181 results about "Self-tuning" patented technology

The invention provides a magnesium alloy electric drive main shell mold machining precision control method and system, and belongs to the field of precision numerical control machining. The method comprises the steps that dynamic milling force, key point temperature and position signals of all shafts are synchronously collected through a multi-source sensor; a recursive least square method is adopted to identify the dynamic rigidity and damping coefficient of the tool-workpiece system on line, and the thermal deformation drift distance is calculated in combination with a temperature signal; predicting a three-dimensional deformation error vector in real time based on the dynamic model, thermal deformation and geometric errors, and constructing a space compensation field; macro motion compensation is achieved by modifying numerical control program coordinate points, and meanwhile high-frequency micro-amplitude compensation is conducted through a spindle tail end fast tool servo system. And establishing an adaptive disturbance observer to perform online estimation on unmodeled disturbance and feed-forward compensation, and realizing online self-tuning of model parameters in combination with in-situ measurement feedback. Real-time sensing, full-band dynamic compensation and closed-loop self-adaptive control of multi-source errors are achieved, and the machining precision and long-term stability of the mold are remarkably improved.

The invention relates to the technical field of data processing, and discloses an automatic control platform operation data management method. The method comprises the steps of collecting industrial equipment data through a field bus, storing the industrial equipment data into a database in a classified mode and establishing an index table, extracting a control loop to construct a DCS model, generating a process abnormality diagnosis report, calculating control parameters by using a self-tuning algorithm and outputting a control instruction, optimizing a process formula based on an implementation effect and constructing a recommendation knowledge base. According to the intelligent data management method, the process abnormality is accurately diagnosed, the control parameters are automatically optimized, and the process knowledge is continuously accumulated, so that the control precision, the diagnosis efficiency, the parameter optimization capability and the knowledge reuse level of the industrial production process are improved.

The invention provides a robust control automatic setting method for a constant-pressure water supply system, and the method comprises the steps: obtaining a system working condition in real time, and extracting multi-dimensional state parameters including real-time flow, pressure deviation, current deviation and power deviation; the current load working condition is judged according to the pressure deviation, disturbance characteristics are analyzed by integrating all parameters, and the disturbance grade and type are determined. On the basis, robust control parameters are automatically set in combination with real-time working conditions, load conditions and disturbance characteristics of the system. And finally, performing multi-stage cooperative control on the system by using the set parameters, so that the constant-pressure water supply system is automatically set. According to the robust control automatic setting method for the constant-pressure water supply system, load working conditions and disturbance characteristics are recognized based on multi-dimensional state parameters, robust control parameters are self-set in a targeted mode, and automatic setting of the constant-pressure water supply system is achieved through multi-stage cooperative control. Therefore, the intelligent level of the constant-pressure water supply system and the adaptability in different operation environments are effectively improved.

The invention relates to the technical field of intelligent gate valve control, in particular to an intelligent induction type automatic adjusting gate valve system.An analysis module of a calibration unit in the intelligent induction type automatic adjusting gate valve system recognizes signal distortion by comparing historical working condition databases, extracts the viscosity change trend and deduces the impurity accumulation rate; a dynamic compensation factor is generated by an offset calculation model subjected to multi-source transfer learning training, the signal amplitude and phase are corrected by a compensation module through dual-channel closed-loop correction, and compensation logic is optimized by combining distortion residual detection and model online incremental learning; a PID controller of the control unit adopts a parameter self-tuning strategy, dynamically adjusts parameters according to the viscosity acceleration, the impurity accumulation rate and the synchronous error, generates a gate valve opening instruction to drive an execution mechanism, counteracts signal distortion caused by viscosity change and impurity accumulation, improves the adjusting precision and guarantees stable and efficient fluid conveying.

The invention discloses an intelligent analysis and management method and system for an integrated controller, relates to the field of integrated control, and aims to complete complex air conditioning system identification model training and off-line optimization of an optimal PID parameter strategy by using historical data at a cloud end with sufficient computing power. And generating an expert strategy library containing various working conditions and corresponding optimal control parameters thereof. Then, a lightweight proxy model with small calculation amount and high reasoning speed is trained based on the strategy library; the proxy model is deployed on a resource-constrained edge controller. Therefore, the edge end does not need to execute complex online optimization calculation, and only needs to input the real-time working condition data into the agent model, so that the current optimal PID parameter can be quickly deduced. According to the cloud training and edge reasoning architecture, online, real-time and intelligent self-tuning of controller parameters is realized, and a gap between an advanced algorithm and industrial landing is effectively filled up.

The invention discloses a cable extrusion temperature control optimization method based on an adaptive control algorithm, and the method comprises the following steps: S1, collecting and preprocessing multi-source process data, and generating a multivariable temperature control input data set; s2, configuring a self-tuning PID (Proportion Integration Differentiation) controller, and setting an initial PID parameter; s3, performing coevolution optimization on PID parameters of each heating section to obtain an optimal multi-section PID parameter combination; s4, distributing an optimal PID parameter, and adaptively adjusting the parameter in combination with the input data set; s5, implementing closed-loop temperature regulation, monitoring deviation, coordinating section management, and collecting temperature control, energy consumption and process data; and S6, periodically feeding back temperature control and energy consumption data, optimizing parameters, dynamically adjusting the parameters, and resetting the parameters when the parameters are abnormal. According to the invention, intelligent self-adaptive optimization control of multi-section temperature in the cable extrusion process is realized, and the temperature control precision, the energy efficiency and the product quality stability are remarkably improved.

The invention discloses a high-voltage circuit breaker short-circuit breaking direct test loop parameter self-tuning method, and belongs to the technical field of power system high-voltage electrical equipment tests. According to the method, an equivalent test loop is firstly established, mathematical modeling is carried out, in order to facilitate subsequent optimization, test loop elements are subjected to per unit, and the model is revised; and establishing a conversion relation formula between the dimensionless parameters and the dimensional parameters. Taking a dimensionless parameter as a decision variable, taking a differential equation corresponding to the model as a constraint condition, taking the sum of absolute values of differences between an obtained value and a standard value as a value function, and calculating a minimum value of the value function by applying a third-generation genetic algorithm; and finally, performing simulation verification on an optimization result. According to the invention, the working efficiency can be greatly improved, and more circuit breaker test tasks can be carried out within the same time.

The invention relates to an automatic instrument parameter self-tuning method and device based on deep learning. According to the method, real-time operation data of an instrument is collected through a multi-source sensor, time sequence alignment is carried out to form a multi-dimensional data tensor, and then local time sequence features and a long-term dependency relationship are respectively captured by using a convolutional layer and a bidirectional long-short-term memory network in a depth feature extraction network; the two types of features are fused through an attention mechanism to form a depth feature vector, on this basis, the vector is mapped into a working condition membership degree vector by adopting a differential fuzzy clustering method, and finally, the working condition membership degree is non-linearly mapped into a PID parameter adjustment amount through a multi-layer perceptron network, and the PID parameter adjustment amount is superposed to a basic parameter to realize parameter self-tuning. Therefore, under the condition that manual intervention is not needed, an automatic instrument can automatically adapt to complex and changeable operation conditions, the control precision and the system stability are remarkably improved, and the problem of adaptability of traditional PID control in a time-varying nonlinear system is effectively solved.

The invention discloses a solid powder intelligent weighing system based on fuzzy adaptive PID. The system comprises a material transfer module, a weighing unit, a material information identification module and an intelligent control unit. The material transfer module realizes automatic transfer and positioning of the weighing container; the weighing unit comprises a weighing container, a high-precision sensor and a discharging module, and the discharging module is provided with a material bin and a feeding valve mechanism; the information identification module is used for automatically identifying and inputting material information; the intelligent control unit is internally provided with a fuzzy self-adaptive PID controller, receives weight and material information, identifies valve-flow model parameters on line based on a recursive least square method and performs self-tuning, dynamically adjusts PID parameters according to a fuzzy rule, and outputs an instruction to realize three-stage control of rapid blanking, fuzzy fine adding and inching compensation. Through a parameter self-tuning and segmentation strategy, the method is adaptive to various material characteristics, the efficiency is improved and the static error is eliminated under the condition of ensuring high precision, and safe and traceable intelligent weighing is realized by relying on full-process automation and information tracing.

The invention discloses a multi-device flexible parameter self-tuning method based on transfer learning, and belongs to the technical field of multi-device parameter tuning, and the method comprises the following steps: S1, data preprocessing and feature screening; s2, aligning the feature space of the target equipment; s3, carrying out transfer learning model initialization and knowledge transfer; s4, performing online adaptive parameter optimization; and S5, multi-device parameter self-tuning circulation and model updating. According to the multi-device flexible parameter self-tuning method based on transfer learning, source device knowledge is reused through transfer learning, data dependence of target devices is reduced, and the cross-device transfer effect is improved; and convergence is accelerated and initial parameter sensitivity is reduced through an optimization strategy, so that efficient self-tuning of multi-device parameters is realized.

The invention relates to the technical field of motor control, and discloses a vector control application of a direct drive motor, which comprises the following steps: S1, collecting stator current, rotor speed and bus voltage signals of the motor, and carrying out filtering preprocessing on the collected signals; and S2, constructing a self-adaptive flux linkage observation model, estimating a stator flux linkage in real time based on stator current and bus voltage signals in combination with rotor rotating speed information, and correcting stator resistance and inductance parameters through a model reference self-adaptive algorithm. According to the method, the motor parameters are corrected in real time through the self-adaptive flux linkage observation model, parameter drift caused by factors such as temperature change and magnetic saturation is effectively counteracted, and the accuracy of flux linkage estimation is improved; the improved PI regulator realizes online self-tuning of control parameters through a fuzzy control algorithm, can quickly adapt to changes of dynamic characteristics of the motor, and shortens the regulation response time of flux linkage and torque; and the resistance of the system to external interferences such as load fluctuation, power supply voltage change and the like is enhanced.

The invention relates to a frequency converter dynamic performance optimization control method, and belongs to the technical field of power electronics. The method comprises the steps that frequency converter operation and device characteristic signals and external working condition correlation signals are collected in real time and integrated into a multi-dimensional operation data set, an analysis model is built, and a mapping relation is preset; extracting transient characteristics of a device switch, calculating a dynamic impedance parameter based on a mapping relation, and matching a parameter self-tuning rule base to generate a current loop proportionality coefficient, an integral time constant and a modulation wave duty ratio correction; a rotating speed and current double-loop fusion framework is built, the weight of an outer loop is dynamically adjusted according to rotating speed deviation and load sudden change, an inner loop adopts an adaptive reaching law and disturbance compensation, and a cooperative control instruction is generated through inter-loop interaction; monitoring instruction execution data to form feedback, correcting a model mapping relation and optimizing control parameters. The dynamic response precision of the frequency converter under complex working conditions is improved, the anti-disturbance capability is enhanced, and meanwhile, the device operation loss and the manual debugging cost are reduced.

The invention relates to the technical field of compressed air system intelligent control, and discloses an intelligent control and air supply distribution method and system for a nuclear facility compressed air system pipe network. Carrying out numerical simulation on the distributed arrangement and operation conditions of different air compression stations and the flow and pressure characteristics of the compressed air pipe network under the intermittent load of different process equipment; on the basis of data generated by numerical simulation, the pipe network tail end pressure of the compressed air pipe network system is adjusted through an intelligent fuzzy self-tuning PID control method, and the operation state of an air compressor unit of the compressed air pipe network system is optimized on the basis of a flow matching strategy; pipe network operation parameters of the compressed air pipe network system are collected in real time, and the control strategy is fed back and adjusted. The whole compressed air system can operate efficiently and stably, the requirements of all links of nuclear facilities for compressed air are guaranteed, meanwhile, the operation intelligence and reliability of the system are improved, and adverse effects caused by unstable pressure and the like are reduced.

The invention relates to the technical field of unmanned aerial vehicle flight control, and discloses an unmanned aerial vehicle adaptive obstacle avoidance control method and system based on environment perception, and the method comprises the steps: obtaining environment perception data and flight state data; constructing a slender obstacle parameter model; constructing an equivalent dangerous volume field and a repulsive potential energy field; generating a controllable risk potential field; generating an obstacle avoidance control quantity and a reference trajectory; performing online self-tuning on potential field parameters; and generating a final flight control instruction. Compared with the prior art, the technical problem that slender obstacles cannot be effectively converted into safety control distances capable of participating in flight control calculation especially under the environmental conditions that a large number of slender obstacles such as electric wires, branches and vines exist in power grid polling, forest low-altitude flight and the like is solved. According to the method, the slender linear obstacle is mapped into the equivalent dangerous volume field, and the continuous guided repulsive potential energy field is constructed to participate in the control quantity solution, so that the flight safety and stability of the unmanned aerial vehicle are improved.

The invention relates to the technical field of internal combustion engine testing and industrial automation control, in particular to a data acquisition and cooperative control method and system of a piston oscillation cooling test system. The system comprises a multi-source heterogeneous data acquisition and synchronization module, a cooperative control logic engine, an intelligent algorithm execution module, a safety interlocking management module and a man-machine interaction and data management module. According to the method, through a predictive pre-cooling strategy, the industrial problem of temperature overshoot of the inertial system is fundamentally solved, temperature control is achieved, and the control precision reaches + / -0.5 DEG C; besides, by constructing a parameter self-tuning PID cluster based on multi-source information, predictive suppression of coupling disturbance in the system is achieved, the hysteresis problem of head pain and foot pain of a multivariable control system is solved, interactive interference in the dynamic adjustment process is reduced by 60% or above, and the overall stability of the system is remarkably improved.

The invention relates to a parameter self-tuning method and device of a magnetic suspension flexible conveying system and a storage medium. The self-tuning starting signal is generated based on a multi-source system triggering mechanism. And then, a rotor of the magnetic suspension flexible conveying system is controlled to execute a preset target excitation motion track, motion data of the rotor are collected, and the load characteristics of the magnetic suspension flexible conveying system are estimated in real time in combination with the translation linear motion model. Then, dynamically calculating a target control parameter adaptive to the current load through a preset setting rule; and finally, the target control parameters calculated in real time are issued to a driver of the magnetic suspension flexible conveying system, and the driver is controlled to operate according to the target control parameters. Therefore, the online efficient self-tuning method of the magnetic suspension flexible conveying system can be realized, so that the stable operation of the magnetic suspension flexible conveying system is ensured while the precision is ensured.

The invention discloses a compensation parameter self-tuning vibration suppression method for a magnetic suspension bearing system, which belongs to the field of magnetic suspension bearing control, and comprises the following steps: S1, carrying out a pulse excitation experiment on a magnetic suspension bearing-rotor system by using an electromagnetic vibration exciter, a magnetic suspension bearing-rotor system model is obtained through parameter identification of the frequency response function; s2, obtaining a phase compensation angle according to the mapping relation of the frequency response function; and S3, according to the system model, designing a compensation controller based on a second-order generalized integral-synchronous rotating coordinate system, and through the system model, the phase compensation angle and stability criterion self-tuning compensation control parameters, realizing vibration suppression of the magnetic suspension system. The method can effectively suppress unbalanced mass vibration of the rotor, compensation parameters do not need to be tested and calibrated in advance, the self-tuning process is rapid and convenient, and the method is suitable for any multi-degree-of-freedom magnetic suspension bearing-rotor system and has good practical value and economic value.

The invention relates to a temperature control method and system for self-tuning PID parameters based on hysteresis control. The method comprises the following steps: initializing a temperature control system; designing a dynamic power adjustment strategy and carrying out oscillation test on the temperature control system by adopting a hysteresis control mode based on the strategy; carrying out preliminary self-tuning on parameters of the PID controller; designing a center point compensation mechanism; a dynamic power adjustment strategy and a center point compensation mechanism are combined, an improved PID control algorithm is executed to carry out real-time temperature control circulation, and the heating power is adjusted; and performing exception processing. Accurate adjustment is carried out by compensating the deviation between the temperature of the central point of the oscillation ring and the target temperature, the temperature deviation in traditional PID control is effectively eliminated, the debugging time and complexity are remarkably reduced, the system adaptability is enhanced, the response speed is increased, the problem that the control temperature is lower than the set temperature in the traditional PID control is effectively solved, and the control precision is improved.

The invention relates to the technical field of industrial automation control, and discloses an event-triggered self-tuning PID temperature control system and method. According to the system, a parameter updating loop is activated when specific conditions are met through an event triggering mechanism, and game theory self-learning and a preset performance control method are integrated into an extended PID controller structure through the loop, so that dynamic adjustment of parameters is achieved. The system can respond to temperature deviation and external disturbance in real time, and therefore multiple performance indexes such as overshoot, stabilization time and energy consumption are optimized at the same time. All the modules jointly optimize a control strategy through data interaction and function cooperation so as to reduce the computing resource consumption of the system. In a resource limited scene, the mechanism improves the robustness of the system. Compared with a traditional PID algorithm, the method is higher in adaptability in an uncertain environment. Through innovative combination of event triggering and reinforcement learning, the method aims at overcoming the limitations of response delay, remarkable overshoot, resource waste and the like of the existing algorithm in a complex scene.

The application relates to a robot parameter self-setting method and system, and belongs to the technical field of robot control. The method obtains a speed loop trajectory model of a robot servo system; based on a preset mode search algorithm, parameter optimization is performed on speed loop parameters of the speed loop trajectory model to obtain optimized parameters, and the speed loop trajectory model is adjusted according to the optimized parameters to obtain an adjusted speed loop trajectory model; an evaluation function is established according to a preset time domain index, and the adjusted speed loop trajectory model is evaluated according to the evaluation function to obtain an evaluation score; when the number of optimization times and the evaluation score of the current time meet preset conditions, the optimized parameters obtained at the current time are confirmed as target parameters, the speed loop parameters of the robot servo system are self-set, the difficulty of parameter setting is effectively reduced, the parameter optimization implementation process is simplified, an accurate model structure and parameters are not needed, and high-reliability parameter self-setting is realized.

The invention relates to the technical field of industrial automation control, in particular to a valve positioner control algorithm switching method, system and device based on self-tuning and a storage medium, and the method comprises the steps that S1, a self-tuning calibration process is executed on a valve, and motion parameters including the whole-course motion time, the position deviation and the minimum effective control quantity of the valve are obtained; s2, according to the motion parameters, a discrimination factor representing the resistance characteristic of the valve is obtained through calculation according to a preset weighted calculation formula; and S3, comparing the discrimination factor with a preset critical value, automatically selecting a target control algorithm from a plurality of pre-stored control algorithms according to a comparison result, and performing closed-loop control on the valve by adopting the target control algorithm. According to the method, the control algorithm and the resistance characteristic of the valve are automatically and accurately matched, the adaptability, the stability and the control quality of valve control are effectively improved, and meanwhile the debugging and maintenance cost is remarkably reduced.

This invention relates to the field of speed control technology, specifically to an intelligent lamination and tension control system and method for multi-ribbed belt production lines in washing machines. The system includes: a multi-dimensional state information extraction module, a real-time collaborative control module, a control performance evaluation module, and a fuzzy rule self-tuning module. In this invention, by calculating tension error and lamination position deviation, a basis for dynamic adjustment is provided, eliminating reliance on preset fixed parameters. By invoking a fuzzy logic inference engine, tension error, error change rate, and position deviation are fused and processed to achieve synchronous and precise control of the transmission roller speed and the position of the correction mechanism. This effectively replaces the slow-responding mechanical tension device, solving the problems of tension fluctuation and lamination deviation. Furthermore, a long-term comprehensive performance index is introduced to evaluate the control effect. When performance deteriorates, a gradient descent algorithm is immediately triggered to self-tune the fuzzy rule parameters, continuously optimizing the control strategy and ensuring the system maintains high stability and high accuracy.

The invention relates to a pilot-scale simulation coiling furnace. The pilot-scale simulation coiling furnace comprises a furnace body, a stirring fan system, an electric exhaust fan system, a water cooling system, an intelligent control unit and a detection unit, and the intelligent control unit takes an intelligent digital regulator as a core and adopts a PID (Proportion Integration Differentiation) self-tuning algorithm to realize accurate control of the furnace temperature, so that a rolled piece can be stably cooled at a settable average rate of 0.2-1.0 DEG C / min in a range of 100-900 DEG C. And the water cooling system cools a motor and a bearing of the stirring fan system through circulating cooling water, so that the service life of equipment is effectively prolonged. The industrial coiling cooling working condition can be accurately simulated, the reliability and reproducibility of experimental data are improved, the automation degree is high, operation is stable, and a powerful platform support is provided for optimization of a pilot plant test material cooling process.

The invention discloses a servo system speed loop parameter self-tuning method based on digital-analog linkage. The method comprises the following steps: establishing an open-loop transfer function of a speed loop of a servo system; parameters of a speed ring are initialized, a same-frequency and same-amplitude speed instruction is sent to a motor to drive a load to operate, and the total rotation inertia of the motor is calculated; a mapping relation equation is determined, and parameters of a speed PI controller are obtained; discretizing the parameters of the speed PI controller by adopting a bilinear method to obtain a discrete proportional gain and a discrete integral gain; determining constraint conditions of the servo system and calculating an evaluation function value according to the ITAE performance evaluation function; obtaining optimal control parameters by adopting a coordinate rotation method; corresponding discrete proportional gain and discrete integral gain are calculated according to the optimal control parameters to serve as parameters of a speed PI controller to complete parameter setting, and load operation is achieved according to a speed instruction. According to the method, the setting process is more efficient, the calculation parameters are more accurate, the manual debugging time can be greatly shortened, and the universality is good.

The invention provides a PID self-tuning control method applied to the lithium battery industry, and the method comprises the steps: obtaining operation parameters of lithium battery production equipment and scene features containing scene type identifiers and material attribute parameters, and carrying out the matching of a PID adjustment model in which adaptive dynamic characteristic parameters are pre-stored; after the deviation between the operation parameters and the scene target value is calculated, the deviation is dynamically corrected based on the material attribute parameters and the association rules; carrying out feature analysis on the corrected deviation by combining the influence weights of the dynamic characteristic parameters and the material attributes on the deviation trend; and then according to an analysis result, calling a parameter adjustment strategy corresponding to the scene to correct a PID adjustment model, and finally outputting PID parameters to adjust the lithium battery production equipment, so as to solve the problems of insufficient control precision and poor scene adaptability caused by the fact that PID parameter setting is not deeply coupled with lithium battery production scene characteristics and material attributes in the prior art.

This invention discloses a multi-parameter coupling-based deep peak-shaving full-condition optimization control method for coal-fired power units. Addressing the problems of existing technologies, this invention constructs a multi-parameter coupling index system, calculates the comprehensive coupling strength between each parameter and the load, and selects core parameters. Dynamic clustering is used to finely divide the full-condition operation from 20% to 100% rated load into multiple operating zones. An LSTM-GRU dual-channel deep learning prediction model is established for each operating zone. A three-layer hierarchical control architecture is designed, comprising load optimization scheduling, boiler-turbine coordination control, and combustion optimization execution. The boiler-turbine coordination layer uses multivariate model predictive control and online self-tuning of multi-objective weights through fuzzy inference. The combustion execution layer uses the NSGA-III multi-objective evolutionary algorithm to optimize air distribution. A constraint-adaptive tuning mechanism based on safety margin is established to form a closed-loop iterative optimization across all operating conditions. This invention can significantly improve the load response speed, main parameter stability, and combustion economy of the unit during wide-load operation.

The invention discloses an optimal control method and system for a waste incineration power generation deacidification process, and relates to the technical field of intelligent control, and the method comprises the steps: collecting the multi-source working condition information of a deacidification tower through arranging a plurality of sensors; preprocessing and fusing the multi-source working condition data to obtain a working condition feature vector and a working condition constraint condition; on the basis of the working condition feature vectors, utilizing an intelligent prediction model to predict the acid gas emission trend and the garbage heat value; optimal control parameters are calculated according to prediction results and working condition constraint conditions, and real-time flow and concentration adjustment is conducted on a spraying system in combination with online heat value feed-forward compensation and self-tuning PID feedback control. According to the method, the response speed and stability of the deacidification system to the furnace condition fluctuation are remarkably improved, the alkali liquor consumption and the emission fluctuation are reduced, and the environmental protection standard and the operation economy are guaranteed.

The invention discloses a power distribution unit self-tuning method based on a neural network digital twinning algorithm, and the method comprises the steps: firstly building an equivalent test loop, carrying out the mathematical modeling, carrying out the per-unit processing of test loop elements (an inductor, a capacitor, a resistor and the like), and carrying out the re-correction of a model, so as to facilitate the subsequent optimization; and establishing a conversion relation formula between the dimensionless parameters and the dimensional parameters. And taking the dimensionless parameter as a decision variable, taking a differential equation corresponding to the model as a constraint condition, taking the sum of absolute values of differences between obtained values and standard values as a value function, continuously training the neural network model, and calculating a minimum value of the value function by using a neural network digital twinning algorithm. And finally, performing simulation verification on an optimization result. The method is suitable for solving the problem that complex nonlinear correlation exists between input and output; compared with a linear model (such as linear regression), finer nonlinear features in the data can be captured.

The invention provides a fault-tolerant control method and system for a local demagnetization fault of a permanent magnet motor based on parameter robust model predictive control, and the method is characterized in that the method comprises the steps: carrying out the super-localization processing of a permanent magnet motor model after the local demagnetization fault, and obtaining a super-localization model; a generalized proportional-integral observer is designed, and lumped disturbance caused by demagnetization is estimated in real time and subjected to feedforward compensation; voltage and current data of adjacent sampling periods are used as real-time updating of super-local model gain, estimated values of current and disturbance are obtained from a generalized proportional-integral observer, and online self-tuning of input gain is achieved. According to the method, super localization is carried out on a motor model after a fault, unbiased estimation is carried out on disturbance introduced by the fault and a high-order derivative thereof through a generalized proportional-integral demagnetization disturbance observer, and input gain in the super localization model can be calculated in real time only by utilizing voltage and current data of two continuous periods through an input gain self-tuning algorithm. And the operation quality of the motor and the robust performance after the fault are improved.

This invention provides a leakage-type adaptive space robot control method with self-tuning of reinforcement learning parameters, belonging to the field of space robot control technology. The control method includes: acquiring the current operating state of the space robot system, the control input from the previous moment, and the control parameters from the previous moment, as the current observation state; inputting the observation state into a policy network to acquire the current control parameters; outputting the current control parameters to a leakage-type adaptive robust controller to acquire the current control input; applying the current control input to the space robot system to drive it to perform a task; acquiring the current driving state of the space robot system; evaluating the driving state and acquiring the evaluation result; and adjusting the parameters of the policy network based on the evaluation result. This invention achieves adaptive parameter optimization by online tuning of key parameters in the leakage-type adaptive robust control structure.