Motor intelligent optimization method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of motor control. The invention relates to a motor intelligent optimization method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining motor operation state information, inputting the motor operation state information into an early warning model, analyzing the motor operation state information through the early warning model, obtaining early warning information, and adjusting the operation parameters of a motor according to the early warning information. And optimizing the motor operation parameters to obtain optimized motor operation parameters, and generating motor operation control information based on the optimized motor operation parameters, the motor operation control information being used for adjusting the working state of the motor. The application has the effect of improving the stability and efficiency of motor operation.

Description

Technical Field

[0001] The present invention relates to the technical field of motor control, and in particular to a motor intelligent optimization method, device, computer equipment and storage medium. Background Art

[0002] As an important power equipment in modern industry, the operating status of motors is directly related to production efficiency and equipment safety. Traditional motor maintenance methods rely on regular manual inspections, but this method is inefficient and difficult to detect potential problems in a timely manner. With the development of technology, real-time monitoring and early warning of motor operating status have become possible, but how to accurately analyze the motor status and optimize the motor operating parameters based on the early warning information is still a technical problem. Therefore, it is particularly important to develop a method that can intelligently optimize motor operation. Summary of the invention

[0003] In order to improve the stability and efficiency of motor operation, the present application provides a motor intelligent optimization method, device, computer equipment and storage medium.

[0004] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A motor intelligent optimization method, the motor intelligent optimization method comprising: Get the motor running status information; Inputting the motor operation status information into the early warning model, analyzing the motor operation status information through the early warning model to obtain early warning information; According to the warning information, adjusting the operating parameters of the motor to obtain optimized motor operating parameters; Based on the optimized motor operation parameters, motor operation control information is generated, and the motor operation control information is used to adjust the working state of the motor.

[0005] By adopting the above technical solution, the early warning model is used to analyze the motor operation status information in real time, so that potential abnormal conditions can be identified in advance and early warning information can be generated. After the abnormality is found, the motor operation parameters are quickly adjusted according to the early warning information, so that the motor can be adjusted to the optimal state in time before the problem occurs, avoiding further deterioration of the fault. In this way, sudden faults in the operation of the motor can be effectively reduced and the operation stability of the motor can be improved. By applying the optimized motor operation parameters, targeted motor operation control information is generated in real time, so that the motor can operate in an optimized state under various working conditions. This real-time adjustment and optimization mechanism enables the energy consumption and performance of the motor to be dynamically adjusted according to actual needs, thereby reducing unnecessary energy consumption and improving the overall operation efficiency of the motor. Through the early warning model and real-time parameter adjustment mechanism, the operation control of the motor is transformed from the traditional fixed setting to intelligent, adaptive dynamic adjustment. This intelligent control method can adapt to changing operating conditions, so that the motor can maintain efficient and stable operation under different loads, environments and operating conditions, further improving the reliability and service life of the motor. Identifying and handling potential abnormal conditions of the motor in advance reduces the probability of sudden equipment failures, thereby reducing maintenance frequency and costs. By optimizing the operating parameters of the motor, stress and wear during operation are reduced, which indirectly extends the service life of the equipment and reduces production losses caused by downtime due to faults.

[0006] In a preferred example, the present application may be further configured as follows: the obtaining of the motor operation status information includes: Remotely monitor the current information, voltage information, speed information and temperature information of the motor; The current information, the voltage information, the speed information and the temperature information are processed in real time to generate the motor operation status information.

[0007] By adopting the above technical solution, by remotely monitoring the current information, voltage information, speed information and temperature information of the motor and processing this information in real time to generate the motor operation status information, remote real-time monitoring of the motor can be realized, which not only reduces the dependence on on-site manual inspections, but also can promptly detect abnormalities in the operation of the motor, thereby improving the efficiency and response speed of monitoring, effectively preventing the occurrence of potential faults, and ensuring the continuity and stability of the motor operation.

[0008] In a preferred example, the present application may be further configured as follows: the motor operation status information is input into the early warning model, and the motor operation status information is analyzed by the early warning model to obtain early warning information, which includes: Acquire historical operation information of the motor, and use the historical operation information of the motor as a training set and a test set; According to the training set, the initial warning model is trained to generate a warning model in training; The test set is used to verify and optimize the early warning model in training to obtain the early warning model.

[0009] By adopting the above technical solution, the historical operation information and fault information of the motor are obtained, and by constructing a training set and a test set with this information, the training set is trained using a machine learning algorithm to generate a warning model, and the test set is used for verification and optimization. In this way, a more accurate warning model can be constructed, and the ability to identify potential motor faults is improved, thereby ensuring that the motor can be effectively handled before an abnormality occurs, further improving the stability and efficiency of the motor operation.

[0010] In a preferred example, the present application may be further configured as follows: the motor operation status information is input into the early warning model, and the motor operation status information is analyzed by the early warning model to obtain early warning information, including: The early warning model analyzes the motor operation status information, determines whether the motor status is abnormal, and obtains a model analysis result; According to the model analysis result, when it is identified that the state of the motor is abnormal, the warning information is obtained.

[0011] By adopting the above technical solution, the motor operating status information is input into the early warning model. The early warning model analyzes the motor operating status information, determines whether there is any abnormality in the motor status, and generates early warning information. It can identify potential problems in the motor operation in advance and provide timely early warnings, thereby preventing small problems from evolving into serious faults, significantly improving the safety and stability of the motor operation, and helping to maintain the efficient operation of the motor.

[0012] In a preferred example, the present application may be further configured as follows: adjusting the operating parameters of the motor according to the warning information to obtain optimized motor operating parameters includes: According to the warning information, obtaining abnormal type information of the motor; Based on the abnormality type information, a parameter adjustment strategy corresponding to the abnormality type information is selected, and the operating parameters of the motor are adjusted according to the parameter adjustment strategy to obtain the optimized motor operating parameters.

[0013] By adopting the above technical solution, the operating parameters of the motor are adjusted according to the early warning information to obtain optimized motor operating parameters, which can enable the motor to quickly self-adjust after an abnormality occurs and return to the optimal operating state, thereby effectively avoiding the reduction in efficiency or expansion of faults due to improper parameters, and further improving the operating efficiency and stability of the motor.

[0014] In a preferred example, the present application may be further configured as follows: based on the abnormality type information, selecting a parameter adjustment strategy corresponding to the abnormality type information, adjusting the operating parameters of the motor according to the parameter adjustment strategy, and obtaining the optimized motor operating parameters, further comprising: The abnormal type information is classified and predicted by a random forest algorithm to obtain the parameter adjustment strategy with the highest matching degree with the abnormal type information.

[0015] By adopting the above technical solution, the abnormal type information is classified and predicted through the random forest algorithm, and the parameter adjustment strategy with the highest matching degree with the abnormal type information is obtained. It can accurately match the optimal adjustment strategy for the current abnormal situation, making the motor parameter adjustment more targeted and effective, thereby restoring the normal operating state of the motor in the shortest time, and further ensuring the operating stability and efficiency of the motor.

[0016] In a preferred example, the present application may be further configured as follows: generating motor operation control information based on the optimized motor operation parameters, wherein the motor operation control information is used to adjust the working state of the motor, including: Determine the target working state of the motor according to the optimized motor operating parameters, analyze the difference between the current motor operating state and the target working state according to the target working state, and obtain the control information that needs to be adjusted; The motor operation control information is generated according to the control information that needs to be adjusted, and the motor operation control information is used to adjust the working state of the motor.

[0017] By adopting the above technical solution, based on the optimized motor operating parameters, motor operation control information is generated to adjust the working state of the motor, including determining the target working state of the motor, analyzing the difference between the current operating state of the motor and the target working state, obtaining the control information that needs to be adjusted, and generating corresponding motor operation control information, it can ensure that the motor is always adjusted to the optimal state during operation, thereby maintaining stable and efficient operation of the motor, reducing energy consumption and extending equipment life.

[0018] The second object of the invention is achieved by the following technical solutions: A motor intelligent optimization device, characterized in that the motor intelligent optimization device comprises: Status monitoring module, used to obtain motor operation status information; An early warning analysis module, used for inputting the motor operation status information into an early warning model, analyzing the motor operation status information through the early warning model, and obtaining early warning information; A parameter optimization module, used for adjusting the operating parameters of the motor according to the warning information to obtain optimized motor operating parameters; The control generation module is used to generate motor operation control information based on the optimized motor operation parameters, and the motor operation control information is used to adjust the working state of the motor.

[0019] By adopting the above technical solution, the early warning model is used to analyze the motor operation status information in real time, so that potential abnormal conditions can be identified in advance and early warning information can be generated. After the abnormality is found, the motor operation parameters are quickly adjusted according to the early warning information, so that the motor can be adjusted to the optimal state in time before the problem occurs, avoiding further deterioration of the fault. In this way, sudden faults in the operation of the motor can be effectively reduced and the operation stability of the motor can be improved. By applying the optimized motor operation parameters, targeted motor operation control information is generated in real time, so that the motor can operate in an optimized state under various working conditions. This real-time adjustment and optimization mechanism enables the energy consumption and performance of the motor to be dynamically adjusted according to actual needs, thereby reducing unnecessary energy consumption and improving the overall operation efficiency of the motor. Through the early warning model and real-time parameter adjustment mechanism, the operation control of the motor is transformed from the traditional fixed setting to intelligent, adaptive dynamic adjustment. This intelligent control method can adapt to changing operating conditions, so that the motor can maintain efficient and stable operation under different loads, environments and operating conditions, further improving the reliability and service life of the motor. Identifying and handling potential abnormal conditions of the motor in advance reduces the probability of sudden equipment failures, thereby reducing maintenance frequency and costs. By optimizing the operating parameters of the motor, stress and wear during operation are reduced, which indirectly extends the service life of the equipment and reduces production losses caused by downtime due to faults.

[0020] The third objective of the present application is achieved through the following technical solutions: A computer 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 intelligent optimization method when executing the computer program.

[0021] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which implements the steps of the above-mentioned motor intelligent optimization method when executed by a processor.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. Real-time analysis of the motor operation status information through the early warning model can identify potential abnormal conditions in advance and generate early warning information. After the abnormality is found, the motor's operating parameters are quickly adjusted according to the early warning information, so that the motor can be adjusted to the optimal state in time before the problem occurs, avoiding further deterioration of the fault. In this way, sudden faults in the motor operation can be effectively reduced and the operating stability of the motor can be improved. By applying the optimized motor operating parameters, targeted motor operation control information is generated in real time, so that the motor can operate in an optimized state under various working conditions. This real-time adjustment and optimization mechanism enables the energy consumption and performance of the motor to be dynamically adjusted according to actual needs, thereby reducing unnecessary energy consumption and improving the overall operating efficiency of the motor. Through the early warning model and real-time parameter adjustment mechanism, the motor's operation control is transformed from traditional fixed settings to intelligent, adaptive dynamic adjustment. This intelligent control method can adapt to changing operating conditions, so that the motor can maintain efficient and stable operation under different loads, environments and operating conditions, further improving the reliability and service life of the motor. Identifying and handling potential abnormal conditions of the motor in advance reduces the probability of sudden equipment failures, thereby reducing maintenance frequency and costs. By optimizing the operating parameters of the motor, the stress and wear during operation are reduced, which indirectly extends the service life of the equipment and reduces production losses caused by downtime due to failures; 2. By remotely monitoring the motor's current, voltage, speed and temperature information and processing this information in real time to generate motor operation status information, remote real-time monitoring of the motor can be achieved, which not only reduces the reliance on on-site manual inspections, but also can promptly detect abnormalities in motor operation, thereby improving monitoring efficiency and response speed, effectively preventing the occurrence of potential faults, and ensuring the continuity and stability of motor operation; 3. Based on the optimized motor operating parameters, the motor operation control information is generated to adjust the working state of the motor, including determining the target working state of the motor, analyzing the difference between the current operating state and the target working state of the motor, obtaining the control information that needs to be adjusted, and generating the corresponding motor operation control information, which can ensure that the motor is always adjusted to the best state during operation, thereby maintaining the stable and efficient operation of the motor, reducing energy consumption and extending the life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a motor intelligent optimization method in one embodiment of the present application; Figure 2 This is a flowchart for implementing step S10 of the motor intelligent optimization method in one embodiment of the present application; Figure 3 This is a flowchart of the implementation of the motor intelligent optimization method before step S20 in an embodiment of the present application; Figure 4This is a flowchart for implementing step S20 of the motor intelligent optimization method in one embodiment of the present application; Figure 5 This is a flowchart for implementing step S30 of the motor intelligent optimization method in one embodiment of the present application; Figure 6 This is a flowchart for implementing step S302 of the motor intelligent optimization method in one embodiment of the present application; Figure 7 This is a flowchart for implementing step S40 of the motor intelligent optimization method in one embodiment of the present application; Figure 8 This is a principle block diagram of a motor intelligent optimization device in one embodiment of the present application; Fig. 9 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a motor intelligent optimization method, which specifically includes the following steps: S10: Obtain the motor operation status information.

[0026] In this embodiment, the motor operation status information refers to real-time operation information generated by the motor during operation.

[0027] Specifically, the operation data of the motor is acquired through remote monitoring, and the real-time operation information of the motor is collected using current sensors, voltage sensors, temperature sensors, speed sensors, etc. The real-time operation information is preprocessed and integrated to obtain the motor operation status information.

[0028] S20: Inputting the motor operation status information into the early warning model, analyzing the motor operation status information through the early warning model, and obtaining early warning information.

[0029] In this embodiment, the early warning model refers to a prediction model based on a random forest algorithm, which is used to identify abnormal conditions in the operation state of the motor. The early warning information refers to the prediction results of potential motor failures or abnormal operation obtained by the early warning model analysis.

[0030] Specifically, the motor operation status information is input into the input layer of the early warning model. The model has been trained and optimized through a large amount of historical data and fault cases to form a stable classification and prediction capability. The random forest model consists of multiple decision trees. Each decision tree receives the input feature data, splits the feature values ​​and selects the decision nodes, and finally outputs the classification results. The results of each decision tree are voted, and the random forest generates the final early warning information by integrating these voting results. The hierarchical nonlinear mapping in the model is completed by combining each decision tree. Each decision tree runs independently under different feature combinations, and optimizes the prediction accuracy of different fault types through weight adjustment, thereby calculating the health index or abnormal probability of the current state of the motor. The output layer integrates these probabilities and classification results to obtain early warning information, indicating the abnormal situation, type, and severity of the motor.

[0031] S30: According to the early warning information, the operating parameters of the motor are adjusted to obtain optimized operating parameters of the motor.

[0032] In this embodiment, the optimized motor operating parameters refer to parameters achieved by adjusting the motor operation, such as optimized current setting, speed adjustment or temperature control value, to maintain the motor operating in the best operating state.

[0033] Specifically, by receiving the warning information, the random forest algorithm is called to adjust the current operating parameters of the motor. The random forest algorithm uses the type and severity of the abnormality in the warning information to select the corresponding parameter adjustment strategy. For example, when the motor is detected to be overheated, the current setting value is lowered or the speed is reduced; if the current is detected to be too large and accompanied by increased vibration, the current limit is adjusted or the current slope is reset. The optimization process includes real-time monitoring of the adjusted parameter changes and evaluating the adjustment effect. If the effect does not meet expectations, iterative optimization will continue until the motor operating state reaches a safe and stable range.

[0034] Furthermore, the random forest algorithm is selected as the optimization algorithm to use the abnormal features in the warning information to adjust the operating parameters of the motor. The random forest algorithm integrates multiple decision trees to classify and predict the adjustment strategy according to the abnormal type and severity in the current operating status information of the motor. In this process, each decision tree is trained based on a different feature subset, independently evaluates the motor operating status, and outputs adjustment suggestions. Finally, the random forest algorithm combines the outputs of all decision trees and determines the optimal parameter adjustment strategy through a majority voting mechanism.

[0035] S40: Based on the optimized motor operation parameters, generate motor operation control information, where the motor operation control information is used to adjust the working state of the motor.

[0036] In this embodiment, the motor operation control information refers to instructions for directly controlling the operation of the motor, such as start, stop, accelerate, decelerate, adjust current and the like.

[0037] Specifically, by analyzing the optimized motor operating parameters, a series of control instruction sets are generated, which include the adjustment signal for the motor speed, the control command for current adjustment, and the command signal for temperature adjustment. The control information is sent to the motor drive part through the control interface, and the drive part adjusts the actual operating state of the motor according to the received signal. The signal processing process includes quantitative control of the input parameters, such as the gradual increase or decrease of the current, the gradual adjustment of the speed, and the real-time control of the temperature, so that the motor runs under the optimized conditions. The execution of the entire control instruction is synchronized with the real-time feedback of the motor to ensure the precise response and adjustment of the instruction, thereby realizing the continuous optimization and control of the motor operation.

[0038] In one embodiment, if Figure 2 As shown, in step S10, the motor operation status information is obtained, including: S101: Remotely monitor the current information, voltage information, speed information and temperature information of the motor.

[0039] Specifically, current sensors, voltage sensors, temperature sensors and speed sensors are used to collect the running information of the motor in real time. The sensors amplify and convert the collected analog signals into digital information.

[0040] S102: Process the current information, voltage information, speed information and temperature information in real time to generate motor operation status information.

[0041] Specifically, after receiving the current, voltage, speed and temperature information of the motor, the information is first cleaned to filter out the noise information generated by interference during the transmission process to obtain the cleaned information. The cleaned information is converted into a unified format, all sensor information is synchronized to the same timestamp, and information with inconsistent units is standardized. Then, the information fusion algorithm is used to comprehensively process various sensor information, such as calculating real-time power by fusing current and voltage information through the weighted average method, and evaluating the load status and heat loss of the motor by combining speed and temperature information. Thereby generating motor operation status information containing multi-dimensional information.

[0042] Furthermore, in order to achieve an accurate assessment of the motor's operating status, the current and voltage information are fused by the weighted average method to calculate the real-time power. In this process, the real-time collected current and voltage information is first filtered and denoised to reduce the influence of interference factors. Next, the instantaneous power value is obtained by multiplying the current and voltage information, and then the instantaneous power at different time points is weighted and averaged using the weighting factor to obtain a smoother real-time power output. For the speed and temperature information, multiple linear regression or Kalman filtering algorithms are used for fusion. By analyzing the influence of the speed on the motor's heat loss, a relationship model between temperature change and speed is established. Through this model, the temperature rise under the current speed conditions can be estimated, and the estimated temperature can be compared with the real-time temperature information to correct the heat loss assessment result. Finally, the results of these fusion processes are integrated into a complete set of motor operating status information, which can reflect the current load condition, energy consumption level and operating stability of the motor in detail.

[0043] In one embodiment, if Figure 3 As shown, before step S20, the motor operation status information is input into the early warning model, and the motor operation status information is analyzed by the early warning model to obtain early warning information, which includes: S21: Obtain historical operation information of the motor, and use the historical operation information of the motor as a training set and a test set.

[0044] Specifically, historical operation information includes information sequences of key parameters such as current, voltage, speed, temperature, etc. that change over time, known fault types, occurrence time, impact range, etc. The historical operation information is sorted, and incomplete or abnormal samples are removed to ensure the quality and consistency of the information. Then, the sorted information is divided into training sets and test sets according to chronological order and frequency of occurrence, with 70% for training sets and 30% for test sets. The training set is used for model learning and parameter adjustment, and the test set is used to verify the prediction ability of the model. The stratified sampling method is used in the division process to ensure that the distribution of fault types in the training set and test set is close to the actual situation.

[0045] S22: Train the initial warning model according to the training set to generate a warning model in training.

[0046] Specifically, the data of the training set is input into the random forest algorithm for training. The random forest algorithm realizes the recognition and prediction of abnormal states by constructing multiple decision tree models. Each decision tree is randomly sampled according to the feature data in the training set, and the features that can maximize the information gain are selected to construct decision rules during the node splitting process. At the beginning of model training, each decision tree independently learns the input data. By continuously dividing the data set, the decision tree gradually establishes the mapping relationship between features and outputs. During the training process, the random forest performs internal cross-validation through "out-of-bag data". These data that are not involved in the current tree training are used to verify the prediction effect of the current tree and adjust it to reduce the overfitting problem. The output of each decision tree is integrated by the voting mechanism of the random forest to produce more stable and reliable prediction results. The performance of the model on the training set will be continuously evaluated, including calculating indicators such as accuracy and recall rate. By adjusting hyperparameters such as the number of trees in the forest, depth, and randomness of feature selection, the overall performance of the model is optimized. Finally, the random forest will generate an early warning model based on the learning of the training data.

[0047] Furthermore, the random forest algorithm refers to the random forest algorithm that generates multiple different training subsets by performing multiple random sampling on the training data set, and each subset is used to train a decision tree. When constructing each decision tree, the random forest will randomly select a part of the features in the feature selection process of each node, and select the features that can maximize the information gain to split the node. In this way, each decision tree will be generated in a "random" way, reducing the risk of overfitting of a single decision tree. The generation process of the decision tree includes continuously dividing the data set to form a mapping relationship between features and output results. Each decision tree learns independently and predicts the input data. Finally, the random forest votes on the prediction results of all decision trees and selects the output of the majority of decision trees as the final prediction result.

[0048] S23: Use the test set to verify and optimize the early warning model in training to obtain the early warning model.

[0049] Specifically, the data of the test set is input into the early warning model in training, the performance of the model on unseen data is evaluated, and its prediction accuracy, recall rate, F1 score and other indicators are calculated. If the performance of the model does not meet the expected standards, the error types of the model on the test set are analyzed, such as whether the false alarm rate and missed alarm rate are too high, and targeted optimization adjustments are made based on the analysis results. Optimization methods include increasing the amount of training data, adjusting the complexity of the model, or introducing new feature variables. Through the iterative verification and optimization process, the prediction performance of the model is continuously improved, and finally an early warning model that can accurately identify abnormal motor operation is obtained to ensure its stability and reliability in practical applications.

[0050] Further, the expected standards are: Prediction accuracy reflects the performance of the early warning model in the overall sample. The expected standard is set as the early warning model needs to achieve an accuracy of more than 90% to ensure that it can reliably identify the normal and abnormal states of the motor in practical applications. Recall rate, also known as sensitivity, refers to the proportion of abnormal samples that the early warning model can correctly identify. For motor fault prediction, the recall rate is not less than 85% as the expected standard to ensure that missed reports are minimized. F1 score, as a standard for comprehensive evaluation of model performance. The F1 score is set to be higher than 0.8 as the expected standard to ensure that the model maintains a balanced performance in classification tasks. False alarm rate refers to the proportion of normal states that the early warning model mistakenly identifies as abnormal states. The expected standard requires a false alarm rate of less than 5% to avoid excessive false alarms from interfering with the system. Missing alarm rate refers to the proportion of abnormal states that the early warning model fails to identify. The expected standard sets a missing alarm rate of less than 10% to ensure that important faults can be identified and handled in a timely manner.

[0051] In one embodiment, if Figure 4 As shown, in step S20, the motor operation status information is input into the early warning model, and the motor operation status information is analyzed by the early warning model to obtain early warning information, including: S201: The early warning model analyzes the motor operation status information, determines whether the motor status is abnormal, and obtains the model analysis result.

[0052] In this embodiment, the model analysis result refers to a health assessment of the current operating state of the motor obtained after processing the input motor operating state information through the early warning model, including whether an abnormality exists and the possibility and severity of the abnormality.

[0053] Specifically, the input motor operating status information is analyzed using a random forest model. The random forest model contains multiple decision trees, each of which independently predicts the motor status based on the motor's characteristic parameters such as current, voltage, speed, and temperature. The prediction results of each decision tree are summarized through a voting mechanism, and the random forest obtains the final model analysis results by integrating the judgment results of most decision trees. The analysis results not only indicate whether the motor is currently in an abnormal state, but also include the possible distribution of the abnormal type, such as abnormal current, excessive temperature, or speed fluctuation, and score the severity of the abnormality.

[0054] S202: According to the model analysis result, when it is identified that the state of the motor is abnormal, a warning message is obtained.

[0055] Specifically, when the analysis results of the random forest model indicate that the running state of the motor is abnormal, an early warning message is obtained. The early warning information includes the identification of the abnormality type, the possibility of the abnormality, the severity score, and the recommended countermeasures. The generation process first determines the most likely abnormality type based on the probability distribution of the abnormality type of the random forest model, and then formulates the early warning level, such as low, medium, and high, according to the abnormal probability value and severity score. Finally, the early warning information is packaged and notified to the operator through the system interface or alarm system to remind the necessary inspection and adjustment of the motor.

[0056] In one embodiment, if Figure 5 As shown, in step S30, the operating parameters of the motor are adjusted according to the warning information to obtain the optimized operating parameters of the motor, including: S301: Obtaining abnormality type information of the motor according to the warning information.

[0057] Specifically, the abnormality type information of the motor is extracted from the warning information. The abnormality type information includes the specific classification of the abnormality, such as overcurrent, undervoltage, overheating or speed fluctuation. The extraction process involves parsing the warning information, identifying the abnormality type field, and combining the probability and severity of the abnormality to determine the abnormality type that needs to be processed first. If the warning information contains multiple abnormality types, they are sorted according to the severity or abnormality probability value, and the highest priority abnormality type information is selected for subsequent processing.

[0058] S302: Based on the abnormality type information, select a parameter adjustment strategy corresponding to the abnormality type information, and adjust the operating parameters of the motor according to the parameter adjustment strategy to obtain optimized motor operating parameters.

[0059] Specifically, based on the extracted abnormality type information, the adjustment strategy most relevant to the current abnormality type is selected by matching the pre-set parameter adjustment strategy library. For example, for the detected overcurrent abnormality, a strategy of reducing the current limit or adjusting the current rising slope is selected; for overheating, a strategy of reducing the load or reducing the speed is selected. The selected strategy is verified by the parameter optimization algorithm to ensure the effectiveness of the adjustment scheme and the minimum impact on the overall system performance. According to the selected strategy, parameter adjustments are automatically performed, such as resetting the current limit, correcting the speed target, or adjusting the temperature control threshold, and finally the optimized motor operating parameters are obtained.

[0060] Furthermore, the pre-set parameter adjustment strategy library refers to a set of parameter adjustment schemes designed for various possible motor abnormalities based on historical operating data and fault analysis. Each strategy defines in detail the specific adjustment measures that need to be performed under different abnormality types, such as current limit adjustment strategies for overcurrent abnormalities, or cooling and speed reduction strategies for overtemperature. These strategies are determined by analyzing the processing effects of different abnormalities in historical data and optimizing them, and include specific adjustment methods and optimization suggestions for key operating parameters such as current, speed, voltage and temperature under various working conditions. Each strategy in the strategy library is marked with applicable abnormality types, trigger conditions and specific parameter adjustment steps, so that the most appropriate parameter adjustment scheme can be quickly selected when the corresponding abnormality occurs, thereby achieving precise control and optimization of the motor operating state.

[0061] In one embodiment, if Figure 6 As shown, in step S302, based on the abnormal type information, a parameter adjustment strategy corresponding to the abnormal type information is selected, and the operating parameters of the motor are adjusted according to the parameter adjustment strategy to obtain the optimized motor operating parameters, which also includes: S3021: Classify and predict the abnormal type information through the random forest algorithm to obtain the parameter adjustment strategy with the highest matching degree with the abnormal type information.

[0062] Specifically, the random forest algorithm is used to select the parameter adjustment strategy corresponding to the anomaly type information. First, the anomaly type information is used as an input feature and input into the trained random forest model. Through previous training, the random forest model has learned the association between different anomaly types and various parameter adjustment strategies. The random forest contains multiple decision trees, each of which independently generates strategy recommendations based on the anomaly type information. When making a decision, each decision tree splits the node according to the features in the anomaly type information, such as the anomaly type, severity, and frequency of occurrence, to make a decision on strategy selection. The random forest summarizes the selection results of all decision trees and uses the majority voting method to select the parameter adjustment strategy that best matches the current anomaly type information.

[0063] The parameter adjustment strategy output by the random forest includes specific operating parameter adjustment plans. For example, when an overcurrent anomaly is identified, the model may output a strategy to reduce the current set value and adjust the current rise rate; for temperature anomalies, the model may output a strategy to reduce the load, adjust the cooling settings, or reduce the motor speed. After the selected strategy is confirmed, it is automatically applied to the motor control system to adjust the motor's operating parameters and generate optimized motor operating parameters. The adjusted parameters will act on the motor's control module in real time to ensure that the motor runs safely and efficiently under the optimized parameters, reduce the impact of anomalies on the motor, and restore the motor's normal operating state.

[0064] In one embodiment, if Figure 7 As shown, in step S40, motor operation control information is generated based on the optimized motor operation parameters, and the motor operation control information is used to adjust the working state of the motor, including: S401: Determine the target working state of the motor according to the optimized motor operating parameters, analyze the difference between the current motor operating state and the target working state according to the target working state, and obtain control information that needs to be adjusted.

[0065] Specifically, based on the optimized motor operating parameters, the target operating state of the motor is calculated, including parameters such as target current, target voltage, target speed, and target temperature. The currently monitored motor operating state is compared with the target operating state to identify the difference between the actual current and the target current, the deviation between the actual speed and the target speed, and the temperature difference. By analyzing these differences, specific adjustment requirements are determined, such as increasing the current, reducing the speed, or adjusting the temperature. These difference values ​​are converted into specific control information, including the adjustment amplitude and direction, and the operating parameters and adjustment strategies that need to be changed are clarified, thereby generating adjustment guidance for guiding the motor to reach the target operating state.

[0066] S402: Generate motor operation control information according to the control information that needs to be adjusted, where the motor operation control information is used to adjust the working state of the motor.

[0067] Specifically, the motor operation control information is generated according to the control information that needs to be adjusted. The adjustment information is converted into specific execution instructions, including instructions to adjust the current, modify the voltage setting, adjust the speed, or change the temperature control. After these control information are processed, they are directly sent to the motor's actuator to drive the motor to perform the corresponding adjustment operations and adjust the motor's operating state toward the target state. The adjustment process is continuously monitored, and the control information is adjusted as necessary based on the actual feedback effect to ensure that the motor gradually stabilizes in the optimized working state and maintains efficient and safe operation.

[0068] 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.

[0069] In one embodiment, a motor intelligent optimization device is provided, and the motor intelligent optimization device corresponds to the motor intelligent optimization method in the above embodiment. Figure 8 As shown, the motor intelligent optimization device includes a state monitoring module, an early warning analysis module, a parameter optimization module and a control generation module. The detailed description of each functional module is as follows: Status monitoring module, used to obtain motor operation status information; The early warning analysis module is used to input the motor operation status information into the early warning model, analyze the motor operation status information through the early warning model, and obtain early warning information; A parameter optimization module is used to adjust the operating parameters of the motor according to the early warning information to obtain the optimized motor operating parameters; The control generation module is used to generate motor operation control information based on the optimized motor operation parameters, and the motor operation control information is used to adjust the working state of the motor.

[0070] Optionally, the condition monitoring module includes: Remote monitoring submodule, used to remotely monitor the current information, voltage information, speed information and temperature information of the motor; The information synthesis submodule is used to process the current information, voltage information, speed information and temperature information in real time to generate the motor operation status information.

[0071] Optionally, the early warning analysis module previously includes: A historical information acquisition module is used to acquire historical operation information of the motor and use the historical operation information of the motor as a training set and a test set; A training module is used to train the initial warning model according to the training set and generate a warning model in training; The model generation module is used to verify and optimize the early warning model in training using the test set to obtain the early warning model.

[0072] Optional, early warning analysis module includes: The model result submodule is used for the early warning model to analyze the motor operation status information, determine whether the motor status is abnormal, and obtain the model analysis result; The early warning submodule is used to obtain early warning information when an abnormal state of the motor is identified based on the model analysis results.

[0073] Optionally, the parameter optimization module includes: The abnormal type submodule is used to obtain the abnormal type information of the motor according to the warning information; The parameter optimization submodule is used to select a parameter adjustment strategy corresponding to the abnormal type information based on the abnormal type information, adjust the operating parameters of the motor according to the parameter adjustment strategy, and obtain optimized motor operating parameters.

[0074] Optionally, the optimization parameter submodule also includes: The random forest algorithm application submodule is used to classify and predict the abnormal type information through the random forest algorithm to obtain the parameter adjustment strategy with the highest matching degree with the abnormal type information.

[0075] Optionally, the control generation module includes: A control information adjustment module is used to determine the target working state of the motor according to the optimized motor operating parameters, and to analyze the difference between the current motor operating state and the target working state according to the target working state, so as to obtain the control information that needs to be adjusted; The working state adjustment module is used to generate motor operation control information according to the control information that needs to be adjusted, and the motor operation control information is used to adjust the working state of the motor.

[0076] For the specific definition of the motor intelligent optimization device, please refer to the definition of the motor intelligent optimization method above, which will not be repeated here. Each module in the above-mentioned motor intelligent optimization device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0077] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer 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 computer device is used for a preset parameter adjustment strategy library. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a motor intelligent optimization method is implemented.

[0078] In one embodiment, a computer 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: Get the motor running status information; Inputting the motor operation status information into the early warning model, analyzing the motor operation status information through the early warning model, and obtaining early warning information; According to the early warning information, the operating parameters of the motor are adjusted to obtain the optimized operating parameters of the motor; Based on the optimized motor operation parameters, motor operation control information is generated, and the motor operation control information is used to adjust the working state of the motor.

[0079] 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: Get the motor running status information; Inputting the motor operation status information into the early warning model, analyzing the motor operation status information through the early warning model, and obtaining early warning information; According to the early warning information, the operating parameters of the motor are adjusted to obtain the optimized operating parameters of the motor; Based on the optimized motor operation parameters, motor operation control information is generated, and the motor operation control information is used to adjust the working state of the motor.

[0080] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented 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 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of 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), etc.

[0081] 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.

[0082] 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 intelligent optimization method, characterized in that: The motor intelligent optimization method comprises: Get the motor running status information; Inputting the motor operation status information into the early warning model, analyzing the motor operation status information through the early warning model to obtain early warning information; According to the warning information, adjusting the operating parameters of the motor to obtain optimized motor operating parameters; Based on the optimized motor operation parameters, motor operation control information is generated, and the motor operation control information is used to adjust the working state of the motor.

2. The motor intelligent optimization method according to claim 1, characterized in that: The step of obtaining the motor operation status information includes: Remotely monitor the current information, voltage information, speed information and temperature information of the motor; The current information, the voltage information, the speed information and the temperature information are processed in real time to generate the motor operation status information.

3. The motor intelligent optimization method according to claim 2, characterized in that: The step of inputting the motor operation status information into the early warning model and analyzing the motor operation status information through the early warning model to obtain early warning information comprises: Acquire historical operation information of the motor, and use the historical operation information of the motor as a training set and a test set; According to the training set, the initial warning model is trained to generate a warning model in training; The test set is used to verify and optimize the early warning model in training to obtain the early warning model.

4. The motor intelligent optimization method according to claim 1, characterized in that: The step of inputting the motor operation status information into the early warning model and analyzing the motor operation status information through the early warning model to obtain early warning information includes: The early warning model analyzes the motor operation status information, determines whether the motor status is abnormal, and obtains a model analysis result; According to the model analysis result, when it is identified that the state of the motor is abnormal, the warning information is obtained.

5. The motor intelligent optimization method according to claim 1, characterized in that: The step of adjusting the operating parameters of the motor according to the warning information to obtain optimized operating parameters of the motor includes: According to the warning information, obtaining abnormal type information of the motor; Based on the abnormality type information, a parameter adjustment strategy corresponding to the abnormality type information is selected, and the operating parameters of the motor are adjusted according to the parameter adjustment strategy to obtain the optimized motor operating parameters.

6. The motor intelligent optimization method according to claim 5, characterized in that: The method further comprises: selecting a parameter adjustment strategy corresponding to the abnormal type information based on the abnormal type information, adjusting the operating parameters of the motor according to the parameter adjustment strategy, and obtaining the optimized motor operating parameters. The abnormal type information is classified and predicted by a random forest algorithm to obtain the parameter adjustment strategy with the highest matching degree with the abnormal type information.

7. The motor intelligent optimization method according to claim 1, characterized in that: The step of generating motor operation control information based on the optimized motor operation parameters, wherein the motor operation control information is used to adjust the working state of the motor, includes: Determine the target working state of the motor according to the optimized motor operating parameters, analyze the difference between the current motor operating state and the target working state according to the target working state, and obtain the control information that needs to be adjusted; The motor operation control information is generated according to the control information that needs to be adjusted, and the motor operation control information is used to adjust the working state of the motor.

8. A motor intelligent optimization device, characterized in that: The motor intelligent optimization device comprises: Status monitoring module, used to obtain motor operation status information; An early warning analysis module, used for inputting the motor operation status information into an early warning model, analyzing the motor operation status information through the early warning model, and obtaining early warning information; A parameter optimization module, used for adjusting the operating parameters of the motor according to the warning information to obtain optimized motor operating parameters; The control generation module is used to generate motor operation control information based on the optimized motor operation parameters, and the motor operation control information is used to adjust the working state of the motor.

9. A computer 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 motor intelligent optimization method according to any one of claims 1 to 7 are 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 the motor intelligent optimization method according to any one of claims 1 to 7 are implemented.

Images