21 results about "Forgetting factor" patented technology

The invention relates to the technical field of power system dispatching, and discloses a power load dispatching optimization method considering dynamic response reliability, which comprises the following steps: collecting and classifying user historical and real-time load data; based on the response proportion, the peak clipping contribution degree and the forgetting factor, establishing a reliability coefficient model for interruptible, transferable and reducible loads; in combination with real-time response performance, a user dynamic response reliability calculation model is constructed, and quantitative indexes are obtained; establishing a scheduling optimization model which takes optimal response reliability and lowest scheduling cost as multiple targets and considers capacity and capability constraints; and finally, solving by adopting a hybrid intelligent algorithm to obtain an optimal scheduling scheme. According to the method, the uncertainty of user response is dynamically quantified, and the reliability index is introduced into a decision, so that economy can be considered on the premise of ensuring scheduling reliability, priority calling of high-reliability resources is realized, and the flexibility and stability of power grid operation are improved.

The application relates to a three-dimensional extended target tracking method of an adaptive Gaussian process under unknown measurement noise. Firstly, a forgetting factor is adaptively updated by recursively calculating the change rate of the Cramer-Rao lower bound trace, so that the dynamic optimization of filter parameters is realized; then, a projection method based on GP is used to represent a three-dimensional cross-shaped target, three-dimensional point clouds acquired by a sensor are projected to three orthogonal planes, and the three-dimensional extended shape of the target is reconstructed by using two-dimensional contour information; finally, a robust state estimator is constructed by fusing variational Bayesian inference and MCC, the joint posterior distribution of unknown measurement noise and system state is solved by variational approximation, and a cost function is constructed based on the maximum correlation entropy criterion, so that the influence of abnormal values is inhibited in a reweighted manner. The tracking method provided by the application can significantly improve the tracking precision and robustness of a three-dimensional extended target under unknown strong non-Gaussian measurement noise.

The application relates to an adaptive wavefront control method and system based on parameter identification and active disturbance rejection. The method comprises a digital architecture adopting PC data processing and FPGA control. The PC data processing module is used to perform complex calculations such as variable forgetting factor recursive least squares, is responsible for dimensionality reduction decoupling and high-precision estimation of disordered data, and utilizes the high-speed parallel processing capability of the FPGA control system to directly execute an active disturbance rejection control algorithm at the bottom layer to offset external interference. The hardware-software collaborative design effectively combines the accuracy of the complex algorithm and the real-time performance of the bottom-layer hardware, thereby significantly enhancing the anti-interference capability and response bandwidth of the system.

The invention discloses a high-voltage circuit breaker driving motor parameter identification method and system based on a least square method, a medium and a processor, and relates to the technical field of motor driving systems for high-voltage circuit breakers. According to the method, data such as current, voltage, rotor speed and position of a driving motor are collected, a parameter identification model including input, output and parameters is established, and a least square method with a forgetting factor is designed for parameter identification. The size of a forgetting factor in a recursive least square algorithm is dynamically adjusted according to an error of output values of an identification model and an actual model, so that the influence of measured value fluctuation on identification parameters under the working conditions of rotating speed or load sudden change and the like can be inhibited, and estimated values of motor parameters can be quickly converged to actual values under the steady-state working condition; and the accuracy of parameter identification is improved.

The invention relates to a Viterbi incoherent demodulation method and system. The method comprises the following steps: acquiring a received symbol sequence; calculating a non-correlation branch metric of each candidate path based on a preset forgetting factor, a correlation cumulant of each candidate path in a previous moment state, and an instantaneous correlation value between a receiving symbol at a current moment and a reference symbol of each candidate path; calculating the path metric of each candidate path at the current moment based on the path metric at the previous moment, and selecting the candidate path with the maximum path metric from the plurality of candidate paths at the current moment state as a surviving path at the current moment state; based on the forgetting factor, the correlation cumulant of the previous moment state corresponding to the selected surviving path and the instantaneous correlation value of the surviving path, updating the correlation cumulant of the current moment state reached by the surviving path; processing the received symbols hourly; and finally, selecting the state corresponding to the maximum value from the path metrics of all the states as a backtracking starting point at the moment, and carrying out step-by-step backtracking to obtain a demodulation data sequence.

The invention discloses a weightlessness scale flow measurement method based on recursive least squares with forgetting factors, and belongs to the technical field of flow measurement, and the method comprises the following steps: S1, determining a linear function of material weight; s2, calculating a slope and an intercept of a linear function in real time by using a recursive least square method with a forgetting factor, and obtaining a flow value of the material; s3, when the time variable exceeds the set upper limit, the flow value of the current material is locked, and time variable overflow processing is carried out; and S4, when materials need to be added, the flow value of the current materials is locked, and material adding operation is carried out. According to the method, the flow fluctuation in the feeding process can be reduced, and the problem of flow negative value or fluctuation in a traditional scheme is avoided through the strategy of freezing control quantity + freezing display in the material supplementing stage.

The application relates to the technical field of knowledge tracking, in particular to a knowledge tracking method based on a forgetting attention mechanism, a knowledge tracking model, a computer system and a storage medium. By introducing a forgetting factor based on relative position coding to simulate the law of student knowledge decay over time, a more realistic learning scenario is constructed to embed the answer sequence, the feature fusion of the answer sequence embedding representation and the question sequence embedding representation is carried out, and the prediction is more targeted and accurate. The application aims to solve the problem of how to overcome the knowledge tracking prediction deviation caused by the "forgetting effect".

The application discloses a kind of long-acting time-varying monitoring methods for dam reinforcement based on Bayes real-time updating, comprising: S1. ARMA model is constructed to simulate dam state and determine model order;S2. using prior distribution and likelihood function, using Bayes method to calculate and obtain the posterior density function of each parameter of dam in running state;S3. using last posterior distribution as prior distribution in real-time calculation, repeat the S2 step, in the calculation process, least square method is used to realize model parameter estimation, variable forgetting factor is introduced, and recursive algorithm is used, different forgetting factor is used to past monitoring data, realize parameter adaptive adjustment.The application can adapt to the time-varying characteristics of dam working behavior, real-time fusion historical data and new monitoring information, more accurately and reasonably reflect the nonlinear time-varying relationship between influence quantity and effect quantity, so as to fully embody the typical time-varying characteristics of dam working behavior.

The present application relates to a kind of micro-milling chatter identification method considering environmental noise influence, the method first uses two accelerometers simultaneously to collect the acceleration signal of workpiece and machine tool side wall position during processing;Then using variable forgetting factor recursive least squares adaptive filter, with the help of machine tool acceleration signal, workpiece acceleration signal is adaptively filtered, remove the environmental noise and periodic component contained in workpiece acceleration signal;Then the power spectral density of filtered workpiece acceleration signal is calculated;Then the corresponding kurtosis, skewness and other characteristics are calculated using the obtained power spectral density, and according to the size of characteristic value, it is compared with the set threshold value, to accurately identify the occurrence of chatter.

This application discloses an online identification method and system for pipe resistance coefficient based on an improved recursive least squares method, belonging to the technical field of heating systems. The method includes: collecting operating data of the heating pipe network; constructing a resistance coefficient identification model based on the operating data; using an improved recursive least squares method to identify the resistance coefficient online based on the identification model; evaluating the reliability of the identification results; and updating the verified resistance coefficients to the intelligent valve control system in real time. The method boasts strong real-time performance, enabling online real-time updates of the resistance coefficient to adapt to dynamic changes in the pipe network. The improved RLS algorithm enhances identification accuracy, with a measured error of <5%. No special testing conditions are required, and it does not affect the normal operation of the system. A variable forgetting factor design allows the algorithm to adapt to different operating states. It is suitable for real-time operation in embedded systems and has been verified in actual projects.

This invention discloses a server intelligent scheduling and control method, relating to the field of industrial process control technology. It addresses the control instability problems caused by thermal response lag and model time-varying behavior of the controlled object. First, the flow excitation and thermal response signals are synchronously differentially sampled. A recursive least squares method with a forgetting factor is used to identify the dynamic transfer function online, extracting the thermal response lag time constant and steady-state gain in real time. Then, based on the time constant, the stability of the step response is analyzed, the maximum input rheological rate is calculated, and a dynamic safe operating envelope domain is constructed by combining the thermal load boundary mapped by the steady-state gain. Under the constraints of this safe domain, a model predictive control objective function is established to solve for the optimal flow allocation and operating condition commands. Finally, a cooperative tracking algorithm drives the flow gateway and voltage module to achieve closed-loop control. The forgetting factor is corrected online using the state observer residual, eliminating model mismatch errors and achieving high-precision adaptive thermal safety control of the server cluster.

The application relates to the field of motor control, in particular to an intelligent operation control method based on a permanent magnet brushless motor, which comprises the following steps: defining the input and output of a recursive least square method; calculating the cosine similarity of an input vector at a current moment and all historical input vectors, selecting the prediction error of a historical moment with the highest similarity to calculate a forgetting factor at the current moment, and updating a coefficient vector at the current moment based on the forgetting factor; according to the coefficient vector, the working condition characteristic vector of the motor at the current moment and the constraint region of the control parameter vector, calculating the predicted output efficiency at the current moment and selecting a group of control parameter vectors with the maximum predicted output efficiency to control the operation of the motor at the next moment. The application can track the time-varying characteristics of the motor and maintain stability under similar working conditions by dynamically adjusting the forgetting factor, improve the adaptability of the model, and inversely solve the optimal control parameters to control the operation of the motor in real time.

The invention provides an improved variable forgetting factor recursive least square and Kalman filtering coupled real-time correction method, and the defects of a traditional Kalman filtering algorithm are effectively overcome. By taking the real-time correction of the flood forecast of the maple dam reservoir as an example, the algorithm is applied, and compared with other methods, the calculation result shows that the algorithm has a better simulation effect.

The invention discloses a PID parameter adjustment method and device based on PILCO reinforcement learning migration PID control, and relates to the technical field of control architecture migration, and the method comprises the steps: obtaining target interaction data based on a PILCO reinforcement learning algorithm when an intelligent agent interacts with a control environment; a state error, an error integral and an error derivative in target interaction data are calculated according to an expected state of a controlled object, and a PID control parameter of a PID controller is identified by applying a recursive least square method combined with a forgetting factor. According to the method, parameter estimation is carried out by using a recursive least square method combined with a forgetting factor, a PILCO offline learning result is migrated and converted into PID control, a PILCO reinforcement learning algorithm and a PID controller architecture do not need to be changed, and the problems that the PILCO reinforcement learning algorithm is high in calculation complexity, poor in high-dimensional state space expansibility and difficult to deploy online are solved.

The application discloses a systematic interval optimization method for a forgetting factor in parameter identification of a lithium battery equivalent circuit model, and belongs to the technical field of battery management. The method comprises the following steps: firstly, obtaining initial values of parameters based on a standard recursive least square method; then, selecting a plurality of forgetting factors in a preset interval, respectively performing recursive least square identification with the forgetting factors, and obtaining parameter identification sequences; then, calculating root mean square trends of the parameter sequences with respect to the forgetting factors, and determining a forgetting factor subinterval at which each parameter keeps stable convergence; finally, obtaining a common intersection of all the subintervals as an optimized interval, and taking a middle value of the optimized interval as a recommended forgetting factor. The application overcomes blindness in empirical selection, can automatically determine an optimal forgetting factor suitable for current data, and improves convergence, stability and precision of online parameter identification.

The invention relates to the technical field of knowledge tracking, in particular to a knowledge tracking method based on a forgetting attention mechanism, a knowledge tracking model, a computer system and a storage medium. A rule that student knowledge declines along with time is simulated by introducing a forgetting factor based on relative position coding, an answer sequence embedded representation more conforming to a real learning scene is constructed, and feature fusion is performed on the answer sequence embedded representation and a question sequence embedded representation, so that prediction is more targeted and accurate. The method aims at solving the problem of knowledge tracking prediction deviation caused by the forgetting effect.

This invention provides a chassis control method for an amphibious humanoid welding robot based on magnetic wheel drive, employing a zero-delay, rapid calculation three-vector model for predictive control of the motor; the input of the zero-delay, rapid calculation three-vector model is the target current; the current parameter Pr(k) in the zero-delay, rapid calculation three-vector model is [RL]. s ψ f ] T The parameters are estimated in real time using a forgetting factor recursive least squares method parameter identification algorithm; where R is the stator resistance of the motor; L s For the stator inductance of the motor; ψ f The rotor flux linkage of the motor is used. The forgetting factor recursive least squares parameter identification algorithm is implemented based on a q-axis discretized mathematical model and a least squares recursive formula with a forgetting factor. This method can effectively reduce current harmonic distortion rate, improve torque stability, and suppress the influence of external environmental changes such as temperature on motor parameters, achieving accurate parameter identification. The model predictive control algorithm can then better control the robot chassis, making its movement smoother and ensuring welding stability.

The application discloses a battery model parameter identification method based on a forgetting recursive least square method with deviation compensation, and belongs to the field of battery model parameter identification.The method comprises the following steps: S1, a second-order equivalent circuit model is established, and model parameters to be identified are determined; S2, a load end voltage and an end current at the k moment are collected in real time; S3, a lower discharge rate is used to collect a state of charge (SOC) and an open circuit voltage (OCV) of the battery, and a relationship expression of the state of charge (SOC) and the open circuit voltage (OCV) is determined through fitting; S4, a discrete regression equation used for model parameter identification is established, and model parameters are updated on line by using an end voltage value and a current input at the k moment; S5, average weighted variances of noises in the voltage and the current are calculated; and S6, the result of the recursive least square method with a forgetting factor in S4 is updated according to the average weighted variances of the voltage and the current noises obtained in S5, and identification parameters at the k moment are obtained.The application can realize the update of a parameter vector and reduce the influence of noises on the estimation accuracy of a model.

This invention discloses an adaptive learning resource recommendation method based on dynamic knowledge state, comprising the following steps: Step 1, assessing the objective difficulty of the questions by considering the difficulty of the questions themselves and the hierarchical difficulty of the knowledge concepts; Step 2, assessing the learner's subjective perception of difficulty based on the assessment results of the objective difficulty of the questions; Step 3, assessing the learner's dynamic knowledge state based on the assessment results of the learner's subjective perception of difficulty, and updating the learner's dynamic knowledge state by considering forgetting factors; Step 4, employing a traction mechanism to bridge the gap between the learner's current knowledge state and the difficulty of the next input question, matching questions of appropriate difficulty to the learner, and implementing adaptive learning resource recommendation. This invention dynamically adjusts the learner's knowledge state by considering both the objective difficulty of the questions and the learner's subjective perception of difficulty, ensuring that the recommended questions align with the learner's knowledge state, thus achieving personalized learning resource recommendation.

The application discloses a kind of electric fork truck control system and method based on time-varying adaptive lateral dynamics model, belong to electric fork truck lateral dynamics control technical field.Through the working condition and dynamics parameter of multi-source sensing collection and preprocessing, construct three degrees of freedom nonlinear time-varying coupling model of yaw-roll-lateral displacement, using improved adaptive forgetting factor recursive least square method to identify time-varying parameter on line, combine with the observation of unmeasured state of extended Kalman filter, form closed-loop control system.The application solves the problem that traditional constant parameter model cannot adapt to heavy load / high position condition, effectively improves the lateral stability and rollover prevention capability of electric fork truck.