Motor equipment and operation control method thereof

Abstract

The invention relates to the technical field of motor control, in particular to motor equipment and an operation control method thereof. The method comprises the following steps of collecting operation data of motor equipment in the numerical control machine tool under various working conditions in real time to obtain an initial operation data set; training a neural network model by using the initial operation data set to identify harmonic characteristics under each working condition, and generating a harmonic spectrum identification model; acquiring current and voltage signals of the motor equipment in real time, inputting the current and voltage signals to the harmonic spectrum identification model for identification, and generating dynamic harmonic characteristic monitoring data; and comparing the dynamic harmonic characteristic monitoring data with a preset threshold value, generating an isolation instruction, and dynamically adjusting the frequency response range of the motor equipment to obtain optimized signal response data. According to the invention, through real-time data acquisition, intelligent model training, dynamic adjustment and a feedback mechanism, the adaptability, efficiency and stability of motor equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of motor control, and in particular to a motor device and an operation control method thereof. Background Art

[0002] As the core component of CNC machine tools, motor equipment directly determines the operating stability, processing accuracy and energy consumption of machine tools. Traditional motor equipment control systems usually rely on preset fixed parameters to control the operation of the motor by setting certain frequency and current parameters. In actual operation, CNC machine tool motor equipment often encounters a variety of complex operating conditions, including different load conditions, different ambient temperatures and other external interference factors. Traditional control methods use fixed parameters and are difficult to respond to these changes in real time, resulting in poor operating stability under different loads or environmental conditions, and problems such as overheating, vibration or reduced accuracy. The lack of dynamic adjustment capabilities makes it easy for the equipment to exceed the safe operating range under complex conditions, resulting in equipment damage or production accidents.

[0003] Harmonics are current or voltage fluctuations caused by the switching operation of nonlinear loads or motor equipment. They can interfere with the operation of the motor, reduce operating efficiency, increase energy consumption, and even interfere with other equipment. Existing motor control technology is relatively weak in harmonic identification and control, and cannot effectively filter or isolate harmonic interference, resulting in reduced equipment operating efficiency and shortened component life.

[0004] Under continuous high load or high-speed operation conditions, the temperature of motor equipment will rise rapidly. Traditional control methods mostly use passive heat dissipation measures, such as relying solely on ventilation or cooling systems, and lack the ability to dynamically adjust heat dissipation based on real-time temperature monitoring. Existing heat dissipation systems often start or stop based on preset thresholds and lack the ability to dynamically adjust based on the real-time thermal state and load conditions of the motor. This method cannot respond in time when overheating or overcooling occurs, which not only affects the normal operation of the motor, but also causes equipment damage. Summary of the invention

[0005] Based on this, it is necessary for the present invention to provide a motor device and an operation control method thereof to solve at least one of the above technical problems.

[0006] To achieve the above object, a method for controlling the operation of a motor device comprises the following steps:

[0007] Step S1: collecting the operating data of the motor equipment in the CNC machine tool under various working conditions in real time to obtain an initial operating data set;

[0008] Step S2: using the initial operation data set to train the neural network model to identify the harmonic characteristics under various working conditions and generate a harmonic spectrum recognition model;

[0009] Step S3: real-time acquisition of current and voltage signals of the motor equipment, and inputting them into the harmonic spectrum recognition model for recognition, generating dynamic harmonic characteristic monitoring data; comparing the dynamic harmonic characteristic monitoring data with a preset threshold, generating an isolation instruction, and dynamically adjusting the frequency response range of the motor equipment to obtain optimized signal response data;

[0010] Step S4: monitoring the temperature of the motor driver and the heat dissipation system in the motor device in real time according to the optimized signal response data to generate comprehensive thermal state monitoring data;

[0011] Step S5: adjusting the current input parameters of the motor device driver based on the comprehensive thermal state monitoring data, optimizing the operating state of the heat dissipation system, and generating hardware adaptive control parameters;

[0012] Step S6: Optimize the load dynamic adjustment module of the motor equipment based on the hardware adaptive control parameters and the dynamic harmonic characteristic monitoring data, and generate load adaptive optimization parameters to improve the operation stability of the motor equipment.

[0013] The present invention collects the operation data of the motor equipment of the numerical control machine tool under various working conditions in real time, and uses the neural network model to identify the harmonic characteristics, so that the system can quickly respond to different operating environments and load conditions. This real-time collection and analysis process greatly improves the adaptability of the equipment to complex working conditions and can effectively cope with various environmental fluctuations. The harmonic spectrum recognition model is used to identify the harmonic characteristics in the current and voltage, so as to monitor the operating status of the equipment in real time, which helps to timely discover potential abnormal signals, reduce the interference of harmonics on the operation of the equipment, effectively reduce the operating loss of the motor equipment, and extend the service life of the equipment. Based on the comparative analysis of the harmonic characteristic data and the preset threshold, by generating isolation instructions and dynamically adjusting the frequency response range, the harmonic interference can be effectively suppressed to ensure the stability of the equipment under different working conditions. This control method enables the frequency response range of the equipment to adapt to the real-time data at any time, improves the operating efficiency and response speed of the motor, and reduces unnecessary power consumption. By monitoring the temperature of the motor driver and the heat dissipation system in real time, the system can dynamically collect thermal state data and realize accurate temperature control. This real-time thermal management can effectively avoid equipment failures caused by overheating and extend the stable operation time of the motor equipment. The monitoring and feedback of temperature data enables the system to adaptively adjust the cooling system under load or high-speed operation, preventing the efficiency from decreasing due to over-temperature, thus ensuring the safety and efficiency of the equipment. Based on the thermal status monitoring data, the system can automatically adjust the current input parameters of the motor driver and optimize the operation of the cooling system. This adaptive control method enhances the adjustment capability of the equipment under different loads and environments, and improves the overall performance. The generation of hardware adaptive control parameters enables the equipment to intelligently and dynamically adjust the driver and cooling system, thereby reducing the frequency of manual debugging, reducing maintenance costs, and ensuring the continuous and efficient operation of the equipment under various environments. By optimizing the load dynamic adjustment module of the motor equipment using hardware adaptive control parameters and dynamic harmonic characteristic monitoring data, the generated load adaptive optimization parameters can significantly improve the stability and operating efficiency of the motor equipment. This load optimization method enables the equipment to remain stable under high load conditions, and adjust the operating parameters in real time according to different loads, reducing the stress and wear of the equipment and improving the overall reliability of the motor equipment.

[0014] The present invention also provides a motor device, comprising a housing, an armature, a drive circuit and a control system, wherein the armature is disposed in the housing, the drive circuit is electrically connected to the armature, the control system is installed in the drive circuit, and the control system is used to execute the operation control method of the motor device, and the control system comprises:

[0015] The operation data acquisition module is used to collect the operation data of the motor equipment in the CNC machine tool under various working conditions in real time to obtain the initial operation data set;

[0016] The harmonic spectrum modeling module is used to train the neural network model using the initial operation data set to identify the harmonic characteristics under various working conditions and generate a harmonic spectrum recognition model;

[0017] The dynamic harmonic monitoring and optimization module is used to collect the current and voltage signals of the motor equipment in real time, input them into the harmonic spectrum recognition model for identification, and generate dynamic harmonic characteristic monitoring data; compare the dynamic harmonic characteristic monitoring data with the preset threshold, generate isolation instructions, and dynamically adjust the frequency response range of the motor equipment to obtain optimized signal response data;

[0018] Thermal status monitoring and management module, used to monitor the temperature of the motor driver and cooling system in the motor equipment in real time according to the optimized signal response data, and generate comprehensive thermal status monitoring data;

[0019] Adaptive current and heat dissipation control module, used to adjust the current input parameters of the motor device driver based on the comprehensive thermal status monitoring data, optimize the operating status of the heat dissipation system, and generate hardware adaptive control parameters;

[0020] The load adaptability optimization module is used to optimize the load dynamic adjustment module of the motor equipment based on the hardware adaptive control parameters and dynamic harmonic characteristic monitoring data, and generate load adaptability optimization parameters to improve the operation stability of the motor equipment.

[0021] The present invention generates an initial operation data set by real-time acquisition of the operation data of the motor equipment of the numerical control machine tool under various working conditions, and provides accurate data support for subsequent analysis and model training. This real-time data acquisition function improves the sensitivity of the system to different operating states, enables the motor equipment to quickly adapt to various complex working conditions, thereby improving the flexibility and intelligence level of the overall system. The neural network model is trained using the collected initial operation data to generate a harmonic spectrum recognition model, so that the system can accurately identify and analyze the harmonic characteristics under different working conditions. This refined harmonic modeling improves the monitoring and diagnostic capabilities of the system, effectively suppresses the impact of harmonics on the equipment, reduces the power consumption and failure probability of the motor equipment, and improves the operating stability of the equipment. By real-time monitoring of the current and voltage signals of the motor equipment, and identifying and optimizing the harmonic characteristics, the module can generate dynamic harmonic characteristic monitoring data, and generate isolation instructions through comparative analysis to dynamically adjust the frequency response range of the motor. This function enables the motor equipment to maintain stable response performance under different harmonic interferences, optimizes the accuracy of signal response, effectively improves the anti-interference ability of the equipment, and ensures efficient operation. By monitoring the temperature of the motor driver and the cooling system in real time and generating thermal status monitoring data, the temperature safety of the equipment under high load or high-speed operation is guaranteed. The module can prevent the loss and failure of the equipment caused by overheating, extend the service life of the equipment through precise temperature control, and ensure the stability and safety of the motor equipment during long-term operation. Based on the comprehensive thermal status monitoring data, the module dynamically adjusts the current input parameters of the motor driver and optimizes the cooling system status to generate hardware adaptive control parameters. This adaptive control method enhances the stability of the equipment under different environments and loads, reduces the efficiency reduction caused by temperature rise, reduces the frequency of manual debugging, and further improves the reliability and maintenance efficiency of the equipment. The module uses hardware adaptive control parameters and dynamic harmonic characteristic monitoring data to dynamically optimize the load to generate load adaptive optimization parameters, so that the motor equipment can run more smoothly under different load conditions. This module effectively enhances the operating adaptability of the equipment under high load, reduces the stress impact of the load on the equipment, and improves the safety and operating efficiency of the overall system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0023] Figure 1 A schematic diagram of the steps of the operation control method of the motor device of the present invention;

[0024] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0025] Figure 3 for Figure 1 Detailed step flow chart of step S2 in FIG. DETAILED DESCRIPTION

[0026] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0028] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0029] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for controlling the operation of a motor device, the method comprising the following steps: Step S1: collecting the operating data of the motor equipment in the CNC machine tool under various working conditions in real time to obtain an initial operating data set; Step S2: using the initial operation data set to train the neural network model to identify the harmonic characteristics under various working conditions and generate a harmonic spectrum recognition model; Step S3: real-time acquisition of current and voltage signals of the motor equipment, and inputting them into the harmonic spectrum recognition model for recognition, generating dynamic harmonic characteristic monitoring data; comparing the dynamic harmonic characteristic monitoring data with a preset threshold, generating an isolation instruction, and dynamically adjusting the frequency response range of the motor equipment to obtain optimized signal response data; Step S4: monitoring the temperature of the motor driver and the heat dissipation system in the motor device in real time according to the optimized signal response data to generate comprehensive thermal state monitoring data; Step S5: adjusting the current input parameters of the motor device driver based on the comprehensive thermal state monitoring data, optimizing the operating state of the heat dissipation system, and generating hardware adaptive control parameters; Step S6: Optimize the load dynamic adjustment module of the motor equipment based on the hardware adaptive control parameters and the dynamic harmonic characteristic monitoring data, and generate load adaptive optimization parameters to improve the operation stability of the motor equipment.

[0036] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for controlling the operation of a motor device according to the present invention. In this example, the method for controlling the operation of the motor device includes the following steps:

[0037] Step S1: collecting the operating data of the motor equipment in the CNC machine tool under various working conditions in real time to obtain an initial operating data set;

[0038] Before the motor device is operated, the embodiment of the present invention connects the operation data acquisition module to each key part of the motor device to ensure that each sensor corresponds to the corresponding monitoring point. The data acquisition system is initialized and each sensor is calibrated to ensure the accuracy of the data. After the motor device starts to operate, the operation data acquisition module will automatically and continuously collect the operation data of the motor under different operating conditions. For example, in each operating state of the motor device, such as starting, accelerating, constant speed, decelerating and stopping, the module will record the dynamic changes of current, voltage, speed and temperature respectively. The collected data will be marked and stored according to different operating conditions to form an initial operation data set.

[0039] Step S2: using the initial operation data set to train the neural network model to identify the harmonic characteristics under various working conditions and generate a harmonic spectrum recognition model;

[0040] The embodiment of the present invention inputs the initial operation data set into the harmonic spectrum modeling module. First, data cleaning and normalization are performed to remove abnormal data and noise to ensure the integrity and consistency of the input data. The data normalization process can process parameters such as current and voltage at the same scale to facilitate the training effect of the model. Feature extraction is performed on the preprocessed data set to extract harmonic characteristic indicators under different working conditions, including the amplitude, phase angle, frequency component, etc. of each harmonic. These features will be used to identify the harmonic distribution of motor equipment under different loads, speeds and temperature conditions, and provide effective feature vectors for neural network training. The extracted harmonic characteristic indicators are input into the neural network model to train the model. During the training process, the model continuously adjusts parameters to adapt to the harmonic characteristics of different working conditions, thereby gradually improving the recognition accuracy and response speed. The neural network model will perform multiple rounds of iterations based on a specific learning rate and optimization algorithm, and finally form a stable harmonic spectrum recognition model.

[0041] Step S3: real-time acquisition of current and voltage signals of the motor equipment, and inputting them into the harmonic spectrum recognition model for recognition, generating dynamic harmonic characteristic monitoring data; comparing the dynamic harmonic characteristic monitoring data with a preset threshold, generating an isolation instruction, and dynamically adjusting the frequency response range of the motor equipment to obtain optimized signal response data;

[0042] The embodiment of the present invention continuously collects the current and voltage signals of the motor equipment in the CNC machine tool through a real-time monitoring device, and transmits the collected data to the dynamic harmonic monitoring and optimization module. These real-time data reflect the working characteristics of the motor equipment under the current operating state, and provide the original data source for the subsequent harmonic characteristic identification. The collected current and voltage signals are input into the harmonic spectrum recognition model. Based on the training result of step S2, the model can identify the harmonic characteristics of the motor equipment under different operating conditions. By analyzing the harmonic characteristics of the current signal, real-time dynamic harmonic characteristic monitoring data is generated to reflect the harmonic distribution of the current working condition. The real-time generated dynamic harmonic characteristic monitoring data is compared and analyzed with the preset safety threshold. If the harmonic characteristic data exceeds the threshold range, the system determines that there is an abnormal or unstable situation in the current operating state, thereby generating a corresponding isolation instruction. This process is used to prevent the performance degradation or damage risk of the motor equipment caused by excessive harmonic fluctuations. According to the judgment result of the isolation instruction, the frequency response range of the motor equipment is dynamically adjusted to optimize the operating state of the equipment. For example, when the harmonic characteristic exceeds the safety range, the specific harmonic component can be suppressed by adjusting the response frequency, thereby improving the electrical performance of the equipment. This adjustment process ensures the harmonic stability of the equipment under changing operating conditions. After the frequency response adjustment is completed, the optimized signal response data is generated.

[0043] Step S4: monitoring the temperature of the motor driver and the heat dissipation system in the motor device in real time according to the optimized signal response data to generate comprehensive thermal state monitoring data;

[0044] The embodiment of the present invention collects the temperature of key components (including motor drivers and heat dissipation systems) in motor equipment in real time through temperature sensors based on the guidance of optimized signal response data. The temperature collection process can accurately obtain the thermal state information of each component and provide raw data for subsequent thermal state analysis. The collected temperature data is sorted and summarized to generate comprehensive thermal state monitoring data. The data includes the temperature change of the motor driver and the heat exchange efficiency of the heat dissipation system, which is used to reflect the overall thermal load of the motor equipment under the current operating conditions. The comprehensive thermal state monitoring data is compared and analyzed with the safe temperature threshold preset by the system to determine whether the current thermal state is within a safe range. If the temperature exceeds the safe threshold range, the system determines that there is an overheating risk and further triggers the optimization and regulation requirements of the heat dissipation system. Based on the temperature comparison results, it is dynamically determined whether the operating state of the heat dissipation system needs to be adjusted. For example, when the temperature of the motor driver is higher than the preset threshold, the fan speed of the heat dissipation system is automatically increased or the enhanced heat dissipation mode is enabled to reduce the temperature and avoid thermal damage. If the temperature is within the normal range, the thermal state is continued to be monitored. After the adjustment of the heat dissipation system is completed, the updated comprehensive thermal state monitoring data is generated again.

[0045] Step S5: adjusting the current input parameters of the motor device driver based on the comprehensive thermal state monitoring data, optimizing the operating state of the heat dissipation system, and generating hardware adaptive control parameters;

[0046] According to the comprehensive thermal state monitoring data, the embodiment of the present invention systematically analyzes the temperature level and operating state of the motor driver to determine whether there is a phenomenon of temperature rise due to excessive current input. If the monitoring data shows that the driver temperature is close to the safety upper limit, the temperature load of the motor driver is reduced by reducing or dynamically adjusting the current input, thereby preventing overheating. The adjustment process generates optimized current input parameters to ensure that the device operates within the controllable temperature range. If the comprehensive thermal state monitoring data shows that the current operating mode of the cooling system cannot effectively reduce the driver temperature, the adaptive current and cooling control module automatically adjusts the operating state of the cooling system. For example, the fan speed can be increased, a more efficient cooling mode can be enabled, or the operating frequency of the cooling device can be adjusted to improve the cooling effect and ensure that the temperature of the motor driver is maintained within the safety threshold. After completing the optimization of the current input parameters and the cooling system, the system will generate hardware adaptive control parameters, including the optimal operating settings of the current and cooling system under the current environment.

[0047] Step S6: Optimize the load dynamic adjustment module of the motor equipment based on the hardware adaptive control parameters and the dynamic harmonic characteristic monitoring data, and generate load adaptive optimization parameters to improve the operation stability of the motor equipment.

[0048] The embodiment of the present invention uses dynamic harmonic characteristic monitoring data to analyze the vibration and harmonic characteristics of the motor equipment under the current load condition to determine whether there is a harmonic characteristic or load fluctuation that exceeds a preset threshold. This analysis can reveal abnormal changes in the operating state of the equipment and provide data support for subsequent optimization. Based on the hardware adaptive control parameters, the load adaptability optimization module dynamically calculates the optimization parameters that adapt to the current load, including parameters such as current, speed and load distribution. These adaptive parameters take into account the real-time harmonic characteristics of the motor equipment, so that the equipment can quickly adapt to changes in the load and reduce the impact on the stability of the equipment operation. The load adaptive parameters are applied to the load dynamic adjustment module to adjust the current input, speed control and load distribution mode of the motor equipment in real time, optimize the frequency response of the motor under different loads, eliminate or reduce unnecessary harmonic components, and improve the load adaptability and stability of the equipment. After applying the load adaptive optimization parameters, the load adaptive optimization module continuously monitors the load state, harmonic characteristics and equipment stability of the motor equipment to ensure that the adjustment effect is as expected. If a new load fluctuation or harmonic characteristic change is detected, the system will automatically update the load adaptive parameters and adjust the load dynamic adjustment module again to maintain the stable operation of the motor equipment.

[0049] The present invention collects the operation data of the motor equipment of the numerical control machine tool under various working conditions in real time, and uses the neural network model to identify the harmonic characteristics, so that the system can quickly respond to different operating environments and load conditions. This real-time collection and analysis process greatly improves the adaptability of the equipment to complex working conditions and can effectively cope with various environmental fluctuations. The harmonic spectrum recognition model is used to identify the harmonic characteristics in the current and voltage, so as to monitor the operating status of the equipment in real time, which helps to timely discover potential abnormal signals, reduce the interference of harmonics on the operation of the equipment, effectively reduce the operating loss of the motor equipment, and extend the service life of the equipment. Based on the comparative analysis of the harmonic characteristic data and the preset threshold, by generating isolation instructions and dynamically adjusting the frequency response range, the harmonic interference can be effectively suppressed to ensure the stability of the equipment under different working conditions. This control method enables the frequency response range of the equipment to adapt to the real-time data at any time, improves the operating efficiency and response speed of the motor, and reduces unnecessary power consumption. By monitoring the temperature of the motor driver and the heat dissipation system in real time, the system can dynamically collect thermal state data and realize accurate temperature control. This real-time thermal management can effectively avoid equipment failures caused by overheating and extend the stable operation time of the motor equipment. The monitoring and feedback of temperature data enables the system to adaptively adjust the cooling system under load or high-speed operation, preventing the efficiency from decreasing due to over-temperature, thus ensuring the safety and efficiency of the equipment. Based on the thermal status monitoring data, the system can automatically adjust the current input parameters of the motor driver and optimize the operation of the cooling system. This adaptive control method enhances the adjustment capability of the equipment under different loads and environments, and improves the overall performance. The generation of hardware adaptive control parameters enables the equipment to intelligently and dynamically adjust the driver and cooling system, thereby reducing the frequency of manual debugging, reducing maintenance costs, and ensuring the continuous and efficient operation of the equipment under various environments. By optimizing the load dynamic adjustment module of the motor equipment using hardware adaptive control parameters and dynamic harmonic characteristic monitoring data, the generated load adaptive optimization parameters can significantly improve the stability and operating efficiency of the motor equipment. This load optimization method enables the equipment to remain stable under high load conditions, and adjust the operating parameters in real time according to different loads, reducing the stress and wear of the equipment and improving the overall reliability of the motor equipment.

[0050] Preferably, step S1 comprises the following steps:

[0051] Step S11: monitoring the operating parameters of the motor in real time under various working conditions of the motor equipment of the CNC machine tool to obtain real-time operating data of the motor equipment;

[0052] Step S12: preprocessing the real-time operation data to obtain cleaned operation data;

[0053] Step S13: extracting features from the cleaned operating data to identify key feature parameters under various operating conditions and generate an operating data feature set;

[0054] Step S14: Classify and label the operating data feature set according to various operating conditions to generate an initial operating data set.

[0055] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in the embodiment of the present invention, step S1 includes the following steps:

[0056] Step S11: monitoring the operating parameters of the motor in real time under various working conditions of the motor equipment of the CNC machine tool to obtain real-time operating data of the motor equipment;

[0057] The operation data acquisition module of the embodiment of the present invention collects the operation parameters of the motor equipment in real time according to the actual working environment of the CNC machine tool. The operation parameters include various data such as the current, voltage, speed, temperature and load condition of the motor. These data reflect the real-time operation status of the motor equipment under different working conditions. In various working modes and different loads of the CNC machine tool, the motor equipment is monitored under all working conditions. The operation parameter collection under multiple working conditions ensures the comprehensiveness of the data, covers various working conditions such as low load, high load, overload, standby, etc., and generates comprehensive real-time operation data of the motor equipment.

[0058] Step S12: preprocessing the real-time operation data to obtain cleaned operation data;

[0059] The data preprocessing module of the embodiment of the present invention cleans the real-time operation data to remove noise, outliers and missing values. By setting reasonable threshold standards, parameters such as current, voltage, speed, temperature, etc. are screened to ensure that only reasonable and valid data information is retained. Statistical methods or machine learning algorithms are used to detect outliers in real-time operation data. For example, the standard deviation and mean can be used to calculate the reasonable range of each data item. Data outside the range will be marked as abnormal and processed, and the processing methods include correction, deletion or replacement. The cleaned operation data is uniformly converted into a standard format to ensure the consistency and comparability of each data. This includes formatting timestamps, unit conversion, data type standardization, etc. For missing data caused by sensor failure or data acquisition problems, interpolation or other appropriate methods are used to fill in to ensure the integrity of the data set. The cleaned operation data is stored in a database for feature extraction and analysis in subsequent steps. The cleaned operation data is accompanied by reference information of the original data to ensure traceability.

[0060] Step S13: extracting features from the cleaned operating data to identify key feature parameters under various operating conditions and generate an operating data feature set;

[0061] The embodiment of the present invention determines the key feature parameters that need to be extracted based on the operating characteristics of the motor equipment and the working requirements under various working conditions. These parameters may include indicators such as current, voltage, speed, temperature, and power. Feature selection can be performed through expert knowledge or using a feature selection algorithm. Use a suitable feature extraction method to analyze the cleaned operating data. Based on the extracted features, construct combined features to enhance the expressive power of the model. For example, the ratio of current to voltage can be used as a new feature, or more representative features can be generated by multiplication, difference, etc. The extracted feature parameters are integrated into a unified operating data feature set.

[0062] Step S14: Classify and label the operating data feature set according to various operating conditions to generate an initial operating data set.

[0063] The embodiment of the present invention first defines the working condition definition of the motor equipment under different working conditions. These working conditions include normal operation, no-load operation, overload operation, starting process and braking process, etc. The performance and characteristic parameters of the motor under each working condition will be different. According to the defined working conditions, the characteristic parameters belonging to each working condition are identified by comparing the operating data feature set. A rule-based matching method is used to automatically identify and classify features. On the basis of confirming the feature match, each set of feature data is labeled and its corresponding working condition type is recorded. The labeling can include the working condition name, category label and related metadata to ensure the traceability and clarity of the data. The labeled data is organized into a structured format, usually in a table format, with each row representing a feature sample and each column representing a feature value and working condition label to form a complete initial operating data set.

[0064] The present invention ensures the timeliness and accuracy of the data through real-time monitoring and data preprocessing of the motor operating parameters. Real-time monitoring captures the state of the motor under different working conditions, and data cleaning eliminates noise and outliers, improves data quality, and lays an accurate foundation for subsequent analysis. Feature extraction further identifies key feature parameters, focuses on the core factors that affect motor performance, and enhances the pertinence of the analysis. The initial operating data set is formed through classification and labeling, making model training and optimization control more efficient. The entire process builds a comprehensive and reliable operating data support, providing a solid foundation for the intelligent and automated control of motor equipment, thereby improving the production efficiency and safety of the equipment.

[0065] Preferably, step S2 comprises the following steps:

[0066] Step S21: grouping, sorting and unifying the initial running data set to obtain standardized training data;

[0067] Step S22: performing feature decomposition on the normalized training data, extracting key feature parameters, and generating a feature data set;

[0068] Step S23: Divide the feature data set into a training set and a validation set to construct input data for the neural network model, thereby obtaining a model training data set and a model validation data set;

[0069] Step S24: training the neural network model using the model training data set to identify and classify the harmonic features under various working conditions to obtain a preliminary harmonic feature model;

[0070] Step S25: using the model verification data set to perform real-time verification on the preliminary harmonic characteristic model to obtain a verification set test result;

[0071] Step S26: Optimize the preliminary harmonic feature model based on the validation set test results, adjust the network layer structure, learning rate and weight, and obtain a harmonic spectrum recognition model.

[0072] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S2 in the embodiment of the present invention, step S2 includes the following steps:

[0073] Step S21: grouping, sorting and unifying the initial running data set to obtain standardized training data;

[0074] The embodiment of the present invention groups the data in the initial operation data set according to different operating conditions. The data in each operating condition group should have similar characteristic parameters to ensure the homogeneity of the data during the training process. This process can be implemented by programming, and the grouping function in the data framework is used for operation. On the basis of grouping, the data in each operating condition group is sorted to ensure consistency in subsequent processing. The sorting basis can be timestamp, characteristic parameter value or other indicators to ensure that the data order of each group meets the analysis requirements. The data in each operating condition group is unified, missing values ​​are filled or missing data are deleted; the characteristic parameters are standardized so that their mean is 0 and the standard deviation is 1; the data is filtered to eliminate noise and outliers. The processed data of each operating condition group is merged into a unified normalized training data.

[0075] Step S22: performing feature decomposition on the normalized training data, extracting key feature parameters, and generating a feature data set;

[0076] When processing normalized training data, the embodiment of the present invention first determines the key parameters that need to be feature decomposed by analyzing the correlation of the data. These key feature parameters include the operating frequency, speed, current, voltage, etc. of the motor equipment. This step can use statistical analysis methods to identify important features that affect the operating performance of the motor. Select a suitable feature decomposition method to process the normalized training data. After completing the feature decomposition, extract the key feature parameters based on the selected feature decomposition method. These parameters should be able to effectively represent the operating status of the motor equipment under various working conditions, and have high explanatory power and recognition. The extraction process involves algorithm calculation, matrix transformation or model training, etc. The extracted key feature parameters are integrated into a new feature data set.

[0077] Step S23: Divide the feature data set into a training set and a validation set to construct input data for the neural network model, thereby obtaining a model training data set and a model validation data set;

[0078] According to the commonly used machine learning practices, the embodiment of the present invention selects a suitable ratio to divide the feature data set into a training set and a validation set. In this step, it is ensured that the divided data set can cover the diversity under various working conditions and ensure that the model can learn effective features. The random sampling method is used for division to avoid potential bias. A random number generator can be used to ensure the randomness of the data at each division. At the same time, it is ensured that the proportion of samples of each category in the training set and the validation set is relatively balanced to avoid the biased learning of the model on a certain type of samples. According to the set division ratio and random sampling method, data is extracted from the feature data set to generate two new data sets. The model training data set contains input data for training the neural network model, ensuring that the sample size of the data set is sufficient to improve the generalization ability of the model. The model verification data set contains data for real-time verification of model performance. This data set will be used to test the performance of the model on unseen data to ensure that the model can accurately identify and classify the harmonic features under various working conditions. The generated model training data set and model verification data set are formatted to ensure that the data structure is consistent and meets the input requirements of the neural network model.

[0079] Step S24: training the neural network model using the model training data set to identify and classify the harmonic features under various working conditions to obtain a preliminary harmonic feature model;

[0080] The embodiment of the present invention selects an appropriate neural network model architecture according to the required application scenario and data characteristics. Ensure that the selected model can effectively handle the harmonic feature recognition task. Before starting training, the parameters of the model, including weights and biases, are randomly initialized. The initialization method selects He initialization to accelerate the convergence process and improve the model performance. The model training data set is input into the selected neural network model to ensure that the data format is consistent with the input layer requirements of the model. It is usually necessary to normalize the data to improve the efficiency and stability of model training. According to the nature of the task, a suitable loss function is selected to evaluate the gap between the output of the model and the true label. At the same time, an optimizer is selected to update the model parameters to minimize the loss function. Set appropriate hyperparameters during the training process, including learning rate, batch size, number of training rounds, etc. The choice of learning rate directly affects the convergence speed and final performance of the model, and should be adjusted by methods such as cross-validation or grid search. During the training process, forward propagation and back propagation are repeated. Pass the input data through the neural network to calculate the prediction result; calculate the loss between the prediction result and the actual label according to the loss function; calculate the gradient by the chain rule, and update the model parameters to reduce the loss. During the training process, monitor the learning progress of the model by recording indicators such as loss value and accuracy. Visualization tools can help track the training process and detect overfitting or underfitting in time. Set up an early stopping mechanism based on the performance of the validation set. During the training process, if the performance of the validation set does not improve within a few rounds, stop training to prevent the model from overfitting. After the training is completed, save the trained preliminary harmonic feature model.

[0081] Step S25: using the model verification data set to perform real-time verification on the preliminary harmonic characteristic model to obtain a verification set test result;

[0082] The embodiment of the present invention ensures that the model validation data set is prepared and the format matches the input requirements of the preliminary harmonic feature model. The data should undergo the same preprocessing steps as the training data, including standardization and normalization, to ensure consistency. The model validation data set is input into the preliminary harmonic feature model and the forward propagation process is performed. The model generates a predicted output for the input data by calculating the activation values ​​of each layer. The process involves using the weights and biases in the model to weight and bias the input features, and finally obtain the prediction results of the model. According to the preset loss function, the difference between the model prediction results and the actual labels in the model validation data set is calculated. This loss value reflects the performance of the model on the validation data. In addition to the loss value, other evaluation indicators are calculated to fully understand the model performance, such as accuracy, precision, recall, and F1 score, to obtain the validation set test results.

[0083] Step S26: Optimize the preliminary harmonic feature model based on the validation set test results, adjust the network layer structure, learning rate and weight, and obtain a harmonic spectrum recognition model.

[0084] The embodiment of the present invention analyzes the test results of the validation set, identifies the performance differences of the model under different working conditions, and pays special attention to the categories with low recognition accuracy. This analysis helps to understand the shortcomings of the model and the direction of improvement. According to the validation results, the learning rate is adjusted appropriately. If the convergence speed of the model is too slow or too fast, the learning rate needs to be increased or decreased to find a suitable training speed. According to the performance of the model on the validation set, it can be decided whether to increase or decrease the number of layers of the neural network or the number of nodes per layer to improve the expressiveness of the model. Fine-tune the weights in the model and use different optimization algorithms to better adapt to the characteristics of the data. After adjusting the parameters, the preliminary harmonic feature model is retrained using the model training data set. Ensure that the training process of the model is stable under the new parameters and that the harmonic features can be effectively learned. During the training process, a cross-validation strategy is implemented, and different combinations of training sets and validation sets are used to evaluate the robustness and stability of the model to ensure that the model performs consistently on different data sets. During the retraining process, the changes and accuracy of the loss function are monitored in real time to determine the training effect of the model. Set appropriate early stopping conditions to avoid overfitting. After completing the retraining, the performance of the optimized model is evaluated again using the model validation data set. Calculate the new validation set test results and compare them with the previous results to observe the effect of the improvement. Use visualization tools (such as loss curves and accuracy curves) to show the performance of the model during training to help intuitively understand the learning process and effect of the model. Save the optimized model as a harmonic spectrum recognition model for subsequent application and deployment.

[0085] The present invention generates standardized data suitable for model training and improves model performance by grouping, sorting and normalizing the initial operation data set. Feature decomposition extracts key parameters, constructs an efficient feature data set, and provides focused input for harmonic feature recognition. The feature data set is divided into a training set and a validation set to ensure the reliability and fairness of the model on different data. The neural network model is trained using the training set to achieve automatic recognition of harmonic features and improve efficiency. Real-time testing of the validation set ensures the accuracy of the model and provides a basis for optimization. By optimizing the model structure, learning rate and weight, a high-precision harmonic spectrum recognition model is obtained. This method effectively supports the intelligent control of motor equipment, enables the equipment to autonomously monitor and identify harmonic features, and achieves more efficient operation management.

[0086] Preferably, step S3 comprises the following steps:

[0087] Step S31: real-time monitoring of the current and voltage signals of the motor equipment during operation, and preprocessing of the data to extract characteristic parameters of the current and voltage signals and generate real-time signal characteristic data;

[0088] Step S32: inputting the real-time signal characteristic data into the harmonic spectrum recognition model to identify the harmonic characteristics of the current signal and obtain dynamic harmonic characteristic monitoring data;

[0089] Step S33: extracting key harmonic parameters from the dynamic harmonic characteristic monitoring data to obtain key parameters of dynamic harmonic characteristics;

[0090] Step S34: recording the vibration frequency of the motor equipment in real time, and extracting and analyzing key parameters to obtain real-time vibration frequency key parameters;

[0091] Step S35: Based on the real-time vibration frequency key parameter, the harmonic frequency and harmonic frequency amplitude in the dynamic harmonic characteristic key parameter are compared and analyzed with the preset vibration stability threshold value to obtain a stability evaluation report;

[0092] Step S36: judging whether the harmonics meet the isolation conditions according to the stability evaluation report, generating an isolation instruction if the harmonics exceed the vibration frequency threshold, and continuously monitoring the harmonics of the motor equipment if the harmonics do not exceed the vibration frequency threshold;

[0093] Step S37: confirming the harmonic frequency range and amplitude requirements currently required to be isolated according to the isolation instruction, and generating frequency response range adjustment parameters;

[0094] Step S38: dynamically configuring the frequency response module of the motor device according to the frequency response range adjustment parameter to obtain optimized frequency response configuration data;

[0095] Step S39: performing an isolation operation according to the optimized frequency response configuration data, suppressing harmonic signal interference within a specific frequency range, and generating optimized signal response data.

[0096] As an embodiment of the present invention, in the embodiment of the present invention, step S3 includes the following steps: Step S31: real-time monitoring of the current and voltage signals of the motor equipment during operation, and preprocessing of the data to extract characteristic parameters of the current and voltage signals and generate real-time signal characteristic data; In the embodiment of the present invention, high-precision sensors are used to monitor current and voltage signals in real time during the operation of the motor equipment. These sensors can record changes in the signals and output the instantaneous values ​​of the current and voltage in digital form. The acquired current and voltage signals are subjected to data preprocessing, including denoising, normalization and time synchronization. A feature extraction algorithm is used to extract key characteristic parameters from the preprocessed current and voltage signals, including effective value, peak value and frequency characteristics. The extracted characteristic parameters are organized into structured data to generate real-time signal characteristic data, including effective value, peak value, frequency component and other statistical characteristics of current and voltage.

[0099] Step S32: inputting the real-time signal characteristic data into the harmonic spectrum recognition model to identify the harmonic characteristics of the current signal and obtain dynamic harmonic characteristic monitoring data;

[0100] The embodiment of the present invention organizes the real-time signal feature data into a suitable input format to ensure that the data can be correctly received and processed by the harmonic spectrum recognition model. The data includes the effective value, peak value, frequency characteristics, etc. of the current and voltage. The trained harmonic spectrum recognition model is loaded from the storage system. The model is generated based on the previous training process and can effectively identify the harmonic characteristics in the current and voltage signals. The real-time signal feature data is input into the harmonic spectrum recognition model. The feature data is received and parsed through the input layer of the model. The harmonic spectrum recognition model analyzes the input signal and uses the parameters learned during its training to identify the harmonic components in the signal. The input signal is Fourier transformed to convert it to the frequency domain for harmonic characteristic analysis. The harmonic frequencies and amplitudes in the signal are identified to determine the presence and intensity of each harmonic component. After the identification is completed, the model will generate dynamic harmonic characteristic monitoring data.

[0101] Step S33: extracting key harmonic parameters from the dynamic harmonic characteristic monitoring data to obtain key parameters of dynamic harmonic characteristics;

[0102] The embodiment of the present invention parses the dynamic harmonic characteristic monitoring data and identifies the data structure and content, including each harmonic frequency and its corresponding amplitude. According to the actual application requirements, the key harmonic parameters to be extracted are determined, including but not limited to the harmonic frequency and harmonic amplitude. The harmonic frequency and amplitude are screened. The threshold standard is set to filter the harmonic frequency and amplitude data below the threshold. The key harmonic frequency and amplitude above the threshold are recorded to form a parameter list to generate the key parameters of the dynamic harmonic characteristic.

[0103] Step S34: recording the vibration frequency of the motor equipment in real time, and extracting and analyzing key parameters to obtain real-time vibration frequency key parameters;

[0104] The embodiment of the present invention is equipped with a vibration sensor and a collection device to ensure that the vibration frequency of the motor equipment can be monitored in real time, and the installation position should be able to accurately capture the vibration signal of the motor during operation. During the operation of the motor equipment, its vibration frequency signal is collected in real time. These signals can be directly acquired by the vibration sensor, and the data acquisition frequency should be high enough to ensure that the rapidly changing vibration characteristics are captured. The acquired vibration signal is preprocessed, including operations such as denoising, smoothing and filtering to improve signal quality and accuracy. This process involves the use of high-pass or low-pass filters to eliminate unnecessary frequency components. Real-time vibration frequency key parameters are extracted from the preprocessed vibration signal, the main vibration frequency components are extracted, the amplitude of the vibration signal is recorded, and the waveform characteristics of the vibration signal are analyzed. The extracted real-time vibration frequency key parameters are organized into a structured data format for subsequent processing and analysis.

[0105] Step S35: Based on the real-time vibration frequency key parameter, the harmonic frequency and harmonic frequency amplitude in the dynamic harmonic characteristic key parameter are compared and analyzed with the preset vibration stability threshold value to obtain a stability evaluation report;

[0106] The embodiment of the present invention presets a vibration stability threshold value, and this threshold value is determined based on the operating standard and historical data of the motor equipment. The threshold value is used to determine whether the vibration state of the motor equipment is within the safe operating range. The acquired real-time vibration frequency key parameters are compared with the preset vibration stability threshold value one by one. The harmonic frequencies in the dynamic harmonic characteristic key parameters are compared with the real-time vibration frequency key parameters one by one to check whether there are frequency components exceeding the threshold. The relationship between the harmonic frequency amplitude and the vibration stability threshold is evaluated to determine whether the current operating state is normal. Based on the comparative analysis results, a stability assessment report is generated, and the report includes the following contents: identifying the harmonic frequencies and their amplitudes that exceed the vibration stability threshold; providing comparative analysis data and charts to show the relationship between the vibration characteristics and harmonic characteristics of the current motor equipment; and providing safety assessments and recommendations for equipment operation.

[0107] Step S36: judging whether the harmonics meet the isolation conditions according to the stability evaluation report, generating an isolation instruction if the harmonics exceed the vibration frequency threshold, and continuously monitoring the harmonics of the motor equipment if the harmonics do not exceed the vibration frequency threshold;

[0108] The embodiment of the present invention determines the isolation condition of the harmonic, and this condition is usually based on a preset vibration frequency threshold. If any value in the real-time vibration frequency key parameter exceeds the threshold, it is determined that the harmonic needs to be isolated. Compare the data in the stability assessment report with the preset vibration frequency threshold. Check whether the harmonic frequency amplitude in each dynamic harmonic characteristic key parameter exceeds the vibration frequency threshold. For harmonic frequencies exceeding the threshold, record their type and amplitude to prepare for the subsequent generation of isolation instructions. If it is detected that a harmonic frequency exceeds the vibration frequency threshold, an isolation instruction is generated, indicating that an isolation operation is performed on the harmonic signal in a specific frequency range. If no threshold is exceeded, the system records this state and maintains continuous monitoring of the harmonics of the motor equipment to ensure that the equipment is not disturbed during normal operation.

[0109] Step S37: confirming the harmonic frequency range and amplitude requirements currently required to be isolated according to the isolation instruction, and generating frequency response range adjustment parameters;

[0110] The embodiment of the present invention parses the information in the isolation instruction and extracts the harmonic frequency range and amplitude requirements. Ensure that the specific frequency band that needs to be isolated and its amplitude limit are understood. Ensure that the extracted frequency range and amplitude meet the safety standards and technical requirements of the motor equipment. According to the operating characteristics of the motor equipment, confirm whether the extracted harmonic frequency range is within the acceptable range of the equipment. If it is found that the extracted frequency range exceeds the safety threshold of the equipment, necessary adjustments and corrections must be made to ensure the safety of the operation. Generate corresponding frequency response range adjustment parameters based on the confirmed harmonic frequency range and its amplitude requirements.

[0111] Step S38: dynamically configuring the frequency response module of the motor device according to the frequency response range adjustment parameter to obtain optimized frequency response configuration data;

[0112] The embodiment of the present invention parses the frequency response range adjustment parameters and extracts the specific values ​​of each frequency segment and the corresponding configuration requirements. Confirm the integrity and accuracy of the parameters to ensure that they meet the technical specifications and operating requirements of the equipment. Ensure that the frequency response module of the motor equipment is in a configurable state, check whether all related systems and components are working properly, and avoid failures during the dynamic configuration process. According to the parsed frequency response range adjustment parameters, the frequency response module of the motor equipment is dynamically configured. Set the corresponding frequency response characteristics, such as suppressing or amplifying specific harmonic frequencies, to ensure that the motor equipment can effectively cope with different harmonic interferences. After the configuration is completed, the performance of the frequency response module is monitored in real time to ensure that the new configuration can effectively optimize the frequency response. According to the monitoring results, make necessary adjustments to the settings of the frequency response module to achieve the expected optimization effect. The completed optimized frequency response configuration data is recorded in the system database for subsequent maintenance and auditing.

[0113] Step S39: performing an isolation operation according to the optimized frequency response configuration data, suppressing harmonic signal interference within a specific frequency range, and generating optimized signal response data.

[0114] The embodiment of the present invention inputs the optimized frequency response configuration data into the frequency response module of the motor device. The configuration data includes the harmonic frequency range to be isolated and the corresponding frequency amplitude limit requirements. According to the optimized frequency response configuration data, the harmonic isolation mode is activated. This mode monitors the harmonics within the preset frequency range in real time when the motor device is running to determine whether the isolation conditions are met. Through the current and voltage signal characteristics collected in real time, the harmonic signal within the target frequency range is identified, and its characteristics are compared with the optimized frequency response configuration data to ensure that the detected harmonic is within the preset range of the configuration data. According to the comparison result, if the detected harmonic signal exceeds the amplitude limit in the configuration data, the suppression strategy is triggered. The suppression strategy includes adjusting the frequency response of the motor device so that it automatically lowers the frequency response sensitivity within the preset harmonic frequency range, or reduces the harmonic amplification factor of the frequency band through software and hardware methods to achieve the harmonic suppression effect. With the implementation of the suppression strategy, the change data of each frequency response of the motor device after the isolation operation is recorded to generate the final optimized signal response data.

[0115] The present invention monitors the current and voltage signals in the operation process of the motor equipment in real time, performs data preprocessing, quickly extracts signal characteristic parameters, and generates real-time signal characteristic data. This processing enhances the response speed of the system and can effectively identify potential problems. The extracted real-time signal characteristic data is input into the harmonic spectrum recognition model for harmonic characteristic recognition, and dynamic harmonic monitoring data is obtained, so that the real-time recognition of harmonic characteristics is more accurate, providing a reliable basis for subsequent analysis. By extracting the dynamic harmonic key parameters, the system can clearly identify the important harmonic information affecting the equipment, thereby improving the depth of data analysis and the ability to understand the equipment status. In addition, the system records the vibration frequency in real time and extracts key parameters to timely discover abnormal vibrations, providing a guarantee for the safe operation of the equipment. Based on the real-time vibration frequency key parameters, the harmonic frequency and amplitude are compared and analyzed with the preset vibration stability threshold to generate a stability evaluation report. This evaluation report helps to identify potential risks and provide data support for harmonic isolation. The stability evaluation report is used to determine whether to generate an isolation instruction, and the strategy is dynamically adjusted to prevent equipment failure. Subsequently, the harmonic frequency range and amplitude requirements to be isolated are confirmed according to the isolation instruction, and the frequency response adjustment parameters are generated to ensure the accuracy of the isolation operation and reduce misoperation. Finally, the isolation operation is performed using optimized frequency response configuration data, which effectively suppresses harmonic signal interference and generates optimized signal response data, significantly improving equipment stability and extending service life.

[0116] Preferably, step S4 comprises the following steps:

[0117] Step S41: collecting and recording the real-time temperature data of the motor driver in the CNC machine tool motor device according to the optimized signal response data, and generating the driver thermal state monitoring data;

[0118] The embodiment of the present invention configures a temperature sensor of the motor driver to ensure that it can monitor the temperature change of the motor driver in real time. The temperature sensor is connected to the data acquisition system to facilitate real-time data transmission and recording. The temperature monitoring program is started to regularly obtain real-time temperature data of the motor driver from the temperature sensor. The acquisition frequency is set, for example, once per second, to ensure the timeliness and accuracy of the monitoring data. The collected real-time temperature data is stored in the database to form the thermal state monitoring data of the driver.

[0119] Step S42: Compare the driver thermal state monitoring data with a preset safety temperature threshold to generate a thermal state threshold comparison result;

[0120] The embodiment of the present invention sets an appropriate safety temperature threshold value according to the technical specifications of the motor driver and the manufacturer's recommendations. This threshold value should take into account the optimal operating temperature under normal working conditions and provide a guarantee for the long life of the motor. The threshold value can be a fixed value or can be dynamically adjusted according to factors such as different workloads and environmental conditions. Real-time temperature data within a recent period of time is extracted from the thermal state monitoring data of the driver to form a set of temperature data to be compared. Ensure that the data format is consistent to facilitate comparative analysis. Develop a comparison algorithm to compare the extracted real-time temperature data with the preset safety temperature threshold value one by one. The result of the comparison should include whether each data point is lower than, equal to, or exceeds the threshold. The results of the comparison are organized into a thermal state threshold comparison result, which includes the following information: the number of temperature records exceeding the threshold, the highest and lowest temperature values, and an overall judgment on whether the current temperature is within a safe range.

[0121] Step S43: Based on the comparison result of the thermal state threshold, determine whether it is necessary to start the cooling system of the motor device. If the temperature exceeds the threshold, adjust the fan speed of the cooling system to generate the motor device cooling control parameter; if the temperature does not exceed the threshold, continue to monitor the motor device state;

[0122] The embodiment of the present invention executes judgment logic according to the comparison result of the thermal state threshold. If any item of the current temperature data exceeds the safe temperature threshold, it indicates that the operating temperature of the motor driver is too high. If all the temperature data do not exceed the safe temperature threshold, it is considered that the motor device is in a safe state. If the judgment result shows that the temperature exceeds the safe temperature threshold, an instruction to start the cooling system is generated, and the fan speed of the cooling system is adjusted according to specific needs to improve the cooling effect. The adjustment of the fan speed can be determined according to the degree to which the current temperature exceeds the threshold. Generate the heat dissipation control parameters of the motor device, which include information such as fan speed setting and start time. If the judgment result shows that the temperature does not exceed the safe temperature threshold, continue to monitor the status of the motor device, maintain real-time monitoring of temperature changes, and ensure that potential overheating risks can be responded to in a timely manner at any time.

[0123] Step S44: Comprehensively analyze the heat dissipation control parameters of the motor equipment and the optimized signal response data to generate comprehensive thermal state monitoring data.

[0124] The embodiment of the present invention integrates the heat dissipation control parameters of the motor equipment with the optimized signal response data to form a comprehensive data set. The process of data integration includes the unification of data formats, the alignment of timestamps, and necessary identifiers for subsequent analysis. The main purpose of analyzing the integrated data is to evaluate the operating safety and performance of the motor equipment under the current heat dissipation state. The analysis includes three aspects: temperature and response relationship, fan efficiency evaluation, and safety evaluation. Among them, the temperature and response relationship is to analyze the impact of temperature changes on the response performance of the motor equipment, and determine whether there is a performance degradation caused by excessive temperature; fan efficiency evaluation is to evaluate whether the current fan speed is sufficient to meet the heat dissipation requirements of the motor driver, and whether the fan speed needs to be further adjusted to improve the heat dissipation efficiency; safety evaluation is based on comprehensive data to determine whether the motor equipment is still in a safe operating state and whether additional measures need to be taken to optimize heat dissipation and performance. Based on the results of the comprehensive analysis, comprehensive thermal state monitoring data is generated.

[0125] The present invention generates thermal status monitoring data by real-time acquisition of motor driver temperature data, ensures accurate monitoring of equipment temperature, and detects anomalies in time to ensure safety. After comparing the monitoring data with the safety temperature threshold, a threshold comparison result is generated to achieve over-temperature warning and enhance the risk identification ability of the system. According to the comparison results, the system automatically adjusts the heat dissipation system and dynamically controls the fan speed to prevent overheating and improve the operating stability of the equipment. If the temperature is normal, the system continues to monitor to avoid unnecessary heat dissipation startup, thereby improving energy efficiency. Through comprehensive analysis with the optimized signal response data, comprehensive thermal status monitoring data is generated to provide reliable support for subsequent decision-making and equipment optimization. This process enables the equipment to achieve intelligent regulation under different working conditions, extend service life and optimize overall performance.

[0126] Preferably, step S44 includes the following steps:

[0127] Step S441: collecting the temperature of the motor driver in real time through the temperature sensor, establishing a temperature data curve, and analyzing the temperature change trend by optimizing the signal response data to obtain abnormal thermal state information data;

[0128] The temperature sensor installed on the motor driver in the embodiment of the present invention starts to monitor its working temperature in real time. The sensor records temperature data regularly and sends the data to the control system. The collected data includes timestamp, current temperature value and other relevant information for comprehensive analysis. The collected temperature data is processed to generate a temperature data curve. This curve shows the trend of the temperature change of the motor driver over time, which is convenient for observing the temperature fluctuation. The temperature data is visualized through chart software or data analysis tools to present the temperature change more intuitively. The temperature data curve is analyzed by optimizing the signal response data. This includes identifying the rate of temperature rise or fall and periodic changes. The temperature curve is smoothed by applying statistical analysis methods to reduce the impact of noise, so as to extract effective temperature change trends. Based on the temperature change trend analysis, the standard of temperature anomaly is determined. For example, when the temperature exceeds a preset threshold or the rate of change is too fast in a short time, it can be regarded as an abnormal state. Record abnormal temperature information, including the time when the abnormality occurs, the duration, and the operating status at that time. The analysis results are organized into abnormal thermal state information data.

[0129] Step S442: Compare the heat dissipation control parameters of the motor equipment with the real-time temperature, and evaluate the control effect of the current heat dissipation system using the relationship between the fan speed and the temperature change rate to obtain heat dissipation control effect data;

[0130] The embodiment of the present invention continuously obtains real-time temperature data of the motor driver from the temperature sensor. These data will include the current temperature value and its rate of change, ensuring that the thermal state of the motor can be reflected in real time. The heat dissipation control parameters are extracted from the control system of the motor device, and these parameters include the current fan speed, the working state of the heat dissipation system, and any active or passive heat dissipation measures. The real-time temperature data is compared with the heat dissipation control parameters to calculate the control effect of the current heat dissipation system under actual operating conditions. By comparing the temperature changes in different time periods, the effectiveness of the heat dissipation system in regulating the temperature is analyzed. The relationship between the fan speed and the temperature change rate is used to evaluate the performance of the current heat dissipation system. For example, the effect of the fan speed on the temperature change can be quantified by establishing a mathematical model or using a regression analysis method. According to the evaluation results, it is determined whether the heat dissipation system effectively reduces the temperature of the motor driver, and then the heat dissipation control effect data is obtained.

[0131] Step S443: performing cluster analysis on the abnormal temperature according to the abnormal thermal state information data to identify the root cause of overheating of the motor equipment and obtain a driver abnormal state report;

[0132] The embodiment of the present invention preprocesses the abnormal thermal state information data, including data cleaning and normalization, to ensure the accuracy and availability of the data. This involves removing noise, filling missing values, and unifying data of different units. Select an appropriate clustering algorithm, such as K-means clustering, hierarchical clustering, or DBSCAN, as the basis for identifying abnormal temperature patterns. The selection is based on the characteristics of the data and its distribution to ensure the effectiveness of the clustering effect. The processed abnormal thermal state information data is input into the selected clustering algorithm for analysis. The clustering algorithm will identify different temperature patterns in the data and cluster similar temperature anomalies together to form multiple clusters. The clustering results are analyzed to identify the potential root causes of overheating of the motor equipment. This can be done by looking at the center point of each cluster and its degree of discreteness to determine which temperature patterns are abnormal, indicating equipment problems or the influence of environmental factors. Based on the results of the cluster analysis, a drive abnormal state report is generated, which records in detail each identified abnormal temperature pattern and its root cause.

[0133] Step S444: Comprehensively analyze the heat dissipation control effect data and the driver abnormal status report to generate comprehensive thermal status monitoring data.

[0134] The embodiment of the present invention integrates the heat dissipation regulation effect data with the drive abnormal status report to form a comprehensive data set. During the integration process, it should be ensured that all relevant parameters are matched, especially the timestamps and device status related to abnormal temperatures. Select an appropriate analysis method to extract valuable information and patterns from the comprehensive data set. The method selection should be based on the complexity of the required results and the characteristics of the data. The comprehensive data set is analyzed using the selected analysis method to identify the relationship between the heat dissipation regulation effect and the abnormal state. Based on the analysis results, comprehensive thermal status monitoring data is generated, which should include an evaluation of the heat dissipation regulation effect, the frequency of abnormal states and their corresponding root cause analysis.

[0135] The present invention uses a temperature sensor to collect the temperature of the motor driver in real time and establish a temperature data curve to achieve accurate monitoring of temperature anomalies. At the same time, by optimizing the signal response data to analyze the temperature trend, reliable abnormal thermal state information is provided to ensure the safety of the equipment. The heat dissipation control parameters are compared with the real-time temperature to evaluate the effect of the heat dissipation system, and the fan speed and temperature change rate are analyzed to ensure that the heat dissipation system remains stable under various working conditions. Cluster analysis is performed using abnormal thermal state data to identify the root cause of overheating, provide a basis for troubleshooting, and extend the life of the equipment. The comprehensive thermal state monitoring data generated by the comprehensive heat dissipation effect data and the abnormal state report improves the accuracy of equipment status monitoring and provides data support for subsequent maintenance optimization. The overall process realizes the intelligent management of motor equipment, which can quickly respond, warn and dynamically adjust in abnormal situations, thereby reducing downtime and improving production efficiency and operational safety.

[0136] Preferably, step S5 comprises the following steps:

[0137] Step S51: performing real-time analysis on the current input parameters of the motor device driver according to the comprehensive thermal state monitoring data to identify the current demand of the driver under various temperature conditions and generate the current input parameters;

[0138] The embodiment of the present invention collects real-time temperature data of the motor device driver from a temperature sensor. Relevant information is extracted from the comprehensive thermal state monitoring data, including the historical current input parameters and current working state of the driver. Based on the historical data, a current demand model is established, and the model should consider the relationship between current and temperature under different temperature conditions. The model can use regression analysis, machine learning algorithms or other suitable methods to ensure its accuracy and reliability. The real-time temperature data is input into the current demand model for analysis, and the current demand of the driver under the current temperature conditions is calculated in real time. The analysis should consider a variety of working states and load conditions to ensure the comprehensiveness of the results. According to the real-time analysis results, the corresponding current input parameters are generated.

[0139] Step S52: optimizing and adjusting the current input parameters of the motor device driver to identify the optimal operating temperature range of the motor device driver and obtain the current optimized input adjustment parameters;

[0140] The embodiment of the present invention collects the operation records of the motor device driver under different temperature conditions, including its working state, power consumption and efficiency information. Based on the collected data, an optimization model is established, which should analyze the relationship between the current input parameters and the temperature. Data analysis methods can be used to determine the correlation between the current demand and the temperature. The model should consider the change in current demand under different workloads to ensure its applicability. Using the established optimization model, the current input parameters of the driver under different temperature conditions are analyzed, and the optimal working state of the driver under each temperature condition is identified. The optimal operating temperature range of the motor device driver is determined, which is usually the temperature range under which the device can operate efficiently and will not cause overheating or overload. According to the optimal operating temperature range, the current optimization input adjustment parameters are generated. These parameters should include the recommended current input value within the optimal temperature range, and the adjustment range required under different temperature conditions. Ensure that the generated current optimization input adjustment parameters help the driver to operate at the optimal efficiency state and avoid potential failures caused by too low or too high current.

[0141] Step S53: Based on the current optimization input adjustment parameter, the operation state of the cooling system is monitored in real time, and the fan speed and coolant flow of the cooling system are adjusted in real time to generate the cooling system control parameter;

[0142] In the embodiment of the present invention, a temperature sensor and a current sensor are installed in the motor device driver to collect the temperature and current input parameters of the motor device in real time. Through the data acquisition system, the current input parameters collected in real time are compared with the comprehensive thermal state monitoring data of the motor device to monitor the operating state of the current heat dissipation system. The key parameters of the heat dissipation system, such as fan speed and coolant flow, are set, and the real-time monitoring data is used to compare with these parameters to analyze the effectiveness of the current heat dissipation system. The workload and ambient temperature of the motor device are monitored to evaluate the performance of the heat dissipation system under different working conditions. According to the current optimization input adjustment parameters, the influence on the heat dissipation demand of the motor device driver is analyzed. If the current input parameters indicate that the driver is overheating under specific temperature conditions, the system needs to make adjustment instructions in time. According to the real-time monitoring results and the current optimization input adjustment parameters, the fan speed and coolant flow of the heat dissipation system are dynamically adjusted. For example, when the temperature of the motor driver rises, the system increases the fan speed to increase air circulation and heat dissipation effect; if the temperature drops, the fan speed is appropriately reduced to save energy. By controlling the coolant flow, the heat dissipation effect is optimized, and the flow rate of the coolant between the motor driver and the radiator is ensured to be appropriate to maintain an ideal heat dissipation state. After completing the above adjustments, the cooling system control parameters are generated and the new fan speed and coolant flow values ​​are recorded.

[0143] Step S54: integrating the current optimization input adjustment parameters and the heat dissipation system control parameters to generate hardware adaptive control parameters.

[0144] An embodiment of the present invention creates a data integration model that combines current optimization input adjustment parameters with cooling system control parameters. The model can correlate these two types of parameters to evaluate their synergistic effect in the overall operation of the motor device. By comparing and analyzing the relationship between current demand and cooling capacity through an algorithm, it is ensured that under different working conditions, the current input of the motor device and the working state of the cooling system can maintain the best match. The integrated data is analyzed to evaluate the compatibility between the current input required by the current motor device driver in actual operation and the responsiveness of the cooling system. Identify potential optimization space, for example, under certain temperature conditions, adjust the fan speed or coolant flow to meet the current input demand and maintain a safe operating temperature. Based on the results of the integrated analysis, new hardware adaptive control parameters are generated.

[0145] The present invention analyzes the comprehensive thermal status monitoring data in real time to accurately identify the current demand of the motor driver at different temperatures, ensure that the equipment operates within a safe range and reduce the risk of failure. The current input parameters are optimized and adjusted to identify the optimal operating temperature range, improve energy efficiency, and reduce damage caused by excessive temperature. The cooling system status is monitored based on the current optimization parameters, and the fan speed and coolant flow are dynamically adjusted to ensure that the cooling system maintains the optimal state under different conditions, effectively extending the life of the equipment. The current optimization and heat dissipation control parameters are integrated to generate hardware adaptive control parameters to achieve intelligent adjustment of the equipment. The overall process enhances the equipment's responsiveness to temperature and current changes, improves operating efficiency, reduces failure downtime, and improves energy-saving effects and system stability.

[0146] Preferably, step S53 includes the following steps:

[0147] Step S531: collecting the parameters of the heat dissipation system in real time through sensors, and monitoring the temperature change in real time to obtain the real-time monitoring parameters of the heat dissipation system;

[0148] In an embodiment of the present invention, a plurality of temperature sensors are arranged at key parts of the heat dissipation system to ensure comprehensive monitoring of the temperature changes of the entire heat dissipation system. These sensors can collect temperature data in real time and transmit the data to a central control system by wireless or wired means. Periodic data collection is implemented and a suitable sampling frequency is set to ensure that the acquired temperature data is real-time and accurate. Temperature changes are recorded, including key parameters such as the temperature of the fan inlet and outlet, the temperature of the coolant, and the operating temperature of the motor driver. The collected real-time temperature data is input into a data processing module for data cleaning and preprocessing to remove abnormal values ​​or noise. Real-time monitoring parameters are generated through temperature data, including information such as the current temperature, the temperature change rate, and the temperature historical trend, for subsequent analysis and use. The processed real-time monitoring parameters are fed back to the control system of the motor equipment to provide detailed information about the current operating status of the heat dissipation system. Changes in real-time monitoring parameters are recorded to obtain real-time monitoring parameters of the heat dissipation system.

[0149] Step S532: Compare and analyze the real-time monitoring parameters of the heat dissipation system with the current optimization input adjustment parameters, evaluate the heat dissipation effect of the fan speed and the coolant flow rate, and obtain heat dissipation demand comparison result data;

[0150] The embodiment of the present invention inputs the real-time monitoring parameters and the current optimization input adjustment parameters into the analysis module, and sets the corresponding algorithm for comparative analysis. The working efficiency of the real-time heat dissipation system is calculated, including the current temperature and the difference between the actual current demand and the theoretical current demand, to evaluate whether the heat dissipation system can meet the heat dissipation requirements of the motor equipment under different working conditions. Based on the comparative analysis results, the heat dissipation effect of the fan speed and the coolant flow rate is evaluated, including whether there is overheating or insufficient cooling. The heat dissipation demand comparison result data is recorded, including the conclusion of whether the evaluated heat dissipation effect and the current heat dissipation capacity meet the working requirements of the equipment.

[0151] Step S533: dynamically adjusting the fan speed of the cooling system based on the cooling demand comparison result data to obtain fan speed optimization data;

[0152] The embodiment of the present invention records the current demand of the motor device driver at different operating temperatures and the actual operating parameters of the current cooling system. According to the cooling demand comparison result data, a dynamic adjustment strategy is set, including the preset fan speed change range, the relationship curve between the fan speed and the temperature, and the adjustment ratio of the coolant flow rate. The threshold for fan speed adjustment is set to ensure that the fan speed is automatically increased or decreased when a certain temperature is reached. The real-time monitoring parameters and the cooling demand evaluation results of the current cooling system are obtained through the control module to determine whether the fan speed needs to be adjusted. If the current cooling effect is insufficient, the fan speed is increased, and a linear or nonlinear adjustment strategy is adopted to gradually increase the fan speed to the required level. If the cooling effect is good, it can be considered to moderately reduce the fan speed to save energy and avoid unnecessary noise and energy consumption. The adjusted fan speed is recorded, and fan speed optimization data is generated, including the newly set fan speed value and the corresponding timestamp.

[0153] Step S534: Adapt and adjust the coolant flow rate according to the fan speed optimization data to obtain the coolant flow optimization data;

[0154] The embodiment of the present invention obtains real-time monitoring parameters of the current heat dissipation system, including information such as coolant flow rate, heat dissipation effect and system temperature. The adaptation strategy of the coolant flow rate is set according to the fan speed optimization data, and the relationship between the fan speed and the coolant flow rate is clarified. The adjustment range of the coolant flow rate is determined to ensure that an appropriate cooling effect can be provided at different fan speeds. The fan speed optimization data is analyzed by the control module to determine the requirements of the current fan speed for the coolant flow rate. If the fan speed increases, the coolant flow rate is increased to meet the overall cooling requirements of the heat dissipation system and prevent the equipment from overheating. If the fan speed decreases, the coolant flow rate is reduced accordingly to optimize the energy consumption and efficiency of the system and avoid excessive cooling. The adjusted coolant flow rate is recorded, and coolant flow optimization data is generated, including the newly set flow value and the relevant timestamp.

[0155] Step S535: Integrate the fan speed optimization data and the coolant flow optimization data to generate cooling system control parameters.

[0156] The embodiment of the present invention determines the relationship between the fan speed optimization data and the coolant flow optimization data, sets appropriate integration rules, and ensures that the results after data integration can reflect the overall operating status of the cooling system. The structure of the cooling system control parameters is clarified, including the fan speed, the coolant flow and their corresponding adjustment strategies. The fan speed optimization data and the coolant flow optimization data are matched item by item to form a comprehensive data set. Timestamps, device status and operating instructions are added to each set of optimization data to generate a complete record of the cooling system control parameters. Through the data integration process, the final cooling system control parameters are generated, including the optimized fan speed setting and the corresponding coolant flow setting.

[0157] The present invention uses sensors to collect and monitor the parameters of the heat dissipation system in real time, quickly identify heat dissipation problems, ensure that the motor equipment operates within a safe temperature, and reduce the risk of equipment damage. By comparing and analyzing the real-time parameters of the heat dissipation system and the current optimization input parameters, the heat dissipation effect of the fan speed and coolant flow rate is accurately evaluated to provide data support for adjustment. Based on demand comparison, the fan speed and coolant flow rate are dynamically adjusted to achieve optimal heat dissipation, avoid equipment overheating, and reduce energy consumption. The fan and coolant data are integrated to generate heat dissipation control parameters, making the heat dissipation system more intelligent and adaptive. The overall process effectively improves the stability, safety and operating efficiency of the equipment, and meets the industrial needs of energy conservation and environmental protection.

[0158] Preferably, step S6 comprises the following steps:

[0159] Step S61: performing real-time analysis on the load dynamic adjustment module of the motor device according to the hardware adaptive control parameters to identify the performance requirements of the motor device under various load conditions and generate load performance requirement analysis data;

[0160] The embodiment of the present invention collects real-time operating data of the motor equipment through sensors and monitoring equipment, including current, speed, torque and load information. Obtain hardware adaptive control parameters, which may include current optimization input adjustment parameters generated in the previous steps, cooling system control parameters, etc. Based on the collected real-time data, establish a performance requirement model of the motor equipment under different load conditions. This model should take into account the operating characteristics of the motor under various working conditions, such as starting, acceleration, full load and no-load states. Use an algorithm to analyze the relationship between real-time data and hardware adaptive control parameters, and identify the optimal performance indicators required for the motor equipment under various load conditions, including the required current, speed and torque. The analysis results are organized into load performance demand analysis data, including the specific values ​​of the current, speed and torque required under each load state and the corresponding working conditions.

[0161] Step S62: Optimizing the configuration of the load dynamic adjustment module based on the load performance demand analysis data and the dynamic harmonic characteristic monitoring data to generate a load optimization strategy;

[0162] The embodiment of the present invention conducts a comprehensive analysis of the load performance demand analysis data and the dynamic harmonic characteristic monitoring data to identify the performance deviation under the current load conditions and harmonic characteristics. Through mathematical modeling or simulation calculation, it is evaluated whether the current configuration of the load dynamic adjustment module can meet the identified performance requirements, and finds potential optimization space. Based on the above evaluation results, a load optimization strategy is formulated, including adjustment of the motor control algorithm, optimization of load distribution, and implementation of harmonic suppression measures. The optimization strategy should clearly define specific adjustment goals, such as reducing the impact of harmonics, improving efficiency, optimizing power factor, etc., while also considering the feasibility and economy of implementation.

[0163] Step S63: applying the load optimization strategy to the control module of the motor device, and adjusting the torque and speed of the motor device in real time to generate load adaptive optimization parameters to improve the operation stability of the motor device.

[0164] The embodiment of the present invention inputs the load optimization strategy into the control module of the motor device. This strategy includes the optimal torque and speed settings under different load conditions, aiming to optimize the operating performance of the motor device. The real-time operating status of the motor device is monitored by sensors, and relevant data is collected, including current torque, speed, load conditions, temperature and other information. These real-time data will be used to evaluate whether the performance of the motor device meets the requirements of the load optimization strategy. According to the data monitored in real time, a comparative analysis is performed with the load optimization strategy to identify the parameters that need to be adjusted. If it is found that the current torque and speed of the motor device do not reach the optimization target, these parameters are dynamically adjusted through the control algorithm. The control module should have a fast response capability and be able to make adjustments quickly after real-time data collection to cope with instantaneous load changes. After the torque and speed adjustment is completed, the new torque and speed parameters are recorded to generate load adaptability optimization parameters.

[0165] The present invention analyzes hardware adaptive control parameters in real time, identifies the performance requirements of the motor under different load conditions, generates load performance requirement data, and ensures the performance adaptability and flexibility of the equipment under various loads. Combined with load requirements and dynamic harmonic data, the load adjustment module is optimized and configured, and a load optimization strategy is generated to improve the operating efficiency of the motor and reduce energy waste. Through the real-time adjustment of torque and speed by the load optimization strategy, the equipment can quickly adapt to load changes, significantly improve operational stability and extend service life, and reduce maintenance costs. This method effectively reduces energy consumption and improves energy efficiency through optimized configuration and real-time parameter adjustment, meets energy conservation and environmental protection requirements, and promotes intelligent manufacturing and sustainable development.

[0166] Preferably, the present invention further provides a motor device for executing the operation control method of the motor device as described above, the motor device comprising:

[0167] The operation data acquisition module is used to collect the operation data of the motor equipment in the CNC machine tool under various working conditions in real time to obtain the initial operation data set;

[0168] The harmonic spectrum modeling module is used to train the neural network model using the initial operation data set to identify the harmonic characteristics under various working conditions and generate a harmonic spectrum recognition model;

[0169] The dynamic harmonic monitoring and optimization module is used to collect the current and voltage signals of the motor equipment in real time, input them into the harmonic spectrum recognition model for identification, and generate dynamic harmonic characteristic monitoring data; compare the dynamic harmonic characteristic monitoring data with the preset threshold, generate isolation instructions, and dynamically adjust the frequency response range of the motor equipment to obtain optimized signal response data;

[0170] Thermal status monitoring and management module, used to monitor the temperature of the motor driver and cooling system in the motor equipment in real time according to the optimized signal response data, and generate comprehensive thermal status monitoring data;

[0171] Adaptive current and heat dissipation control module, used to adjust the current input parameters of the motor device driver based on the comprehensive thermal status monitoring data, optimize the operating status of the heat dissipation system, and generate hardware adaptive control parameters;

[0172] The load adaptability optimization module is used to optimize the load dynamic adjustment module of the motor equipment based on the hardware adaptive control parameters and dynamic harmonic characteristic monitoring data, and generate load adaptability optimization parameters to improve the operation stability of the motor equipment.

[0173] The present invention generates an initial operation data set by real-time acquisition of the operation data of the motor equipment of the numerical control machine tool under various working conditions, and provides accurate data support for subsequent analysis and model training. This real-time data acquisition function improves the sensitivity of the system to different operating states, enables the motor equipment to quickly adapt to various complex working conditions, thereby improving the flexibility and intelligence level of the overall system. The neural network model is trained using the collected initial operation data to generate a harmonic spectrum recognition model, so that the system can accurately identify and analyze the harmonic characteristics under different working conditions. This refined harmonic modeling improves the monitoring and diagnostic capabilities of the system, effectively suppresses the impact of harmonics on the equipment, reduces the power consumption and failure probability of the motor equipment, and improves the operating stability of the equipment. By real-time monitoring of the current and voltage signals of the motor equipment, and identifying and optimizing the harmonic characteristics, the module can generate dynamic harmonic characteristic monitoring data, and generate isolation instructions through comparative analysis to dynamically adjust the frequency response range of the motor. This function enables the motor equipment to maintain stable response performance under different harmonic interferences, optimizes the accuracy of signal response, effectively improves the anti-interference ability of the equipment, and ensures efficient operation. By monitoring the temperature of the motor driver and the cooling system in real time and generating thermal status monitoring data, the temperature safety of the equipment under high load or high-speed operation is guaranteed. The module can prevent the loss and failure of the equipment caused by overheating, extend the service life of the equipment through precise temperature control, and ensure the stability and safety of the motor equipment during long-term operation. Based on the comprehensive thermal status monitoring data, the module dynamically adjusts the current input parameters of the motor driver and optimizes the cooling system status to generate hardware adaptive control parameters. This adaptive control method enhances the stability of the equipment under different environments and loads, reduces the efficiency reduction caused by temperature rise, reduces the frequency of manual debugging, and further improves the reliability and maintenance efficiency of the equipment. The module uses hardware adaptive control parameters and dynamic harmonic characteristic monitoring data to dynamically optimize the load to generate load adaptive optimization parameters, so that the motor equipment can run more smoothly under different load conditions. This module effectively enhances the operating adaptability of the equipment under high load, reduces the stress impact of the load on the equipment, and improves the safety and operating efficiency of the overall system.

[0174] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is not limited by the above description, so it is intended to include all changes within the meaning and scope of the equivalent elements of the application documents in the present invention.

[0175] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for controlling the operation of a motor device, characterized in that: The following steps are involved: Step S1: collecting the operating data of the motor equipment in the CNC machine tool under various working conditions in real time to obtain an initial operating data set; Step S2: using the initial operation data set to train the neural network model to identify the harmonic characteristics under various working conditions and generate a harmonic spectrum recognition model; Step S3: real-time acquisition of current and voltage signals of the motor equipment, and inputting them into the harmonic spectrum recognition model for recognition, generating dynamic harmonic characteristic monitoring data; comparing the dynamic harmonic characteristic monitoring data with a preset threshold, generating an isolation instruction, and dynamically adjusting the frequency response range of the motor equipment to obtain optimized signal response data; Step S4: monitoring the temperature of the motor driver and the heat dissipation system in the motor device in real time according to the optimized signal response data to generate comprehensive thermal state monitoring data; Step S5: adjusting the current input parameters of the motor device driver based on the comprehensive thermal state monitoring data, optimizing the operating state of the heat dissipation system, and generating hardware adaptive control parameters; Step S6: Optimize the load dynamic adjustment module of the motor equipment based on the hardware adaptive control parameters and the dynamic harmonic characteristic monitoring data, and generate load adaptive optimization parameters to improve the operation stability of the motor equipment.

2. The operation control method of the motor equipment according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: monitoring the operating parameters of the motor in real time under various working conditions of the motor equipment of the CNC machine tool to obtain real-time operating data of the motor equipment; Step S12: preprocessing the real-time operation data to obtain cleaned operation data; Step S13: extracting features from the cleaned operating data to identify key feature parameters under various operating conditions and generate an operating data feature set; Step S14: Classify and label the operating data feature set according to various operating conditions to generate an initial operating data set.

3. The operation control method of the motor equipment according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: grouping, sorting and unifying the initial running data set to obtain standardized training data; Step S22: performing feature decomposition on the normalized training data, extracting key feature parameters, and generating a feature data set; Step S23: Divide the feature data set into a training set and a validation set to construct input data for the neural network model, thereby obtaining a model training data set and a model validation data set; Step S24: training the neural network model using the model training data set to identify and classify the harmonic features under various working conditions to obtain a preliminary harmonic feature model; Step S25: using the model verification data set to perform real-time verification on the preliminary harmonic characteristic model to obtain a verification set test result; Step S26: Optimize the preliminary harmonic feature model based on the validation set test results, adjust the network layer structure, learning rate and weight, and obtain a harmonic spectrum recognition model.

4. The operation control method of the motor equipment according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: real-time monitoring of the current and voltage signals of the motor equipment during operation, and preprocessing of the data to extract characteristic parameters of the current and voltage signals and generate real-time signal characteristic data; Step S32: inputting the real-time signal characteristic data into the harmonic spectrum recognition model to identify the harmonic characteristics of the current signal and obtain dynamic harmonic characteristic monitoring data; Step S33: extracting key harmonic parameters from the dynamic harmonic characteristic monitoring data to obtain key parameters of dynamic harmonic characteristics; Step S34: recording the vibration frequency of the motor equipment in real time, and extracting and analyzing key parameters to obtain real-time vibration frequency key parameters; Step S35: Based on the real-time vibration frequency key parameter, the harmonic frequency and harmonic frequency amplitude in the dynamic harmonic characteristic key parameter are compared and analyzed with the preset vibration stability threshold to obtain a stability evaluation report; Step S36: judging whether the harmonics meet the isolation condition according to the stability evaluation report, generating an isolation instruction if the harmonics exceed the vibration frequency threshold, and continuously monitoring the harmonics of the motor equipment if the harmonics do not exceed the vibration frequency threshold; Step S37: confirming the harmonic frequency range and amplitude requirements currently required to be isolated according to the isolation instruction, and generating frequency response range adjustment parameters; Step S38: dynamically configuring the frequency response module of the motor device according to the frequency response range adjustment parameter to obtain optimized frequency response configuration data; Step S39: performing an isolation operation according to the optimized frequency response configuration data, suppressing harmonic signal interference within a specific frequency range, and generating optimized signal response data.

5. The operation control method of the motor equipment according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: collecting and recording the real-time temperature data of the motor driver in the CNC machine tool motor device according to the optimized signal response data, and generating the driver thermal state monitoring data; Step S42: Compare the driver thermal state monitoring data with a preset safety temperature threshold to generate a thermal state threshold comparison result; Step S43: Based on the comparison result of the thermal state threshold, determine whether it is necessary to start the cooling system of the motor device. If the temperature exceeds the threshold, adjust the fan speed of the cooling system to generate the motor device cooling control parameter; if the temperature does not exceed the threshold, continue to monitor the motor device state; Step S44: Comprehensively analyze the heat dissipation control parameters of the motor equipment and the optimized signal response data to generate comprehensive thermal state monitoring data.

6. The operation control method of the motor equipment according to claim 5, characterized in that: Step S44 includes the following steps: Step S441: collecting the temperature of the motor driver in real time through the temperature sensor, establishing a temperature data curve, and analyzing the temperature change trend by optimizing the signal response data to obtain abnormal thermal state information data; Step S442: Compare the heat dissipation control parameters of the motor equipment with the real-time temperature, and evaluate the control effect of the current heat dissipation system using the relationship between the fan speed and the temperature change rate to obtain heat dissipation control effect data; Step S443: performing cluster analysis on the abnormal temperature according to the abnormal thermal state information data to identify the root cause of overheating of the motor equipment and obtain a driver abnormal state report; Step S444: Comprehensively analyze the heat dissipation control effect data and the driver abnormal status report to generate comprehensive thermal status monitoring data.

7. The operation control method of the motor equipment according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: performing real-time analysis on the current input parameters of the motor device driver according to the comprehensive thermal state monitoring data to identify the current demand of the driver under various temperature conditions and generate the current input parameters; Step S52: optimizing and adjusting the current input parameters of the motor device driver to identify the optimal operating temperature range of the motor device driver and obtain the current optimized input adjustment parameters; Step S53: Based on the current optimization input adjustment parameter, the operation state of the cooling system is monitored in real time, and the fan speed and coolant flow of the cooling system are adjusted in real time to generate the cooling system control parameter; Step S54: integrating the current optimization input adjustment parameters and the heat dissipation system control parameters to generate hardware adaptive control parameters.

8. The operation control method of the motor equipment according to claim 7, characterized in that: Step S53 includes the following steps: Step S531: collecting the parameters of the heat dissipation system in real time through sensors, and monitoring the temperature change in real time to obtain the real-time monitoring parameters of the heat dissipation system; Step S532: Compare and analyze the real-time monitoring parameters of the heat dissipation system with the current optimization input adjustment parameters, evaluate the heat dissipation effect of the fan speed and the coolant flow rate, and obtain heat dissipation demand comparison result data; Step S533: dynamically adjusting the fan speed of the cooling system based on the cooling demand comparison result data to obtain fan speed optimization data; Step S534: Adapt and adjust the coolant flow rate according to the fan speed optimization data to obtain the coolant flow optimization data; Step S535: Integrate the fan speed optimization data and the coolant flow optimization data to generate cooling system control parameters.

9. The operation control method of the motor equipment according to claim 1, characterized in that: Step S6 includes the following steps: Step S61: performing real-time analysis on the load dynamic adjustment module of the motor device according to the hardware adaptive control parameters to identify the performance requirements of the motor device under various load conditions and generate load performance requirement analysis data; Step S62: Optimizing the configuration of the load dynamic adjustment module based on the load performance demand analysis data and the dynamic harmonic characteristic monitoring data to generate a load optimization strategy; Step S63: applying the load optimization strategy to the control module of the motor device, and adjusting the torque and speed of the motor device in real time to generate load adaptive optimization parameters to improve the operation stability of the motor device.

10. A motor device, characterized in that: The invention comprises a housing, an armature, a drive circuit and a control system, wherein the armature is disposed in the housing, the drive circuit is electrically connected to the armature, the control system is installed in the drive circuit, and the control system is used to execute the operation control method of the motor device according to claim 1, and the control system comprises: The operation data acquisition module is used to collect the operation data of the motor equipment in the CNC machine tool under various working conditions in real time to obtain the initial operation data set; The harmonic spectrum modeling module is used to train the neural network model using the initial operation data set to identify the harmonic characteristics under various working conditions and generate a harmonic spectrum recognition model; The dynamic harmonic monitoring and optimization module is used to collect the current and voltage signals of the motor equipment in real time, input them into the harmonic spectrum recognition model for identification, and generate dynamic harmonic characteristic monitoring data; compare the dynamic harmonic characteristic monitoring data with the preset threshold, generate isolation instructions, and dynamically adjust the frequency response range of the motor equipment to obtain optimized signal response data; Thermal status monitoring and management module, used to monitor the temperature of the motor driver and cooling system in the motor equipment in real time according to the optimized signal response data, and generate comprehensive thermal status monitoring data; Adaptive current and heat dissipation control module, used to adjust the current input parameters of the motor device driver based on the comprehensive thermal status monitoring data, optimize the operating status of the heat dissipation system, and generate hardware adaptive control parameters; The load adaptability optimization module is used to optimize the load dynamic adjustment module of the motor equipment based on the hardware adaptive control parameters and dynamic harmonic characteristic monitoring data, and generate load adaptability optimization parameters to improve the operation stability of the motor equipment.

Images