345 results about "System dynamics" patented technology

An adaptive impedance-based multi-mobile-robot collaborative transportation control method. Each mobile robot estimates the actual pose and ideal pose of a reference point and the first and second derivatives of the ideal pose by means of two finite-time fully-distributed observers, respectively; and then, on the basis of the estimated poses of the reference point, the pose of an end-effector of a mechanical arm, and closed-chain constraints for collaborative transportation, an ideal trajectory of the end-effector of the mobile robot, and an estimated value of a pose deviation between the end-effector of the mobile robot and the reference point are obtained. An adaptive impedance system of each mobile robot is interconnected with a virtual energy tank, and the energy tank is used to guide the updating of impedance parameters, thereby ensuring the passivity of the entire collaborative adaptive impedance system. To process unknown system dynamics of mobile robots, an asymptotic tracking adaptive neural network controller is designed using a neural network, thereby asymptotically achieving an ideal adaptive impedance relationship. The operational accuracy of multi-robot collaborative transportation systems is improved while ensuring safe collaboration.

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 provides a new energy automobile high-voltage system dynamic risk assessment method and device based on multi-source data fusion, and is applied to the technical field of data processing. According to the method, data such as high-voltage component operation parameters, battery states, environment perception, fault history and whole vehicle control instructions are obtained. Pre-processing the first working condition label, the second working condition label and the third working condition label, analyzing a CONTROLSIGNAL field to obtain a working mode of the high-voltage system, and generating a dynamic working condition label; combining a Pearson's correlation coefficient and XGBoost feature importance, screening risk sensitive features from the two, and forming a risk related feature subset; the method comprises the following steps of: establishing an improved Bayesian network model, training a subset by using an improved Bayesian network model, establishing an exclusive risk assessment model for different working conditions, reasoning real-time data by using the model to obtain a probability value of each risk dimension, and generating a dynamic risk assessment result and an early warning signal in combination with grade standard judgment.

The invention discloses a backup task scheduling method based on load prediction and an improved SAC algorithm, and relates to the technical field of data backup and intelligent scheduling. Aiming at the problems of response lagging, insufficient key task guarantee and low strategy exploration efficiency of a traditional scheduling method under a dynamic load, a task weight monitoring matrix is constructed, server performance, a network state and data importance are fused, and a task risk coefficient is calculated in combination with an exponential smoothing algorithm; carrying out sequence decomposition on a service load by adopting an Autoformer model, identifying a periodic mode through a weighted autocorrelation mechanism, and predicting a future load change trend; on this basis, an improved SAC scheduling framework is designed, a task weight guidance and temperature coefficient adaptive adjustment mechanism is introduced, and the task starting opportunity and execution duration are optimized in combination with an elastic time window. The invention provides an intelligent scheduling method with strong adaptive capability, which can autonomously optimize the task scheduling strategy according to the dynamic change of the system and effectively reduce the peak load of the server and the task backlog risk.

The invention relates to a wireless power transmission system parameter identification method based on a time domain differential model, and belongs to the technical field of wireless power transmission system control. The method comprises the following steps: establishing a parameterized time domain dynamic physical model; collecting system dynamic response data; constructing an optimization target based on a time domain residual error; and performing optimal parameter estimation based on iterative optimization. According to the method, a time domain dynamic physical model of a wireless power transmission system is constructed, and unknown parameters are solved through an iterative optimization algorithm with a minimum waveform matching error as a target. According to the algorithm, in an iteration process, a physical model is called to carry out forward differential equation solution, a time domain residual error between a model solution current and a real measurement current is used to drive a parameter estimation value to converge, and finally high-precision and high-robustness wireless power transmission system parameter identification under any working frequency is realized. The problem that in the prior art, due to static stiffness and sensitivity to waveform distortion of a theoretical model, the identification precision is insufficient is effectively solved.

The invention relates to the technical field of new energy power system instability risk assessment, in particular to a new energy power system frequency instability risk assessment method based on a heterogeneous graph attention network. The method comprises the following steps: constructing a wind power-photovoltaic heterogeneous graph model according to a power grid topology; performing combined sampling on different operation modes and anticipated disturbances, and determining corresponding input feature vectors; calculating a frequency stability index value label of the sample set; expanding the training set through an active learning iteration process, and carrying out model training; and inputting the collected operation data into the trained heterogeneous graph attention model, outputting a frequency stability index value, and evaluating the system frequency instability risk in combination with the risk matrix. By adopting the frequency instability risk assessment method for the new energy power system based on the heterogeneous graph attention network, the problem of low efficiency of risk assessment in a high-dimensional uncertain scene is solved, and the heterogeneous graph attention network can reflect the influence of different types of devices at different positions and disturbance types on the dynamic frequency of the system; and the accuracy of frequency instability risk assessment is improved.

The invention discloses an engine state estimation and system modeling correction method based on double-layer variational inference, which relates to the field of engine state estimation and comprises a variational inference stage aiming at component performance states and kinetic model parameters; a system output prediction stage based on an observation equation; and a solving stage of performing objective function optimization through an evidence lower bound. The structure clearly presents information flow and key calculation links of the proposed algorithm in state estimation and model learning. According to the method, combined reasoning of state variables and model parameters is achieved by building a probability modeling structure, the modeling problem when system dynamics is partially or completely unknown is solved by combining a modeling method of a stochastic differential equation, and while the state variables and the model parameters are optimized, the modeling efficiency is improved. Precise inference of component states and reliable identification of fault features are achieved, the fault detection accuracy of sudden gas circuit abnormity reaches the standard, and meanwhile the performance is better in the aspect of tracking long-term performance degradation.

The invention discloses a cooperative control simulation system for an underwater robot and an umbilical cable system, belongs to the technical field of ocean engineering simulation and automatic control, and is used for analyzing system dynamic characteristics in the research and development stage of deep sea operation equipment. Comprising an environment initialization and marine environment construction module, a mother ship model construction module, an underwater robot and umbilical cable coupling module, an instruction generation module, a man-machine interaction control module and a data acquisition and storage module. According to the method, an external interference source with physical authenticity is provided for a control algorithm by combining an energy density function and simulating a composite environment modeling method of a sea level height field and an LOD dynamic grid, and a distributed model prediction control algorithm for uniformly optimizing underwater robot trajectory tracking and umbilical cable tension safety maintenance is constructed; data such as the motion state of the underwater robot and the tension of the umbilical cable can be output in real time, algorithm performance testing is completed in a virtual environment, and dependence on high-cost sea testing is not needed.

The invention discloses a color consistency control method in a bamboo kitchen ware carbonization process, and belongs to the technical field of bamboo processing. The method comprises the following steps: acquiring a multi-dimensional spectral data vector of the surface of the bamboo kitchen ware; determining a multi-dimensional change rate vector of the spectral data; respectively generating a first candidate control signal and a second candidate control signal based on the spectral data and the change rate vector; determining a system dynamic state index based on the change rate vector; generating a dynamic weighting coefficient according to the dynamic state index of the system; and performing weighted fusion on the first candidate control signal and the second candidate control signal by using a dynamic weighting coefficient to generate a final heat regulation control signal. According to the invention, the method achieves the self-adaptive optimal control of all working conditions through the construction of a dual-mode decision fusion composite control system, guarantees the quick response in a dynamic stage, guarantees the smooth convergence in a steady-state stage, and fundamentally improves the thermal inertia problem of the system.

The invention discloses a tethered satellite system dynamics modeling method considering perturbation factors. The tethered satellite system dynamics modeling method comprises the steps that a geocentric coordinate system, an orbital coordinate system of a Kepler orbit where a tethered satellite system is located and a body coordinate system of a unit satellite are established; according to the movement of the centroid of the tethered satellite system on the orbit, the generalized coordinates are the distance from the centroid of the system to the earth center and the true anomaly of the orbit, the Lagrange function of the centroid of the system is obtained; according to the movement of the unit star relative to the centroid, the generalized coordinates are the distance between the unit star and the centroid, the relative first rotation angle and the relative second rotation angle, the relative Lagrange function of the unit star is obtained; comprehensively considering perturbation factors to obtain non-spherical earth, third gravitational force and solar pressure perturbation potential energy; establishing a system kinetic equation considering comprehensive perturbation factors; and obtaining a complete Lagrange equation of the tethered satellite system. The error problem caused by the fact that the master satellite directly serves as the mass point of the system and the influence of comprehensive perturbation on system motion is not considered is solved, and the number of the slave satellites is not limited.

The invention relates to the field of artificial intelligence control, in particular to a world model and reinforcement learning collaborative optimization method based on constraint perception gradient projection, which comprises the following steps: constructing a world model based on Transform architecture, performing unified modeling on an environment state, system dynamics and a reward function, and training the model based on reference model data to predict an environment future state; training a reinforcement learning strategy based on a virtual track and a reward signal generated by the world model, and calculating strategy gradient information; an explicit gradient projection operator of constraint perception is designed, a strategy gradient is corrected in real time according to future constraint conditions predicted by the world model, and it is ensured that the gradient updating direction meets the safety constraint and the optimization target at the same time; and synchronously updating world model parameters and reinforcement learning strategy parameters by using the gradient after projection correction to realize collaborative optimization of the world model parameters and the reinforcement learning strategy parameters. According to the method, the key problems of local optimal trap, low convergence speed, insufficient stability and the like in the collaborative optimization process of a traditional method are solved.

The invention discloses a power grid mode system dynamic file configuration method and device, electronic equipment and a medium, which are used for solving the technical problems of low development efficiency, high code maintenance cost, low reuse rate and poor configuration information expansibility in the prior art. The method comprises the following steps: acquiring a metadata configuration file; constructing a field configuration mapping table according to the metadata configuration file; based on the field configuration mapping table, table column configuration, screening item configuration and form item configuration are generated respectively; and transmitting the table column configuration, the screening item configuration and the form item configuration to a front-end rendering engine of the power grid mode system, so that the front-end rendering engine performs dynamic rendering according to the table column configuration, the screening item configuration and the form item configuration.

The invention discloses a power grid transformer technical renovation and overhaul time domain interval evaluation method. The method comprises the steps of 1, establishing an evaluation basic data set through multi-source data acquisition and data preprocessing; 2, screening key influence variables, quantifying variable influence weights by adopting regression modeling, and realizing accurate quantification of the health state of the transformer in combination with a TOPSIS algorithm; 3, forming a dynamic fault rate model; 4, constructing a system dynamics-Monte Carlo cooperation model, a fault tree-Bayesian network dynamic and static diagnosis model and a long and short term memory network time sequence prediction model; 5, setting an optimization target and a constraint condition, and outputting an optimal time point and a reasonable time domain interval of technical renovation and overhaul of the transformer by adopting a multi-target optimization solution method; and 6, model evaluation precision is tested back and verified through historical data, and key parameters of the model are subjected to feedback adjustment by adopting a particle swarm optimization algorithm. The method effectively solves the problems that a traditional method is low in evaluation precision, single in target and poor in dynamic adaptability, and is convenient to popularize and use.

The invention discloses an aeromagnetic compensation method based on multi-source error modeling and adaptive closed-loop optimization. The aeromagnetic compensation method comprises the following steps: synchronously acquiring multi-source sensor data; noise suppression and signal fusion are carried out by adopting adaptive Kalman filtering; performing temperature error compensation by using a dynamically estimated nonlinear temperature excursion model; adjusting and screening a core feature set through a dynamic weight; constructing an adaptive network with dynamic residual connection to carry out magnetic interference modeling; and finally, real-time reasoning is realized through high-precision quantification and calculation power optimization. According to the method, through multi-link collaborative design and closed-loop optimization, the noise suppression capability, the wide-temperature-range compensation precision and the system dynamic adaptability are remarkably improved, the problem that the performance of a traditional method is reduced in a complex state and an extreme environment is effectively solved, full-dimension suppression of multiple types of error sources is achieved, and the robustness of the system is improved. And the measurement reliability and the interpretation precision of aeromagnetic data are integrally improved.

The invention relates to the technical field of environmental protection and monitoring, and discloses an arid region oasis water environment ecological safety early warning method, which comprises the following steps: step 1, constructing a sky-air-land-water three-dimensional monitoring network, the monitoring network comprises a satellite remote sensing monitoring subsystem, an unmanned aerial vehicle remote sensing monitoring subsystem, a ground sensor monitoring subsystem and an underwater monitoring subsystem, and the monitoring network is used for acquiring multi-scale and multi-element water environment ecological data; step 2, establishing an ecological safety evaluation index system of the oasis water environment in the arid region, the evaluation system including four first-level indexes of hydrology and water resource dimension, water environment quality dimension, ecological health dimension and social economy dimension, and setting a plurality of quantifiable second-level indexes under each first-level index. A combined prediction model in which a Markov chain and a long-short-term memory neural network are coupled is adopted, and a system dynamics scene simulation method is combined, so that the perspectiveness and scene adaptability of the early warning method are effectively enhanced.

The invention provides a dynamic carbon reduction method and system for a building air-conditioning system, and the method comprises the steps: obtaining a BIM building information model and multi-source heterogeneous data of the building air-conditioning system, and constructing a digital twinborn model of the building air-conditioning system based on the BIM building information model and the multi-source heterogeneous data of the building air-conditioning system; according to the dynamic digital twinborn model, creating a deep learning prediction model for performing synchronous time sequence prediction on the plurality of state variables; establishing a multi-objective optimization function taking the total operation cost, the total carbon emission and the comprehensive user comfort degree deviation degree in the prediction time window as objectives; solving a multi-objective optimization algorithm, and selecting an optimal control strategy from the Pareto optimal control strategy set according to the building operation contextual model; the operation scene modes at least comprise an economic priority mode, a low-carbon priority mode, a comfort priority mode and a power grid demand response mode; the problem that in the prior art, the reliability of carbon reduction of a building air conditioning system is not high is effectively solved, and the reliability of carbon reduction of the building air conditioning system is effectively improved.

The invention relates to the technical field of automobile steer-by-wire system control, in particular to a trajectory tracking control method based on data-driven fuzzy value iteration. For nonlinearity and uncertainty of a steer-by-wire (SBW) system, a T-S fuzzy technology is adopted to construct a local linear model of the SBW system. Constructing a fuzzy augmented tracking system by introducing a reference signal; secondly, a fuzzy discount coupling algebraic Riccati equation based on a Hamilton-Jacobi-Bellman equation is deduced; and a data-driven fuzzy tracking value iteration (VI) algorithm is designed, and the tracking control problem of the system is solved through online iteration. The algorithm has the prominent characteristics that the dependence on system dynamics information is completely eliminated, and closed-loop trajectory tracking control can be realized without an initial stable control strategy. The method can be widely applied to the fields of intelligent driving, automatic driving steering control and the like, and is particularly suitable for scenes with uncertain system models and difficult control initialization.

A dynamic competition perception workflow scheduling method for a heterogeneous computing system comprises the following steps: constructing a scheduling problem model based on a scheduling object set and bus resources of an obtained system; constructing a dynamic competition perception simulator according to the scheduling problem model, wherein the method comprises the following steps of: decomposing a time-varying behavior of cross-domain bus data transmission into a time-invariant meta-process; each meta-process is mapped into a timeout event carrying a specific timestamp; the completion event indicates that all the timeout events to which the same scheduling object belongs are completed, so that the end of the task or cross-domain bus data transmission is marked; according to an event-driven mechanism, a completion event is arranged on the premise that the preorder constraint of a scheduling object is met, and total completion time estimation is generated while integration of multiple scheduling strategies is supported; according to the total completion time estimation, generating an approximate optimal scheduling solution by using a hybrid earliest completion time genetic algorithm; and optimizing the approximate optimal scheduling solution by adopting a quota weighted ant colony algorithm to generate a final scheduling solution.

The invention relates to the technical field of industrial process automatic control, and discloses an automatic control method for a water sample analysis process, which comprises the following steps: establishing a unit step response reference model for representing a normalized standard track of a controlled object; iteratively searching an optimal amplitude scaling and time elastic factor in the two-parameter search space to minimize the fitting residual error of the reference model and the real-time data; the optimal amplitude scaling factor is utilized to determine a projection steady-state value to drive an execution unit, and the sampling interval is adaptively adjusted according to the optimal time elastic factor, the time elastic factor is introduced to realize closed-loop compensation of system kinetic parameter drift, a steady-state target can be accurately locked in an unbalanced state, and the stability of the system is improved. And the problem of control model mismatch caused by device aging or environment fluctuation is solved.

The invention discloses a water turbine governor fault modeling and parameter optimization method based on iterative learning control. The method comprises the following steps: S1, system dynamics modeling; s2, iterative learning parameter updating, wherein a water turbine governor fault diagnosis method based on iterative learning control realizes progressive identification of fault features through periodically correcting model parameters; s3, fault feature extraction: calculating a residual signal of an actual output and a model predicted value, performing time-frequency analysis on the residual signal by adopting improved Morlet wavelet transform, and extracting an energy entropy feature and a time domain statistical feature; s4, fault diagnosis and dynamic optimization: based on the extracted fault features, fault detection and classification are realized through a three-level linkage decision mechanism, a dynamic adjustment strategy is introduced to carry out online optimization on a diagnosis rule base, and fault modeling and parameter optimization closed loop are completed; according to the method, the problem of modeling misalignment of a traditional method under a nonlinear working condition is effectively solved.

The invention relates to the technical field of retrieval enhancement, in particular to a big language model-based dynamic knowledge retrieval enhancement method, which comprises the following steps of: acquiring theoretical regulations and actual operation data of an unmanned aerial vehicle, and driving a model generation request; monitoring the reasoning text stream in real time, intercepting a logic triple to perform causal verification, and constructing negative feedback prompt blocking and resetting for unsupported logic; executing double-track system dynamic retrieval aiming at regulations and data, evaluating content conformity by utilizing reflection Token and executing conflict resolution correction; and generating a fault hypothesis by adopting tree decoding, constructing an anti-fact query to retrieve the evidence of the security, and pruning the path with the evidence of the security to determine a final path. According to the method, illusion is effectively blocked through real-time logic verification and a negative feedback mechanism, double-track retrieval and anti-fact pruning are combined, strict alignment between the reasoning process and physical facts and theoretical regulations is ensured, and the accuracy and credibility of fault diagnosis are remarkably improved.

The invention discloses a PID (Proportion Integration Differentiation) tracking control method based on error perception nonlinear gain, which is used for high-precision tracking control of an MIMO (Multiple Input Multiple Output) nonlinear system. Comprising the following steps: 1) constructing an adaptive gain by using current error information, historical error information and prediction error information; 2) realizing intrinsic integral saturation resistance through nonlinear integral design; and 3) complete autonomous operation can be realized without accurate system dynamics priori knowledge or manual adjustment. According to the method, the nonlinear compensation capability and the robust adaptive performance are enhanced while the structural simplicity of the PID controller is kept. Through rigorous Lyapunov analysis, the stability of the method to a non-linear system in a general form is verified, and the method shows excellent performance in both adjustment and time-varying reference tracking scenes. The method can be widely applied to the fields of linear motor servo systems, sea surface ship control, unmanned vehicle dynamics control and the like needing high-precision tracking control.

The invention relates to the technical field of energy scheduling, in particular to a dynamic scheduling method for a green electricity ammonia production system based on deep reinforcement learning. According to the big name, a deep reinforcement learning agent is constructed, a near-end strategy optimization algorithm is adopted, and training is carried out by maximizing an innovative composite reward function. According to the composite reward function, accumulated green penalty constraints and multiple high-risk aversion penalty terms are introduced, and complex economic, physical and policy constraints are coupled and optimized. According to the method, multiple constraints can be effectively treated, the load smoothness and energy storage dynamic balance of the electrolytic cell are realized, the accumulated electricity purchase quantity is strictly controlled to be below a preset proportion, the problems of greenness, stability and economy in a high green electricity ammonia production project are solved, and the continuity of back-end production is guaranteed.

The invention relates to the technical field of overwater construction, and discloses a hinge sinking row unit hoisting path optimization and construction intelligent scheduling method, which comprises the following steps: S1, initializing and preparing a system, digitally modeling a construction environment, tasks and resources, instantiating a task agent and a market scheduler, and calculating a construction contribution value; s2, hoisting path optimization and intelligent construction scheduling are carried out, a market scheduler issues resource time slots, a task agent executes path planning and constructs a bidding vector, and comprehensive risks are considered in the path planning; the market scheduler calculates a net contribution value based on the construction contribution value and the opportunity cost, and selects a scheme with the maximum net contribution value to issue an instruction; and S3, monitoring and dynamic intervention are executed, and when preset interruption conditions such as high-priority task preemption or environment safety interruption are met, the current task is interrupted, and scheduling circulation is restarted. According to the method, the resource utilization efficiency, the path security and the system dynamic response capability are improved.

The invention discloses a wide-working-condition steam turbine system operation data correction method based on digital twinning, and relates to the technical field of steam turbine equipment digitalization, and the method comprises the steps: collecting operation data of a wide-working-condition steam turbine system in real time; constructing a digital twinborn model of the steam turbine system; performing prior covariance estimation on the operation data according to the statistical distribution condition and the design parameters; generating a Sigma point by adopting an unscented Kalman filtering algorithm, iteratively updating a state vector and a covariance in combination with a state transition equation and an observation equation, and outputting an updated known variable; performing smoothing processing on the updated known variable in a plurality of time point regions by adopting an RLOESS algorithm to obtain corrected operation data; according to the method, the real dynamic characteristics of the wide-working-condition steam turbine are approached by building the digital twinborn model, the calculation complexity of dynamic data fusion of a steam turbine system can be remarkably reduced, and the problems that the convergence speed is low and calculation is complex due to strong nonlinearity of a traditional method are solved.

The invention discloses a power relay protection fault analysis and fixed value setting method, system and device and a medium, and relates to the technical field of power system relay protection, and the method comprises the steps: obtaining the topological structure information and new energy access information of a power distribution system, and determining a to-be-analyzed fault point set; based on the line parameters of the power distribution system and the new energy grid-connected parameters, establishing a short-circuit current calculation model based on the new energy grid-connected characteristics, and calculating the short-circuit current contribution of each fault point in the fault point set; according to the short-circuit current contribution, the detection sensitivity of the protection device to various faults is analyzed, and a protection characteristic curve reflecting the new energy access influence is generated; and based on the protection characteristic curve, optimizing the setting value of the power relay protection device, and verifying the optimized protection cooperation relationship. According to the method, accurate evaluation and compensation of protection characteristics of different regions are realized, and the technical problem that relay protection setting is difficult to accurately adapt to dynamic characteristics of a system under the condition of new energy access is effectively solved.

The invention discloses an energy structure planning method and system based on an entropy flow dynamic model, and relates to the field of comprehensive energy planning, and the method comprises a first model building module which is used for building a decision matrix and a state matrix, and building an evolution model based on a system dynamics principle; the second model construction module is used for constructing a target function which takes system entropy generation as an optimization target and takes policy implementation cost and system orderliness as constraint conditions according to the entropy balance equation and the thermodynamic force-flow relationship, and constructing a maximum entropy generation model based on the target function and an evolution model; and the path output module is used for performing iterative calculation by utilizing an outer layer nested optimization algorithm based on the maximum entropy generation model to obtain an optimal policy combination of each time node in a preset planning period, and outputting an energy planning maximum entropy path. According to the method, system dynamics and an entropy theory are fused, source-network-load-storage full-link interaction is described, and a scientific and reliable benchmark reference is provided for low-carbon transformation of an energy system.

The invention provides a dynamic grouping method and device for a heterogeneous direct current delivery system, and relates to the technical field of dynamic analysis and control of a power system, and the method comprises the steps: deducing a linear time-varying variation equation which is satisfied by the trajectory sensitivity of a system state trajectory to a system parameter vector based on a parameterized differential-algebraic equation model; calculating the track sensitivity of each device to a system parameter vector, projecting the track sensitivity to a common connection point corresponding to each device, and constructing a unified sensitivity feature vector of each device; calculating the dynamic similarity between the devices based on the unified sensitivity feature vector, and constructing a mixed similarity matrix in combination with the electrical distance similarity between the devices; and feature decomposition and feature vector clustering are carried out based on the mixed similarity matrix, and dynamic clustering of heterogeneous equipment is realized. According to the dynamic grouping method provided by the invention, unified grouping of heterogeneous equipment such as a synchronous machine and a converter can be realized in a heterogeneous power system containing high-proportion new energy and direct-current power transmission.

The application discloses a heterogeneous hardware SM4 adaptive acceleration method based on reinforcement learning, which models the SM4 adaptive acceleration problem in a heterogeneous environment as a reinforcement learning process, and through a closed-loop link of 'full-stack perception-intelligent decision-dynamic library calling-feedback evolution', utilizes the powerful nonlinear fitting capability of a deep network and a proximal policy optimization algorithm to find an optimal solution in a complex software and hardware combination space, and through preset binary libraries, shields the differences of underlying heterogeneous instruction sets, so that an upper intelligent agent can focus on strategy optimization, and thus the unity of performance and flexibility is realized. The application can solve the technical problems that the existing specific instruction set acceleration method based on static compilation optimization cannot effectively cope with the complexity of a heterogeneous Internet of Things environment, and the existing runtime distribution method based on a simple heuristic rule lacks the perception and adaptive capacity for system dynamic load.

The invention belongs to the field of aero-engine control, and particularly relates to a variable cycle engine active disturbance rejection control system which comprises a tracking differentiator, an expansion state observer, an error nonlinear feedback unit and a disturbance compensation unit. The tracking differentiator can obtain the target rotating speed or pressure ratio of the engine and generate the tracking trajectory of the target. The extended state observer can collect the state quantity of the engine and the control quantity of the disturbance compensation unit to generate disturbance estimation and state estimation. The method does not depend on an object accurate model, and only needs to estimate the system dynamics online through an extended state observer. Compared with a traditional PID which needs to repeatedly set parameters (such as a proportionality coefficient and integral time) for different working conditions, control parameters (such as the tracking speed of TD, the bandwidth of an extended state observer and the gain of nonlinear feedback) of the algorithm only need to be calibrated based on the typical working conditions of the engine, and the design complexity and the maintenance cost of the controller are greatly reduced.