Intelligent frequency converter of mechanical equipment driving system based on vector model identification

Abstract

The invention relates to the technical field of intelligent frequency converters, in particular to a mechanical equipment driving system intelligent frequency converter based on vector model recognition, which comprises an abrasion state monitoring module, a vector model recognition module, an intelligent frequency conversion control module and a self-adaptive learning module, the vector model identification module establishes a vector model of the motor according to the collected data, and analyzes the real-time operation state of the motor, including the abrasion state. The intelligent frequency conversion control module receives the analysis result of the vector model identification module and the real-time data of the abrasion state monitoring module, and intelligently adjusts the output frequency and voltage of the frequency converter. The adaptive learning module continuously optimizes a vector model and a frequency conversion control strategy by using a machine learning algorithm in combination with historical data and real-time feedback. Through combination of the vector model and the adaptive learning module, faults caused by inaccurate abrasion parameter identification are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent frequency converters, and in particular to an intelligent frequency converter for a mechanical equipment drive system based on vector model recognition. Background Art

[0002] In the field of industrial control, the intelligent inverter of the mechanical equipment drive system is a key power electronic device. Its core function is to achieve accurate and continuous adjustment of the speed of the AC motor by changing the frequency and voltage of the power supply. This technology plays a vital role in improving energy efficiency, optimizing process flow and enhancing production efficiency. However, after setting the rated frequency conversion range, the intelligent inverter in the existing technology is often unable to intelligently adjust its rated frequency conversion range according to wear factors such as the inverter's usage time and number of operations. This limitation causes the intelligent inverter to fail to meet the operating requirements when running for a long time, especially in the high-frequency state, due to failure to adapt to wear changes in time, thereby increasing safety risks.

[0003] In response to this challenge, publication number CN115425907A discloses an innovative intelligent inverter solution. The solution includes four main modules: the acquisition module is used to capture the initial frequency conversion demand; the self-judgment module evaluates the feasibility of the initial frequency conversion demand based on the actual wear parameters of the inverter, and determines the target frequency conversion demand accordingly; the processing module is responsible for setting the output frequency and voltage of the inverter according to the target frequency conversion demand; finally, the intelligent frequency conversion module performs intelligent frequency conversion operations according to the set frequency and voltage. This system aims to solve the problem that traditional intelligent inverters cannot intelligently adjust the rated frequency conversion range when facing changes in wear parameters, thereby reducing safety hazards under high-frequency operation.

[0004] Nevertheless, the effectiveness of this patented technology depends largely on the accurate identification and analysis of wear parameters. If the identification of actual wear parameters is deviated, the prediction of the inverter's current frequency conversion capability will also be affected, which may cause the inverter to fail to achieve the expected performance and safety standards in actual applications. Therefore, the development of more accurate and reliable wear parameter identification technology is crucial to improving the prediction accuracy and system reliability of intelligent inverters. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent frequency converter for a mechanical equipment drive system based on vector model recognition, which solves the problem that the effectiveness of the prior art depends largely on the accurate recognition and analysis of wear parameters.

[0006] To achieve the above-mentioned object, the present invention provides an intelligent frequency converter for a mechanical equipment drive system based on vector model recognition, comprising a wear state monitoring module, a vector model recognition module, an intelligent frequency conversion control module and an adaptive learning module, wherein the vector model recognition module is connected to the wear state monitoring module, the intelligent frequency conversion control module is respectively connected to the vector model recognition module and the wear state monitoring module, and the adaptive learning module is respectively connected to the wear state monitoring module, the vector model recognition module and the intelligent frequency conversion control module;

[0007] The wear state monitoring module is used to collect the operating parameters of the motor and the inverter, including current, voltage, temperature and vibration;

[0008] The vector model recognition module is used to establish a vector model of the motor and analyze the running state of the motor, including the wear state, through the data collected in real time;

[0009] The intelligent frequency conversion control module is used to intelligently adjust the output frequency and voltage of the inverter according to the output of the vector model recognition module and the data of the wear state monitoring module;

[0010] The adaptive learning module is used to continuously optimize the vector model and the variable frequency control strategy based on historical data and real-time feedback using a machine learning algorithm.

[0011] Wherein, the intelligent frequency converter of the mechanical equipment drive system based on vector model recognition further includes a safety protection module, and the safety protection module is connected to the intelligent frequency conversion control module;

[0012] The safety protection module is used to monitor the output of the intelligent frequency conversion control module to ensure operation within a safe range, and to cut off power supply or sound an alarm when an abnormality is detected.

[0013] Wherein, the intelligent frequency converter of the mechanical equipment drive system based on vector model recognition further includes a user interface, and the user interface is respectively connected to the vector model recognition module, the wear state monitoring module and the intelligent frequency conversion control module;

[0014] The user interface is used to display status information of the vector model identification module, the wear status monitoring module and the intelligent frequency conversion control module, and allows the user to input instructions to adjust parameters of the vector model identification module and the intelligent frequency conversion control module.

[0015] Wherein, the vector model identification module includes a vector control algorithm unit and a model building unit, the vector control algorithm unit is connected to the wear state monitoring module, and the model building unit is connected to the vector control algorithm unit;

[0016] The vector control algorithm unit is used to receive the operating parameter data of the motor and the inverter from the wear state monitoring module, and use the received data to decompose the three-phase current of the motor into two components related to torque and magnetic flux according to vector control theory, and control them;

[0017] The model building unit is used to build a mathematical model of the motor based on the physical parameters and operation data of the motor, including static and dynamic characteristics.

[0018] Wherein, the vector model recognition module further comprises a real-time analysis unit and a state evaluation unit, the real-time analysis unit is connected to the vector control algorithm unit, and the state evaluation unit is connected to the real-time analysis unit;

[0019] The real-time analysis unit is used to process and analyze the real-time data to monitor the running state and wear state of the motor;

[0020] The state evaluation unit is used to evaluate the current state and wear degree of the motor according to the results of the vector control algorithm unit and the real-time analysis unit, and output the analysis results and evaluation state to the intelligent variable frequency control module and the adaptive learning module.

[0021] Wherein, the intelligent variable frequency control module includes a control strategy generation unit and an output calculation unit, the control strategy generation unit is respectively connected to the wear state monitoring module, the state evaluation unit and the adaptive learning module, and the output calculation unit is connected to the control strategy generation unit;

[0022] The control strategy generating unit is used to generate a control strategy adapted to the current motor operation state according to the output of the state evaluation unit and the data of the wear state monitoring module;

[0023] The output calculation unit is used to calculate the frequency and voltage values ​​that the inverter needs to output according to the instructions of the control strategy generation unit.

[0024] Wherein, the intelligent frequency conversion control module further includes a feedback monitoring unit, and the feedback monitoring unit is connected to the control strategy generation unit;

[0025] The feedback monitoring unit is used to monitor the output state of the frequency converter in real time, including the actual output frequency and voltage, and feed back the monitoring data to the control strategy generation unit.

[0026] The invention discloses an intelligent frequency converter for a mechanical equipment drive system based on vector model recognition. First, the wear state monitoring module collects the operating parameters of the motor and the frequency converter, such as current, voltage, temperature and vibration, to provide raw data for subsequent analysis. Then, the vector model recognition module establishes a vector model of the motor according to the collected data, and analyzes the real-time operating state of the motor, including the wear state. The intelligent frequency conversion control module receives the analysis results of the vector model recognition module and the real-time data of the wear state monitoring module, and intelligently adjusts the output frequency and voltage of the frequency converter to meet the actual operating requirements of the motor. The adaptive learning module uses a machine learning algorithm, combines historical data and real-time feedback, and continuously optimizes the vector model and frequency conversion control strategy to improve the adaptability and prediction accuracy of the system. Through vector model recognition and real-time data analysis, accurate control of the motor speed and torque is achieved. The adaptive learning module enables the system to continuously optimize the control strategy according to historical and real-time data, and improves the adaptability and flexibility of the system. The intelligent frequency conversion control module can adjust the frequency conversion range according to the actual wear state of the motor to reduce the safety hazards caused by overclocking. By accurately controlling and optimizing the frequency conversion strategy, the wear of the motor is reduced and the service life of the equipment is extended. Intelligently adjust the inverter output so that the motor can run efficiently under different loads and reduce energy consumption. The vector model recognition module and the adaptive learning module are used for fault prediction and diagnosis, to detect potential problems in advance and reduce unexpected downtime. Through the combination of the vector model and the adaptive learning module, the wear state of the motor can be predicted, maintenance can be carried out in advance, and faults caused by inaccurate identification of wear parameters can be avoided. The accuracy of identification and analysis of the motor wear state is improved, thereby solving the limitations of the existing technology and improving the overall performance and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0028] Figure 1 It is a principle block diagram of an intelligent frequency converter for a mechanical equipment drive system based on vector model recognition according to a first embodiment of the present invention.

[0029] Figure 2 It is a principle block diagram of a vector model recognition module according to the first embodiment of the present invention.

[0030] Figure 3 It is a principle block diagram of the intelligent frequency conversion control module of the first embodiment of the present invention.

[0031] Figure 4 It is a principle block diagram of an intelligent frequency converter for a mechanical equipment drive system based on vector model recognition according to a second embodiment of the present invention.

[0032] In the figure: 101-wear state monitoring module, 102-vector model identification module, 103-intelligent frequency conversion control module, 104-adaptive learning module, 105-vector control algorithm unit, 106-model building unit, 107-real-time analysis unit, 108-state evaluation unit, 109-control strategy generation unit, 110-output calculation unit, 111-feedback monitoring unit, 201-safety protection module, 202-user interface. DETAILED DESCRIPTION

[0033] Embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0034] The first embodiment of the present application is:

[0035] See also Figures 1 to 3 ,in, Figure 1 It is a principle block diagram of an intelligent frequency converter for a mechanical equipment drive system based on vector model recognition according to a first embodiment of the present invention. Figure 2 It is a principle block diagram of the vector model recognition module 102 according to the first embodiment of the present invention. Figure 3 It is a principle block diagram of the intelligent frequency conversion control module 103 according to the first embodiment of the present invention.

[0036] The present invention provides an intelligent frequency converter for a mechanical equipment drive system based on vector model recognition, comprising a wear state monitoring module 101, a vector model recognition module 102, an intelligent frequency conversion control module 103 and an adaptive learning module 104, wherein the vector model recognition module 102 comprises a vector control algorithm unit 105, a model building unit 106, a real-time analysis unit 107 and a state evaluation unit 108, and the intelligent frequency conversion control module 103 comprises a control strategy generation unit 109, an output calculation unit 110 and a feedback monitoring unit 111. The above-mentioned solution solves the problem that the effectiveness of the prior art depends largely on the accurate recognition and analysis of wear parameters.

[0037] According to this specific implementation, the vector model recognition module 102 is connected to the wear state monitoring module 101, the intelligent variable frequency control module 103 is respectively connected to the vector model recognition module 102 and the wear state monitoring module 101, and the adaptive learning module 104 is respectively connected to the wear state monitoring module 101, the vector model recognition module 102 and the intelligent variable frequency control module 103;

[0038] The wear state monitoring module 101 is used to collect the operating parameters of the motor and the inverter, including current, voltage, temperature and vibration;

[0039] The vector model recognition module 102 is used to establish a vector model of the motor and analyze the running state of the motor, including the wear state, through the data collected in real time;

[0040] The intelligent frequency conversion control module 103 is used to intelligently adjust the output frequency and voltage of the inverter according to the output of the vector model recognition module 102 and the data of the wear state monitoring module 101;

[0041] The adaptive learning module 104 is used to continuously optimize the vector model and the variable frequency control strategy based on historical data and real-time feedback using a machine learning algorithm.

[0042] The wear state monitoring module 101 first starts all relevant sensors, including current sensors, voltage sensors, temperature sensors and vibration sensors. The sensors start to monitor the key operating parameters of the motor and the inverter in real time. The current sensor measures the three-phase current of the motor, the voltage sensor measures the supply voltage, the temperature sensor monitors the temperature of the motor and the inverter, and the vibration sensor records the vibration data of the motor when it is running. The collected data analog signal is amplified, filtered and isolated to improve the signal quality and protect the subsequent equipment. Then, the analog signal is converted into a digital signal through an analog-to-digital converter (ADC) for subsequent processing. The converted digital signal is further preprocessed, including denoising, feature extraction and data formatting, for subsequent analysis and processing. The preprocessed data is stored in a cache or a non-volatile storage unit, and can be sent to the vector model identification module 102 and the intelligent frequency conversion control module 103 through a communication interface according to a set data transmission protocol. The adaptive learning module 104 collects real-time operating data of the motor and the inverter from the wear state monitoring module 101 and the vector model identification module 102, including parameters such as current, voltage, temperature, and vibration. Past operating data and system responses are also extracted from the historical database for model training and comparative analysis. The collected data is preprocessed, including data cleaning: removing outliers and noise to ensure data quality. Feature extraction: extracting key features that affect motor performance and wear status from the raw data. Data annotation: For supervised learning, data annotation is required to facilitate training of classification or regression models. Model training is then performed, and appropriate machine learning algorithms such as neural networks, support vector machines, random forests, etc. are selected according to the nature of the problem. The model is trained using the preprocessed data and the model parameters are adjusted to achieve optimal performance. The accuracy and generalization ability of the model are evaluated through the validation set to ensure the effectiveness of the model. Cross-validation and other techniques are used to test the performance of the model on different data sets to ensure the robustness of the model. The prediction effect of the model is tested in actual operation and compared with the actual system response. The trained model is deployed to the intelligent frequency conversion control module 103 for real-time data analysis and control decision-making. The frequency conversion control strategy is adjusted according to the output of the model, such as adjusting the PID controller parameters, to improve system performance. The actual operation effect of the intelligent inverter is monitored and feedback data is collected. The model is continuously iterated and optimized based on feedback data and new operating data to adapt to system changes and improve prediction accuracy. Model parameters and control strategies are automatically adjusted to adapt to changes in the motor's operating state. Predictive maintenance is performed based on the results of model prediction to reduce unexpected downtime and extend equipment life. The adaptive learning module 104 can improve the performance of the intelligent inverter, reduce energy consumption, and improve the reliability and life of the system. This data-driven approach enables the intelligent inverter to adapt to complex industrial environments and achieve more intelligent and automated control.

[0043] The vector control algorithm unit 105 is connected to the wear state monitoring module 101, and the model building unit 106 is connected to the vector control algorithm unit 105;

[0044] The vector control algorithm unit 105 is used to receive the operating parameter data of the motor and the inverter from the wear state monitoring module 101, and use the received data to decompose the three-phase current of the motor into two components related to torque and flux according to vector control theory, and control them;

[0045] The model building unit 106 is used to build a mathematical model of the motor based on the physical parameters and operation data of the motor, including static and dynamic characteristics.

[0046] The real-time analysis unit 107 is connected to the vector control algorithm unit 105, and the state evaluation unit 108 is connected to the real-time analysis unit 107;

[0047] The real-time analysis unit 107 is used to process and analyze the real-time data to monitor the running state and wear state of the motor;

[0048] The state evaluation unit 108 is used to evaluate the current state and wear degree of the motor according to the results of the vector control algorithm unit 105 and the real-time analysis unit 107 , and output the analysis result and evaluation state to the intelligent variable frequency control module 103 and the adaptive learning module 104 .

[0049] The vector control algorithm unit 105 receives real-time operating parameter data of the motor and the inverter from the wear state monitoring module 101, including three-phase current, voltage, temperature and vibration. Using vector control theory, the three-phase current of the motor is decomposed into two components related to torque (Id) and flux (Iq). This step usually involves Clarke transformation and Park transformation to convert the three-phase current into two-phase orthogonal current. Using Clarke transformation: V abc =T c V xyz , using Park transform: V dq =T p V xyz , where V abc : Three-phase voltage vector. T c : Clarke transformation matrix. V xyz : Two-phase orthogonal voltage vector. V dq : Direct-axis and quadrature-axis voltage vectors. T p: Park transformation matrix. According to the decomposed current components, the vector control algorithm unit 105 calculates the voltage vector to be applied to the motor to control the torque and speed of the motor. This usually involves a PID controller or other advanced control strategies. The model building unit 106 receives the operating data of the motor from the vector control algorithm unit 105, including current, voltage, and speed. Based on the physical parameters of the motor (such as resistance, inductance, moment of inertia, etc.) and the operating data, a mathematical model of the motor is established. This may include a static model (such as a circuit model) and a dynamic model (such as a state space model). By comparing with the real-time data, the accuracy of the model is verified and necessary adjustments are made. The established mathematical model is output to the real-time analysis unit 107 and the state evaluation unit 108 for further analysis and evaluation. The real-time analysis unit 107 receives the processed current and voltage data from the vector control algorithm unit 105. The real-time data is processed and analyzed to monitor the operating state and wear state of the motor. This may include frequency analysis, time domain analysis, etc. The analysis results are output to the state evaluation unit 108 for evaluating the current state and wear degree of the motor. The state evaluation unit 108 integrates the results of the vector control algorithm unit 105 and the real-time analysis unit 107, as well as the mathematical model provided by the model building unit 106. Based on the integrated data and model, the current state and degree of wear of the motor are evaluated. This involves machine learning algorithms to identify wear patterns and predict potential faults. The analysis results and evaluation status are output to the intelligent variable frequency control module 103 and the adaptive learning module 104 for adjusting the control strategy and optimizing the vector model.

[0050] Secondly, the control strategy generation unit 109 is connected to the wear state monitoring module, the state evaluation unit 108 and the adaptive learning module 104 respectively, and the output calculation unit 110 is connected to the control strategy generation unit 109;

[0051] The control strategy generating unit 109 is used to generate a control strategy adapted to the current motor operation state according to the output of the state evaluating unit 108 and the data of the wear state monitoring module 101;

[0052] The output calculation unit 110 is used to calculate the frequency and voltage values ​​that the inverter needs to output according to the instructions of the control strategy generation unit 109.

[0053] The feedback monitoring unit 111 is connected to the control strategy generating unit 109;

[0054] The feedback monitoring unit 111 is used to monitor the output state of the inverter in real time, including the actual output frequency and voltage, and feed back the monitoring data to the control strategy generation unit 109 .

[0055] The control strategy generation unit 109 receives the real-time operating parameters of the motor and the inverter from the wear state monitoring module 101, such as current, voltage, temperature and vibration. At the same time, it receives the evaluation results of the motor state and wear degree from the state evaluation unit 108. According to the received real-time data and state evaluation results, the control strategy generation unit 109 formulates a control strategy adapted to the current motor operation state. Including determining the optimal working point of the motor, adjusting the parameter settings of the inverter, etc. The generated control strategy is converted into a specific instruction, such as the set value of the output frequency and voltage of the inverter, and sent to the output calculation unit 110. The output calculation unit 110 receives the instruction from the control strategy generation unit 109. According to the instruction of the control strategy generation unit 109, the specific frequency and voltage value that the inverter needs to output is calculated, using the PID control algorithm or other advanced control algorithms. The calculated frequency and voltage values ​​are sent to the actuator of the inverter as control instructions to adjust the output of the inverter. The feedback monitoring unit 111 monitors the actual output state of the inverter in real time, including the actual output frequency and voltage. The actual frequency and voltage data of the inverter output are collected and used for closed-loop control and system performance evaluation. The actual output data monitored is fed back to the control strategy generation unit 109 to adjust and optimize the control strategy. If the actual output monitored deviates significantly from the expected output, the feedback monitoring unit 111 will trigger the abnormality handling process, including alarm, emergency shutdown or automatic adjustment of the control strategy.

[0056] Using an intelligent frequency converter for a mechanical equipment drive system based on vector model recognition of this embodiment, the wear state monitoring module 101 starts current, voltage, temperature and vibration sensors to monitor the operating parameters of the motor and the frequency converter in real time. The sensor data is amplified, filtered, isolated, and converted into digital signals through ADC, and then pre-processed such as denoising and feature extraction. The vector control algorithm unit 105 receives the processed data, decomposes the three-phase current into torque and flux components according to the vector control theory, and controls the motor. The model building unit 106 builds a mathematical model of the motor based on the physical parameters and operating data of the motor. The real-time analysis unit 107 further analyzes the data to monitor the operation and wear state of the motor. The state evaluation unit 108 evaluates the current state and wear degree of the motor, and outputs the results to the intelligent frequency conversion control module 103 and the adaptive learning module 104. The control strategy generation unit 109 generates a control strategy adapted to the current motor operating state based on the output of the state evaluation unit 108 and the data of the wear state monitoring module 101. The output calculation unit 110 calculates the frequency and voltage values ​​that the inverter needs to output according to the instructions of the control strategy generation unit 109, and sends these values ​​to the inverter for execution. The feedback monitoring unit 111 monitors the output state of the inverter in real time, and feeds back the data to the control strategy generation unit 109 so as to adjust and optimize the control strategy. The adaptive learning module 104 uses machine learning algorithms to continuously optimize the vector model and frequency conversion control strategy according to historical data and real-time feedback. Through vector control and accurate mathematical models, accurate control of motor speed and torque is achieved. The adaptive learning module 104 enables the system to continuously optimize the control strategy according to real-time data and historical data, and improve the adaptability and flexibility of the system. The intelligent frequency conversion control module 103 can adjust the frequency conversion range according to the actual wear state of the motor to reduce the safety hazards caused by overclocking. By accurately controlling and optimizing the frequency conversion strategy, the wear of the motor is reduced and the service life of the equipment is extended. Intelligently adjust the inverter output so that the motor can operate efficiently under different loads and reduce energy consumption. The vector model recognition module 102 and the adaptive learning module 104 are used for fault prediction and diagnosis, to detect potential problems in advance and reduce unexpected downtime. Based on the results of model prediction, predictive maintenance is performed to reduce unexpected downtime and extend the life of the equipment. The accuracy of the identification and analysis of the motor wear state is improved, thereby solving the limitations of the existing technology and improving the overall performance and reliability of the system.

[0057] The second embodiment of the present application is:

[0058] Based on the first embodiment, please refer to Figure 4 ,in, Figure 4The schematic diagram of the intelligent frequency converter for mechanical equipment drive system based on vector model recognition according to the second embodiment of the present invention is shown in FIG. The intelligent frequency converter for mechanical equipment drive system based on vector model recognition according to the present embodiment further includes a safety protection module 201 and a user interface 202 .

[0059] According to this specific implementation, the safety protection module 201 is connected to the intelligent frequency conversion control module 103;

[0060] The safety protection module 201 is used to monitor the output of the intelligent frequency conversion control module 103 to ensure that the operation is within a safe range, and to cut off the power supply or sound an alarm when an abnormality is detected.

[0061] The safety protection module 201 first sets monitoring parameters, including safety thresholds of voltage, current, temperature, frequency, etc. Real-time inverter output data, including actual output frequency, voltage, current, etc., are received from the intelligent frequency conversion control module 103. The received data is analyzed in real time and compared with the preset safety threshold to detect whether there is an abnormality. If the monitored data exceeds the safety threshold or other abnormal signals appear, the safety protection module 201 will automatically trigger the protection mechanism. Depending on the type and severity of the abnormality, the safety protection module 201 will perform one of the following operations: Cut off the power supply: immediately stop the output of the inverter to prevent equipment damage or accidents. Issue an alarm: notify the operator through sound and light signals so that further manual intervention can be taken. The safety protection module 201 records the detailed information of the abnormal event, including time, parameter value and measures taken, for subsequent analysis and reporting. After the safety conditions are restored, the safety protection module 201 controls the inverter to gradually resume work, or wait for manual reset by the operator.

[0062] The user interface 202 is respectively connected to the vector model recognition module 102, the wear state monitoring module 101 and the intelligent frequency conversion control module 103;

[0063] The user interface 202 is used to display status information of the vector model identification module 102 , the wear status monitoring module 101 and the intelligent variable frequency control module 103 , and allows the user to input instructions to adjust parameters of the vector model identification module 102 and the intelligent variable frequency control module 103 .

[0064] The user interface 202 displays real-time data collected by the wear state monitoring module 101, such as parameters such as current, voltage, temperature and vibration. Displays the analysis results of the vector model identification module 102, including the torque and flux components, operating status and wear status of the motor. Displays the control strategy and output of the intelligent frequency conversion control module 103, such as the output frequency and voltage value of the inverter. Provides system status indication, such as the operating mode of the motor (such as start, stop, fault, etc.). Displays the status of the safety protection module 201, including any abnormal alarms and protection actions. Displays historical operating data and trend charts to help users analyze changes in the performance and wear state of the motor. Displays fault diagnosis information, including fault type, time and possible causes. Allows the user to enter instructions to adjust the control parameters of the intelligent frequency conversion control module 103, such as the gain value of the PID controller. The user can adjust the set values ​​of the output frequency and voltage of the inverter as needed. Allows the user to adjust the parameters of the vector model identification module 102, such as the parameters in the vector control algorithm. The user can modify the mathematical model parameters of the motor according to actual conditions to adapt to different operating conditions. Provide a system configuration interface to allow users to set the threshold and response strategy of the security protection module 201. Users can configure communication parameters such as baud rate and protocol to adapt to different communication needs. Provide a manual control function to allow users to directly control the output of the inverter when necessary. Provide debugging tools to help users diagnose and solve system problems. Receive instructions entered by the user through the interface and send them to the corresponding module for execution. After confirming the execution of the instruction, update the status information displayed on the interface.

[0065] Using an intelligent frequency converter for a mechanical equipment drive system based on vector model recognition of this embodiment, the safety protection module 201 monitors the frequency converter output in real time to ensure that the operation is within a safe range, responds to abnormal situations in a timely manner, and reduces equipment damage and accident risks. The system can analyze the frequency converter output data in real time, quickly detect abnormalities, and provide immediate protection measures, such as cutting off power or sounding an alarm. The user interface 202 provides an intuitive operating platform that allows users to easily monitor the system status and adjust and control parameters. Users can dynamically adjust the parameters of the frequency converter and vector model recognition module 102 according to real-time data and system status to adapt to different operating conditions. In addition to automatic control, the user interface 202 also provides manual control functions and debugging tools, which enhances the flexibility and problem-solving capabilities of the system.

[0066] What is disclosed above is only one or more preferred embodiments of the present application, and cannot be used to limit the scope of rights of the present application. Ordinary technicians in this field can understand that all or part of the processes of implementing the above embodiments and equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. Intelligent inverter for mechanical equipment drive system based on vector model recognition, characterized in that: It includes a wear state monitoring module, a vector model recognition module, an intelligent frequency conversion control module and an adaptive learning module, wherein the vector model recognition module is connected to the wear state monitoring module, the intelligent frequency conversion control module is respectively connected to the vector model recognition module and the wear state monitoring module, and the adaptive learning module is respectively connected to the wear state monitoring module, the vector model recognition module and the intelligent frequency conversion control module; The wear state monitoring module is used to collect the operating parameters of the motor and the inverter, including current, voltage, temperature and vibration; The vector model recognition module is used to establish a vector model of the motor and analyze the running state of the motor, including the wear state, through the data collected in real time; The intelligent frequency conversion control module is used to intelligently adjust the output frequency and voltage of the inverter according to the output of the vector model recognition module and the data of the wear state monitoring module; The adaptive learning module is used to continuously optimize the vector model and the variable frequency control strategy based on historical data and real-time feedback using a machine learning algorithm.

2. The intelligent inverter for mechanical equipment drive system based on vector model recognition according to claim 1, characterized in that: The intelligent frequency converter for the mechanical equipment drive system based on vector model recognition further includes a safety protection module, which is connected to the intelligent frequency conversion control module; The safety protection module is used to monitor the output of the intelligent frequency conversion control module to ensure operation within a safe range, and to cut off power supply or sound an alarm when an abnormality is detected.

3. The intelligent inverter for mechanical equipment drive system based on vector model recognition according to claim 1, characterized in that: The intelligent frequency converter for the mechanical equipment drive system based on vector model recognition further includes a user interface, which is respectively connected to the vector model recognition module, the wear state monitoring module and the intelligent frequency conversion control module; The user interface is used to display status information of the vector model identification module, the wear status monitoring module and the intelligent frequency conversion control module, and allows the user to input instructions to adjust parameters of the vector model identification module and the intelligent frequency conversion control module.

4. The intelligent inverter for mechanical equipment drive system based on vector model recognition according to claim 1, characterized in that: The vector model identification module includes a vector control algorithm unit and a model building unit, the vector control algorithm unit is connected to the wear state monitoring module, and the model building unit is connected to the vector control algorithm unit; The vector control algorithm unit is used to receive the operating parameter data of the motor and the inverter from the wear state monitoring module, and use the received data to decompose the three-phase current of the motor into two components related to torque and magnetic flux according to vector control theory, and control them; The model building unit is used to build a mathematical model of the motor based on the physical parameters and operation data of the motor, including static and dynamic characteristics.

5. The intelligent inverter for mechanical equipment drive system based on vector model recognition as claimed in claim 4, characterized in that: The vector model recognition module further comprises a real-time analysis unit and a state evaluation unit, wherein the real-time analysis unit is connected to the vector control algorithm unit, and the state evaluation unit is connected to the real-time analysis unit; The real-time analysis unit is used to process and analyze the real-time data to monitor the running state and wear state of the motor; The state evaluation unit is used to evaluate the current state and wear degree of the motor according to the results of the vector control algorithm unit and the real-time analysis unit, and output the analysis results and evaluation state to the intelligent variable frequency control module and the adaptive learning module.

6. The intelligent inverter for mechanical equipment drive system based on vector model recognition as claimed in claim 5, characterized in that: The intelligent variable frequency control module includes a control strategy generation unit and an output calculation unit, the control strategy generation unit is respectively connected to the wear state monitoring module, the state evaluation unit and the adaptive learning module, and the output calculation unit is connected to the control strategy generation unit; The control strategy generating unit is used to generate a control strategy adapted to the current motor operation state according to the output of the state evaluation unit and the data of the wear state monitoring module; The output calculation unit is used to calculate the frequency and voltage values ​​that the inverter needs to output according to the instructions of the control strategy generation unit.

7. The intelligent inverter for mechanical equipment drive system based on vector model recognition as claimed in claim 6, characterized in that: The intelligent frequency conversion control module further includes a feedback monitoring unit, which is connected to the control strategy generation unit; The feedback monitoring unit is used to monitor the output state of the frequency converter in real time, including the actual output frequency and voltage, and feed back the monitoring data to the control strategy generation unit.

Images