Intelligent control system and method for switched reluctance motor

Abstract

The invention relates to the technical field of reluctance motor intelligent control, and discloses a switch reluctance motor intelligent control system and method, and the system comprises a collection module which is used for collecting the inductance, flux linkage and winding current of a magnetic circuit, and a data processing module which is used for processing the collected data, calculating the angular position of a rotor, and outputting an electromagnetic torque. The system comprises a switch reluctance motor, a torque monitoring unit used for monitoring electromagnetic torque of the switch reluctance motor, a control module used for controlling operation of the motor, a fault monitoring module used for monitoring abnormal conditions, and an energy recovery module used for recovering energy generated during braking of the motor. Parameters such as motor torque and angle can be dynamically adjusted according to the motor operation state, and the operation efficiency and response speed of the motor are improved.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent control of reluctance motors, and discloses an intelligent control system and method for a switched reluctance motor. Background Art

[0002] Although reluctance motor monitoring technology is constantly improving, it still needs further improvement and optimization in terms of accuracy, real-time performance, multi-parameter monitoring capabilities, durability and cost. For example, under high-speed and high-load conditions, the response and accuracy of the reluctance motor monitoring system may not be sufficient to meet the real-time requirements. The reluctance motor monitoring system may still be limited in terms of real-time performance and response speed. The delay of the monitoring system may affect the accurate grasp of the motor's operating status. Most monitoring systems can only monitor a single or limited number of parameters, such as current, speed or temperature. However, the complexity of the reluctance motor itself means that multiple parameters need to be monitored simultaneously to fully evaluate its operating status, which makes monitoring more difficult. At this time, a new reluctance motor monitoring system is urgently needed.

[0003] For example, the existing patent application with publication number CN116404937A discloses a switched reluctance motor driver control system and control method, in which a power conversion module is electrically connected to the switched reluctance motor for adjusting the output power of the switched reluctance motor; a power conversion module is electrically connected to the DSP chip for supplying power to the DSP chip; a current detection module is electrically connected to the ADC port of the DSP chip for detecting the phase current of the switched reluctance motor; a fault detection module is electrically connected to the PDPINTA port of the DSP chip for overcurrent protection of the switched reluctance motor; a position detection module is electrically connected to the CAP port of the DSP chip for detecting the rotor position signal of the switched reluctance motor; an input end of the drive module is electrically connected to the PWM port of the DSP chip, and an output end is electrically connected to the power conversion module for amplifying the PWM signal level generated by the DSP chip and isolating the DSP chip and the power conversion module; a host computer module is electrically connected to the SCI port of the DSP chip for setting a given speed for the switched reluctance motor.

[0004] Although the above patent provides a fault detection method for a switched reluctance motor, the current detection method lacks real-time performance, and the control intelligence and automation level of the switched reluctance motor is not high, resulting in poor overall fault detection reliability. In addition, since there are too many signals that need to be detected overall, the overall complexity of the system is high and the subsequent maintenance cost is high. Summary of the invention

[0005] In order to solve the above technical problems, the main purpose of the present invention is to provide a switched reluctance motor intelligent control system and method, the switched reluctance motor intelligent control system comprising: The acquisition module includes an inductance acquisition unit for acquiring the inductance of the magnetic circuit, a flux acquisition unit for acquiring the flux of the magnetic circuit, and a current acquisition unit for acquiring the winding current; A data processing module, comprising a data processing unit for processing collected data, a rotor calculation unit for calculating the rotor angular position, and a torque data unit for outputting electromagnetic torque; A control model module, including a torque monitoring unit for monitoring the electromagnetic torque of the switched reluctance motor, a data analysis unit for analyzing parameter data of the switched reluctance motor, and an optimization unit for fitting the error between the predicted value and the monitored value of the switched reluctance motor; A control module, used for controlling the operation of the switched reluctance motor; Fault monitoring module, used to monitor abnormal conditions; The energy recovery module is used to recover the energy generated by the switched reluctance motor during braking.

[0006] As a preferred solution of the intelligent control system of a switched reluctance motor of the present invention, wherein: The inductance acquisition unit is used to measure the inductance value in the magnetic circuit of the switched reluctance motor; The flux collection unit is used to measure the flux in the magnetic circuit of the switched reluctance motor; The current acquisition unit is used to measure the current of the switched reluctance motor winding in real time.

[0007] As a preferred solution of the intelligent control system of a switched reluctance motor of the present invention, wherein: The data processing unit includes performing noise reduction and filtering processing on the collected data, and performing normalization processing; The noise reduction process is used to eliminate the noise in the sensor signal acquisition process; The normalization process is used to unify the data collected by different sensors into the same proportion; The filtering process is used to remove unnecessary frequency components in the sensor signal.

[0008] As a preferred solution of the intelligent control system of a switched reluctance motor of the present invention, wherein: The rotor calculation unit calculates the electromagnetic torque of the switched reluctance motor through the winding current, magnetic circuit flux and inductance, and outputs the motion parameters of the switched reluctance motor through the electromagnetic torque of the switched reluctance motor and the load torque; The data analysis unit performs weight correction through repeated iterative calculations to find the optimal weight of the hidden layer so as to minimize the learning rate; The weight correction calculation expression is as follows: Among them, Δy is the hidden layer weight adjustment coefficient, ω0 is the initial weight of the hidden layer, and τ is the generalization parameter; ω j is the weight corresponding to the torque data of the input hidden layer at the jth moment; By calculating the electromagnetic torque of the switched reluctance motor and the hidden layer weight, the electromagnetic torque of the switched reluctance motor is analyzed; The torque monitoring model is pre-built, and the optimization unit makes the predicted value output by the torque monitoring model close to the actual value by minimizing the loss function, and then predicts the torque data through the output of the torque monitoring model. The loss function calculation expression is as follows: Among them, F r (x) is the rth group of predicted torque data output by the torque monitoring model, F ● (x) is the actual torque data of the switched reluctance motor, M is the torque loss value, and n is the number of predicted torque data.

[0009] As a preferred solution of the intelligent control system of a switched reluctance motor of the present invention, wherein: The control module includes unit time torque control and voltage control; The input of the torque control per unit time is the difference between the monitored data and the reference torque data, and the actual torque is controlled by controlling the phase current; Controlling the actual torque by controlling the phase current includes: transforming the phase current into a discrete mathematical signal by A / D conversion, and calculating an initial phase current control variable by a current controller; The product of the integral gain parameter and the phase current control variable error from the 0th moment to the bth moment is used as compensation for correcting the initial phase current control variable; By multiplying the phase current differential parameter by the differential of the phase current signal with respect to time, the law of the phase current change of the switched reluctance motor with respect to time is obtained; The initial phase current control variable is optimized by compensating the initial phase current control variable, and the optimized phase current control variable is restricted based on the law of phase current change over time. Finally, the optimized phase current control signal is converted into an executable control signal through non-fuzzy processing to complete the phase current control.

[0010] As a preferred solution of the intelligent control system of a switched reluctance motor of the present invention, wherein: The phase current control expression is as follows: ; in, is the optimized fuzzy phase current control signal, is the current controller control constant, is the phase current compensation integral gain constant, is the phase current control compensation constraint constant, is the phase current input value, t is the independent variable; b is the time; The current controller control constant, the phase current compensation integral gain constant and the phase current control compensation constraint constant are calibrated by an integral calibration function, and the dynamic characteristics of the switched reluctance motor are optimized by learning the dynamic characteristics of the switched reluctance motor when running. , , ; Based on the torque parameters of the switched reluctance motor in different working modes, the phase current parameters are calculated through the torque parameters, and the phase current parameters of the switched reluctance motor in different working modes are calculated in reverse. , , The value of Different working modes , , The value of is used as a label, and the data is divided into a training set and a validation set. The training set is input into the initial neural network, the neural network is trained, the trained neural network is calculated, and the loss function of the trained neural network is calculated through the validation set; The trained neural network is input with flux linkage, switched reluctance motor voltage and phase current as data basis, and the trained neural network outputs , , Adjust and complete the , , The phase current is controlled.

[0011] As a preferred solution of the intelligent control system of a switched reluctance motor of the present invention, wherein: The trained neural network expression is as follows: ; in is a trained neural network used to output , , , is the neural network weight matrix, is the neural network excitation function matrix, x is the phase current, magnetic flux and voltage signal data of the input switched reluctance motor, and P is the bias value; The neural network weight update uses the following expression: ; in, is the updated neural network weight, is a full rank symmetric matrix, take the unit matrix, The value range is (0,1), e is , , Adjust the error value; The control module controls the switched reluctance motor parameters and inputs the torque parameters of the switched reluctance motor into a torque monitoring model for monitoring and correction, thereby forming a switched reluctance motor intelligent control closed loop.

[0012] As a preferred solution of the intelligent control system of a switched reluctance motor of the present invention, wherein: The fault monitoring module includes abnormality detection and diagnosis, fault diagnosis and alarm, protection measures and emergency response, as well as remote monitoring and data recording; The anomaly detection and diagnosis is used to monitor key parameters of the switched reluctance motor; The fault diagnosis and alarm are used to monitor abnormal conditions and, if an abnormal fault occurs, an alarm or signal is issued to notify the system operator or the switched reluctance motor intelligent control system; The protection measures and emergency responses described are used to implement emergency measures; The remote monitoring and data recording are used to remotely monitor and record data of the switched reluctance motor intelligent control system.

[0013] As a preferred solution of the intelligent control system of a switched reluctance motor of the present invention, wherein: The energy recovery module includes energy capture and conversion storage; The energy capture is used to recover the inertia energy and motor braking energy generated by the switched reluctance motor when the switched reluctance motor is braked and decelerated; The conversion storage is used to store and process the captured energy after rectification and conversion.

[0014] The present invention discloses an intelligent control method for a switched reluctance motor, wherein: S1, collecting the switched reluctance motor torque and driver current, and performing data processing on the collected switched reluctance motor torque and driver current; S2. Using the processed data as the data basis, a torque monitoring model and a current monitoring model are established to monitor and predict the switched reluctance motor torque and driver current; S3, fitting the prediction results and actual data through the optimization unit, and optimizing and pruning the torque monitoring model and the current monitoring model; S4, outputting the switched reluctance motor torque data and the driver current data through the torque monitoring model and the current monitoring model, and outputting the driver current control instruction through the current control, and the torque monitoring unit outputting the switched reluctance motor torque control instruction; S5, the control module receives the driver current control instruction and the switched reluctance motor torque control instruction, and controls the switched reluctance motor and the switched reluctance motor driver; S6. Transmit synchronous switched reluctance motor and drive parameter information through data communication and display it on a visualization screen.

[0015] An electronic device, comprising: A memory for storing instructions; The processor is used to execute the instructions so that the device implements the above-mentioned intelligent control method for a switched reluctance motor.

[0016] A computer-readable storage medium stores a computer program, which, when executed, implements the above-mentioned intelligent control method for a switched reluctance motor.

[0017] Beneficial effects of the present invention: The control module of the present invention integrates control strategies and algorithms, and can dynamically adjust motor torque, angle and other parameters according to the operating state of the switched reluctance motor, thereby improving the operating efficiency and response speed of the switched reluctance motor; The present invention provides a fault monitoring module that can timely monitor abnormal conditions in the operation of the switched reluctance motor and take corresponding protective measures, such as shutdown protection and alarm prompts, to ensure the safe operation of the motor and the entire system; The present invention is provided with an energy recovery module, which utilizes the energy generated during motor braking for feedback, thereby improving the energy utilization efficiency of the system, reducing energy consumption, and meeting the requirements of energy conservation and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them: Figure 1 A system composition diagram of a switched reluctance motor intelligent control system of the present invention; Figure 2 This is a flow chart of a switched reluctance motor intelligent control method of the present invention; Figure 3 This is a fuzzy control flow chart of a switched reluctance motor intelligent control system of the present invention; Figure 4 This is a simulation diagram of weight correction of an intelligent control system for a switched reluctance motor according to the present invention. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0022] Example 1 like Figure 1 As shown, a switched reluctance motor intelligent control system includes: The acquisition module includes an inductance acquisition unit for acquiring the inductance of the magnetic circuit, a flux acquisition unit for acquiring the flux of the magnetic circuit, and a current acquisition unit for acquiring the winding current.

[0023] The inductance acquisition unit is used to measure the inductance value in the magnetic circuit of the switched reluctance motor. The inductance value is measured through an AC bridge circuit, a sensor and a signal conditioning circuit, and is converted into a digital form for processing by the switched reluctance motor intelligent control system.

[0024] The flux acquisition unit is used to measure the flux in the magnetic circuit of the switched reluctance motor. The Hall sensor converts the magnetic field changes into voltage or current signals, which are then converted into digital signals through the ADC.

[0025] The current acquisition unit is used to measure the current of the switched reluctance motor winding in real time. The current passing through the winding is measured by a current sensor, which is then converted into a voltage signal and then converted into a digital signal by an ADC.

[0026] The data processing module includes a data processing unit for processing the collected data, a rotor calculation unit for calculating the rotor angular position, and a torque data unit for outputting the electromagnetic torque.

[0027] The data processing unit includes noise reduction and filtering processing on the collected data, and normalization processing.

[0028] Noise reduction processing is used to eliminate noise during sensor signal acquisition to ensure that the system can stably obtain accurate data.

[0029] Common noise reduction methods include moving average filtering, median filtering, wavelet transform, etc. These methods can effectively remove high-frequency noise and retain the main components of the signal, thereby improving the quality and reliability of the data.

[0030] Filtering is used to remove unnecessary frequency components in sensor signals and retain useful information.

[0031] Commonly used filters include low-pass filters, high-pass filters, band-pass filters, etc. Selecting the appropriate filter can optimize data processing according to the frequency characteristics of the signal, ensuring that the system captures and analyzes key information more accurately.

[0032] Normalization is used to unify the data collected by different sensors into the same scale or range for comparison and comprehensive analysis.

[0033] Linear normalization or standardization is usually used to map the data to a specified range (such as between 0 and 1 or standard normal distribution), which helps to simplify the data processing and algorithm design process.

[0034] The rotor calculation unit calculates the electromagnetic torque of the switched reluctance motor through the winding current, magnetic circuit flux and inductance, and outputs the motion parameters of the switched reluctance motor through the electromagnetic torque of the switched reluctance motor and the load torque.

[0035] The data analysis unit performs weight correction through repeated iterative operations to find the optimal weight of the hidden layer and minimize the learning rate.

[0036] The weight correction calculation expression is as follows: ; in, is the hidden layer weight adjustment coefficient, is the initial weight of the hidden layer, is the generalization parameter; is the weight corresponding to the torque data of the input hidden layer at the jth moment;.

[0037] By calculating the electromagnetic torque of the switched reluctance motor and the hidden layer weights, the electromagnetic torque of the switched reluctance motor is analyzed.

[0038] like Figure 4 As shown, the vertical axis is the data group, the horizontal axis is the weight correction coefficient, the dotted line represents the theoretical weight correction rate, the optimal correction coefficient is 1, the solid line is the actual weight correction rate, and the correction coefficient is infinitely close to the optimal correction coefficient through continuous training.

[0039] The torque monitoring model is pre-built, and the optimization unit makes the predicted value output by the torque monitoring model close to the actual value by minimizing the loss function, and then predicts the torque data through the output of the torque monitoring model. The loss function calculation expression is as follows: Among them, F r (x) is the rth group of predicted torque data output by the torque monitoring model, F ● (x) is the actual torque data of the switched reluctance motor, M is the torque loss value, and n is the number of predicted torque data.

[0040] A control module is used to control the operation of the switched reluctance motor.

[0041] The control module includes unit time torque control and voltage control.

[0042] like Figure 3 As shown, e(t) is the input phase current signal, e(t) is transmitted through A / D ( Figure 3 The A / D conversion in the conversion phase current is transformed into a discrete mathematical signal, and the initial phase current control variable is calculated by the current controller, that is, the calculated control variable. The fuzzy quantization processing is to use the product of the integral gain parameter and the phase current control variable error from the 0th moment to the bth moment as the compensation for correcting the initial phase current control variable. Through the compensation of the initial phase current control variable, the initial phase current control variable is optimized, and based on the law of phase current change over time, the optimized phase current control variable is restricted, and fuzzy control rules are formulated. Finally, the optimized fuzzy phase current control signal (fuzzy decision) is output, and the non-fuzzy processing module converts the output optimized fuzzy phase current control signal into a clear and executable control signal (non-fuzzy processing). The control signal is converted by D / A into a control signal that can be recognized by the switched reluctance motor (actuator), and the torque of the switched reluctance motor is controlled (controlled object). After being controlled, the switched reluctance motor will re-output the phase current signal, which will be collected by the acquisition module and enter the phase current controller to complete the control closed loop.

[0043] The unit time torque control input is the difference between the monitored data and the reference torque data. The actual torque is controlled by controlling the phase current. The phase current control expression is as follows: ; in, is the optimized fuzzy phase current control signal, is the current controller control constant, is the phase current compensation integral gain constant, is the phase current control compensation constraint constant, is the phase current input value, t is the independent variable; b is the time.

[0044] Used to calculate the initial phase current control variables.

[0045] It is used to calculate the error of the phase current control variable from time 0 to time b. The algorithm is used to compensate and optimize the initial phase current control variable, rather than addition and subtraction calculation in the mathematical sense.

[0046] It is used to limit the compensation range of the optimized phase current control variable to prevent the compensation from being too large or too small, affecting the normal operating parameters of the switched reluctance motor and causing equipment damage.

[0047] The optimized fuzzy phase current control signal belongs to the phase current control strategy and is used to dynamically control the torque of the switched reluctance motor.

[0048] The control method can also achieve control of the switched reluctance motor by controlling parameters such as inductance, flux linkage and motor speed.

[0049] The control module controls the parameters of the switched reluctance motor and inputs the torque parameters of the switched reluctance motor into the torque monitoring model for monitoring and correction, thereby forming an intelligent control closed loop of the switched reluctance motor.

[0050] The current controller control constant, the phase current compensation integral gain constant and the phase current control compensation constraint constant are calibrated by an integral calibration function, and the dynamic characteristics of the switched reluctance motor are optimized by learning the dynamic characteristics of the switched reluctance motor when running. , , .

[0051] Based on the torque parameters of the switched reluctance motor in different working modes, the phase current parameters are calculated through the torque parameters, and the phase current parameters of the switched reluctance motor in different working modes are calculated in reverse. , , The value of .

[0052] Different working modes , , The value of is used as a label, and the data is divided into a training set and a validation set. The training set is input into the initial neural network, the neural network is trained, the trained neural network is calculated, and the loss function of the trained neural network is calculated through the validation set.

[0053] The trained neural network is input with flux linkage, switched reluctance motor voltage and phase current as data basis, and the trained neural network outputs , , Adjust and complete the , , The phase current is controlled.

[0054] For the above current controller control constant , Phase current compensation integral gain constant , Phase current control compensation constraint constant , neural network is used for calibration to achieve intelligent regulation and realize the goal of intelligent control. The neural network input is designed to be the data obtained by the flux acquisition unit and the voltage, phase current and other signals of the switched reluctance motor, and the output is , , .

[0055] The trained neural network expression is as follows: ; in is a trained neural network used to output , , , is the neural network weight matrix, is the neural network excitation function matrix, x is the phase current, magnetic flux and voltage signal data of the input switched reluctance motor, and P is the bias value.

[0056] The neural network weight update uses the following expression: ; in, is the updated neural network weight, is a full rank symmetric matrix, take the unit matrix, is a small positive constant selected, e is , , Adjust the error value.

[0057] The value is usually between 0 and 1.

[0058] The control module controls the switched reluctance motor parameters and inputs the torque parameters of the switched reluctance motor into a torque monitoring model for monitoring and correction, thereby forming a switched reluctance motor intelligent control closed loop.

[0059] Furthermore, by monitoring the flux, voltage and phase current of the switched reluctance motor, , , Intelligent adjustment can be achieved in the following steps: S1001. Establish a data acquisition unit that can monitor key parameters of the switched reluctance motor in real time.

[0060] The flux linkage is calculated using sensors or model-based methods, measuring the voltage on each phase and measuring the current on each phase.

[0061] S1002. The collected data usually needs to be preprocessed to improve the training effect of the neural network: Normalize the flux, voltage and phase current data to the same range (e.g., between 0 and 1) to facilitate learning of the neural network, use a low-pass filter or other filtering techniques to remove noise, and extract some additional features, such as the rate of change of current, the rate of change of voltage, etc., which may help improve the performance of the model.

[0062] S1003. Design a neural network whose input is flux, voltage and phase current, and whose output is , , ; Furthermore, the number of neural network nodes is 3 (magnetic flux, voltage, phase current), the hidden layer has multiple layers, and the number of nodes in each layer can be selected according to the complexity of the problem. Common activation functions include ReLU, Tanh, etc. The output layer is a single node because the output is the integral constant (Ki) of the PID controller.

[0063] Furthermore, the activation function hidden layer selects nonlinear activation functions such as ReLU, Tanh or Sigmoid.

[0064] Activation function The output layer uses a linear activation function (i.e. no activation function).

[0065] S1004. Train the neural network.

[0066] Furthermore, in different working modes , , The value of is used as the label, and the data is divided into a training set and a validation set. The training set is input into the initial neural network, the neural network is trained, the trained neural network is calculated, and the loss function of the trained neural network is calculated through the validation set. Usually the ratio is 80% training set and 20% validation set.

[0067] The loss function is calculated by the mean square error (MSE) of the predictions , , The error between the actual parameters.

[0068] Furthermore, the training process includes forward propagation, back propagation and iterative training.

[0069] Forward propagation propagates the input data forward through the network to obtain the predicted output.

[0070] Backpropagation is used to calculate the error between the predicted output and the true label, and the weights are updated through backpropagation.

[0071] Iterative training involves repeating the above process until the loss function converges or a predetermined number of training times is reached.

[0072] S1005. Verification and adjustment.

[0073] Evaluate model performance on the validation set to ensure that the model performs well on unseen data.

[0074] According to the verification results, hyperparameters such as network structure, learning rate, batch size, etc. are adjusted to improve model performance.

[0075] S1006, Real-time application adjustment , , .

[0076] Fault monitoring module, used to monitor abnormal conditions.

[0077] Among them, the fault monitoring module includes anomaly detection and diagnosis, fault diagnosis and alarm, protection measures and emergency response, as well as remote monitoring and data recording.

[0078] Abnormal detection and diagnosis is used to monitor various key parameters of the switched reluctance motor, such as current, voltage, temperature, etc., to detect whether there are abnormal conditions, such as overload, short circuit, open circuit, etc., and analyze the collected data in real time through preset thresholds and algorithms. For example, a sudden increase in current may indicate a short circuit, and abnormal voltage fluctuations may indicate a power supply problem. These characteristics can quickly identify possible fault types.

[0079] Fault diagnosis and alarm are used to monitor abnormal conditions. If an abnormal fault occurs, an alarm or signal is issued to notify the system operator or the switched reluctance motor intelligent control system. Furthermore, the alarm can be a visual, audible or network-transmitted notification. At the same time, the switched reluctance motor intelligent control system may record the time and cause of the fault for subsequent fault analysis and maintenance.

[0080] Protection measures and emergency responses are used to implement emergency measures, such as cutting off power, reducing load, or changing operating conditions to avoid further damage to the motor or other equipment.

[0081] Remote monitoring and data logging are used to remotely monitor and log the switched reluctance motor intelligent control system, allowing operators to remotely view the operating status and historical data of the switched reluctance motor, providing support for remote diagnosis and maintenance.

[0082] The energy recovery module is used to recover the energy generated by the switched reluctance motor during braking.

[0083] The energy recovery module includes energy capture and conversion storage.

[0084] Energy capture is used to recover the inertial energy and motor braking energy generated by the switched reluctance motor when the switched reluctance motor is braking and decelerating. The energy recovery module captures this energy and converts it into usable electrical energy through specific electronic circuits and control algorithms.

[0085] Conversion storage is used to store the captured energy after rectification and conversion, usually in capacitors, batteries or other suitable energy storage devices for future use.

[0086] By recovering braking energy, the system can reduce energy consumption to a certain extent and improve energy efficiency. Reducing energy consumption means reducing operating costs, especially in applications that require frequent braking or speed changes.

[0087] Example 2 like Figure 2 As shown, a switched reluctance motor intelligent control method includes: S1. Collect the switched reluctance motor torque and driver current, and perform data processing on the collected switched reluctance motor torque and driver current.

[0088] S2. Using the processed data as the data basis, a torque monitoring model and a current monitoring model are established to monitor and predict the switched reluctance motor torque and driver current.

[0089] S3. The prediction results and actual data are fitted through the optimization unit, and the torque monitoring model and the current monitoring model are optimized and pruned.

[0090] S4. Output the switched reluctance motor torque data and driver current data through the torque monitoring model and the current monitoring model, and output the driver current control instruction through the current control, and the torque monitoring unit outputs the switched reluctance motor torque control instruction.

[0091] S5. The control module receives the driver current control instruction and the switched reluctance motor torque control instruction, and controls the switched reluctance motor and the switched reluctance motor driver.

[0092] S6. Transmit synchronous switched reluctance motor and drive parameter information through data communication and display it on a visualization screen.

[0093] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only two embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible, for example, the size, scale, structure, shape and ratio of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc., without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. Any "device plus function" clause is intended to cover the structure of the execution function described in this article, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiment. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0094] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those features that are not relevant to implementing the invention).

[0095] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, the development effort will be a routine task of design, fabrication, and production without undue experimentation.

[0096] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A switched reluctance motor intelligent control system, characterized in that: include: The acquisition module includes an inductance acquisition unit for acquiring the inductance of the magnetic circuit, a flux acquisition unit for acquiring the flux of the magnetic circuit, and a current acquisition unit for acquiring the winding current; A data processing module, comprising a data processing unit for processing collected data, a rotor calculation unit for calculating the rotor angular position, and a torque data unit for outputting electromagnetic torque; A control model module, including a torque monitoring unit for monitoring the electromagnetic torque of the switched reluctance motor, a data analysis unit for analyzing parameter data of the switched reluctance motor, and an optimization unit for fitting the error between the predicted value and the monitored value of the switched reluctance motor; A control module, used for controlling the operation of the switched reluctance motor; Fault monitoring module, used to monitor abnormal conditions; The energy recovery module is used to recover the energy generated by the switched reluctance motor during braking.

2. The intelligent control system of a switched reluctance motor according to claim 1, characterized in that: The inductance acquisition unit is used to measure the inductance value in the magnetic circuit of the switched reluctance motor; The flux collection unit is used to measure the flux in the magnetic circuit of the switched reluctance motor; The current acquisition unit is used to measure the current of the switched reluctance motor winding in real time.

3. The intelligent control system of a switched reluctance motor according to claim 2, characterized in that: The data processing unit includes performing noise reduction and filtering processing on the collected data, and performing normalization processing; The noise reduction process is used to eliminate the noise in the sensor signal acquisition process; The normalization process is used to unify the data collected by different sensors into the same proportion; The filtering process is used to remove unnecessary frequency components in the sensor signal.

4. The intelligent control system for a switched reluctance motor according to claim 3, characterized in that: The rotor calculation unit calculates the electromagnetic torque of the switched reluctance motor through the winding current, magnetic circuit flux and inductance, and outputs the motion parameters of the switched reluctance motor through the electromagnetic torque of the switched reluctance motor and the load torque; The data analysis unit performs weight correction through repeated iterative calculations to find the optimal weight of the hidden layer so as to minimize the learning rate; The weight correction calculation expression is as follows: Among them, Δy is the hidden layer weight adjustment coefficient, ω0 is the initial weight of the hidden layer, and τ is the generalization parameter; ω j is the weight corresponding to the torque data of the input hidden layer at the jth moment; By calculating the electromagnetic torque of the switched reluctance motor and the hidden layer weight, the electromagnetic torque of the switched reluctance motor is analyzed; The torque monitoring model is pre-built, and the optimization unit makes the predicted value output by the torque monitoring model close to the actual value by minimizing the loss function, and then predicts the torque data through the output of the torque monitoring model. The loss function calculation expression is as follows: Among them, F r (x) is the rth group of predicted torque data output by the torque monitoring model, F ● (x) is the actual torque data of the switched reluctance motor, M is the torque loss value, and n is the number of predicted torque data.

5. The intelligent control system for a switched reluctance motor according to claim 4, characterized in that: The control module includes unit time torque control and voltage control; The input of the torque control per unit time is the difference between the monitored actual torque data and the reference torque data, and the actual torque is controlled by controlling the phase current; Controlling the actual torque by controlling the phase current includes: transforming the phase current into a discrete mathematical signal by A / D conversion, and calculating an initial phase current control variable by a current controller; The product of the integral gain parameter and the phase current control variable error from the 0th moment to the bth moment is used as compensation for correcting the initial phase current control variable; By multiplying the phase current differential parameter by the differential of the phase current signal with respect to time, the law of the phase current change of the switched reluctance motor with respect to time is obtained; The initial phase current control variable is optimized by compensating the initial phase current control variable, and the optimized phase current control variable is restricted based on the law of phase current change over time. Finally, the optimized phase current control signal is converted into an executable control signal through non-fuzzy processing to complete the phase current control.

6. The intelligent control system for a switched reluctance motor according to claim 5, characterized in that: The phase current control expression is as follows: ； in, For the optimized fuzzy phase current control signal, is the current controller control constant, is the phase current compensation integral gain constant, is the phase current control compensation constraint constant, is the phase current input value, t is the independent variable; b is the time; The current controller control constant, the phase current compensation integral gain constant and the phase current control compensation constraint constant are calibrated by an integral calibration function, and the dynamic characteristics of the switched reluctance motor are optimized by learning the dynamic characteristics of the switched reluctance motor when running. , , ; Based on the torque parameters of the switched reluctance motor in different working modes, the phase current parameters are calculated through the torque parameters, and the phase current parameters of the switched reluctance motor in different working modes are calculated in reverse. , , The value of Different working modes , , The value of is used as a label, and the data is divided into a training set and a validation set. The training set is input into the initial neural network, the neural network is trained, the trained neural network is calculated, and the loss function of the trained neural network is calculated through the validation set; The trained neural network is input with flux linkage, switched reluctance motor voltage and phase current as data basis, and the trained neural network outputs , , Adjust and complete the , , The phase current is controlled.

7. The intelligent control system for a switched reluctance motor according to claim 6, characterized in that: The trained neural network expression is as follows: ； in is a trained neural network used to output , , , is the neural network weight matrix, is the neural network excitation function matrix, x is the phase current, magnetic flux and voltage signal data of the input switched reluctance motor, and P is the bias value; The neural network weight update uses the following expression: ； in, is the updated neural network weight, is a full rank symmetric matrix, take the unit matrix, The value range is (0,1), e is , , Adjust the error value; The control module controls the switched reluctance motor parameters and inputs the torque parameters of the switched reluctance motor into a torque monitoring model for monitoring and correction, thereby forming a switched reluctance motor intelligent control closed loop.

8. The intelligent control system for a switched reluctance motor according to claim 7, characterized in that: The fault monitoring module includes abnormality detection and diagnosis, fault diagnosis and alarm, protection measures and emergency response, as well as remote monitoring and data recording; The anomaly detection and diagnosis is used to monitor key parameters of the switched reluctance motor; The fault diagnosis and alarm are used to monitor abnormal conditions and, if an abnormal fault occurs, an alarm or signal is issued to notify the system operator or the switched reluctance motor intelligent control system; The protection measures and emergency responses described are used to implement emergency measures; The remote monitoring and data recording are used to remotely monitor and record data of the switched reluctance motor intelligent control system.

9. The intelligent control system for a switched reluctance motor according to claim 8, characterized in that: The energy recovery module includes energy capture and conversion storage; The energy capture is used to recover the inertia energy and motor braking energy generated by the switched reluctance motor when the switched reluctance motor is braked and decelerated; The conversion storage is used to store and process the captured energy after rectification and conversion.

10. A method for intelligent control of a switched reluctance motor, implemented based on an intelligent control system of a switched reluctance motor according to any one of claims 1 to 9, characterized in that: include: S1, collecting the switched reluctance motor torque and driver current, and performing data processing on the collected switched reluctance motor torque and driver current; S2. Using the processed data as the data basis, a torque monitoring model and a current monitoring model are established to monitor and predict the switched reluctance motor torque and driver current; S3, fitting the prediction results and actual data through the optimization unit, and optimizing and pruning the torque monitoring model and the current monitoring model; S4, outputting the switched reluctance motor torque data and the driver current data through the torque monitoring model and the current monitoring model, and outputting the driver current control instruction through the current control, and the torque monitoring unit outputting the switched reluctance motor torque control instruction; S5, the control module receives the driver current control instruction and the switched reluctance motor torque control instruction, and controls the switched reluctance motor and the switched reluctance motor driver; S6. Transmit synchronous switched reluctance motor and drive parameter information through data communication and display it on a visualization screen.

Images