constructing a resistance data set based on the actual resistance value in history;

[0018] The aging model analyzes the resistance data set to generate a resistance aging factor, wherein the calculation formula of the resistance aging factor is s=[(R m(i+1) -R mi ) / R i ] / Δt, where Δt is a preset time interval and i is the number of records;

[0019] The aging model predicts first aging prediction data corresponding to a certain time in the future based on the resistance aging factor, wherein the first aging prediction data includes first predicted resistance data, and the calculation formula of the first predicted resistance data is: R Vi =r×exp(st), where r is the rated armature resistance.

[0020] By adopting the above technical solution, by constructing a resistance data set and analyzing the resistance change trend of the motor, it is helpful to understand the aging speed of the motor and provide a more accurate basis for subsequent aging predictions. The aging model calculates two adjacent actual resistance value data in the resistance data set to generate a resistance aging factor for calculating the aging degree of the motor. The resistance prediction value is calculated through the resistance aging factor, and the resistance data is predicted based on the resistance aging factor, which improves the accuracy of the prediction and the accuracy of the motor life.

[0021] In a preferred example, the present application may be further configured as follows: after the step of predicting the first aging prediction data corresponding to a certain time in the future based on the resistance aging factor by the aging model, the following steps are included:

[0022] Obtain the actual resistance value corresponding to a certain time in the future, and compare it with the first predicted resistance data corresponding to the time to generate a predicted deviation value R z , based on the historical forecast deviation value R z Constructing a set of prediction deviations;

[0023] The predicted deviation number set is input into a preset predicted deviation correction model, and the predicted deviation correction model corrects the resistor aging factor based on a statistical algorithm.

[0024] By adopting the above technical solution, the predicted deviation value R z(i+1) It will gradually decrease. In practical applications, the predicted deviation value can be used as the basis for data denoising, improve the efficiency of data processing, and facilitate self-learning of the model.

[0025] In a preferred example, the present application may be further configured as follows: in the step of correcting the resistor aging factor based on the statistical algorithm by the prediction deviation correction model, the following steps are included:

[0026] The prediction formula of the first predicted resistance data relative to the previous time is: R V(i+1) =[exp(st)]×R Vi ; and the actual resistance value corresponding to the first predicted resistance data is R m(i+1) , then the predicted deviation value R z(i+1) =R m(i+1) -R V(i+1) ;

[0027] The prediction results are weighted based on the Gaussian distribution function. The formula is:

[0028] Where f(z) is the weight value of the prediction result, and the value of σ is 1;

[0029] The resistance aging factor is corrected based on the predicted result weight value to obtain a corrected resistance aging factor.

[0030] By adopting the above technical scheme, the predicted value and the actual value are compared through the Gaussian distribution function, and the resistance aging factor s is corrected to improve the correlation of the prediction. The resistance aging factor s is continuously updated to improve the accuracy of the prediction, thereby further improving the accuracy of the motor life prediction.

[0031] In a preferred example, the present application can be further configured as follows: the construction of the environment judgment model includes the following steps:

[0032] Acquiring historical working environment data of the motor, wherein the working environment data includes ambient temperature, ambient humidity and dust concentration;

[0033] Performing data feature extraction on the working environment data to obtain an average value, a maximum value, and a minimum value corresponding to the working environment data;

[0034] Building a usage environment profile based on the historical working environment data and corresponding data features, wherein the labels of the usage environment profile include ambient temperature, ambient humidity and dust concentration;

[0035] Associating the usage environment portrait with the corresponding historical actual resistance value based on the timestamp to construct an environment-resistance change data set;

[0036] The data of the environment-resistance change data set is input into the environmental judgment model, the resistance change rate corresponding to different usage environment portraits is analyzed, and an environmental judgment model is constructed using a machine learning algorithm to generate environmental impact factors corresponding to different usage environment portraits. The environmental impact factors are used to reflect the degree of influence of different environments on the performance and life of the motor.

[0037] By adopting the above technical solution, customized designs are carried out for different working environments based on historical data to ensure that the model can accurately reflect the impact of the environment on the motor and provide a reliable basis for the motor's service life assessment. Compared with the existing motor life assessment, this solution has different calculation parameters for different usage environments, making the motor's service life assessment suitable for a variety of different usage environments, thereby improving the adaptability and accuracy of the motor life assessment.

[0038] In a preferred example, the present application can be further configured as follows: in the step of inputting the data of the environment-resistance change data set into the environment judgment model, analyzing the resistance change rate corresponding to different usage environment portraits, and using a machine learning algorithm to construct an environment judgment model to generate environmental impact factors corresponding to different usage environment portraits, the machine learning algorithm is a neural network machine algorithm.

[0039] By adopting the above technical solutions, the neural network machine algorithm can handle nonlinear relationships and has good modeling capabilities for complex relationship patterns in the environment-resistance change data set. Compared with traditional linear models, the neural network can more accurately capture the impact of environmental factors on the resistance change rate; the neural network machine algorithm can adaptively adjust the weights and parameters of the model by learning the characteristics and patterns of the input data. In the environmental judgment model, the neural network can learn the complex relationship of environmental influencing factors based on different usage environment portraits, thereby more accurately predicting the resistance change rate. The neural network machine algorithm is suitable for processing large-scale data sets and can learn more comprehensive environmental influencing factors from a large amount of environment-resistance change data.

[0040] In a preferred example, the present application can be further configured as follows: in the step of obtaining the historical fault data of the motor and generating the fault life correction data according to the historical fault data, the following steps are included:

[0041] Collecting historical fault data of the motor, wherein the historical fault data includes fault type, fault occurrence time, and fault repair time;

[0042] Classify and mark the historical fault data, and record the motor life loss values ​​corresponding to different historical fault data;

[0043] Performing a fault analysis based on the historical fault data and the corresponding motor life loss value, and establishing a fault life correction model by a statistical method based on the result of the fault analysis;

[0044] The fault life correction model is used to input the historical fault data and output the predicted correction value of the fault on the motor life as the fault life correction data.

[0045] By adopting the above technical scheme, a fault life correction model is established by conducting statistical analysis on historical fault data, such as the frequency of occurrence of a certain fault within a certain period of time, the distribution of life loss values ​​of different fault types, etc. The model can input historical fault data and output the predicted correction value of the fault on the life of the motor as fault life correction data. Establishing a fault life correction model helps to more accurately predict the impact of different faults on the life of the motor. The beneficial effect of this scheme over the prior art is that through the systematic collection, classification, recording and analysis of historical fault data, combined with statistical methods to establish a fault life correction model, it can more accurately predict the impact of different faults on the life of the motor, providing a basis for formulating more effective maintenance strategies and extending the life of the motor. In addition, this scheme can also help to provide early warning of potential faults, reduce maintenance costs, and improve the reliability and maintainability of the motor.

[0046] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions:

[0047] A motor service life assessment system, the motor service life assessment system comprising: a first aging prediction module, used to obtain the working data of the motor, and input the historical working data into a preset aging model for analysis to generate first aging prediction data;

[0048] An environment judgment module is used to obtain the working environment data of the motor, input the working environment data into a preset environment judgment model, and output the environmental impact factor;

[0049] A second aging prediction module, used for correcting the first aging prediction data based on the environmental influencing factors to generate second aging prediction data;

[0050] A life prediction module, used for presetting a life prediction model to calculate a basic motor service life according to the second aging prediction data;

[0051] A fault life correction module, used for acquiring historical fault data of the motor and generating fault life correction data according to the historical fault data, wherein the historical fault data includes the fault type and the fault time duration;

[0052] The service life assessment report generating module is used to correct the basic motor service life based on the fault life correction data to generate corrected service life data, and generate a motor service life assessment report based on the corrected service life data.

[0053] On the third aspect, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0054] 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 method for evaluating the service life of a motor when executing the computer program.

[0055] Fourthly, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0056] 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 method for evaluating the service life of a motor are implemented.

[0057] In summary, the present application includes at least one of the following beneficial technical effects:

[0058] 1. Output the first aging prediction data corresponding to the working data through the preset aging model, analyze the working data of the motor, and predict the aging state of the motor, which is helpful to identify potential problems of the motor in advance. The environmental impact factor reflects the degree of influence of the environment on the motor. Considering the influence of the working environment on the performance and life of the motor, compared with the existing life assessment of the motor limited to a certain working environment, this solution adds the dimension judgment of the working environment on the aging of the motor, and more accurately assesses the life of the motor under specific environmental conditions. By considering environmental factors, the service life of the motor can be more accurately assessed, so as to formulate a more accurate maintenance plan to ensure the reliability and stability of the motor under various environmental conditions. The service life of the basic motor is corrected according to the fault life correction data. By adding the fault life correction data to the basic motor service life or applying other correction methods, the corrected service life can be obtained. This step takes into account the influence of historical faults on the life of the motor, and further improves the accuracy of the motor service life assessment.

[0059] 2. By constructing a resistance data set and analyzing the resistance change trend of the motor, it is helpful to understand the aging speed of the motor and provide a more accurate basis for subsequent aging prediction. The aging model calculates two adjacent actual resistance value data in the resistance data set to generate a resistance aging factor for calculating the aging degree of the motor. The resistance prediction value is calculated by the resistance aging factor, and the resistance data is predicted based on the resistance aging factor, which improves the accuracy of the prediction and the accuracy of the motor life.

[0060] 3. Customized design for different working environments based on historical data to ensure that the model can accurately reflect the impact of the environment on the motor and provide a reliable basis for the motor life assessment. Compared with the existing motor life assessment, this solution has different calculation parameters for different use environments, making the motor life assessment applicable to a variety of different use environments, improving the adaptability and accuracy of the motor life assessment;

[0061] 4. By conducting statistical analysis on historical fault data, such as the frequency of occurrence of a certain fault within a certain period of time, the distribution of life loss values ​​of different fault types, etc., a fault life correction model is established. The model can input historical fault data and output the predicted correction value of the fault on the life of the motor as fault life correction data. Establishing a fault life correction model helps to more accurately predict the impact of different faults on the life of the motor. The beneficial effect of this scheme compared to the prior art is that through the systematic collection, classification, recording and analysis of historical fault data, combined with statistical methods to establish a fault life correction model, it can more accurately predict the impact of different faults on the life of the motor, and provide a basis for formulating more effective maintenance strategies and extending the life of the motor. In addition, this scheme can also help to provide early warning of potential faults, reduce maintenance costs, and improve the reliability and maintainability of the motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 is a flow chart of a method for evaluating the service life of a motor in one embodiment of the present application;

[0063] Figure 2 This is a principle block diagram of a motor service life assessment system in one embodiment of the present application;

[0064] Figure 3 It is a schematic diagram of an electronic device in an embodiment of the present application. Description of the drawings:

[0066] 1. First aging prediction module; 2. Environmental judgment module; 3. Second aging prediction module; 4. Life prediction module; 5. Fault life correction module; 6. Service life assessment report generation module. DETAILED DESCRIPTION

[0067] The present application is further described in detail below in conjunction with the accompanying drawings.

[0068] In one embodiment, if Figure 1 As shown, the present application discloses a method for evaluating the service life of a motor, which specifically includes the following steps:

[0069] S10: Acquire the working data of the motor, and input the historical working data into a preset aging model for analysis to generate first aging prediction data;

[0070] Specifically, it is necessary to obtain the past working data of the motor as historical working data, including parameters such as current, voltage, and speed, input the historical working data into a preset aging model for analysis, and output the first aging prediction data corresponding to the working data through the preset aging model. The aging state of the motor is predicted based on the analysis of the working data of the motor, which helps to identify potential problems of the motor in advance.

[0071] S20: Acquire working environment data of the motor, input the working environment data into a preset environment judgment model, and output an environmental impact factor;

[0072] Specifically, the working environment data of the motor is obtained, including parameters such as temperature, humidity, and vibration. Then, the working environment data is input into a preset environmental judgment model, which evaluates the impact of the environment on the performance and life of the motor based on the working environment data. The environmental impact factor reflects the degree of impact of the environment on the motor. Considering the impact of the working environment on the performance and life of the motor, compared with the existing life assessment of the motor limited to a certain working environment, this solution adds the dimension of the working environment to judge the aging of the motor, and more accurately evaluates the life of the motor under specific environmental conditions. By considering environmental factors, the service life of the motor can be more accurately evaluated, so as to formulate a more accurate maintenance plan to ensure the reliability and stability of the motor under various environmental conditions.

[0073] S30: Correcting the first aging prediction data based on the environmental influencing factors to generate second aging prediction data;

[0074] S40: a preset life prediction model calculates the basic motor service life according to the second aging prediction data;

[0075] Specifically, the second aging prediction data is generated in combination with actual working data and environmental factors to judge the service life of the motor. The service life of the motor is judged from multiple dimensions to improve the prediction accuracy of the service life of the motor.

[0076] S50: Acquire historical fault data of the motor, and generate fault life correction data according to the historical fault data, wherein the historical fault data includes the fault type and the fault time duration;

[0077] Specifically, historical fault data of the motor is obtained, including information such as fault type and fault duration, and fault life correction data is generated based on these historical fault data. In an embodiment of the present application, a fault life correction model is used to generate fault life correction data. The model can be established and verified based on historical fault data to predict the impact of the fault on the life of the motor.

[0078] S60: Correcting the basic motor service life based on the fault life correction data to generate corrected service life data, and generating a motor service life assessment report based on the corrected service life data;

[0079] Specifically, the service life of the basic motor will be corrected according to the fault life correction data. The corrected service life can be obtained by adding the fault life correction data to the service life of the basic motor or applying other correction methods. In the embodiment of the present application, the service life assessment report includes the motor's usage time, predicted effective usage time and maintenance and replacement schedule. This step takes into account the impact of historical faults on the motor life, further improving the accuracy of the motor service life assessment. Based on actual experience, a threshold is preset for determining whether the motor needs to be replaced, wherein the working data includes the motor's armature current data and voltage data. In the embodiment of the present application, the armature resistance is used as the judgment threshold. When the armature resistance value reaches the preset judgment threshold, it indicates that the motor needs to be replaced or maintained.

[0080] Specifically, in S10: obtaining the working data of the motor, and inputting the historical working data into a preset aging model for analysis to generate the first aging prediction data, the steps include the following:

[0081] S11: Acquire the armature current data and voltage data, and associate the armature current data and voltage data based on a timestamp, and calculate the actual armature resistance value according to the armature current data and voltage data. The specific actual resistance value calculation formula is: Rm=Um / Im, wherein Rm is the actual resistance value, Um is the voltage data, and Im is the armature current data;

[0082] Specifically, in the embodiment of the present application, Um is regarded as a stable value, so that the actual resistance value is calculated by detecting the actual armature current data of the motor, and the aging condition of the motor is judged based on the actual resistance value. In other embodiments, other working data of the motor can be used as the basis for judging the aging condition.

[0083] S12: Recording the actual resistance value in history based on the timestamp, and constructing a resistance data set based on the actual resistance value in history;

[0084] Specifically, in the embodiment of the present application, the unit of the timestamp is day, and the actual resistance value of the motor is obtained every day, and the obtained actual resistance value is used to construct a resistance data set.

[0085] S13: The aging model analyzes the resistance data set to generate a resistance aging factor, wherein the calculation formula of the resistance aging factor is s=[(R m(i+1) -Rmi ) / R i ] / Δt, where Δt is a preset time interval and i is the number of records;

[0086] Specifically, the aging model generates a resistance aging factor for calculating the aging degree of the motor by calculating two adjacent actual resistance value data, and calculates the resistance prediction value by the resistance aging factor.

[0087] S14: The aging model predicts first aging prediction data corresponding to a certain time in the future based on the resistance aging factor, wherein the first aging prediction data includes first predicted resistance data, and the calculation formula of the first predicted resistance data is: R Vi =r×exp(st), where r is the rated armature resistance;

[0088] In this scheme, resistance data is predicted based on the resistance aging factor to improve the accuracy of the prediction and the accuracy of the motor life. It should be noted that the value of r can be modified according to actual conditions. It can be the resistance value used for the first time or the average resistance value within a certain time interval during the previous use.

[0089] After the step of predicting the first aging prediction data corresponding to a certain time in the future based on the resistance aging factor by the aging model in S14, the following steps are included:

[0090] S141: Obtain the actual resistance value corresponding to a certain time in the future, and compare it with the first predicted resistance data corresponding to the time to generate a predicted deviation value R z , based on the historical forecast deviation value R z Constructing a set of prediction deviations;

[0091] S142: Inputting the predicted deviation number set into a preset predicted deviation correction model, wherein the predicted deviation correction model corrects the resistor aging factor based on a statistical algorithm.

[0092] Specifically, in the step of correcting the resistor aging factor using the prediction deviation correction model based on a statistical algorithm, the following steps are included:

[0093] The prediction formula of the first predicted resistance data relative to the previous time is: R V(i+1) =[exp(st)]×R Vi ; and the actual resistance value corresponding to the first predicted resistance data is R m(i+1) , then the predicted deviation value R z(i+1) =R m(i+1) -R V(i+1) ;

[0094] The prediction results are weighted based on the Gaussian distribution function. The formula is:

[0095] Where f(z) is the weight value of the prediction result, and the value of σ is 1;

[0096] The resistor aging factor is corrected based on the predicted result weight value to obtain a corrected resistor aging factor.

[0097] In the embodiment of the present application, the actual value at time i+1 is obtained and combined with the predicted value at time i+1, and the corresponding weight of each resistance value prediction is calculated by the time resistance value collected at time i+1. The closer the predicted value is to the actual value, the greater the weight. This is reflected in the Gaussian distribution function, that is, the closer to the peak value, the greater the weight. Specifically, the larger the value of f(z), the greater the value of f(z). The value of f(z) is used as the basis for judging the correlation, and the predicted value and the actual value are compared through the Gaussian distribution function, and the resistance aging factor s is corrected to improve the correlation of the prediction. The resistance aging factor s is continuously updated to improve the accuracy of the prediction, thereby further improving the accuracy of the motor life prediction.

[0098] It should be noted that the predicted deviation value R z(i+1) will gradually decrease, but because of fluctuations in actual working conditions, the predicted deviation value R z(i+1) It is difficult to approach 0. In practical applications, the predicted deviation value can be used as the basis for data denoising, improve the efficiency of data processing, and facilitate self-learning of the model.

[0099] In step S20: obtaining the working environment data of the motor, and inputting the working environment data into a preset environment judgment model, and outputting the environmental impact factor, the construction of the environment judgment model includes the following steps:

[0100] S21: Acquire historical working environment data of the motor, wherein the working environment data includes ambient temperature, ambient humidity and dust concentration;

[0101] S22: extracting data features from the working environment data to obtain an average value, a maximum value, and a minimum value corresponding to the working environment data;

[0102] S23: constructing a usage environment portrait based on the historical working environment data and corresponding data features, wherein the labels of the usage environment portrait include ambient temperature, ambient humidity and dust concentration;

[0103] S24: associating the usage environment portrait with the corresponding historical actual resistance value based on the timestamp to construct an environment-resistance change data set;

[0104] S25: Input the data of the environment-resistance change data set into the environment judgment model, analyze the resistance change rate corresponding to different usage environment portraits, and use a machine learning algorithm to build an environment judgment model to generate environmental impact factors corresponding to different usage environment portraits. The environmental impact factors are used to reflect the degree of influence of different environments on the performance and life of the motor.

[0105] Among them, the machine learning algorithm used to construct the environmental judgment model is a neural network machine algorithm. It should be noted that the environmental judgment model has life prediction for different use environments. For example, the first environmental portrait, the second environmental portrait and the third environmental portrait are constructed using environmental portraits, wherein the environmental temperature of the first environmental portrait is 25-30°C, the environmental humidity is 75-80%, and the dust concentration is 20-50%; the environmental temperature of the second environmental portrait is 25-30°C, the environmental humidity is 80-85%, and the dust concentration is 20-50%; the environmental temperature of the third environmental portrait is 20-50°C, the environmental humidity is 50-55%, and the dust concentration is 20-50%. In the embodiment of the present application, the first environmental portrait among the three different environmental portraits is selected as the benchmark, and the resistance change rate of the second environmental portrait and the third environmental portrait relative to the first environmental portrait is analyzed. In the embodiment of the present application, the resistance change rate of the second environmental portrait is 20% greater than that of the first environmental portrait, then the environmental impact factor of the second environmental portrait is 1.2, and similarly, the third environmental portrait is 25% greater than the first environmental portrait, then the environmental impact factor of the third environmental portrait is 1.25.

[0106] Based on historical data, customized designs are performed for different working environments to ensure that the model can accurately reflect the impact of the environment on the motor and provide a reliable basis for the motor's service life assessment. Compared with the existing motor life assessment, this solution has different calculation parameters for different usage environments, making the motor's service life assessment applicable to a variety of different usage environments, thereby improving the adaptability and accuracy of the motor's life assessment.

[0107] In step S50: acquiring historical fault data of the motor and generating fault life correction data according to the historical fault data, the following steps are included:

[0108] S51: Collecting historical fault data of the motor, wherein the historical fault data includes fault type, fault occurrence time, and fault repair time;

[0109] Specifically, the historical fault data collected includes brush wear, winding breakage, bearing failure, etc. Each fault should include the fault type (such as wear, breakage, fault level, etc.), fault occurrence time, and fault repair time. By collecting historical fault data, a comprehensive fault database can be established, which helps to gain a deeper understanding of the fault characteristics and trends of the motor and provide data support for subsequent fault analysis and life correction model establishment.

[0110] S52: Classify and mark the historical fault data, and record the motor life loss values ​​corresponding to different historical fault data;

[0111] Specifically, different types of faults are classified and marked, such as wear, wire breakage, bearing failure, etc., and the motor life loss value corresponding to each fault is recorded. In the embodiment of the present application, the motor life loss value is a specific value, which indicates the degree of influence of the fault on the motor life. For example, wear faults will reduce the service life of the motor by 100 days. By classifying and marking historical fault data and recording life loss values, the influence of different faults on the motor life is quantified, which provides a basis for subsequent fault analysis and life correction model establishment.

[0112] S53: performing a fault analysis based on the historical fault data and the corresponding motor life loss value, and establishing a fault life correction model by a statistical method based on the result of the fault analysis;

[0113] The fault life correction model is used to input the historical fault data and output the predicted correction value of the fault on the motor life as the fault life correction data.

[0114] Specifically, by conducting statistical analysis on historical fault data, such as the frequency of occurrence of a certain fault within a certain period of time, the distribution of life loss values ​​of different fault types, etc., a fault life correction model is established. The model can input historical fault data and output the predicted correction value of the fault on the motor life as fault life correction data. Establishing a fault life correction model helps to more accurately predict the impact of different faults on the motor life, and provide a basis for formulating maintenance plans and extending the motor life.

[0115] It is further explained that the beneficial effect of this solution compared with the existing technology is that through the systematic collection, classification, recording and analysis of historical fault data, combined with statistical methods to establish a fault life correction model, it can more accurately predict the impact of different faults on the life of the motor, and provide a basis for formulating more effective maintenance strategies and extending the life of the motor. In addition, this solution can also help to warn of potential faults in advance, reduce maintenance costs, and improve the reliability and maintainability of the motor.

[0116] 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.

[0117] In one embodiment, a motor service life assessment system is provided, and the motor service life assessment system corresponds one-to-one to the motor service life assessment method in the above embodiment. Figure 2 As shown, the motor service life assessment system includes a first aging prediction module 1, which is used to obtain the working data of the motor, and input the historical working data into a preset aging model for analysis to generate first aging prediction data;

[0118] The environment judgment module 2 is used to obtain the working environment data of the motor, input the working environment data into a preset environment judgment model, and output the environmental impact factor;

[0119] A second aging prediction module 3, used to correct the first aging prediction data based on the environmental influencing factors to generate second aging prediction data;

[0120] A life prediction module 4, used for presetting a life prediction model to calculate a basic motor service life according to the second aging prediction data;

[0121] A fault life correction module 5 is used to obtain historical fault data of the motor and generate fault life correction data according to the historical fault data, wherein the historical fault data includes the fault type and the fault time duration;

[0122] The service life assessment report generating module 6 is used to correct the basic motor service life based on the fault life correction data to generate corrected service life data, and generate a motor service life assessment report based on the corrected service life data.

[0123] For the specific definition of the motor service life assessment system, please refer to the definition of the motor service life assessment method mentioned above, which will not be repeated here. Each module in the above motor service life assessment 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.

[0124] 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 3As 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 method for evaluating the service life of a motor is implemented.

[0125] 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:

[0126] Acquire the working data of the motor, and input the historical working data into a preset aging model for analysis to generate first aging prediction data;

[0127] Acquire the working environment data of the motor, input the working environment data into a preset environment judgment model, and output the environmental impact factor;

[0128] Correcting the first aging prediction data based on the environmental influencing factors to generate second aging prediction data;

[0129] The preset life prediction model calculates the basic motor service life according to the second aging prediction data;

[0130] Acquire historical fault data of the motor, and generate fault life correction data according to the historical fault data, wherein the historical fault data includes the fault type and the fault time duration;

[0131] The basic motor service life is corrected based on the fault life correction data to generate corrected service life data, and a motor service life assessment report is generated based on the corrected service life data.

[0132] 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:

[0133] Acquire the working data of the motor, and input the historical working data into a preset aging model for analysis to generate first aging prediction data;

[0134] Acquire the working environment data of the motor, input the working environment data into a preset environment judgment model, and output the environmental impact factor;

[0135] Correcting the first aging prediction data based on the environmental influencing factors to generate second aging prediction data;

[0136] The preset life prediction model calculates the basic motor service life according to the second aging prediction data;

[0137] Acquire historical fault data of the motor, and generate fault life correction data according to the historical fault data, wherein the historical fault data includes the fault type and the fault time duration;

[0138] The basic motor service life is corrected based on the fault life correction data to generate corrected service life data, and a motor service life assessment report is generated based on the corrected service life data.

[0139] 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).

[0140] 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.

[0141] 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 method for evaluating the service life of a motor, characterized in that: The method comprises the following steps: obtaining the working data of the motor, and inputting the historical working data into a preset aging model for analysis to generate first aging prediction data; Acquire the working environment data of the motor, input the working environment data into a preset environment judgment model, and output the environmental impact factor; Correcting the first aging prediction data based on the environmental influencing factors to generate second aging prediction data; The preset life prediction model calculates the service life of the motor according to the second aging prediction data; Acquire historical fault data of the motor, and generate fault life correction data according to the historical fault data, wherein the historical fault data includes the fault type and the fault time duration; Correcting the service life of the motor based on the fault life correction data to generate corrected service life data, and generating a motor service life assessment report based on the corrected service life data; Wherein, in the step of obtaining the working data of the motor and inputting the historical working data into a preset aging model for analysis to generate the first aging prediction data, the working data includes the armature current data and voltage data of the motor, including the following steps: The armature current data and voltage data are obtained, and the armature current data and voltage data are associated based on the timestamp, and the actual armature resistance value is calculated according to the armature current data and voltage data. The specific actual resistance value calculation formula is: = ,in is the actual resistance value, is the voltage data, is the armature current data; Recording the actual resistance value based on a timestamp, and constructing a resistance data set based on the actual resistance value; The aging model analyzes the resistance data set to generate a resistance aging factor, wherein the calculation formula of the resistance aging factor is: ,in is a preset time interval, i is the number of records; The aging model predicts first aging prediction data corresponding to a certain time in the future based on the resistance aging factor, wherein the first aging prediction data includes first predicted resistance data, and the calculation formula of the first predicted resistance data is: , where r is the rated armature resistance value and s is the resistance aging factor; Obtain the actual resistance value corresponding to a certain time in the future, and compare it with the first predicted resistance data corresponding to the time to generate a predicted deviation value , based on the historical forecast deviation value Construct a set of prediction deviations; The predicted deviation number set is input into a preset predicted deviation correction model, and the predicted deviation correction model corrects the resistor aging factor based on a statistical algorithm.

2. The method for evaluating the service life of a motor according to claim 1, characterized in that: In the step of correcting the resistor aging factor using the prediction deviation correction model based on a statistical algorithm, the following steps are included: The prediction formula of the first predicted resistance data relative to the previous time is: ; and the actual resistance value corresponding to the first predicted resistance data is , then the predicted deviation value - ; The prediction results are weighted based on the Gaussian distribution function. The formula is: ],in is the weight value of the prediction result, The value of is 1; The resistance aging factor is corrected based on the predicted result weight value to obtain a corrected resistance aging factor; Among them, the actual value at time i+1 is obtained and combined with the predicted value at time i+1, and the corresponding weight of each resistance value prediction is calculated through the time resistance value collected at time i+1. The closer the predicted value is to the actual value, the greater the weight is. This is reflected in the Gaussian distribution function, that is, the closer to the peak value, the greater the weight is. Specifically, the larger the value of f(z) is, the greater the value of f(z) is. The value of f(z) is used as the basis for judging the correlation, and the predicted value and the actual value are compared through the Gaussian distribution function, and the resistance aging factor s is corrected to improve the correlation of the prediction. The resistance aging factor s is continuously updated to improve the accuracy of the prediction, thereby further improving the accuracy of the motor life prediction.

3. A method for evaluating the service life of a motor according to claim 1, characterized in that: The construction of the environment judgment model includes the following steps: Acquiring historical working environment data of the motor, wherein the working environment data includes ambient temperature, ambient humidity and dust concentration; Performing data feature extraction on the working environment data to obtain an average value, a maximum value, and a minimum value corresponding to the working environment data; Building a usage environment profile based on the historical working environment data and corresponding data features, wherein the labels of the usage environment profile include ambient temperature, ambient humidity and dust concentration; Associating the usage environment portrait with the corresponding historical actual resistance value based on the timestamp to construct an environment-resistance change data set; The data of the environment-resistance change data set is input into the environmental judgment model, the resistance change rate corresponding to different usage environment portraits is analyzed, and an environmental judgment model is constructed using a machine learning algorithm to generate environmental impact factors corresponding to different usage environment portraits. The environmental impact factors are used to reflect the degree of influence of different environments on the performance and life of the motor.

4. A method for evaluating the service life of a motor according to claim 3, characterized in that: In the step of inputting the data of the environment-resistance change data set into the environment judgment model, analyzing the resistance change rate corresponding to different usage environment portraits, and using a machine learning algorithm to build an environment judgment model to generate environmental impact factors corresponding to different usage environment portraits, the machine learning algorithm is a neural network machine algorithm.

5. A method for evaluating the service life of a motor according to claim 1, characterized in that: The step of obtaining the historical fault data of the motor and generating the fault life correction data according to the historical fault data includes the following steps: Collecting historical fault data of the motor, wherein the historical fault data includes fault type, fault occurrence time, and fault repair time; Classify and mark the historical fault data, and record the motor life loss values ​​corresponding to different historical fault data; Performing a fault analysis based on the historical fault data and the corresponding motor life loss value, and establishing a fault life correction model by a statistical method based on the result of the fault analysis; The fault life correction model is used to input the historical fault data and output the predicted correction value of the fault on the motor life as the fault life correction data.

6. A motor service life assessment system, applied to a motor service life assessment method as described in any one of claims 1 to 5, characterized in that: It comprises a first aging prediction module (1) for acquiring working data of the motor and inputting the historical working data into a preset aging model for analysis to generate first aging prediction data; An environmental judgment module (2) is used to obtain working environment data of the motor, input the working environment data into a preset environmental judgment model, and output an environmental impact factor; A second aging prediction module (3), configured to modify the first aging prediction data based on the environmental influencing factor to generate second aging prediction data; A life prediction module (4), used for presetting a life prediction model to calculate the life of the motor according to the second aging prediction data; A fault life correction module (5) is used to obtain historical fault data of the motor and generate fault life correction data based on the historical fault data, wherein the historical fault data includes the fault type and the fault time duration; A service life assessment report generating module (6) is used to correct the service life of the motor based on the fault life correction data to generate corrected service life data, and to generate a motor service life assessment report based on the corrected service life data.

7. 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 steps of the method for evaluating the service life of a motor as claimed in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating the service life of a motor as claimed in any one of claims 1 to 5 are implemented.

Images