343 results about "Non linear functions" patented technology

The invention relates to the technical field of power system operation and control, and discloses a primary and secondary frequency modulation cooperative control system of a hybrid energy storage coupling wind generating set, which comprises a wind power generation unit, a hybrid energy storage unit and a central cooperative controller. A total power demand including inertia response and primary and secondary frequency modulation is synthesized, a primary and secondary frequency modulation cooperative distribution module generates a dynamic adjustment weight by using an S-type nonlinear function based on a frequency change rate and frequency deviation coupling relationship, and an energy relay compensation mechanism is introduced to fill a power gap in a switching process. And the SOC adaptive constraint and execution module applies direction selective boundary constraint to the state of charge, and controls hybrid energy storage to perform internal energy self-balancing in a frequency modulation dead zone. According to the invention, seamless connection of multi-time scale frequency modulation is realized, frequency secondary drop is effectively prevented, and the frequency support capability and the self-recovery capability of the system are improved.

The invention relates to the technical field of electrical testing, in particular to a battery testing method and system, and the method comprises the steps: obtaining a voltage data sequence and historical log data of each cell in a to-be-tested battery pack; determining a dynamic instability score of each battery cell according to the parameter volatility index of each battery cell and the spatial correlation weight between each battery cell and the adjacent battery cell; on the basis of the historical log data, analyzing a repeated cumulative effect of all historical damage events corresponding to each battery cell, and determining a historical damage degree of each battery cell; performing deep fusion on the dynamic instability score and the historical damage degree through a nonlinear function to obtain a comprehensive risk index of each battery cell; and based on the extreme values and distribution of the comprehensive risk indexes of all the cells, determining a fault degree capable of representing the overall health risk of the battery pack, and determining a health test result of the battery pack according to the fault degree. According to the method, the accuracy and reliability of battery pack testing are improved.

The invention discloses a self-adaptive safety control method of a nonlinear MIMO system under intermittent DoS attack, which comprises the following steps: establishing a nonlinear MIMO system model suffered from intermittent DoS attack, and the system model is in a strict feedback form and comprises an unknown nonlinear function and bounded external disturbance; the DoS attack causes periodic interruption of a communication link from a sensor to a controller, so that actual measurement data is unavailable in an attack activation period; designing a switching type adaptive state estimator; coordinate transformation is carried out by introducing a filter, and a system error is decomposed into a tracking error and a dynamic surface filtering error; a Lyapunov function is constructed; performing stability analysis in stages; designing an adaptive law to update unknown parameter estimation values of the FLS; and a final event triggering controller is designed, and the event triggering controller is combined with a virtual controller to track an error compensation term and an FLS approximation term. The problem that the state cannot be measured is solved.

The invention relates to a vehicle and unmanned aerial vehicle combined scheduling method for wide-range low-cost inspection. The method comprises the following steps: acquiring prior information; modeling the unmanned aerial vehicle inspection problem of each target area according to the prior information to obtain a mixed integer non-convex optimization problem with the goal of minimizing the weighted sum of the total execution time and the energy consumption of all the inspection unmanned aerial vehicles; performing linearization on a non-convex bilinear term in the mixed integer non-convex optimization problem, and performing discretization processing on a nonlinear function by adopting piecewise linear approximation; an approximate mixed integer linear programming problem is obtained and solved, and an unmanned aerial vehicle scheduling strategy is obtained; modeling according to the unmanned aerial vehicle scheduling strategy and the prior information to obtain an inspection vehicle path planning problem taking the comprehensive driving cost as a target; the routing inspection vehicle path planning problem is converted and modeled into a Markov decision process, a routing inspection vehicle is used as an intelligent agent, a state, an action and a reward function are defined, and a routing inspection vehicle scheduling strategy is obtained. Therefore, combined inspection of the inspection vehicle and the unmanned aerial vehicle is realized, and the inspection range is expanded.

The invention provides a nonlinear data generation and processing method based on light quantum and a light quantum computer, and the method comprises the steps: obtaining a nonlinear function and attribute information of a nonlinear layer; according to the frequency spectrum number and the attribute information of the nonlinear function, constructing an initial light quantum circuit; measuring the initial light quantum circuit, and determining a target function corresponding to the initial light quantum circuit according to a measurement result; loss information of the target function is determined, whether the initial light quantum circuit is applied or not is determined according to the loss information, and if yes, the initial light quantum circuit serves as a target light quantum circuit; and performing operation on input data of the nonlinear layer based on the target light quantum circuit. According to the method, the low-energy-consumption characteristic of photon calculation, the nonlinear characteristic of light quantum calculation and the general programmable capability of electronic calculation can be fused, and high-energy-efficiency calculation can be carried out on input data of a nonlinear layer. In addition, the method also has the advantages that the complexity of a quantum circuit is smaller, and the participation of a nonlinear optical device is not needed.

The invention discloses a correction method for saturation spectral line intensity in a laser spectrum, and relates to the technical field of spectral data analysis, the method comprises the following steps: identifying saturation characteristics in the spectrum, determining a saturation point based on an intensity threshold, and recording the original intensity of the saturation point; determining a target spectrum peak wavelength range containing a saturation point; eliminating saturation points from the wavelength range of the target spectrum peak, and retaining unsaturation points; fitting the unsaturated point through a nonlinear function to obtain the maximum fitting strength; if the maximum fitting strength is lower than the original strength, performing strength correction by adopting a linear extension mode by taking an unsaturated point as a reference, and otherwise, performing strength correction directly based on a fitting model; and outputting the corrected spectral intensity data, and calculating the maximum intensity of the spectral peak and the integral area of the spectral peak. According to the method, the accuracy of saturation judgment and the reliability of a correction result are improved, and a direct intensity data basis and core derivative parameters are provided for quantitative analysis.

The invention discloses a multi-dimensional layered current limiting method based on spatio-temporal feature fusion. The method comprises the following steps: acquiring a hardware limit speed, and generating a global quota based on a reinforcement learning model; calculating a variable coefficient, and if the variable coefficient exceeds a preset critical value, introducing a conservative coefficient and generating a weight factor through nonlinear function mapping to suppress the micro network jitter; constructing a priority factor matrix based on the service priority and the service type, and obtaining a service priority factor; correcting the average bandwidth of the node by integrating the multi-dimensional dynamic weight factor and the service priority factor to obtain a suggested speed, inputting a historical performance index into the LSTM model to predict the load of the next period, and if the historical performance index exceeds a critical value, triggering connection migration before executing current limiting to realize active avoidance; otherwise, comparing and selecting the minimum value of the global quota, the suggested speed and the hardware limit speed as the final current-limiting speed. The problems of current limiting strategy lag and wide oscillation can be solved, and the bandwidth utilization rate and the system stability are improved.

A data storage device has an inference engine that can infer a read threshold based on a non-linear function of inputs that reflect current memory and data conditions. The read threshold can be used in reading a wordline in the memory. Using a machine-learning-based approach to infer a read threshold can provide significant improvement in read threshold accuracy, which can reduce bit error rate and also improve latency, throughput, power consumption, and quality of service.

The invention provides a heterogeneous multi-agent system control method under a DoS attack based on an event triggering strategy. Robust cooperative control under a complex attack environment is realized through the following steps: S1, performing state description and topological structure modeling on a heterogeneous multi-agent system; s2, carrying out approximation on an unknown nonlinear function in the system; s3, restraining the error dynamic state through a performance function, and ensuring that the system response meets the preset precision; s4, designing a time-varying threshold function, and dynamically adjusting a trigger condition to reduce communication burden; s5, designing an anti-attack controller in combination with event triggering and a Lyapunov theory; s6, designing an adaptive law to carry out online estimation on disturbance; and S7, testing synchronization precision, communication efficiency and anti-attack performance based on a physical platform. According to the method, deep fusion of the event triggering mechanism and the preset performance constraint is realized for the first time, and the self-adaptive dynamic threshold strategy is introduced, so that malicious interference of DoS attacks on a communication link is effectively dealt with, and it is ensured that the heterogeneous nodes can still meet preset performance indexes in an attack scene.

The invention discloses a self-adaptive finite time fuzzy safety control method for a flexible joint mechanical arm, which comprises the following steps that a flexible joint mechanical arm state space model influenced by spoofing attack is established, and a control signal comprises an unknown time-varying parameter and an unknown bounded attack function; introducing a Nussbaum function meeting a preset limit integral property; designing a control method based on a finite time stability principle, and ensuring that a system state converges to a bounded residual set within finite time; a fuzzy logic system is adopted to approach an unknown nonlinear function in the mechanical arm model; defining an error variable through coordinate transformation, and constructing a parameter which exponentially decays along with time; constructing a Lyapunov function containing the exponential decay parameter, and designing a virtual control function, a controller and a parameter adaptive law based on the function; and the Nussbaum function is constructed to be used for processing the unknown time-varying parameters. According to the invention, the influence of spoofing attacks on state signals can be reduced.

The invention relates to a virtual inertia-damping cooperative adaptive control method for a voltage source type direct-driven permanent magnet wind turbine generator. The method comprises the following steps: constructing a voltage source type direct-driven permanent magnet wind turbine grid-connected equivalent model; constructing a wind turbine generator frequency response model based on a dynamic coupling relationship between virtual inertia and virtual damping; collecting a frequency signal of a common connection point of a power grid, and carrying out collaborative optimization processing on the frequency signal by adopting a composite filter to obtain a virtual power increment; the active power reference value is introduced into an active power control loop of the grid-side converter; and controlling the power grid side converter after the additional power reference value is introduced by adopting a rotational inertia and damping coefficient adaptive control method based on a nonlinear function. According to the method, frequency steady-state deviation compensation and dynamic change rate correction can be realized, the frequency stability under wide-range disturbance can be improved through segmented nonlinear adjustment, and the requirements of unit active inertia response and power grid frequency stability are met.

The invention provides a level protection-oriented network security configuration checking method, which comprises the following steps of: constructing a knowledge graph associated with a security control item and a technical implementation mode by relying on a standard document and configuration data, and implementing a control item logic dependency and semantic weight reconstruction model; security configuration of assets is automatically collected and semantically mapped to map nodes, configuration deviation is recognized, a risk influence path template is matched in combination with asset importance and service context, semantic propagation path influence intensity is dynamically calculated, and an accumulated risk influence value of configuration deviation is generated in an aggregation mode; according to the method, risk level judgment is carried out by adopting a piecewise nonlinear function, a structured risk assessment record is output, risk identification and reinforcement suggestion closed loop are realized, and the hierarchical management and control and automatic compliance response capability of security configuration deviation in a network environment is improved.

The invention discloses a heat dissipation system and method for a sealed motor, and belongs to the technical field of sealed motors and transmission devices. The system comprises a motor unit, a multistage gearbox unit, a liquid cooling unit, an air cooling unit, a plurality of groups of sensors and a controller. The liquid cooling unit is integrated in the motor outer cover, and the air cooling unit is installed on the motor radiating ribs. According to the method, the total heating power and the variable target temperature of the system are dynamically calculated by collecting the current, the temperature and the rotating speed of the motor and gear signals of the gear box in real time, the required heat dissipation power is calculated in real time through a nonlinear function based on the temperature difference, and then heat dissipation resources of the air cooling unit and the liquid cooling unit are cooperatively distributed with the optimal energy efficiency ratio. According to the invention, feedforward prediction temperature control of dynamic working conditions is realized, the problems of heat dissipation lag, low energy efficiency and overheating risk of the sealed motor under complex load and multi-gear operation are solved, and the reliability, adaptability and overall energy efficiency of the system are significantly improved.

The invention provides a printed circuit board surface defect intelligent detection method and system, and the method comprises the steps: firstly collecting a batch-level defect classification original confidence sequence and synchronous process state parameters, extracting the mean value, variance, change rate and other dynamic characteristics of confidence, and fusing the dynamic characteristics with process parameters to obtain a data fusion model; inputting a pre-training time sequence model to predict the confidence coefficient trend of the next batch; the classification threshold value of the key defect category is dynamically adjusted through the deviation between the actual confidence coefficient mean value and the predicted confidence coefficient mean value, non-linear function self-adaptive mapping is adopted for the adjustment coefficient, and self-adaptive optimization of the classification model threshold value along with quality fluctuation is achieved; when the production line is in a stable stage, threshold adjustment is automatically frozen. The method improves the accuracy of defect identification and the adaptability of the production line.

The embodiment of the invention provides a nonlinear function calculation method and a special function calculation unit (SFU). The method comprises the following steps: determining a to-be-fitted function and a fitting interval corresponding to the to-be-fitted function; based on the to-be-fitted function and the fitting interval, configuring segment parameters and linear parameters corresponding to the to-be-fitted function; and performing fitting calculation based on the piecewise parameters and the linear parameters to obtain a first target function corresponding to the to-be-fitted function, and completing nonlinear function calculation based on the first target function. According to the invention, the problems of low precision, poor performance and low efficiency of SFU processing in the prior art are solved, and the effect of improving the SFU processing precision, efficiency and performance is achieved.

The invention provides an IGBT junction temperature prediction model construction method and system, and relates to the technical field of power electronic device thermal management, and the method comprises the steps: obtaining an initial data set representing the transient thermal response relation between an IGBT chip and an NTC temperature measurement point in an IGBT power module where the IGBT chip is located; training a neural network model based on the initial data set, and learning and representing a nonlinear function relationship between time and thermal impedance; inputting a preset new time sequence into the trained neural network model, and generating a time-continuous and noise-suppressed optimized thermal impedance data set; and based on the data set, performing parameter fitting on a preset lumped parameter thermal network model to identify thermal resistance and thermal capacity parameters of the model so as to complete construction of the junction temperature prediction model. According to the method, the neural network is used as a data optimization tool in a physical model parameter identification process, and accurate and convenient online prediction of the IGBT junction temperature is realized only by using the temperature signal of the NTC temperature measurement point of the module.

The invention relates to the technical field of mobile payment, in particular to a dynamic adjustment method for a mobile payment password-free limit, which comprises the following steps: when a payment terminal initiates a payment request, acquiring a network environment, an equipment unlocking mode, an SIM card state, system integrity and a discrete state of an application environment in real time, and establishing an equipment security state vector; according to the invention, multi-dimensional acquisition is carried out on the network environment, the equipment unlocking mode, the SIM card state, the system integrity and the discrete state of the application environment, and the security state vector is constructed, so that the equipment security can be subjected to structured description before the transaction is initiated, and the security fluctuation characteristics during the operation of the equipment are captured; by means of a security product attenuation value generated by a security state vector and in combination with a highest password-free quota reference value set by a user, a comprehensive equipment security score is output in a nonlinear function form, and quantitative filtering of equipment credibility is realized in a previous stage of quota calculation.

The invention discloses a predefined space-time pitch angle control method of a variable-speed wind generating set, and belongs to the technical field of variable-speed wind generating set control. The method is characterized by comprising the following steps of 1, obtaining a dynamic model of the variable-speed wind turbine according to the Betz theory; step 2, obtaining a predefined space-time reaching law with a buffer area according to the improved barrier function; 3, constructing a sliding mode variable, and converting a non-affine model of the variable speed wind turbine into an affine model based on an unknown smooth nonlinear function; and 4, compensating the unknown smooth nonlinear function by using a neural network, and obtaining a pitch angle controller according to the neural network. According to the predefined space-time pitch angle control method of the variable-speed wind generating set, the state space is divided into the multiple parts including the buffer areas, dependence on model parameters is reduced, the buffeting phenomenon is weakened through the improved obstacle function, and then the power generation efficiency is improved, and the operation cost is reduced.

The invention relates to the technical field of network acceleration, and discloses an edge-end large language model reasoning acceleration method and accelerator, and the method comprises the following steps: reconstructing a calculation process of a decoding stage, and carrying out the deep fusion of a multi-head attention mechanism and the calculation operation of a feedforward network; the weight and key value data are stored in HBM, and the coefficient and the accumulated attention score are stored in DDR; for linear matrix calculation, a unified matrix calculation unit is used for executing multi-precision matrix operation; for nonlinear function calculation, a mathematical transformation and linear fitting method is adopted, a Softmax function is converted into operation with 2 as the bottom through a bottom conversion formula, and truncation and third-order linear fitting are conducted on a Sigmoid function; and constructing a key value screening algorithm based on the accumulated attention score, dynamically adjusting a key value storage position, maintaining a recent key value cache region and an important key value cache region in a limited cache space, and realizing key value efficient cache in long text reasoning.

The invention discloses a wind driven generator pitch angle tracking control method based on self-adaptive predefined time, and belongs to the technical field of wind driven generator pitch angle tracking control. The method is characterized by comprising the following steps: step 1001, obtaining a dynamic model of the variable-speed wind driven generator by using the Betz theory; step 1002, constructing a non-singular predetermined time sliding mode variable, and converting the dynamic model of the variable speed wind driven generator obtained in the step 1001 into an affine model based on an unknown smooth nonlinear function; and step 1003, approaching an unknown smooth nonlinear function by using a neural network to obtain a pitch angle controller. According to the wind driven generator pitch angle tracking control method based on the self-adaptive predefined time, accurate adjustment of the pitch angle is achieved through the predefined response time, the pitch angle can be adjusted within the limited time, and the dynamic response capacity of a system is improved.

A data processing method, comprising: receiving a first fragment among two fragments obtained by performing secret fragmentation on input data (S602); dividing an original calculation function for processing the input data into a non-linear function in a symmetric interval and a linear function in an asymmetric interval (S604); obtaining a first representation vector of the first fragment on the basis of a Fourier series expression of the non-linear function, sending to a second computing service provider a first ciphertext obtained by performing homomorphic encryption on the first representation vector, receiving a blinded ciphertext returned by the second computing service provider on the basis of the first ciphertext and a second fragment among the two fragments, and decrypting the blinded ciphertext to obtain a result fragment of the non-linear function corresponding to the first fragment (S606); and, on the basis of the result fragment of the non-linear function corresponding to the first fragment and a result fragment of the linear function corresponding to the first fragment, obtaining a first result fragment, which is used for, together with a second result fragment obtained by the second computing service provider on the basis of the second fragment, generating a computing result corresponding to the input data (S608).

The invention relates to the technical field of artificial intelligence and control, in particular to a non-linear multi-agent system fixed time consistency control method and device and a medium. According to the control method, a backstepping recursion method is used as a control design framework, a self-adaptive fixed time consistency controller based on an auxiliary compensation system is provided, and the problem of non-linear multi-self-body system consistency control under time-varying input delay is solved. By providing and changing a control input signal by a person, the motion trajectory of the multi-agent system can be modified as required. Time-varying input time delay and an unknown nonlinear function are considered in a system model, so that the system is more general. Wherein an unknown time-varying delay function is processed by constructing an auxiliary compensation system, and an unknown nonlinear function is processed by using radial basis function neural network approximation. According to a fixed time control correlation lemma, an actual fixed time adaptive consistency control method is provided to ensure that the consistency error of the multi-agent system converges to a neighborhood near an original point in fixed time.

A simulation system and method for implementing a model based on an iterative neural network, the system comprising: a simulation vector-matrix multiplication circuit that encodes a weight matrix of the model based on the iterative neural network; and an analog non-linear circuit that encodes a non-linear function arranged in a feedback loop configured to return an output signal from the non-linear circuit as input to the vector-matrix multiplication circuit, wherein the system is configured to output a solution vector of values of the model based on the iterative neural network upon convergence of the system.

The invention relates to the technical field of battery management systems, and discloses a lithium battery SOC estimation method based on model predictive control and dynamic parameter calibration, and the method comprises the steps: constructing a second-order RC equivalent circuit model of a lithium battery, and obtaining a nonlinear function relation between an open-circuit voltage and a state of charge; real-time current and voltage data are collected, model parameters are identified on line through a recursive least square method with a forgetting factor, and dynamic calibration of the parameters is achieved; constructing a discrete state space prediction model based on the identified parameters; and solving an optimal control sequence through rolling optimization under a constraint condition by utilizing a model prediction control algorithm, and calculating a state-of-charge estimation value of the lithium battery in combination with feedback correction. According to the method, on-line parameter identification and model prediction control are combined, the problem of model mismatch under battery parameter time varying and dynamic working conditions is effectively solved, and the precision and robustness of lithium battery SOC estimation are improved.

The invention discloses a self-adaptive control method, system and device for inertia coefficients of a network-forming converter and a storage medium, and relates to the technical field of power electronic converter control, and the method comprises the steps: collecting the DC side voltage of a converter in real time through a voltage sensor, and calculating the deviation between the DC side voltage and a DC voltage reference value; the output angular velocity deviation of the converter is obtained, the inertia coefficient of the converter is dynamically adjusted through a nonlinear function in combination with the direct-current side voltage deviation, and self-adaptive adjustment of control parameters of the converter is achieved; the dynamically adjusted inertia coefficient of the converter is substituted into a converter control link in real time, and the output characteristic of the converter is changed, so that the output performance of the converter is optimized; self-synchronization grid connection can be realized, the anti-interference capability of the system is enhanced, the converter adapts to complex working conditions, virtual inertia is provided for a power grid, the frequency of the power grid is stabilized, and the operation stability of the grid-forming converter and the new energy accepting capability of the power grid are improved.

The invention relates to the field of reinforcement learning, in particular to a reinforcement learning-based large language model antagonism fine-tuning enhancement system. The state prediction module is used for acquiring system state data and robot action data; based on the robot action data, generating a prediction state vector through a neural network prediction model, and comparing the prediction state vector with the system state data to obtain a residual vector; the action decoding module inputs the residual vector into a feedforward neural network, codes the residual vector to generate a natural language state report, and performs autoregression decoding through a large language model to obtain a loss value; the strategy optimization module converts a penalty function value into a reinforcement learning reward signal through a nonlinear function, and the PPO algorithm calculates the total loss according to the reinforcement learning reward signal; and calculating, optimizing and updating the gradient of the low-rank adaptive parameter in the large language model based on the total loss. According to the invention, through the feedforward neural network and the PPO algorithm, the tiny dynamic deviation is captured, and the predictability and safety of the system are improved.

This invention proposes a GQA-LUT method, utilizing a genetic algorithm and LUT-based circuit to efficiently approximate non-linear operators in Transformers. It adaptively finds optimal solutions for various non-linear functions, outperforming conventional neural network methods. A novel rounding mutation (RM) algorithm enhances approximation accuracy during quantization, improving low-bit integer precision. The invention also introduces a LayerNorm folding strategy as a near-memory computing principle, reducing IO and energy overheads with a two-stage memory hierarchy. Additionally, an additive partial sum quantization method is proposed to reduce energy consumption by quantizing accumulated PSUMs in matrix multiplication, alongside a PSQ-APSQ grouping strategy and floating-point regularization.

This invention discloses a design method for a submarine vertical plane motion controller based on a closed-loop gain shaping algorithm. Based on this algorithm, the submarine depth controller and pitch controller designed according to the state-space equations of the submarine dynamics model can quickly and accurately achieve variable depth and constant depth maneuvers, optimizing the response time and steady-state error of the submarine's vertical plane motion controller, thus improving the submarine's underwater performance and safety. By constructing the depth and pitch nonlinear functions of the submarine's vertical plane motion controller, and combining these functions with the control laws of the bow and stern rudder actuators obtained from the vertical plane motion controller, the linear error feedback of the submarine's vertical plane motion controller is improved, enhancing the controller's robustness and energy-saving effect, reducing the impact of external interference, and decreasing the energy consumption of the servo motors.

The invention provides a GQA-LUT method. According to the GQA-LUT method, a non-linear operator in a converter is effectively approximated by utilizing a genetic algorithm and an LUT-based circuit. The GQA-LUT method can adaptively find optimal solutions of various nonlinear functions, and is superior to a conventional neural network method. A novel rounding variation (RM) algorithm enhances approximation accuracy during quantization, thereby improving low order integer precision. In the invention, a LayerNorm folding strategy is also introduced as a near memory calculation principle, so that IO and energy overhead of the hierarchical structure of the two-stage memory is reduced. Furthermore, an additive partial and quantization method is proposed to reduce energy consumption by quantizing accumulated PSUM in matrix multiplication as well as a PSQ-APSQ grouping policy and floating point regularization.