Permanent magnet synchronous motor control system and control method for electrically-driven hydraulic source

Abstract

The invention relates to the technical field of motor control, and discloses a permanent magnet synchronous motor control system and method for an electric drive hydraulic source, and the system comprises a data collection module which is used for collecting the state parameters of the electric drive hydraulic source and the operation data of a permanent magnet synchronous motor in real time through multiple sensors; the sensor redundancy and fault-tolerant module is used for performing parallel sampling through hardware dual-redundancy configuration and dual sensors; the self-adaptive fuzzy logic control module is used for dynamically adjusting a rotating speed instruction and a torque instruction of the permanent magnet synchronous motor based on the collected state parameters; a data driving optimization module; and a digital twinning prediction maintenance module. A self-adaptive fuzzy logic control module is used for dynamically generating a motor rotating speed and torque instruction based on parameters such as real-time pressure, flow deviation and change rate, a fuzzy logic algorithm is used for processing a nonlinear time-varying load and quick response, a self-adaptive fuzzy logic control rule weight and a power conversion circuit parameter are optimized through a reinforcement learning algorithm, and the control precision is improved. And dynamic self-optimization of permanent magnet synchronous motor control is realized.

Description

Technical Field

[0001] This invention relates to the field of motor control technology, specifically to a permanent magnet synchronous motor control system and control method for an electro-hydraulic power source. Background Technology

[0002] Under the trend of intelligent and green development of industrial equipment, electro-hydraulic power source systems are widely used in engineering machinery, aerospace, high-end equipment manufacturing and other fields due to their advantages of combining the high power density of hydraulic transmission with the precise control of motor drive. As the core power component of electro-hydraulic power sources, the control performance of permanent magnet synchronous motors (PMSMs) directly affects the energy efficiency, response speed and stability of the system. In view of the nonlinear load characteristics of hydraulic systems (such as pressure change and flow time variation) and complex working conditions (high temperature, vibration, multivariable coupling), it is necessary to build a control system with dynamic response capability, robustness and reliability. In traditional technology, electro-hydraulic power source control systems mostly rely on proportional integral derivative (PID) controllers, and adjust the PID parameters to adapt to the control requirements under different working conditions.

[0003] However, in current technology, proportional-integral-derivative controllers are slow in dynamic response, consume more energy, and are more sensitive to external disturbances. They perform poorly in high-precision and fast-response applications, leading to reduced reliability. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a permanent magnet synchronous motor control system and method for electro-hydraulic power sources, solving the problems of slow dynamic response, high energy consumption, and sensitivity to external disturbances.

[0005] In a first aspect, the present invention provides a permanent magnet synchronous motor control system for an electro-hydraulic power source, comprising: The data acquisition module is used to collect the status parameters of the electro-hydraulic power source and the operating data of the permanent magnet synchronous motor in real time through multiple sensors; The sensor redundancy and fault tolerance module is used to form a signal channel between the main sensor and the redundant sensor through hardware dual redundancy configuration and parallel sampling of dual sensors; The adaptive fuzzy logic control module dynamically adjusts the speed and torque commands of the permanent magnet synchronous motor based on the collected state parameters. The data-driven optimization module uses reinforcement learning algorithms to optimize the weights of adaptive fuzzy logic control rules and power conversion circuit parameters, minimizing system energy consumption and torque ripple. The digital twin predictive maintenance module constructs a digital twin model of the permanent magnet synchronous motor and the hydraulic power source, and predicts the risk of bearing wear, winding aging and oil contamination failures through real-time data synchronization.

[0006] Preferably, the operating data in the data acquisition module includes the pressure, flow rate, temperature, and oil viscosity of the electric hydraulic power source, as well as the three-phase current, speed, and load torque of the motor.

[0007] Preferably, the sensor redundancy and fault tolerance module includes a data redundancy verification unit and a dynamic threshold adaptive unit; The data redundancy verification unit is used to collect operating data using dual sensors and monitor signal consistency through difference comparison and trend consistency analysis between the two sensors. The dynamic threshold adaptive unit is used to dynamically adjust the verification threshold based on historical operating data statistics and real-time operating data. When an anomaly of a single sensor is detected, it automatically switches to the redundant sensor signal. After the main sensor signal returns to normal, it automatically switches back to the main channel after passing the consistency verification for 5 cycles.

[0008] Preferably, the adaptive fuzzy logic control module includes: The input variables are hydraulic source pressure error ΔP, flow error ΔQ, temperature deviation ΔT and their rate of change; The output variables are the d-axis voltage and q-axis voltage of the permanent magnet synchronous motor; The fuzzy rule base dynamically adjusts membership function parameters using an online gradient descent algorithm, with a response time of less than 10ms. Specifically, when ΔP > 5MPa and the rate of change is less than 0, the weight of the q-axis voltage is increased to 0.8. When ΔT>10℃, reduce the d-axis current limit by 20%.

[0009] Preferably, the data-driven optimization module includes a strategy generation unit and a mode switching unit; The strategy generation unit is used to generate optimized operating parameters through reinforcement learning algorithms; The mode switching unit is used to output adaptive fuzzy logic control rules according to real-time load requirements.

[0010] Preferably, the digital twin prediction and maintenance module includes a model building unit, a data mapping unit, and a fault prediction unit; The model building unit is used to construct a virtual model of the electro-hydraulic power source system based on mechanism modeling and parameter identification algorithms, combined with real-time operation data to calibrate model parameters. The data mapping unit is used to establish a mapping relationship between physical sensors and virtual models through the OPC UA (Open Platform UA) protocol; The fault prediction unit is used to output a fault warning signal by comparing the health parameters of the virtual model with those of the LSTM neural network.

[0011] Secondly, the present invention provides a control method for a permanent magnet synchronous motor control system for an electro-hydraulic power source, the method comprising the following steps: S1. The data acquisition module collects hydraulic source status parameters and motor operation data in real time; S2. The collected operating data is verified in real time through the sensor redundancy and fault tolerance module, and redundancy switching is performed when sensor abnormality is detected. S3. Calculate ΔP, ΔQ and the corresponding rate of change based on the collected operating data, and generate motor speed and torque commands through a fuzzy rule base; S4. Combining historical data and real-time load, optimize the control instructions output by the adaptive fuzzy logic control module to generate the final control signal to drive the power conversion circuit. S5. Monitor the operating status through a virtual model, compare the health parameters of the virtual model to predict faults, and output fault warning signals.

[0012] Preferably, step S3 specifically includes the following steps: S301: Collect current workload data and hydraulic source status parameters, including pressure, flow rate, and temperature.

[0013] S302. Construct an AFLC model (Adaptive Fuzzy Logic Control Model) to automatically adjust control rules based on real-time load data and optimize the speed and torque output of the permanent magnet synchronous motor.

[0014] S303. Implement control commands to regulate the permanent magnet synchronous motor according to the output of the AFLC model.

[0015] Preferably, the control command optimization strategy in S4 includes: when the hydraulic system pressure reaches the target value and the flow demand is stable, outputting an idle speed command; when rapid braking of the hydraulic cylinder is detected, outputting a field weakening control command.

[0016] Preferably, the fault prediction process in S5 includes: inputting real-time collected operating data into a machine learning model, comparing the health status parameters of the virtual model to identify early fault characteristics, and outputting diagnostic information including fault type and location.

[0017] This invention provides a control system and method for a permanent magnet synchronous motor oriented towards an electro-hydraulic power source. It offers the following advantages: 1. This invention uses an adaptive fuzzy logic control module to dynamically generate motor speed and torque commands based on parameters such as real-time pressure, flow deviation, and rate of change. It uses fuzzy logic algorithms to handle nonlinear time-varying loads and respond quickly. Furthermore, it optimizes the adaptive fuzzy logic control rule weights and power conversion circuit parameters through reinforcement learning algorithms, thereby achieving dynamic self-optimization of permanent magnet synchronous motor control. 2. This invention utilizes hardware dual redundancy and a dynamic threshold adaptive algorithm, employing parallel sampling and difference comparison of dual sensors, combined with historical data to dynamically adjust the threshold, thereby achieving intelligent switching between the main channel and redundant channels. This avoids misjudgment due to instantaneous interference, solves the problem of single sensors being susceptible to failure or noise interference, ensures continuous and stable control commands, and reduces the risk of unplanned downtime.

[0018] 3. This invention constructs a digital twin model by fusing mechanistic modeling with LSTM neural networks, enabling early warning and precise fault location. It also synchronizes physical system and virtual model data based on the OPC UA protocol, dynamically calibrates key parameters by combining parameter identification, compares health baselines with real-time data, and uses time-series analysis to identify performance degradation characteristics, thereby reducing unplanned downtime and maintenance costs. Attached Figure Description

[0019] Figure 1 This is an architecture diagram of the permanent magnet synchronous motor control system and control method for an electro-hydraulic power source according to the present invention. Figure 2 This is a flowchart of the control method for the permanent magnet synchronous motor control system for an electro-hydraulic power source according to the present invention. Detailed Implementation

[0020] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Please see the appendix Figure 1 This invention provides a permanent magnet synchronous motor control system for an electro-hydraulic power source, comprising: The data acquisition module is used to collect the status parameters of the electro-hydraulic power source and the operating data of the permanent magnet synchronous motor in real time through multiple sensors; The sensor redundancy and fault tolerance module is used to form a signal channel between the main sensor and the redundant sensor through hardware dual redundancy configuration and parallel sampling of dual sensors; The adaptive fuzzy logic control module dynamically adjusts the speed and torque commands of the permanent magnet synchronous motor based on the collected state parameters. The data-driven optimization module uses reinforcement learning algorithms to optimize the weights of adaptive fuzzy logic control rules and power conversion circuit parameters, minimizing system energy consumption and torque ripple. The digital twin predictive maintenance module constructs a digital twin model of the permanent magnet synchronous motor and the hydraulic power source, and predicts the risk of bearing wear, winding aging and oil contamination failures through real-time data synchronization.

[0022] Specifically, the data acquisition module collects the status parameters (such as hydraulic system pressure, flow rate, temperature, motor current, speed, rotor position, etc.) and operating data of the electro-hydraulic source in real time through multiple sensors, providing raw data input for the control system and supporting the operation of modules such as sensor redundancy verification, fuzzy logic control, data-driven optimization and digital twin predictive maintenance. It realizes the real-time acquisition of multi-dimensional data, providing a data foundation for system control, optimization and prediction functions. The sensor redundancy and fault tolerance module forms a signal channel between the main sensor and the redundant sensor through hardware dual redundancy configuration and parallel sampling of dual sensors. It verifies the consistency of sensor signals in real time and automatically switches to the redundant channel when a single sensor is abnormal, ensuring the reliability of critical data acquisition, avoiding control interruption caused by a single sensor failure, realizing the continuity and stability of the control process, and improving the fault tolerance and operational reliability of the system under complex working conditions. The adaptive fuzzy logic control module dynamically generates motor speed and torque commands based on real-time collected state parameters (such as pressure, flow deviation and rate of change) to quickly respond to the real-time control requirements of nonlinear and time-varying loads. It also processes complex dynamic characteristics through fuzzy logic algorithms to achieve stable control and rapid response of the system when the load changes abruptly, ensuring the accuracy and robustness of motor speed and torque output. The data-driven optimization module optimizes the weights of adaptive fuzzy logic control rules and power conversion circuit parameters through reinforcement learning algorithms. By mining the value of data, the control strategy is adaptively adjusted to adapt to complex operating conditions, thereby reducing system energy consumption, reducing torque ripple, and improving system operating efficiency and stability. The digital twin predictive maintenance module constructs a digital twin model of the permanent magnet synchronous motor and the hydraulic power source, and synchronizes the physical system operation data in real time. It dynamically monitors and predicts potential faults such as bearing wear, winding aging, and oil contamination. It can identify early signs of equipment performance degradation in advance, realize proactive fault diagnosis, and help maintenance personnel to formulate maintenance strategies in advance (such as spare parts replacement and maintenance plans), reduce unplanned downtime, lower maintenance costs, improve the reliability and availability of system operation, and transform passive maintenance into proactive predictive maintenance.

[0023] The data acquisition module includes operating data such as pressure, flow rate, temperature, and oil viscosity of the electro-hydraulic power source, as well as the three-phase current, speed, and load torque of the motor.

[0024] In the specific data acquisition module, the running data is the core input for system control and optimization. Its function is to provide signal verification basis for the sensor redundancy and fault tolerance module, provide real-time operating parameters for the adaptive fuzzy logic control module, provide algorithm training samples for the data-driven optimization module, and provide model calibration data for the digital twin prediction and maintenance module.

[0025] The sensor redundancy and fault tolerance module includes a data redundancy verification unit and a dynamic threshold adaptive unit; The data redundancy verification unit is used to collect operational data using dual sensors and monitor signal consistency through difference comparison and trend consistency analysis between the two sensors. The dynamic threshold adaptive unit is used to dynamically adjust the verification threshold based on historical operation data statistics and real-time operation data. When an anomaly of a single sensor is detected, it automatically switches to the redundant sensor signal. After the main sensor signal returns to normal, it automatically switches back to the main channel after passing the consistency check for 5 cycles.

[0026] The system uses a data redundancy verification unit to collect operational data from dual sensors. It monitors signal consistency by comparing the differences between the two sensors and analyzing the trend consistency. The difference comparison can directly detect the differences between the readings of the two sensors, while the trend consistency analysis focuses on whether the trend of data changes over time is consistent. This allows for timely detection of possible sensor anomalies, preventing erroneous data from entering the control system due to a single sensor failure, and improving the stability and reliability of the system. The dynamic threshold adaptive unit dynamically adjusts the verification threshold based on historical operating data statistics and real-time operating data. It determines whether the sensor signal is abnormal based on historical operating conditions and the current real-time status. When an abnormality is detected in a single sensor, it can automatically switch to the redundant sensor signal to ensure the continuity of system data acquisition and maintain the normal operation of the system.

[0027] Specifically, the adaptive fuzzy logic control module takes the hydraulic source pressure error ΔP, flow error ΔQ, temperature deviation ΔT, and their rate of change as inputs. It generates d-axis and q-axis voltage commands for the permanent magnet synchronous motor through a fuzzy rule base mapping. An online gradient descent algorithm is used to dynamically optimize the membership function parameters (adjusting the center value and width of the membership function) to achieve real-time iteration of the control strategy. When ΔP > 5MPa and the rate of change is negative (indicating pressure overshoot and subsequent drop), the q-axis voltage weight is increased to 0.8 through the rule base to enhance torque response. When ΔT > 10℃ (abnormal temperature rise), the d-axis current limit is automatically reduced by 20% to reduce motor losses. Through fuzzy processing of nonlinear operating conditions and parameter self-optimization, it achieves rapid dynamic response under complex loads, improves system stability during pressure surges, and avoids motor overheating risks through a temperature-related current limiting mechanism, significantly improving system reliability.

[0028] The data-driven optimization module includes a strategy generation unit and a mode switching unit; The policy generation unit is used to generate optimized operating parameters through reinforcement learning algorithms; The mode switching unit is used to output adaptive fuzzy logic control rules according to real-time load requirements.

[0029] Specifically, the strategy generation unit uses reinforcement learning algorithms to deeply mine system operation data. Based on the mapping relationship between state space (load characteristics, motor parameters) and action space (control rule weights, circuit parameters), it generates optimized operating parameters that are suitable for the current working conditions. This enables the motor to dynamically adjust key parameters such as field weakening control boundary and energy recovery threshold under variable load conditions, significantly reducing system energy consumption and improving motor operating efficiency and stability. The mode switching unit analyzes load demand (pressure and flow fluctuations) in real time and outputs corresponding adaptive fuzzy logic control rules based on preset rules or learned strategies. This drives the system to switch between different operating modes (full load and energy saving), ensuring dynamic matching between motor output and hydraulic source load. It provides sufficient power under high load and automatically enters energy-saving mode under low load, achieving efficient operation under all working conditions. The digital twin predictive maintenance module includes a model building unit, a data mapping unit, and a fault prediction unit; The model building unit is used to construct a virtual model of the electro-hydraulic power source system based on mechanism modeling and parameter identification algorithms, combined with real-time operation data to calibrate model parameters; The data mapping unit is used to establish the mapping relationship between physical sensors and virtual models via the OPC UA protocol; The fault prediction unit is used to output a fault warning signal by comparing the health parameters of the virtual model with those of the LSTM neural network.

[0030] Specifically, the model building unit integrates hydraulic system fluid dynamics mechanism models (such as Bernoulli's equation and continuity equation), motor thermal network models, and pump mechanical wear models, and combines parameter identification algorithms (leakspan method) with real-time operating data to dynamically calibrate key parameters of the virtual model (leakage coefficient, winding resistance, bearing friction coefficient), thereby achieving consistency between the behavior of the physical system and the virtual model and providing reliable benchmark data for fault prediction. The data mapping unit establishes a real-time mapping relationship between physical sensors and virtual model input / output nodes based on the OPC UA protocol, enabling bidirectional interaction of data such as hydraulic source pressure, motor current, and oil temperature, ensuring that the virtual model reflects the real state of the physical system in real time, and providing real-time data-driven model calibration and fault prediction. The fault prediction unit uses an LSTM neural network to perform time-series analysis on the health parameters (bearing vibration characteristic value, winding equivalent impedance change rate, and oil contamination index) output by the virtual model. By comparing historical health baselines with real-time data, it identifies abnormal patterns and outputs fault warning signals, enabling early detection of faults such as bearing wear, winding aging, and oil contamination, thereby reducing operation and maintenance costs and safety risks.

[0031] Please see the appendix Figure 2A control method for a permanent magnet synchronous motor control system for an electro-hydraulic power source, the method comprising the following steps: S1. The data acquisition module collects hydraulic source status parameters and motor operation data in real time. S2. The collected operating data is verified in real time through the sensor redundancy and fault tolerance module, and redundancy switching is performed when sensor abnormality is detected. S3. Calculate ΔP, ΔQ and the corresponding rate of change based on the collected operating data, and generate motor speed and torque commands through a fuzzy rule base; S4. Combining historical data and real-time load, optimize the control instructions output by the adaptive fuzzy logic control module to generate the final control signal to drive the power conversion circuit. S5. Monitor the operating status through a virtual model, compare the health parameters of the virtual model to predict faults, and output fault warning signals.

[0032] Specifically, the S1 acquires multi-dimensional operating data such as pressure, flow, temperature, oil viscosity, and three-phase current, speed, and load torque of the electric drive hydraulic source in real time. This provides raw data support for subsequent sensor redundancy verification, fuzzy logic control rule generation, control command optimization, and fault prediction, ensuring the accuracy and real-time performance of the entire process control, avoiding control deviations caused by missing or delayed data, and improving the overall robustness and reliability of the system. The S2 performs real-time verification of the collected operating data to promptly detect potential faults or anomalies in individual sensors. When an anomaly is detected, redundancy switching is performed to ensure that the system always has a reliable data source. This prevents erroneous data from entering subsequent control stages due to sensor failure and ensures that the system can continue to operate stably even when a sensor fails. By calculating the pressure error ΔP, flow error ΔQ and their rate of change based on the operating data collected by S3, the difference and trend between the actual state and the expected state of the hydraulic source can be accurately grasped. The motor speed and torque commands are generated using a fuzzy rule base, so that the motor output matches the real-time demand of the hydraulic source, in order to cope with the complex and ever-changing working conditions of the electric drive hydraulic source system, thereby improving the working efficiency and control accuracy of the entire electric drive hydraulic source system. By combining historical operating data and real-time load characteristics, S4 dynamically optimizes the control commands generated by fuzzy logic. By adjusting the control rule weights or power conversion circuit parameters (such as voltage vector and switching frequency), the motor output is made to better meet the actual working conditions, making up for the limitations of single fuzzy control under complex working conditions, realizing the adaptive iteration of motor control strategy, while suppressing torque ripple and improving the smoothness of motor operation and power conversion efficiency. By using S5 with a virtual model, the operating status of the electro-hydraulic power source system can be monitored in real time. Using the health parameters of the virtual model as a reference standard, potential anomalies in the physical system can be accurately identified by comparison. Faults such as bearing wear, winding aging, and oil contamination can be predicted in advance, and early warning signals can be output. This allows maintenance personnel to take measures before the fault occurs, prevent the fault from worsening, achieve early warning of faults, effectively reduce unplanned downtime, and improve equipment availability and production efficiency.

[0033] S3 specifically includes the following steps: S301: Collect current workload data and hydraulic source status parameters, including pressure, flow rate, and temperature.

[0034] S302. Construct an AFLC model and automatically adjust the control rules based on real-time load data to optimize the speed and torque output of the permanent magnet synchronous motor.

[0035] S303. Implement control commands to regulate the permanent magnet synchronous motor according to the output of the AFLC model.

[0036] Specifically, the S301 collects current workload data and hydraulic source pressure, flow, temperature and other status parameters to provide real-time working condition input for building the AFLC model and dynamically adjusting control rules. This ensures that the AFLC model can automatically optimize motor control rules based on the latest working condition data, enabling the motor speed and torque output to quickly adapt to load changes, improving the system's dynamic response capability and control accuracy under nonlinear working conditions, and avoiding control deviations caused by data lag. An adaptive fuzzy logic control model is constructed using S302. Based on real-time load data, the control rules (membership function parameters and output weight allocation) are dynamically adjusted to establish a nonlinear mapping relationship between the hydraulic source working conditions and the motor control commands, thereby achieving intelligent optimization of the speed and torque output of the permanent magnet synchronous motor. The S303 converts the motor speed and torque commands generated by the adaptive fuzzy logic control model into actual control signals, driving the power conversion circuit to adjust the motor input voltage or current, thereby achieving real-time control of the permanent magnet synchronous motor, effectively suppressing system pressure fluctuations, improving the dynamic following performance of the hydraulic system, ensuring stable operation of the electro-hydraulic power source under complex working conditions, and meeting the control requirements of high-precision industrial applications.

[0037] The control command optimization strategy in S4 includes: when the hydraulic system pressure reaches the target value and the flow demand is stable, outputting an idle speed command; when rapid braking of the hydraulic cylinder is detected, outputting a field weakening control command.

[0038] Specifically, the control command optimization strategy identifies the system's operating status and outputs targeted idle speed commands or field weakening control commands, dynamically adjusting the motor's operating mode to adapt to the energy demands and braking characteristics of different operating conditions.

[0039] The fault prediction process in S5 includes: inputting real-time collected operating data into a machine learning model, comparing the health status parameters of the virtual model to identify early fault characteristics, and outputting diagnostic information including fault type and location.

[0040] Specifically, by inputting real-time operational data into a machine learning model and comparing it with the health status parameters of a digital twin virtual model, data-driven methods are used to identify early abnormal characteristics of equipment performance degradation (such as abnormal vibration signals and temperature gradient changes). This provides accurate type and location information for fault diagnosis, enabling maintenance personnel to develop targeted maintenance strategies in advance, reduce maintenance costs, and improve the reliability of the system throughout its entire lifecycle.

[0041] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A permanent magnet synchronous motor control system for an electro-hydraulic power source, characterized in that, include: The data acquisition module is used to collect the status parameters of the electro-hydraulic power source and the operating data of the permanent magnet synchronous motor in real time through multiple sensors; The sensor redundancy and fault tolerance module is used to form a signal channel between the main sensor and the redundant sensor through hardware dual redundancy configuration and parallel sampling of dual sensors; The adaptive fuzzy logic control module dynamically adjusts the speed and torque commands of the permanent magnet synchronous motor based on the collected state parameters. The data-driven optimization module uses reinforcement learning algorithms to optimize the weights of adaptive fuzzy logic control rules and power conversion circuit parameters, minimizing system energy consumption and torque ripple. The digital twin predictive maintenance module constructs a digital twin model of the permanent magnet synchronous motor and the hydraulic power source, and predicts the risk of bearing wear, winding aging and oil contamination failures through real-time data synchronization.

2. The permanent magnet synchronous motor control system for an electro-hydraulic power source according to claim 1, characterized in that, The data acquisition module includes operating data such as pressure, flow rate, temperature, and oil viscosity of the electro-hydraulic power source, as well as the three-phase current, speed, and load torque of the motor.

3. The permanent magnet synchronous motor control system for an electro-hydraulic power source according to claim 1, characterized in that, The sensor redundancy and fault tolerance module includes a data redundancy verification unit and a dynamic threshold adaptive unit; The data redundancy verification unit is used to collect operating data using dual sensors and monitor signal consistency through difference comparison and trend consistency analysis between the two sensors. The dynamic threshold adaptive unit is used to dynamically adjust the verification threshold based on historical operating data statistics and real-time operating data. When an anomaly of a single sensor is detected, it automatically switches to the redundant sensor signal. After the main sensor signal returns to normal, it automatically switches back to the main channel after passing the consistency verification for 5 cycles.

4. The permanent magnet synchronous motor control system for an electro-hydraulic power source according to claim 1, characterized in that, The adaptive fuzzy logic control module includes: The input variables are hydraulic source pressure error ΔP, flow error ΔQ, temperature deviation ΔT and their rate of change; The output variables are the d-axis voltage and q-axis voltage of the permanent magnet synchronous motor; The fuzzy rule base dynamically adjusts membership function parameters using an online gradient descent algorithm, with a response time of less than 10ms. Specifically, when ΔP > 5MPa and the rate of change is less than 0, the weight of the q-axis voltage is increased to 0.

8. When ΔT>10℃, reduce the d-axis current limit by 20%.

5. The permanent magnet synchronous motor control system for an electro-hydraulic power source according to claim 1, characterized in that, The data-driven optimization module includes a strategy generation unit and a mode switching unit; The strategy generation unit is used to generate optimized operating parameters through reinforcement learning algorithms; The mode switching unit is used to output adaptive fuzzy logic control rules according to real-time load requirements.

6. The permanent magnet synchronous motor control system for an electro-hydraulic power source according to claim 1, characterized in that, The digital twin prediction and maintenance module includes a model building unit, a data mapping unit, and a fault prediction unit. The model building unit is used to construct a virtual model of the electro-hydraulic power source system based on mechanism modeling and parameter identification algorithms, combined with real-time operation data to calibrate model parameters. The data mapping unit is used to establish a mapping relationship between physical sensors and virtual models through the OPC UA protocol; The fault prediction unit is used to output a fault warning signal by comparing the health parameters of the virtual model with those of the LSTM neural network.

7. A control method for a permanent magnet synchronous motor control system for an electro-hydraulic power source, characterized in that, The method for a permanent magnet synchronous motor control system for an electro-hydraulic power source as described in any one of claims 1-6 includes the following steps: S1. The data acquisition module collects hydraulic source status parameters and motor operation data in real time. S2. The collected operating data is verified in real time through the sensor redundancy and fault tolerance module, and redundancy switching is performed when sensor abnormality is detected. S3. Calculate ΔP, ΔQ and the corresponding rate of change based on the collected operating data, and generate motor speed and torque commands through a fuzzy rule base; S4. Combining historical data and real-time load, optimize the control instructions output by the adaptive fuzzy logic control module to generate the final control signal to drive the power conversion circuit. S5. Monitor the operating status through a virtual model, compare the health parameters of the virtual model to predict faults, and output fault warning signals.

8. The control method for a permanent magnet synchronous motor control system for an electro-hydraulic power source according to claim 7, characterized in that, S3 specifically includes the following steps: S301. Collect current workload data and hydraulic source status parameters, including pressure, flow rate, and temperature; S302. Construct an AFLC model and automatically adjust the control rules based on real-time load data to optimize the speed and torque output of the permanent magnet synchronous motor. S303. Implement control commands to regulate the permanent magnet synchronous motor according to the output of the AFLC model.

9. The control method for a permanent magnet synchronous motor control system for an electro-hydraulic power source according to claim 7, characterized in that, The control command optimization strategy in S4 includes: when the hydraulic system pressure reaches the target value and the flow demand is stable, outputting an idle speed command; when rapid braking of the hydraulic cylinder is detected, outputting a field weakening control command.

10. The control method for a permanent magnet synchronous motor control system for an electro-hydraulic power source according to claim 7, characterized in that, The fault prediction process in S5 includes: inputting real-time collected operating data into a machine learning model, comparing the health status parameters of the virtual model to identify early fault characteristics, and outputting diagnostic information including fault type and location.

Images