High-order sliding mode compound control method for speed regulation of motor of electric forklift

Abstract

The invention relates to the technical field of motor control, and provides a high-order sliding mode compound control method for electric forklift motor speed regulation, which comprises the following steps: selecting a control period signal in motor operation state data to generate a control parameter sample; sending the sample to a sliding mode control model main controller module pre-deployed in a local controller, and extracting motor speed regulation characteristic data; the data is sent to a parameter adjusting module of the central processing unit for dynamic compensation, and a regulation and control instruction is generated; and the local controller execution unit responds to the instruction and outputs the instruction. According to the method, dynamic optimization of speed regulation parameters is achieved through cooperation of a main controller and a central processing unit, and state quantity extraction covers the characteristics of current, torque, rotating speed and the like so as to achieve multi-parameter fusion control. According to the invention, the response speed, the anti-interference capability and the control precision of electric forklift motor speed regulation can be improved, and the operation stability under multiple working conditions is optimized.

Description

Technical Field

[0001] This invention relates to the field of motor control technology, and more specifically, to a high-order sliding mode composite control method for speed regulation of electric forklift motors. Background Technology

[0002] In modern industrial production, electric forklifts are crucial material handling equipment, and the speed control performance of their motors directly impacts work efficiency and operational precision. Traditional motor speed control methods mainly include simple PID control and vector control. While these methods can achieve motor speed control to some extent, they often exhibit problems such as slow response speed, low speed control accuracy, and weak anti-interference capability when facing complex operating conditions and dynamic disturbances. For example, PID control relies on precise system model parameters; when system parameters change or external disturbances occur, the control effect will significantly decrease. Although vector control can achieve high-performance motor speed control, it requires high precision in measuring and identifying motor parameters, and its speed control performance will also be affected by large load changes.

[0003] In recent years, with the development of control theory, sliding mode control, as an effective nonlinear control method, has been gradually applied to the field of motor speed regulation. Sliding mode control, by designing a sliding surface, allows the system state to switch rapidly on the sliding surface, thereby achieving rapid control of the system. However, traditional sliding mode control methods also have some shortcomings in practical applications. For example, sliding mode control can produce jitter during the switching process, which not only affects the stability of motor speed regulation but may also lead to accelerated mechanical wear of the motor. Furthermore, traditional sliding mode control methods have poor adaptability to changes in system parameters and external disturbances, making it difficult to meet the speed regulation requirements of electric forklifts under complex operating conditions.

[0004] In the process of implementing the embodiments of the present invention, the inventors have discovered that the prior art has at least the following problems or defects: the existing motor speed control method is insufficient in speed regulation accuracy and anti-interference capability when facing complex working conditions and dynamic disturbances; although the traditional sliding mode control method can achieve fast control, it has a jitter phenomenon and poor adaptability to changes in system parameters and external disturbances, making it difficult to meet the speed regulation requirements of electric forklifts under complex working conditions. Summary of the Invention

[0005] This invention provides a high-order sliding mode composite control method for speed regulation of electric forklift motors, comprising: Select the control cycle signal from the motor operating status data, and generate control parameter samples from the control cycle signal; The control parameter samples are sent to the main controller module in the pre-built sliding mode control model for state variable extraction to obtain motor speed regulation feature data. The main controller module of the sliding mode control model is pre-deployed in the local controller. The motor speed regulation characteristic data is sent to the central processing unit so that the parameter adjustment module in the central processing unit corresponding to the sliding mode control model can perform dynamic compensation of the speed regulation parameters and obtain the motor speed regulation control command. In response to the control command returned by the central processing unit, the execution unit of the local controller outputs the command.

[0006] Furthermore, before sending the control parameter samples to the pre-built sliding mode control model, the following steps are performed: The control parameter samples are subjected to noise suppression processing to remove high-frequency interference signals.

[0007] Furthermore, the method also includes: State parameters are detected for each sampling period signal in the motor operating status data to generate a state evaluation result set; The evaluation results that satisfy the preset conditions in the set of state evaluation results are determined, and the sampling signals corresponding to the evaluation results that satisfy the preset conditions are determined as control cycle signals.

[0008] Furthermore, the method also includes: Fluctuation detection is performed on the motor operating status data to determine the dynamic disturbance component in the status data; The detected dynamic disturbance components are state tracked, wherein the marked dynamic disturbance components are tracked to obtain a disturbance identifier set; Determine the fluctuation range of the detected dynamic disturbance components in the operating state data to obtain the disturbance fluctuation boundary set; Based on the disturbance identifier set and the disturbance fluctuation boundary set, state parameters are detected for the sampled signals corresponding to each detected dynamic disturbance component to generate a state evaluation result set.

[0009] Furthermore, the method also includes: In response to the determination that there is no evaluation result in the set of state evaluation results that meets the preset conditions, the control cycle is reselected for the motor operating state data collected by the sensor.

[0010] Further, the step of performing state parameter detection on the sampled signals corresponding to each detected dynamic disturbance component based on the disturbance identifier set and the disturbance fluctuation boundary set to generate a state evaluation result set includes: Based on the disturbance fluctuation boundary set, determine the signal-to-noise ratio set and interference suppression ratio set of the sampled signals corresponding to each identifier in the disturbance identifier set; Load characteristics are identified for the sampled signals corresponding to each fluctuation boundary in the disturbance fluctuation boundary set to generate a set of operating condition mode information. Each operating condition mode information in the set of operating condition mode information corresponds to an operating state. Each operating condition mode information includes a running condition label of the motor relative to the drive device in the control cycle signal. The running condition label includes at least one of the following: no-load operating condition label, half-load operating condition label, and full-load operating condition label. Based on the signal-to-noise ratio set, the interference suppression ratio set, and the operating condition mode information set, determine the state assessment result set corresponding to each disturbance identifier.

[0011] Furthermore, the method also includes: Determine the signal-to-noise ratio (SNR) of the sampled signal corresponding to each identifier in the disturbance identifier set to obtain the SNR set; The interference suppression ratio of the sampled signal corresponding to each identifier in the disturbance identifier set is determined to obtain the interference suppression ratio set.

[0012] Furthermore, the sliding mode control model is generated through training using a preset parameter tuning method; wherein, the preset parameter tuning method includes: Obtain a training dataset, wherein the training samples in the training dataset include a reference speed control signal, a perturbation speed control signal pair, and corresponding reference feature labels and perturbation feature labels; Training samples are selected from the training dataset and input into the main controller module of the initial sliding mode control model to generate a reference feature matrix and a disturbance feature matrix. The parameters of the main controller module in the initial sliding mode control model remain fixed. The parameter adjustment module in the initial sliding mode control model includes a global adjustment unit and a local adjustment unit, and the parameter adjustment module corresponds to a single control loop. The reference feature matrix is ​​input into the parameter adjustment module of the initial sliding mode control model, and a reference prediction label is output. The local adjustment unit in the parameter adjustment module is used to dynamically adjust the transient features in the reference feature matrix. The disturbance feature matrix is ​​input into the parameter adjustment module of the initial sliding mode control model, and the disturbance prediction label is output. The global adjustment unit in the parameter adjustment module is used to dynamically adjust the steady-state features in the reference feature matrix. An adjustment error value is generated based on the obtained reference prediction label, the disturbance prediction label, the reference feature label, and the disturbance feature label; The control parameters in the parameter adjustment module are adjusted according to the adjustment error value.

[0013] Furthermore, the training dataset is generated through the following steps: Receive the operator's filtering and removal operations on the displayed control parameters and centralized speed regulation parameters; The speed regulation parameters corresponding to the filter removal operation are determined as disturbance speed regulation signals to obtain a disturbance signal group, wherein the disturbance speed regulation signal is the abnormal disturbance signal eliminated by the operator; The tracking identifier corresponding to each disturbance speed control signal in the disturbance signal group is determined as the disturbance feature label, thus obtaining the disturbance label group; Receives the operator's parameter integration operation on the displayed control parameters and centralized speed regulation parameters; The tracking identifier corresponding to the parameter integration operation is adjusted to the same identifier, and each speed regulation parameter in the control parameter set is determined as a reference speed regulation signal to obtain a reference signal group; Each tracking identifier corresponding to a reference speed control signal in the reference signal group is determined as a reference feature label to obtain a reference label group; The reference signal group, reference label group, perturbation signal group, and perturbation label group are combined to train the dataset.

[0014] Furthermore, the state quantity extraction is used to extract multiple operating characteristics of the motor, including at least one of the following: current characteristics, torque characteristics, and speed characteristics, in order to perform multi-parameter fusion speed control.

[0015] The embodiments of the present invention have at least the following beneficial effects: (1) The high-order sliding mode composite control method for electric forklift motor speed regulation proposed in this invention can improve the accuracy and stability of motor speed regulation. By selecting the control cycle signal in the motor operating state data and generating control parameter samples, and then using the sliding mode control model to extract state variables and dynamically compensate speed regulation parameters, it is possible to achieve accurate extraction of motor speed regulation characteristic data and efficient generation of control commands. In addition, this method can also perform noise suppression processing on the control parameter samples to remove high-frequency interference signals, thereby further improving the anti-interference capability of speed regulation control and ensuring that the motor can still operate stably under complex working conditions; (2) The parameter adjustment module in the initial sliding mode control model used in this invention includes a global adjustment unit and a local adjustment unit. The global adjustment unit is used to dynamically adjust the steady-state characteristics in the reference feature matrix, and the local adjustment unit is used to dynamically adjust the transient characteristics in the reference feature matrix. In this way, the parameter adjustment module can simultaneously handle the steady-state and transient characteristics of motor speed regulation, and achieve more precise speed regulation control; (3) This invention can also perform fluctuation detection and state tracking on motor operating status data, determine dynamic disturbance components and their fluctuation range, and generate a state evaluation result set based on this, thereby realizing real-time monitoring and accurate evaluation of motor operating status. More specifically, when processing motor operating status data, fluctuation detection and dynamic disturbance component state tracking steps are further introduced, the disturbance identifier set and disturbance fluctuation boundary set are determined, and based on the disturbance identifier set and disturbance fluctuation boundary set, the sampled signal is subjected to state parameter detection. The generated state evaluation result set can more comprehensively reflect the operating status of the motor under different working conditions, thereby providing a more accurate basis for speed control. (4) In processing the motor operating status data, this invention introduces a feedback mechanism: when no evaluation result that meets the preset conditions exists in the status evaluation result set, the control cycle of the motor operating status data is reselected. This mechanism ensures that the selection of the control cycle signal is always based on the actual operating state of the motor, avoiding speed control failure due to incorrect or unmet signals. Through this feedback mechanism, the selection strategy of the control cycle signal can be dynamically adjusted to adapt to changes in the motor operating state. Attached Figure Description

[0016] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated in the drawings by way of example and not limitation, wherein: Figure 1 This is a flowchart illustrating a high-order sliding mode composite control method for speed regulation of electric forklift motors provided in an embodiment of the present invention. Detailed Implementation

[0017] The principles and spirit of the invention will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided merely to enable those skilled in the art to better understand and implement the invention, and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided to make the invention more thorough and complete, and to fully convey the scope of the invention to those skilled in the art.

[0018] Those skilled in the art will recognize that embodiments of the present invention can be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present invention can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0019] It should be noted that the number of any elements in the accompanying drawings is for illustrative purposes only and not as a limitation, and any naming is for distinction only and has no limiting meaning.

[0020] The following is for reference. Figure 1 , Figure 1 This is a flowchart illustrating a high-order sliding mode composite control method for electric forklift motor speed regulation according to an embodiment of the present invention. Figure 1 As shown, a high-order sliding mode composite control method for speed regulation of electric forklift motors includes: S1. Select the control cycle signal from the motor operating status data, and generate control parameter samples from the control cycle signal; S2. The control parameter samples are sent to the main controller module in the pre-built sliding mode control model to extract state variables and obtain motor speed regulation feature data. The main controller module of the sliding mode control model is pre-deployed in the local controller. S3. The motor speed regulation characteristic data is sent to the central processing unit so that the parameter adjustment module in the central processing unit corresponding to the sliding mode control model can perform dynamic compensation of the speed regulation parameters and obtain the motor speed regulation control command. S4. In response to the control instruction returned by the central processing unit, the local controller's execution unit outputs the instruction.

[0021] It should be noted that this invention proposes a high-order sliding mode composite control method for speed regulation of electric forklift motors. The core of this method lies in achieving precise speed control through the analysis and processing of motor operating state data. Specifically, firstly, control cycle signals are selected from the motor operating state data. Control cycle signals refer to signals with periodic characteristics during motor operation, such as the periodic changes in motor speed or current signals. These signals reflect the characteristic information of the motor under different operating states. Based on the control cycle signals, control parameter samples are generated. These control parameter samples are a set of parameters extracted from the control cycle signals that can be used for subsequent control model analysis, such as the average value of motor speed and the peak value of current. These parameter samples will serve as input data for subsequent sliding mode control model processing.

[0022] Specifically, the sliding mode control model is a control model based on sliding mode variable structure control theory. Its main controller module is used to extract state variables from the input control parameter samples. State variable extraction refers to extracting data that characterizes the motor speed regulation characteristics from the control parameter samples, such as the motor's current characteristics, torque characteristics, and speed characteristics. These characteristic data reflect the motor's operating state under different working conditions and are key information for achieving precise speed regulation. The main controller module is pre-deployed in the local controller, which is a controller installed on the electric forklift motor drive unit, used to process and execute speed regulation control commands in real time. After extraction, the motor speed regulation characteristic data is sent to the central processing unit (CPU), the core computing unit of the electric forklift control system, used to further process the motor speed regulation characteristic data. The parameter adjustment module in the CPU, corresponding to the sliding mode control model, performs dynamic compensation of the speed regulation parameters based on the motor speed regulation characteristic data. Dynamic compensation of speed regulation parameters refers to adjusting the speed regulation control parameters in real time according to the actual operating state of the motor to adapt to the motor's operating needs under different working conditions. Finally, the central processing unit generates control instructions for motor speed regulation and returns these instructions to the execution unit of the local controller. The execution unit then outputs specific speed control signals based on the control instructions, thereby achieving precise control of the motor speed.

[0023] Preferably, the construction process of the sliding mode control model is as follows: First, a training dataset is acquired, which includes a reference speed control signal, a disturbance speed control signal pair, and corresponding reference feature labels and disturbance feature labels. The reference speed control signal refers to the motor speed control signal under ideal operating conditions, while the disturbance speed control signal refers to the motor speed control signal when there is disturbance or dynamic change. The reference feature labels and disturbance feature labels are used to identify the characteristics of the reference speed control signal and the disturbance speed control signal, respectively. Then, the training samples are input into the main controller module of the initial sliding mode control model to generate a reference feature matrix and a disturbance feature matrix. The reference feature matrix and the disturbance feature matrix are used to describe the feature information of the reference speed control signal and the disturbance speed control signal, respectively. The parameter adjustment module in the initial sliding mode control model includes a global adjustment unit and a local adjustment unit. The global adjustment unit is used to dynamically adjust the steady-state features in the reference feature matrix, and the local adjustment unit is used to dynamically adjust the transient features in the reference feature matrix. In this way, the parameter adjustment module can simultaneously handle the steady-state and transient characteristics of motor speed control, achieving more precise speed control.

[0024] In some embodiments, the following steps are performed before sending the control parameter samples to a pre-built sliding mode control model: The control parameter samples are subjected to noise suppression processing to remove high-frequency interference signals.

[0025] It should be noted that this invention particularly emphasizes the importance of noise suppression when processing control parameter samples. Noise suppression refers to removing high-frequency interference signals from control parameter samples using specific signal processing techniques to improve signal quality and control accuracy. High-frequency interference signals are usually caused by electromagnetic interference during motor operation, sensor noise, or other external factors. These interference signals can seriously affect the accuracy and stability of motor speed control. Noise suppression can effectively reduce the impact of these interferences, thereby providing a more reliable data foundation for subsequent speed control.

[0026] Specifically, noise suppression involves the analysis and processing of control parameter samples. These samples are extracted from motor operating data and contain various characteristic information about motor operation, such as sampled values ​​of parameters like current, speed, and torque. High-frequency interference signals typically manifest as rapidly changing signal components with frequencies much higher than the frequency range of the motor's normal operating signals. Noise suppression can be achieved through various methods, such as using a low-pass filter to remove high-frequency components. A low-pass filter is a signal processing tool that allows low-frequency signals to pass while attenuating high-frequency signals. In practical applications, the cutoff frequency of the low-pass filter can be set according to the frequency characteristics of the motor's operating signals to ensure that useful information from the motor's operating signals is preserved while removing high-frequency interference signals.

[0027] Preferably, the specific implementation steps of noise suppression processing may include the following: First, determine the frequency characteristics of the control parameter samples. Analyze the frequency component distribution in the control parameter samples using Fast Fourier Transform (FFT) or other spectral analysis methods to determine the frequency range of high-frequency interference signals. Then, select a suitable low-pass filter type based on the analysis results, such as a Butterworth filter or a Chebyshev filter, and set its cutoff frequency. The selection of the cutoff frequency should be based on the highest frequency component of the motor's normal operating signal to ensure that the filter does not distort the motor's operating signal. Finally, filter the control parameter samples through the low-pass filter to remove high-frequency interference signals. The control parameter samples after noise suppression processing are cleaner and can more accurately reflect the actual operating state of the motor, providing high-quality input data for subsequent sliding mode control models, thereby improving the performance and reliability of motor speed control.

[0028] In some embodiments, the method further includes: State parameters are detected for each sampling period signal in the motor operating status data to generate a state evaluation result set; The evaluation results that satisfy the preset conditions in the set of state evaluation results are determined, and the sampling signals corresponding to the evaluation results that satisfy the preset conditions are determined as control cycle signals.

[0029] It should be noted that this invention, when processing motor operating status data, particularly emphasizes the importance of state parameter detection for signals in each sampling period. State parameter detection refers to generating a state evaluation result set by analyzing the sampling period signals in the motor operating status data, thereby providing a basis for selecting subsequent control period signals. The state evaluation result set is a set of evaluation results obtained through the analysis of the sampling period signals, used to reflect whether the motor's operating status in different sampling periods meets preset conditions. These preset conditions are set according to the normal operating requirements of the motor, such as whether the motor speed is within the allowable range and whether the current is abnormal. In this way, it can be ensured that the selected control period signal accurately reflects the actual operating status of the motor, thereby improving the accuracy and reliability of speed control.

[0030] Specifically, state parameter detection involves analyzing the sampling period signals in the motor's operating state data. Sampling period signals refer to the motor's operating data collected at regular time intervals during motor operation, such as sampled values ​​of parameters like current, speed, and torque. The purpose of state parameter detection is to determine whether the motor's operating state is normal within each sampling period by analyzing these sampling period signals. The state evaluation result set is obtained by processing the sampling period signals using a series of detection algorithms, which may include threshold judgment, trend analysis, etc. For example, setting a current threshold can determine if the motor is overloaded, or analyzing the trend of speed changes can determine if the motor is in a stable operating state. Evaluation results that meet preset conditions refer to those state evaluation results that conform to the requirements for normal motor operation, such as the motor speed being within the allowable range and the current not exceeding the rated value. The sampling signals corresponding to these evaluation results will be determined as control period signals for subsequent speed control.

[0031] Preferably, the specific implementation steps for state parameter detection can be further refined. First, the sampling period signals in the motor operating state data are determined. These signals typically include sampled values ​​of parameters such as motor current, speed, and torque. Then, preset conditions are set according to the motor's operating requirements, such as current thresholds and speed ranges. Next, each sampling period signal is analyzed using a detection algorithm to generate a state evaluation result. For example, a sliding window algorithm can be used to smooth the speed signal, and then its average value and fluctuation range are calculated to determine whether the preset speed range conditions are met. For the current signal, a current threshold can be set; when the sampled current exceeds this threshold, it is determined that the motor is overloaded. Finally, the sampling signals corresponding to the state evaluation results that meet the preset conditions are determined as control period signals. These control period signals will serve as the basis for subsequent speed control, ensuring that the motor can achieve precise speed control under different operating conditions.

[0032] In some embodiments, the method further includes: Fluctuation detection is performed on the motor operating status data to determine the dynamic disturbance component in the status data; The detected dynamic disturbance components are state tracked, wherein the marked dynamic disturbance components are tracked to obtain a disturbance identifier set; Determine the fluctuation range of the detected dynamic disturbance components in the operating state data to obtain the disturbance fluctuation boundary set; Based on the disturbance identifier set and the disturbance fluctuation boundary set, state parameters are detected for the sampled signals corresponding to each detected dynamic disturbance component to generate a state evaluation result set.

[0033] It should be noted that this invention further incorporates fluctuation detection and dynamic disturbance component state tracking steps when processing motor operating status data. Fluctuation detection refers to identifying dynamic disturbance components within the motor operating status data through analysis. These disturbance components may be caused by load changes, power grid fluctuations, or other external interferences. Dynamic disturbance component state tracking involves marking and tracking these disturbance components to more accurately address their impact on motor speed regulation. By determining the fluctuation range of the dynamic disturbance components, i.e., the disturbance fluctuation boundary set, the amplitude and impact range of the disturbance can be better understood. Based on the disturbance identifier set and the disturbance fluctuation boundary set, state parameter detection is performed on the sampled signal. The generated state evaluation result set can more comprehensively reflect the motor's operating status under different operating conditions, thereby providing a more accurate basis for speed control.

[0034] Specifically, fluctuation detection and dynamic disturbance component state tracking involve several key concepts. Dynamic disturbance components refer to the abnormal fluctuations in motor operating status data caused by external interference or internal changes. These disturbances may be transient or continuous, manifesting as abnormal changes in parameters such as current, speed, or torque. The disturbance identifier set is the result of marking the detected dynamic disturbance components, with each disturbance identifier corresponding to a specific disturbance event. The disturbance fluctuation boundary set defines the fluctuation range of each disturbance component, describing the amplitude and duration of the disturbance. State parameter detection is a process of further analyzing the sampled signal, evaluating signal quality and reliability by calculating parameters such as signal-to-noise ratio and interference suppression ratio. The operating condition mode information set is identified based on load characteristics and describes the motor's operating status under different load conditions, such as no-load, half-load, or full-load. The generation of these parameters and information sets provides rich data support for subsequent speed control.

[0035] Preferably, the specific implementation steps for fluctuation detection and dynamic disturbance component state tracking can be further refined. First, fluctuation detection is performed on the motor operating state data using signal processing algorithms (such as wavelet transform or adaptive filtering) to identify dynamic disturbance components. Then, each detected disturbance component is marked to form a disturbance identifier set. Next, the disturbance component is state-tracked using a tracking algorithm (such as a Kalman filter) to determine its fluctuation range and generate a disturbance fluctuation boundary set. Based on this, state parameters are detected on the sampled signal corresponding to each disturbance identifier, and the signal-to-noise ratio and interference suppression ratio are calculated to evaluate the signal quality. Simultaneously, load characteristics are identified on the sampled signal corresponding to each disturbance fluctuation boundary to generate a working condition mode information set, clarifying the motor's operating conditions under different disturbances. Finally, by combining the signal-to-noise ratio, interference suppression ratio, and working condition mode information, a state evaluation result set is generated to provide accurate data support for subsequent speed control.

[0036] In some embodiments, the method further includes: In response to the determination that there is no evaluation result in the set of state evaluation results that meets the preset conditions, the control cycle is reselected for the motor operating state data collected by the sensor.

[0037] It should be noted that this invention introduces a feedback mechanism when processing motor operating status data. Specifically, if no evaluation result in the status evaluation result set meets the preset conditions, the control cycle for the motor operating status data is reselected. This mechanism ensures that the selection of the control cycle signal is always based on the actual operating state of the motor, avoiding speed control failure due to erroneous or unmet signals. The status evaluation result set is generated by detecting the status parameters of the sampled cycle signal and is used to determine whether the motor operating state meets the preset speed control requirements. The preset conditions are set according to the normal operating parameter range of the motor, such as whether the speed is within the allowable range and whether the current exceeds the rated value. Through this feedback mechanism, the selection strategy of the control cycle signal can be dynamically adjusted to adapt to changes in the motor operating state.

[0038] Specifically, the state evaluation result set refers to a set of evaluation results obtained through state parameter detection, with each evaluation result corresponding to the state of a sampling period signal. Preset conditions refer to the parameter ranges or conditions that the motor should meet during normal operation, such as current not exceeding the rated value and speed within the set range. When there are no evaluation results in the state evaluation result set that meet these preset conditions, it indicates that the currently selected control period signal cannot reflect the motor's true operating state or does not meet the speed regulation requirements. Control period selection refers to choosing a suitable signal period from the motor's operating state data as the basis for subsequent speed regulation control. This process needs to be dynamically adjusted according to the actual operating conditions of the motor to ensure that the selected signal can accurately reflect the motor's operating state. Re-selecting the control period signal means that the motor's operating state data needs to be re-analyzed to find a signal period that meets the preset conditions.

[0039] Preferably, the specific implementation steps for reselecting the control cycle signal can be further refined. First, when no evaluation result meeting the preset conditions is found in the state evaluation result set, the reselection mechanism is triggered. At this time, the motor operating state data needs to be re-analyzed, which can be done by increasing the sampling frequency or adjusting the sampling time window to obtain more detailed operating data. Next, the re-acquired data is used to detect state parameters, and a new state evaluation result set is generated. This process may require adjusting the parameters of the detection algorithm, such as threshold or filter parameters, to adapt to changes in the motor operating state. Finally, the control cycle signal is re-determined based on the new state evaluation result set. If a signal meeting the conditions still cannot be found, the preset conditions can be further adjusted or the detection algorithm optimized to ensure that a suitable control cycle signal can be selected in the end, thereby providing reliable data support for motor speed control.

[0040] In some embodiments, the step of performing state parameter detection on the sampled signals corresponding to each detected dynamic disturbance component based on the disturbance identifier set and the disturbance fluctuation boundary set to generate a state assessment result set includes: Based on the disturbance fluctuation boundary set, determine the signal-to-noise ratio set and interference suppression ratio set of the sampled signals corresponding to each identifier in the disturbance identifier set; Load characteristics are identified for the sampled signals corresponding to each fluctuation boundary in the disturbance fluctuation boundary set to generate a set of operating condition mode information. Each operating condition mode information in the set of operating condition mode information corresponds to an operating state. Each operating condition mode information includes a running condition label of the motor relative to the drive device in the control cycle signal. The running condition label includes at least one of the following: no-load operating condition label, half-load operating condition label, and full-load operating condition label. Based on the signal-to-noise ratio set, the interference suppression ratio set, and the operating condition mode information set, determine the state assessment result set corresponding to each disturbance identifier.

[0041] It should be noted that this invention proposes a state parameter detection method based on a disturbance fluctuation boundary set and a disturbance identifier set when processing the sampled signal corresponding to dynamic disturbance components. This method generates a state evaluation result set by comprehensively considering the signal-to-noise ratio (SNR), interference rejection ratio (ISR), and operating mode information, thereby providing a more comprehensive assessment of the motor's operating state. The signal-to-noise ratio (SNR) and interference rejection ratio (ISR) are important parameters for measuring signal quality, reflecting the ratio of effective components to noise components in the signal and the ability to suppress interference, respectively. The operating mode information is obtained by identifying the load characteristics of the sampled signal and is used to describe the characteristics of the motor under different operating conditions, such as no-load, half-load, or full-load. In this way, the operating state of the motor under dynamic disturbances can be evaluated more accurately, providing a more accurate basis for subsequent speed control.

[0042] Specifically, the disturbance fluctuation boundary set refers to the fluctuation range of dynamic disturbance components, defining the amplitude and duration of the disturbance. The disturbance identifier set is the result of labeling detected dynamic disturbance components, with each identifier corresponding to a specific disturbance event. The signal-to-noise ratio (SNR) is the ratio of signal power to noise power, used to measure signal quality and reliability. The interference rejection ratio (ISR) is a parameter measuring the system's ability to suppress interference signals, reflecting the degree to which interference components are reduced in the processed signal. The operating condition mode information set is obtained by identifying the load characteristics of the sampled signal; it includes labels for the motor's operating status under different load conditions, such as no-load, half-load, and full-load labels. These labels describe the motor's operating condition relative to the drive unit, whether it is no-load, half-load, or full-load. By combining these parameters and information, a state assessment result set can be generated, thereby providing a more comprehensive evaluation of the motor's operating status.

[0043] Preferably, the specific implementation steps for state parameter detection based on the disturbance fluctuation boundary set and disturbance identifier set can be further refined. First, based on the disturbance fluctuation boundary set, the signal-to-noise ratio (SNR) and interference rejection ratio (ISR) of the sampled signal corresponding to each disturbance identifier are determined. This can be achieved by calculating the power spectral density of the sampled signal, using the ratio of signal power to noise power as the SNR, and simultaneously calculating the interference rejection ratio by comparing the signal power before and after processing. Next, load characteristics are identified for the sampled signal corresponding to each fluctuation boundary in the disturbance fluctuation boundary set, generating a set of operating condition mode information. Load characteristic identification can be achieved by analyzing the changing trends of parameters such as motor current, speed, and torque; for example, the magnitude of the current can be used to determine whether the motor is in an unloaded or fully loaded state. Finally, combining the signal-to-noise ratio, interference rejection ratio, and operating condition mode information, a state evaluation result set is generated. Each evaluation result in the state evaluation result set reflects the quality of the sampled signal under specific disturbance conditions, the interference rejection effect, and the operating condition of the motor, providing comprehensive data support for subsequent speed control.

[0044] In some embodiments, the method further includes: Determine the signal-to-noise ratio (SNR) of the sampled signal corresponding to each identifier in the disturbance identifier set to obtain the SNR set; The interference suppression ratio of the sampled signal corresponding to each identifier in the disturbance identifier set is determined to obtain the interference suppression ratio set.

[0045] It should be noted that this invention further refines the analysis process of the sampled signals corresponding to each identifier in the disturbance identifier set, particularly in determining the signal-to-noise ratio (SNR) and interference rejection ratio (ISR). SNR and ISR are important indicators for measuring signal quality and system anti-interference capability. By calculating these parameters separately, the quality of the sampled signal and the system's interference suppression effect can be evaluated more accurately. SNR reflects the ratio of effective components to noise components in the signal, while ISR measures the degree to which interference components are reduced in the processed signal. The calculation results of these two parameters will provide crucial data support for subsequent state assessment, thereby more accurately reflecting the operating state of the motor under dynamic disturbance conditions.

[0046] Specifically, the disturbance identifier set refers to the result of labeling detected dynamic disturbance components, with each identifier corresponding to a specific disturbance event. The sampled signal refers to the signal extracted from the motor operating status data, used for subsequent analysis and processing. The signal-to-noise ratio (SNR) is the ratio of signal power to noise power, typically determined by calculating the signal's power spectral density. The interference rejection ratio (ISR) is a parameter measuring the system's ability to suppress interference signals, calculated by comparing the signal power before and after processing. In practical applications, the SNR can be calculated by performing a Fourier transform on the sampled signal and analyzing its spectral characteristics. The interference rejection ratio can be evaluated by comparing the signal power before and after processing; for example, it can be calculated as the ratio of the signal power after processing with a low-pass filter to the original signal power. The calculation results of these parameters provide important basis for subsequent state assessment, helping to more accurately determine the motor's operating status.

[0047] Preferably, the specific implementation steps for determining the signal-to-noise ratio (SNR) and interference rejection ratio (ISR) can be further refined. First, for each disturbance flag, the sampled signal's spectral characteristics are analyzed using Fourier transform to calculate the signal's power spectral density. Then, the ratio of signal power to noise power is calculated based on the power spectral density to obtain the SNR. Next, noise suppression processing is applied to the sampled signal, for example, using a low-pass filter to remove high-frequency interference signals. After processing, the power spectral density is calculated again, and the ratio of the processed signal power to the original signal power is calculated to obtain the ISR. Finally, the calculated SNR and ISR are stored in their respective sets to provide data support for subsequent state assessment. In this way, the quality of the sampled signal and the system's anti-interference capability can be evaluated more accurately, thus providing a more reliable basis for motor speed control.

[0048] In some embodiments, the sliding mode control model is generated through training using a preset parameter tuning method; wherein, the preset parameter tuning method includes: Obtain a training dataset, wherein the training samples in the training dataset include a reference speed control signal, a perturbation speed control signal pair, and corresponding reference feature labels and perturbation feature labels; Training samples are selected from the training dataset and input into the main controller module of the initial sliding mode control model to generate a reference feature matrix and a disturbance feature matrix. The parameters of the main controller module in the initial sliding mode control model remain fixed. The parameter adjustment module in the initial sliding mode control model includes a global adjustment unit and a local adjustment unit, and the parameter adjustment module corresponds to a single control loop. The reference feature matrix is ​​input into the parameter adjustment module of the initial sliding mode control model, and a reference prediction label is output. The local adjustment unit in the parameter adjustment module is used to dynamically adjust the transient features in the reference feature matrix. The disturbance feature matrix is ​​input into the parameter adjustment module of the initial sliding mode control model, and the disturbance prediction label is output. The global adjustment unit in the parameter adjustment module is used to dynamically adjust the steady-state features in the reference feature matrix. An adjustment error value is generated based on the obtained reference prediction label, the disturbance prediction label, the reference feature label, and the disturbance feature label; The control parameters in the parameter adjustment module are adjusted according to the adjustment error value.

[0049] It should be noted that this invention proposes a method for constructing a sliding mode control model. This method uses a training dataset to tune the parameters of an initial sliding mode control model, generating a high-order sliding mode composite control model capable of adapting to complex operating conditions. The sliding mode control model is based on sliding mode variable structure control theory. Its core lies in designing sliding surfaces and parameter adjustment modules to achieve rapid and precise control of motor speed regulation. The training dataset includes a reference speed regulation signal, a disturbance speed regulation signal pair, and corresponding reference feature labels and disturbance feature labels. This data is used to train the model to identify the speed regulation signal characteristics under different operating conditions. Through the global and local adjustment units in the parameter adjustment module, the model can dynamically compensate for the speed regulation parameters, thereby improving the adaptability and stability of the speed regulation control.

[0050] Specifically, the main controller module of the sliding mode control model is the core of the model. It extracts state variables from the input control parameter samples to generate a reference feature matrix and a disturbance feature matrix. The reference and disturbance feature matrices describe the characteristic information of the reference speed control signal and the disturbance speed control signal, respectively. The parameter tuning module includes a global tuning unit and a local tuning unit. The global tuning unit dynamically adjusts the steady-state characteristics in the reference feature matrix, while the local tuning unit dynamically adjusts the transient characteristics. The reference prediction label and disturbance prediction label are outputs obtained by inputting the feature matrix into the parameter tuning module and are used to evaluate the model's predictive performance. The tuning error value is calculated by comparing the predicted label with the actual feature label and is used to adjust the control parameters in the parameter tuning module to optimize model performance.

[0051] Preferably, the construction steps of the sliding mode control model can be further refined. First, a training dataset containing a reference speed control signal and a disturbance speed control signal is collected. These signals reflect the operating state of the motor under different operating conditions. Then, the training samples are input into the main controller module of the initial sliding mode control model to generate a reference feature matrix and a disturbance feature matrix. Next, the reference feature matrix is ​​input into the local adjustment unit of the parameter adjustment module, outputting a reference prediction label; the disturbance feature matrix is ​​input into the global adjustment unit, outputting a disturbance prediction label. By comparing the predicted label with the actual label, the adjustment error value is calculated. Finally, the control parameters in the parameter adjustment module are adjusted according to the adjustment error value to optimize the model performance. For example, the parameters can be adjusted using gradient descent or other optimization algorithms to minimize the adjustment error value, thereby improving the model's adaptability to different operating conditions and speed control accuracy.

[0052] In some embodiments, the training dataset is generated through the following steps: Receive the operator's filtering and removal operations on the displayed control parameters and centralized speed regulation parameters; The speed regulation parameters corresponding to the filter removal operation are determined as disturbance speed regulation signals to obtain a disturbance signal group, wherein the disturbance speed regulation signal is the abnormal disturbance signal eliminated by the operator; The tracking identifier corresponding to each disturbance speed control signal in the disturbance signal group is determined as the disturbance feature label, thus obtaining the disturbance label group; Receives the operator's parameter integration operation on the displayed control parameters and centralized speed regulation parameters; The tracking identifier corresponding to the parameter integration operation is adjusted to the same identifier, and each speed regulation parameter in the control parameter set is determined as a reference speed regulation signal to obtain a reference signal group; Each tracking identifier corresponding to a reference speed control signal in the reference signal group is determined as a reference feature label to obtain a reference label group; The reference signal group, reference label group, perturbation signal group, and perturbation label group are combined to train the dataset.

[0053] It should be noted that this invention further elaborates on the method for generating the training dataset. This method constructs the training dataset through the operator's filtering and removal operations and parameter integration operations on the control parameter set. This method can fully utilize the operator's experience to classify and label abnormal disturbance signals and normal speed regulation signals in actual operation, thereby generating a high-quality training dataset. The construction of the training dataset is the foundation for the training of the sliding mode control model. The dataset generated in this way can better reflect the operating conditions of the motor in actual operation, providing strong support for model training and optimization.

[0054] Specifically, the generation of the training dataset involves several key concepts. The filtering removal operation refers to the process by which the operator excludes abnormal disturbance signals from the control parameter set. These abnormal disturbance signals are usually caused by interference or faults during motor operation. Disturbance speed control signals refer to these excluded abnormal signals; they are labeled with disturbance feature labels to represent the abnormal characteristics of the signals. The parameter integration operation refers to the process by which the operator integrates the normal speed control signals from the control parameter set. These normal speed control signals are labeled with reference feature labels to represent the normal characteristics of the signals. Reference speed control signals are the integrated normal speed control signals, which, together with the reference feature labels, constitute the reference signal group in the training dataset. In this way, the training dataset can include speed control signals under both normal and abnormal operating conditions, providing comprehensive data support for model training.

[0055] Preferably, the steps for generating the training dataset can be further refined. First, the operator observes the speed regulation parameters in the control parameter set through the monitoring system, identifies and performs filtering removal operations to remove abnormal disturbance signals from the dataset and label them as disturbance feature labels. Next, the operator performs parameter integration operations on the remaining normal speed regulation signals and labels these signals as reference feature labels. Then, the reference speed regulation signals and disturbance speed regulation signals are combined into reference signal groups and disturbance signal groups, respectively, and the corresponding feature labels are combined into reference label groups and disturbance label groups. Finally, these signal groups and labels are combined to form a complete training dataset. For example, the operator can identify abnormal signals by setting a threshold; when the speed regulation parameter exceeds the threshold, it is labeled as a disturbance signal. For normal signals, statistical analysis is used for integration to ensure the representativeness and consistency of the reference signals. The training dataset generated in this way can more accurately reflect various operating conditions of the motor, providing a high-quality data foundation for training the sliding mode control model.

[0056] In some embodiments, the state quantity extraction is used to extract multiple operating characteristics of the motor, including at least one of the following: current characteristics, torque characteristics, and speed characteristics, for multi-parameter fusion speed control.

[0057] It should be noted that this invention emphasizes the function of the sliding mode control model in state variable extraction, particularly its ability to extract various operating characteristics of the motor, including current, torque, and speed characteristics, to achieve multi-parameter fusion-based speed control. State variable extraction refers to extracting key information characterizing the motor's operating state from the motor's operating state data; this information is crucial for achieving precise speed control. Through multi-parameter fusion, the sliding mode control model can comprehensively consider multiple key factors in motor operation, thereby improving the accuracy and adaptability of speed control and enabling it to better cope with complex operating conditions.

[0058] Specifically, state variable extraction refers to extracting key parameters reflecting the motor's operating state from motor operating state data. Current characteristics refer to information such as the magnitude and trend of the current during motor operation, including peak value, average value, and fluctuation range. Torque characteristics refer to the magnitude and variation of the motor's output torque, such as torque stability and dynamic response characteristics. Speed ​​characteristics refer to the value of the motor's speed and its trend, such as speed stability, acceleration, and deceleration performance. These characteristic parameters comprehensively reflect the motor's operating state, providing important basis for speed control. Multi-parameter fusion speed control refers to comprehensively considering multiple characteristic parameters, analyzing and processing these parameters through algorithms, thereby achieving precise control of motor speed. This method can better adapt to the motor's operating needs under different conditions, improving the flexibility and stability of speed control.

[0059] Preferably, the specific implementation steps for extracting state variables can be further refined. First, motor operating state data, including real-time values ​​of parameters such as current, torque, and speed, are collected through sensors. Then, the collected data is preprocessed, such as removing noise and filling in missing values, to improve data quality. Next, signal processing algorithms are used to extract current, torque, and speed features. For example, current features can be extracted by calculating the mean and standard deviation of the current signal, torque features by analyzing the rate of change of the torque signal, and speed features by calculating the frequency and amplitude of the speed signal. Finally, these feature parameters are input into the sliding mode control model. The model generates speed control commands by comprehensively analyzing these parameters, achieving multi-parameter fusion speed control. For example, when an abnormal increase in current is detected, the model can determine that the motor may be in an overload state and adjust the speed control parameters accordingly to reduce the motor load; when the speed fluctuates greatly, the model can stabilize the motor operation by adjusting the speed feature parameters. In this way, the sliding mode control model can achieve comprehensive monitoring and precise control of the motor operating state, improving the performance and reliability of motor speed regulation.

[0060] The above-described embodiments of the present invention have the following beneficial effects: The present invention can improve the control performance of the electric forklift motor speed control system. Through intelligent selection of control cycle signals and noise suppression processing, the accuracy of control parameters can be ensured. The collaborative working mechanism of the main controller module and the central processing unit using a sliding mode control model can achieve accurate extraction and dynamic compensation of speed control characteristics, thereby optimizing the speed control command generation process. Combined with state parameter detection and dynamic disturbance component tracking and compensation mechanisms, the system's anti-interference capability under complex working conditions can be enhanced. Furthermore, through signal-to-noise ratio analysis and load characteristic identification, it can adapt to speed control requirements under different load conditions.

[0061] By training a model using a pre-defined parameter tuning method, an intelligent control system with both global and local adjustment capabilities can be established, enabling the speed regulation process to achieve both steady-state accuracy and transient response performance. The operator-interactive training data generation method ensures that the system learns the optimal speed regulation parameter characteristics. A multi-parameter fusion speed regulation strategy can integrate key characteristics such as current, torque, and speed to achieve high-precision control of the motor drive device. This composite control method can simultaneously consider response speed, control accuracy, and operational stability.

[0062] Furthermore, the storage medium in the embodiments of this application stores program instructions capable of implementing all the above methods. These program instructions can be stored in the storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0063] The above description is merely an explanation of some preferred embodiments of the present invention and the technical principles employed. Those skilled in the art should understand that the scope of the invention as described in the embodiments of the present invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A high-order sliding mode composite control method for speed regulation of electric forklift motors, applied to motor drive devices, characterized in that, The method includes: Select the control cycle signal from the motor operating status data, and generate control parameter samples from the control cycle signal; The control parameter samples are sent to the main controller module in the pre-built sliding mode control model for state variable extraction to obtain motor speed regulation feature data. The main controller module of the sliding mode control model is pre-deployed in the local controller. The motor speed regulation characteristic data is sent to the central processing unit so that the parameter adjustment module in the central processing unit corresponding to the sliding mode control model can perform dynamic compensation of the speed regulation parameters and obtain the motor speed regulation control command. In response to the control command returned by the central processing unit, the execution unit of the local controller outputs the command.

2. The method according to claim 1, characterized in that, Before sending the control parameter samples to the pre-built sliding mode control model, perform the following steps: The control parameter samples are subjected to noise suppression processing to remove high-frequency interference signals.

3. The method according to claim 1, characterized in that, The method further includes: State parameters are detected for each sampling period signal in the motor operating status data to generate a state evaluation result set; The evaluation results that satisfy the preset conditions in the set of state evaluation results are determined, and the sampling signals corresponding to the evaluation results that satisfy the preset conditions are determined as control cycle signals.

4. The method according to any one of claims 1 or 3, characterized in that, The method further includes: Fluctuation detection is performed on the motor operating status data to determine the dynamic disturbance component in the status data; The detected dynamic disturbance components are state tracked, wherein the marked dynamic disturbance components are tracked to obtain a disturbance identifier set; Determine the fluctuation range of the detected dynamic disturbance components in the operating state data to obtain the disturbance fluctuation boundary set; Based on the disturbance identifier set and the disturbance fluctuation boundary set, state parameters are detected for the sampled signals corresponding to each detected dynamic disturbance component to generate a state evaluation result set.

5. The method according to claim 3, characterized in that, The method further includes: In response to the determination that there is no evaluation result that meets the preset conditions in the set of state evaluation results, the control cycle is reselected for the motor operating state data collected by the sensor.

6. The method according to claim 4, characterized in that, The step of performing state parameter detection on the sampled signals corresponding to each detected dynamic disturbance component based on the disturbance identifier set and the disturbance fluctuation boundary set to generate a state evaluation result set includes: Based on the disturbance fluctuation boundary set, determine the signal-to-noise ratio set and interference suppression ratio set of the sampled signals corresponding to each identifier in the disturbance identifier set; Load characteristics are identified for the sampled signals corresponding to each fluctuation boundary in the disturbance fluctuation boundary set to generate a set of operating condition mode information. Each operating condition mode information in the set of operating condition mode information corresponds to an operating state. Each operating condition mode information includes a running condition label of the motor relative to the drive device in the control cycle signal. The running condition label includes at least one of the following: no-load operating condition label, half-load operating condition label, and full-load operating condition label. Based on the signal-to-noise ratio set, the interference suppression ratio set, and the operating condition mode information set, determine the state assessment result set corresponding to each disturbance identifier.

7. The method according to claim 6, characterized in that, The method further includes: Determine the signal-to-noise ratio (SNR) of the sampled signal corresponding to each identifier in the disturbance identifier set to obtain the SNR set; The interference suppression ratio of the sampled signal corresponding to each identifier in the disturbance identifier set is determined to obtain the interference suppression ratio set.

8. The method according to claim 1, characterized in that, The sliding mode control model is generated through training using a preset parameter tuning method; wherein, the preset parameter tuning method includes: Obtain a training dataset, wherein the training samples in the training dataset include a reference speed control signal, a perturbation speed control signal pair, and corresponding reference feature labels and perturbation feature labels; Training samples are selected from the training dataset and input into the main controller module of the initial sliding mode control model to generate a reference feature matrix and a disturbance feature matrix. The parameters of the main controller module in the initial sliding mode control model remain fixed. The parameter adjustment module in the initial sliding mode control model includes a global adjustment unit and a local adjustment unit, and the parameter adjustment module corresponds to a single control loop. The reference feature matrix is ​​input into the parameter adjustment module of the initial sliding mode control model, and a reference prediction label is output. The local adjustment unit in the parameter adjustment module is used to dynamically adjust the transient features in the reference feature matrix. The disturbance feature matrix is ​​input into the parameter adjustment module of the initial sliding mode control model, and the disturbance prediction label is output. The global adjustment unit in the parameter adjustment module is used to dynamically adjust the steady-state features in the reference feature matrix. An adjustment error value is generated based on the obtained reference prediction label, the disturbance prediction label, the reference feature label, and the disturbance feature label; The control parameters in the parameter adjustment module are adjusted according to the adjustment error value.

9. The method according to claim 8, characterized in that, The training dataset is generated through the following steps: Receive the operator's filtering and removal operations on the displayed control parameters and centralized speed regulation parameters; The speed regulation parameters corresponding to the filter removal operation are determined as disturbance speed regulation signals to obtain a disturbance signal group, wherein the disturbance speed regulation signal is the abnormal disturbance signal eliminated by the operator; The tracking identifier corresponding to each disturbance speed control signal in the disturbance signal group is determined as the disturbance feature label, thus obtaining the disturbance label group; Receives the operator's parameter integration operation on the displayed control parameters and centralized speed regulation parameters; The tracking identifier corresponding to the parameter integration operation is adjusted to the same identifier, and each speed regulation parameter in the control parameter set is determined as a reference speed regulation signal to obtain a reference signal group; Each tracking identifier corresponding to a reference speed control signal in the reference signal group is determined as a reference feature label to obtain a reference label group; The reference signal group, reference label group, perturbation signal group, and perturbation label group are combined to train the dataset.

10. The method according to claim 1, characterized in that, The state quantity extraction is used to extract multiple operating characteristics of the motor, including at least one of the following: current characteristics, torque characteristics, and speed characteristics, in order to perform multi-parameter fusion speed control.

Images