1719 results about "State-space representation" patented technology

The invention, which relates to the technical field of air transportation and income management, discloses a dynamic generation method and system for an air travel price, and the system comprises a user behavior fine-grained tracking module, a dynamic pricing decision engine module, a cross-channel cooperative control module, and a compliance auditing and feedback module. Through a real-time data stream fusion technology, multivariate signals such as competition dynamic signals, user behavior signals and external environment signals are integrated, and second-level strategy response is realized in combination with the online training capability of a reinforcement learning model; through dynamic state space modeling, variables such as demand popularity, user sensitivity and external risk are coded into six-dimensional vectors, and the limitation of a fixed formula is broken through in combination with the nonlinear mapping capability of a deep Q network; through three measures of dynamic modeling, elastic constraint and cross-chain cooperation, the problems of response lag, high compliance risk and split user experience of a traditional pricing technology are solved.

The invention relates to the technical field of power distribution network evaluation, and discloses a power distribution network bearing capacity evaluation system based on dynamic correction. The system comprises a dynamic data acquisition module, a multi-dimensional state space construction module, a security domain analysis module, a partition coupling degree calculation module and a bearing capacity evaluation engine module. The dynamic data acquisition module acquires a power injection quantity sequence, a voltage deviation ratio sequence and uncontrollable parameter fluctuation data of each partition node of the power distribution network; a multi-dimensional state space construction module performs dimension raising mapping on the sequence to generate a linearized power flow state space model containing a power-voltage Jacobian matrix; the security domain analysis module corrects the boundary of the model according to uncontrollable parameter fluctuation and generates a dynamic security operation constraint set; the partition coupling degree calculation module quantifies an electrical independence index by means of a spectrum radius; and the bearing capacity evaluation engine constructs a chance constraint optimization model, outputs the photovoltaic maximum accessible capacity of each partition and a safety guarantee supply control strategy set, and improves the evaluation accuracy and practicability.

The invention discloses a target detection method based on Mama feature fusion, and relates to the technical field of image target detection. According to the method, the innovative implementation of the VSSA module is utilized, a selective scanning mechanism of the state space model is applied to 2D visual data processing, the long-distance dependency relationship in the image is effectively captured through state space modeling in four directions, the limitation of a traditional state space model in the two-dimensional visual data processing process is solved through the multi-direction processing strategy, and the processing precision of the 2D visual data is improved. The model can comprehensively perceive spatial dependency relationships in different directions in an image, the VSSA adopts learnable state space parameters to dynamically model a feature sequence, the ability of the network to understand a complex space structure is enhanced, the method is particularly suitable for processing scenes needing long-distance context information, and in addition, the method is combined with MTMHSA, so that the complexity of the network is reduced. And the fusion capability of different levels of features in target detection is further enhanced. Through the innovation, the model can better understand the target in the image, and the positioning and classification precision of the target is improved.

The invention relates to the field of mechanical equipment health management, in particular to a large sliding bearing fault detection and evaluation method, device and system. Comprising the following steps: collecting multi-source sensing data, and constructing a comprehensive data set; constructing a state space model based on a sliding bearing physical mechanism; the multi-source sensing data and the state space model are fused through Bayesian filtering, and hidden state parameter posterior distribution is dynamically estimated; generating a virtual fault sample by using a generative adversarial network in combination with a physical rule base; designing a Bayesian space-time sequence diagnosis model based on an attention mechanism, and generating fusion health state features; processing and fusing the health state features by using a degradation process model, and predicting the remaining service life of the bearing; and based on the health state, the fault probability and the remaining service life, setting multi-stage early warning threshold values, and triggering intelligent early warning. According to the method, the defect that a single model is insufficient in adaptability and generalization ability under complex working conditions is overcome, and the accuracy and reliability of fault detection are remarkably improved.

The invention discloses a power system load dynamic optimization method based on reinforcement learning. The method comprises the following steps: S1, collecting power system data to construct a state space; s2, constructing a hierarchical reinforcement learning model based on the state space, and dividing a high-level decision and a low-level execution task; s3, training a high-level decision model, and outputting a scheduling task target category instruction in a high-level state; s4, training a low-layer execution model, and outputting a control action in combination with a current node state and a high-layer instruction; s5, introducing an evolutionary mechanism to generate a strategy population and optimizing a low-layer execution model; s6, fusing an evolutionary mechanism and a strategy gradient to synchronously optimize individuals with excellent performance; s7, deploying the trained model to a power dispatching system; s8, performing model parameter fine tuning based on scheduling feedback; and S9, continuously applying the fine-tuned model to load scheduling control. According to the invention, power load accurate scheduling and strategy efficient adaptive optimization are realized, and system responsiveness and operation stability are improved.

The invention relates to the technical field of power grid operation and maintenance, and discloses an AI-based reactive compensation optimization method and system, and the method comprises the following steps: integrating the four-dimensional characteristics of traffic flow, power grid load, user preference and equipment health degree, constructing a space-time correlation graph model, achieving the adaptive evolution of a topological structure through dynamic graph convolution and an attention mechanism, and obtaining a reactive compensation optimization model. The method comprises the following steps: fusing spatial-temporal features of a graph neural network with a BiGRU time sequence for modeling, injecting an equipment health degree attenuation factor, generating a charging demand prediction result with uncertainty quantification, expanding an intelligent agent state space, improving a reward function, and embedding equipment health degree constraints in a strategy network and near-end optimization. By sensing the degradation state of the equipment in real time and intelligently adjusting the reactive compensation strategy, the service life of the old equipment is prolonged while the voltage stability is guaranteed, the deviation accumulation effect is effectively inhibited through feedforward-feedback composite control and dynamic rescheduling, and accurate matching of a scheduling instruction and actual output is ensured.

The invention discloses an efficient approaching rainfall forecasting method, and belongs to the technical field of meteorology. The method specifically comprises the following steps: firstly, acquiring radar echo data of a public meteorological platform, constructing an echo sequence data set, and dividing the echo sequence data set into a training set and a test set; then, on the basis of the state space model and the convolution model, an efficient double-branch fusion approach rainfall forecasting model is constructed; the model is composed of an encoder, a middle layer and a decoder. The middle layer adopts a state space module and a convolution module to form a double-branch architecture to realize multi-frequency feature extraction, and dynamic weight distribution of multi-scale features is realized through a feature fusion module. Thirdly, training an approaching rainfall forecasting model by using the training set; and finally, inputting radar data observed in real time to obtain a forecast result at a future moment. According to the invention, characteristics of different scales and frequencies in echo data can be effectively captured; while the parameter quantity and the calculation quantity of the model are reduced, the performance of forecasting the short temporary rainfall can be greatly improved.

The invention relates to the technical field of clean environment control, in particular to a dynamic pipe network and model predictive control clean room energy-saving pressure control method and system. Obtaining current pipe network impedance according to the pipe network impedance curve; calculating the current valve impedance according to the valve opening; calculating the total pressure drop of the current pipe network; constructing a fan dynamic model based on a fan similarity law to calculate the air volume at the next moment; a clean room pressure difference dynamic model is constructed, and the clean room pressure difference at the next moment is calculated; constructing a state space model and a target function of a model prediction controller; and when the pressure difference of the clean room is unstable, predicting the change trend of the pressure difference of the clean room in the next time period, and reversely solving the optimal fan frequency and valve opening of the discretization state space model by using the model prediction controller so as to achieve the lowest pipe network impedance and obtain the optimal fan frequency. The control precision and robustness of the pressure difference of the clean room are remarkably improved, and meanwhile energy consumption is reduced.

The invention discloses a physical information neural network-driven ocean island typhoon scene generation method and system. The method comprises the steps of collecting multi-source heterogeneous meteorological data and performing space-time alignment preprocessing; constructing a coarse-scale space-time probability prediction model, capturing space correlation of meteorological elements by using a graph topology learning network, efficiently processing long-time-sequence dependence of typhoon evolution by integrating a state space model with linear complexity, and generating a probabilistic typhoon scene with coarse resolution through a multivariable joint distribution probability model; further constructing a physical downscaling model, taking a coarse-scale prediction result as condition input, and performing physical consistency downscaling on a coarse-scale scene by embedding an atmospheric fluid mechanics equation in a loss function as a physical hard constraint; and finally, outputting a high-resolution typhoon scene with probability reliability and physical authenticity.

The invention belongs to the related technical field of artificial intelligence, and discloses a robot time sequence imitation learning method and system based on a Mama coding complete history, and the method comprises the steps: receiving a multi-modal observation sequence in a task execution process of a robot, the multi-modal observation sequence comprising observation data of at least one sensor; processing the multi-modal observation sequence by using a sequence processing module based on a state space model, and updating a time sequence output of complete historical information of one code up to the current time step at each time step; and predicting the next step or a series of future actions of the robot based on the time sequence output of the current time step so as to control the robot to simulate. The time sequence processing module based on the state space model is utilized to process and encode the complete observation history in the task execution process of the robot, so that a non-Markov decision-making imitation learning method is realized, and the learning efficiency and the execution success rate of the robot in a complex and state-dependent long time sequence operation task are improved.

The invention relates to the technical field of artificial intelligence computer vision, in particular to an event camera pedestrian detection method based on a space-time state space model, and the method comprises the steps: collecting a pedestrian detection data set based on an event camera, obtaining original event data, carrying out the preprocessing, determining an event tensor, and obtaining an event frame sequence; modeling is carried out through combination of a state space and an event tensor, an event-driven recursive space-time state space module is defined as a core unit, and an isomorphic deep neural network architecture is constructed; training the isomorphic deep neural network architecture by adopting the training set, and verifying through the verification set; inputting the test set into the verified isomorphic deep neural network architecture for detection, and generating a pedestrian detection result; the collaborative optimization of sparse adaptation-dynamic capture-noise suppression is realized in a unified framework, the essential characteristics of the event camera triggered based on brightness change are theoretically fit, and higher robustness and generalization ability are shown in an actual complex scene.

The invention relates to the technical field of intelligent mechanical arm control, and discloses a mechanical arm track optimization method and system based on deep learning and a fuzzy algorithm, and the method comprises the steps: building a kinematic model of a mechanical arm, determining the working space of the mechanical arm, carrying out the high-density random sampling, and generating a three-dimensional point cloud picture of a reachable region at the tail end of the mechanical arm; constructing a path planning model, designing a state space and an action space, and constructing a reward function; time-impact double-target optimization is carried out on the tail end path point sequence, a smooth joint trajectory is constructed, and balance between the shortest trajectory execution time and the minimum joint impact is achieved on the premise that speed and acceleration constraints are met; and tracking control is carried out on the trajectory, external disturbance and unmodeled dynamics are estimated and compensated in real time, a parameter adaptive law is designed, and the trajectory tracking precision of the system in a complex environment is improved. The autonomy, the accuracy and the anti-interference capability of the hot-line work mechanical arm in a complex environment are improved.

The invention discloses an engine residual service life prediction method and system based on space-time state selection, and belongs to the field of equipment residual service life prediction. According to the method, multiple technologies such as a time sequence-space double-branch coding and hierarchical fusion mechanism, a selective state space model, a cross-layer residual jump connection and parameter sharing mechanism and an efficient self-attention mechanism are integrated, and an STSSFormer network model is constructed to predict the residual service life of the aero-engine; the system mainly comprises a data selection and preprocessing module, an input sample construction module, a model training module and a residual service life prediction module. According to the method, the feature expression and fusion capability is comprehensively enhanced, and the method has remarkable advantages in the aspects of prediction accuracy of the remaining service life, model robustness and engineering practicability.

The invention relates to the technical field of aerocar mode switching, and discloses a distributed driving aerocar self-adaptive fault-tolerant control method for actuator multimode failure, which comprises the following steps: constructing a unified six-degree-of-freedom dual-mode state space model; residual signals are generated based on extended Kalman filtering and a sliding-mode observer, and fault types and positions are positioned in real time through a lightweight classifier; the method comprises the following steps: extracting residual time-frequency features, identifying hard faults by using a lightweight convolutional neural network, quantifying soft fault degrees through an incremental support vector machine, fusing multi-source information based on a Bayesian network to output fault types, levels and confidence coefficients, and introducing an incremental learning mechanism to realize self-evolution of a diagnosis model; a virtual control instruction is generated by adopting hierarchical sliding mode control, thrust and torque distribution of remaining actuators is optimized based on a dynamic quadratic programming algorithm, control parameters are adjusted online in combination with a Lyapunov adaptive law, aerodynamic interference and model uncertainty are inhibited, attitude stability and trajectory tracking in air-ground mode switching are guaranteed, and the method has the advantages of being high in reliability and high in reliability. And the fault-tolerant performance and the operation safety of the hovercar in the air-ground mode switching process are obviously enhanced.

The invention discloses a course resource recommendation method and device based on an improved state space model, equipment and a medium, and relates to the technical field of learning resource recommendation, and the method comprises the steps: collecting user course resource data, obtaining and preprocessing an interaction sequence, mapping the user interaction sequence to a low-dimensional vector space, and inputting the low-dimensional vector space into the improved state space model; the target interest course is matched with the candidate course resource set, the recommendation score is calculated, and the recommendation list is generated, so that the calculation complexity is reduced, the user interest is accurately captured, and the efficiency and accuracy of course resource recommendation are improved.

The invention relates to the technical field of 5G edge collaborative power supply driving, and discloses an intelligent 5G edge collaborative power supply driving system, which comprises a state sensing module used for collecting multi-source data of each power supply device in the power supply driving system in real time through a multi-source sensor; the load prediction module is used for predicting a future load by using a load prediction algorithm and outputting a load prediction value; the thermal path analysis module is used for constructing a thermal path diagram, predicting a thermal diffusion trend and adjusting power output of the power supply driving system; the power dispatching optimization module is used for adjusting the power of the power supply based on the optimization objective function; and the remote cooperative control module is used for the cloud platform to generate an optimization strategy according to the real-time states of load prediction, temperature prediction and power supply scheduling. According to the method, the integrity and the time relevance of the equipment operation state expression are improved by constructing the continuous time state evolution model in a modeling mode of combining the multi-source state perception and the state space model.

The invention discloses a high-resolution remote sensing image semantic segmentation method based on multidirectional parallel selective scanning, and belongs to the technical field of high-resolution remote sensing image processing. According to the method, a multidirectional parallel selective scanning model is provided, direction perception modeling is carried out through 8-direction serialization scanning in combination with a state space model SSM, and the multidirectional long-distance dependence capture capability is enhanced while the linear calculation complexity is kept. A pyramid encoder-decoder structure is constructed, multi-level feature extraction is realized through a four-stage OSSBlock module, and local details and global semantics are dynamically fused in cooperation with SE attention jump connection of a decoder. A selective scanning mechanism is adopted to replace self-attention, and linear complexity calculation is realized through a state space parameter matrix; and designing a mixed loss function, and improving the small target segmentation precision in combination with the class balance of Dice Loss and the difficult sample mining capability of Focal Loss.

The invention provides a transient overvoltage risk assessment method, device and equipment for an AC / DC system containing high-proportion new energy, and a storage medium. Relates to the technical field of power systems and automation thereof. The method comprises the following steps: modeling a power system into a discrete nonlinear power system based on phase change measurement unit data, constructing a state space, introducing a Koopman operator to determine an observation function, and establishing a dynamic time sequence track prediction model based on the observation function to output a predicted dynamic time sequence track; an Informer model is constructed, in response to an input predicted dynamic time sequence track, feature weights are distributed through a ProbSparse self-attention mechanism, hierarchical feature down-sampling is performed by using a distillation mechanism, and a predicted transient voltage amplitude is output; and quantifying the transient overvoltage risk level according to the predicted transient voltage amplitude. According to the method, the problems of low isolated time section feature prediction precision and poor long-sequence dynamic evolution feature evaluation timeliness in the prior art are solved.

The invention relates to a hyperspectral image classification method and device based on a state space model. The hyperspectral image classification method based on the state space model comprises the following steps: sequentially carrying out feature extraction and serialization processing on hyperspectral image data to obtain a shallow feature projection vector; performing global-local feature extraction on the shallow feature projection vector by adopting a neural network based on a state space model to obtain a fused feature projection vector; and carrying out pixel-by-pixel classification and dimension rearrangement on the hyperspectral image data in sequence to generate a classification result of the hyperspectral image data. According to the hyperspectral image classification method based on the state space model, long-range dependence modeling is achieved through the neural network based on the state space model with linear complexity, the calculation complexity is effectively reduced, and through feature fusion and residual error connection, the classification accuracy of the hyperspectral image is improved. And the perception capability of the neural network on different scale space-spectrum structures in the hyperspectral image is effectively enhanced.

The invention discloses a millisecond regulation and control method for hydrogen fluoride production based on reinforcement learning and model prediction control, and relates to the field of hydrogen fluoride production regulation and control. In the multi-scale neural symbol dynamics modeling step, GNN, a cellular automaton and a state space model are fused, and parameters are updated in real time; in the causal reinforcement learning decision optimization step, an effect is calculated through a causal graph, and a reward function is optimized; in the time-space fractional order sliding mode control step, a fractional order sliding mode surface and a controller are designed, and rapid and stable control is achieved; in the memory enhancement element learning adaptation step, a DNC storage strategy is utilized, new working conditions are quickly adapted through element gradient, and millisecond-level precise regulation and control are achieved. According to the method, prediction errors are greatly reduced, the response speed is increased, and overshoot is reduced; the product yield is improved, the energy consumption is reduced, and new working conditions are quickly adapted; fault detection and risk early warning are more accurate, equipment operation is more stable, production efficiency is effectively improved, cost is reduced, and safety is enhanced.

The invention relates to the technical field of inverter control, and provides an MBD-based reinforcement learning inverter control algorithm optimization method, which comprises the steps of S1, establishing a state space model of an inverter, designing a baseline controller of double-loop control, and constructing an MBD simulation platform containing multiple load models; s2, defining a state space of the 12-dimensional state vector, designing a continuous action space, and constructing an adaptive multi-target reward function; s3, training a control parameter optimization strategy by adopting an Actor-Critic algorithm architecture in combination with an experience playback mechanism and a hybrid exploration strategy; s4, establishing a security constraint mechanism of three-layer security protection, designing a fault detection and isolation strategy, realizing a closed-loop online learning strategy of pre-training-transfer learning-online fine tuning, and meanwhile, adopting a self-adaptive updating mechanism; and S5, verifying the optimization effect of the control algorithm through quantitative index evaluation, an experimental verification scheme and a real-time performance requirement test. And the upgrade of inverter control from model driving to data and model cooperative driving is realized.

The invention discloses a blockage detection method, system and equipment for a flow measurement device and a medium, and relates to the field of blockage detection. The method comprises the following steps: acquiring an original pressure signal and an original flow signal of a to-be-measured flow measuring device, and generating an intrinsic mode function according to the original pressure signal and the original flow signal; extracting a time vector, a space vector and a frequency domain vector of the intrinsic mode function, obtaining an attention weight through a double-path cross attention mechanism, and performing weighted fusion on the time vector, the space vector, the frequency domain vector and the attention weight to obtain a multi-dimensional feature vector; inputting the multi-dimensional feature vector into a pre-trained blockage probability prediction model based on deep learning to obtain a blockage probability value; and constructing a state space according to the blockage probability value, the historical maintenance record and the equipment operation duration, balancing false alarm and leak detection punishment in combination with a reward function, and determining execution operation. By implementing the technical scheme provided by the invention, the accuracy and reliability of blockage detection are improved.

The invention relates to the technical field of oil and gas well management, in particular to an intelligent remote transmission control oil and gas well system based on the Internet of Things and multi-dimensional physical sensing feedback. Comprising a multi-dimensional sensor module; a 4G unvarnished transmission communication module and an intelligent remote decision module; the intelligent remote decision-making module is used for analyzing the collected data and generating a control strategy based on a self-adaptive gradient lifting decision-making tree algorithm; and the wide-temperature adaptive power supply module is used for providing continuous power supply for the system based on a multi-energy collaborative energy management algorithm and realizing energy optimization in an off-grid environment. By integrating multi-dimensional physical quantities such as pressure, flow, temperature and vibration, a multi-parameter coupled state space model is constructed, high-confidence real-time data input is provided for control strategy generation, limitation of traditional data processing on dimension coverage and feature extraction is broken through, and comprehensiveness and accuracy of gas well operation state evaluation are improved.

The invention discloses a reasoning optimization method and device for a code generation large model, equipment and a medium, and relates to the technical field of model reasoning, and the method comprises the steps: in the reasoning process of a code generation task of a target code generation large model, executing a multi-granularity uncertainty quantification step in parallel every time a new Token is generated, obtaining a multi-granularity uncertainty score; constructing a state space vector, and utilizing a preset reinforcement learning strategy network to evaluate the selection probability of a plurality of preset reasoning optimization strategies based on a preset smooth decision mechanism so as to determine a target reasoning optimization strategy; if the strategy is a preset reasoning acceleration strategy, optimization processing is carried out through speculation decoding; if the strategy is a preset exploration optimization strategy, performing optimization processing by using a preset multi-path sampling technology and a preset knowledge enhancement technology; if the strategy is the preset fuzzy processing strategy, taking the plurality of candidate outputs as target reasoning outputs for optimization processing; and evaluating the decision effect according to the reasoning result to optimize the preset reinforcement learning strategy network.

A natural language test case for an application is automatically converted into a test script by a test script generator. During the generation of the test script, the test script generator may access a blueprint of the application. The blueprint may include a time-evolving model of the application, which may include a set of translations and a state machine model of the application. The state machine model may include a state space and a set of state transitions. During the test script generation process, the blueprint may be continually updated to include new knowledge of the application. The test script generator may communicate with an artificial intelligence (AI) engine in order to determine the semantic similarity between two phrases, convert images into textual description, and perform tasks requiring the use of a large language model (LLM).

The invention discloses a directional drilling track accurate control technology based on machine learning, and relates to the technical field of drilling engineering. The directional drilling track accurate control technology comprises the following steps that underground parameters of a drilling tool during underground operation are obtained; establishing a dynamic model based on the drilling tool structure and the motion state; based on the dynamic model, introducing a long-short-term memory neural network, and constructing a hybrid prediction model; drilling parameters are input into the hybrid prediction model, and trend information of multiple tracks is output; based on current geological conditions, drilling tool configuration and operation safety constraints, performing simulation evaluation on the trend information of the plurality of candidate tracks, and screening out an optimal track meeting track precision and underground safety requirements from the candidate tracks; based on the optimal track, control strategy input is constructed, and a state space containing a tool face angle, target azimuth deviation and a drilling tool state is set; and through a deep reinforcement learning method, an advanced adjustment instruction for the guiding tool is generated, and drilling operation is executed according to the optimal track and the advanced adjustment instruction.

The invention belongs to the technical field of expressway operation and maintenance, and relates to an intelligent operation and maintenance method and device for an expressway strong current system, and the method comprises the following steps: collecting and preprocessing multi-source data; constructing a state space model and defining a system state vector; obtaining an estimated state value by adopting a state estimation algorithm; performing fault anomaly detection based on the estimated state value and the multi-source data; extracting a device feature vector and calculating a health index; predicting the remaining service life of the equipment and judging the potential fault risk, and generating a maintenance work order and determining the priority when the threshold value is exceeded. According to the technical scheme of the invention, work orders are generated through multi-source data acquisition, state modeling and estimation, anomaly detection, health assessment and life prediction, so that the whole-process intelligent operation and maintenance of the highway strong current system is realized, and the real-time sensing and diagnosis capability of the operation state can be improved. And the requirements of operation and maintenance real-time performance improvement, data unified management, intelligent diagnosis enhancement and emergency disposal high efficiency are met.

The invention relates to the technical field of power systems, and provides a power distribution network multi-dimensional regulation and control decision method, system and device and a medium, and the method comprises the steps: inputting the preprocessed multi-source operation data into a preset state perception model, and obtaining a multi-dimensional state vector representing the operation state of a power distribution network; a multi-dimensional state vector is used as a state space, regulation and control operation is used as an action space, a composite reward function is established according to a power distribution network operation target, and modeling is carried out to obtain a Markov decision process framework; interacting with a power distribution network simulation environment by adopting a deep reinforcement learning algorithm, obtaining a current state from a state space, selecting and executing regulation and control operation in an action space according to a strategy network, updating strategy network parameters based on feedback of a composite reward function until an optimal regulation and control strategy network is obtained, and obtaining a deep reinforcement learning strategy model; and performing strategy rolling updating based on the real-time monitoring data to obtain a target regulation and control strategy. According to the invention, comprehensive optimal regulation and control of a complex operation scene can be realized.

The invention relates to the technical field of bridge engineering intelligent construction, discloses a digital twinborn and multi-physics field simulation-based lattice pier assembly error intelligent prediction method, and aims to construct a lattice pier assembly error prediction model. The lattice pier assembly error prediction model is composed of a channel independent feature extraction module of multi-physics field data, a self-adaptive space-time coupling and multi-factor dynamic fusion module and a training lattice pier assembly error prediction model, the multi-physical field data channel independent feature extraction module maps data of each physical field to a high-dimensional feature space through calculation, and according to a state space model, the adaptive space-time coupling and multi-factor dynamic fusion module introduces a plurality of factors to dynamically adjust weights of the physical fields in different time steps. Carrying out adaptive fusion on the processed physical field data through a space-time coupling function to obtain coupled physical field data; and finally, taking the output of the two as the input, and combining a regression model to predict the lattice pier assembly error.

The invention discloses a layered optimization regulation and control method and system for electricity-hydrogen coupling in a multi-energy complementary system, and relates to the technical field of multi-energy complementary system optimization regulation and control, and the method comprises the following steps: obtaining the operation data of the multi-energy complementary system, and carrying out the aggregation of the operation data based on the correlation of an optimization target, and forming a layered optimization data set; constructing a corresponding state space model based on the hierarchical optimization data set, defining an action space of each level, and designing a multi-target reward function; inputting the state space model, the action space and the multi-target reward function into a reinforcement learning agent for training to obtain a strategy model; based on the strategy model and the multi-target reward function, collaborative optimization is carried out on the strategies of all levels to generate a global optimization strategy; inputting the global optimization strategy and the state space model into a prediction optimization module, and performing rolling optimization to generate an optimization scheduling scheme; and according to the optimized scheduling scheme, generating a scheduling instruction after security constraint inspection, issuing the scheduling instruction to a system for execution, and updating the strategy model based on operation feedback.