499 results about "Systems design" patented technology

The invention discloses an automatic scheduling method and system for ship unloading equipment, and relates to the technical field of port automation. According to the method, a high-precision digital twinborn model for ship unloading operation is constructed, physical equipment is abstracted into a digital intelligent agent with an autonomous decision-making capability, real-time multi-dimensional data and historical data are utilized to perform deep fusion to drive system synchronization, and a future multi-step scheduling strategy is deduced in a parallel simulation manner in a virtual space based on rolling time domain control, so that the real-time multi-dimensional data and historical data are subjected to real-time multi-dimensional data synchronization driving system synchronization is realized. Dynamic evaluation and optimization are carried out by adopting a multi-objective evolutionary algorithm combined with a cooperative game mechanism, and conflicts and cooperation among equipment are effectively coordinated by defining an individual utility function and introducing cooperative game negotiation and a meta-controller to dynamically adjust target weights, so that system-level global optimal scheduling is realized under multiple objectives of efficiency, energy consumption, safety and the like, and the scheduling efficiency is improved. The intellectualization, the self-adaptability and the comprehensive operation benefit of port ship unloading operation are comprehensively improved.

This patent discloses a computer system for humanoid robot control system design and implementation, featuring a digital humanoid robot with dynamical models and a set of single-input-single-output (SISO) and multi-input-multi-output (MIMO) controllers. The system comprises a main software program, a generative Al humanoid robot intelligence engine, a robot motion path planner module, and a control system simulation engine. It enables efficient design, testing, validation, and implementation of robot control systems, significantly reducing time to market. The system supports seamless upgrades to accommodate new designs and components, enhancing applications in industrial automation, healthcare, public safety, and more, aligning with the goals of the 4th Industrial Revolution.

The invention relates to the technical field of distributed computing, and discloses a distributed computing modeling system design method for high-dimensional discrete data, which comprises the following steps: acquiring a feature identifier access request in a high-dimensional discrete data stream, counting an access frequency, and marking a feature identifier of high-frequency access as a high-frequency access state; constructing a local parameter copy on a non-master node physical computing unit of the distributed cluster; routing gradient update data aiming at the feature identifier to a local parameter copy closest to the network and generating a local residual tensor; calculating the direction cosine similarity of the local residual tensor and the global gradient update vector; calculating a real-time access entropy based on the access source distribution and converting the real-time access entropy into a dynamic synchronous threshold value; according to the method, through a dynamic synchronization judgment mechanism based on semantic information gain, high-frequency but invalid redundant communication is effectively inhibited, and network congestion under long-tail distribution is reduced.

The invention discloses an intelligent tea withering control system based on multi-modal feature fusion and time sequence prediction. The system is composed of a multi-modal feature extraction module, a time sequence modeling module, a transfer learning module and an intelligent decision control module, a Transform attention mechanism is adopted to construct a cross-modal fusion framework, RGB images, hyperspectrum and time sequence information are fused, and accurate recognition and trend prediction of the withering state are achieved. According to the system, an adaptive attention fusion network is designed, optimal fusion of images, spectrums and grade information is realized through dynamic distribution of modal weights, and the recognition accuracy and stability are remarkably improved. The classification accuracy of 180 verification samples reaches 93.33%, and is improved by 15.93%-34.83% compared with that of a single-mode method. And cross-environment self-adaption is realized through fusion transfer learning, and the performance is improved by 6.7%-14.3%. The intelligent decision engine optimizes temperature and humidity parameters based on a multivariable coupling control theory, the control precision reaches + / -0.5 DEG C and + / -2.0%, and the response time is 2.5 seconds.

The invention discloses an assembly process knowledge graph construction and updating method based on graph attention network mapping, and the method mainly comprises the following steps: standardization system design construction, data collection, data classification, multi-modal data preprocessing, multi-source information extraction and graph node feature initialization. Semantic modeling and vector space mapping driven by a graph attention network, knowledge storage, construction of an assembly process knowledge graph by using stored knowledge data, and semantic complementation and dynamic updating of a process information model. Through the unique self-attention mechanism of the GAT, the weight can be dynamically distributed for the relationship among different information nodes, so that knowledge reasoning and expression are more accurately carried out, and the problems of knowledge fragmentation, management rigidity, semantic understanding deficiency, low knowledge utilization efficiency and the like in the prior art are systematically solved.

The invention discloses a protocol conversion method and device, a medium and a server system, and relates to the technical field of servers. Once an original protocol type is determined, a dynamic interface routing controller calls a corresponding conversion program stored in a mapping table; and converting the detected heterogeneous bus protocol command into a unified single-line serial bus protocol operation code. As the conversion program and the protocol characteristics are stored in the mapping table, the method has infinite protocol expansion capability, a new protocol can be supported by updating the mapping table and a detection engine without redesigning hardware or modifying codes of an editable logic device, the system design is greatly simplified, and the development cost is reduced. Therefore, the problem that the current programmable logic device can only realize single interface protocol conversion is solved.

The invention provides a deep evidence fusion-based target detection and tracking method for an intelligent maritime investigation instrument, and belongs to the technical field of multi-modal sensor fusion. The method comprises the following steps: performing feature extraction on data of each modal by using a deep learning model, generating a corresponding evidence quality function, then correcting the weight of a sensor through context discount, and finally performing evidence fusion through a Dempster-Shafer rule to generate a global decision result. Another technical innovation point is that the system designs a mechanism for dynamically adjusting the weight of the sensor, and the fusion process is dynamically optimized according to a real-time environment and historical data so as to ensure the self-adaptability of the system in different environments. According to the invention, through combination of a real-time weight adjustment mechanism and a multi-modal fusion algorithm, the precision of sea target detection is improved, sudden environmental changes can be dealt with, and the robustness and high efficiency of the system in long-time operation are ensured.

The invention belongs to the technical field of airborne radar phased-array antenna wave control system design, and particularly relates to an airborne radar phased-array antenna wave control system multi-node software online upgrading method, which comprises the following steps of: 1, synthesizing upgrading files of software needing to be upgraded into a total upgrading file; step 2, extracting a total upgrading file from the software configuration library, sending the total upgrading file to a main node of a system to be upgraded by an upper computer, and performing file verification; step 3, extracting frame header information of the total upgrade file by the master node of the system to be upgraded, comparing the information of each upgrade file with the information of each slave node software collected in real time, and judging whether to upgrade each slave node software; 4, the master node of the to-be-upgraded system disassembles the upgrade file needing software upgrade according to the upgrade file information in the total upgrade file frame header, and issues the upgrade file to the corresponding slave node; and step 5, upgrading the software by the slave nodes needing to be subjected to software upgrading according to the upgrading file.

The invention belongs to the technical field of aviation airborne system design, and provides a helicopter airborne system-oriented novel software architecture and a construction method thereof, and the architecture comprises a hardware abstraction layer, a framework resource layer, an intelligent platform service layer and an application software layer from bottom to top. And the hardware abstraction layer realizes decoupling of hardware and basic software of an operating system. The framework resource layer supports operation of a hybrid key operating system, supports and isolates tasks and application programs with different key levels, software bases and computing power requirements, and provides basic computing communication resources and AI computing power resources. The intelligent platform service layer comprises middleware, a servitization function unit and a servitization management unit, and the servitization function unit comprises atomic services and enhanced services. And the application layer interacts with the intelligent platform service layer and is decoupled from a bottom software and hardware environment. The framework is suitable for unmanned / manned helicopters, and generalization of platform support and maximum reuse of software assets are achieved.

The invention relates to a different intelligence traffic subject interaction information model construction method based on a three-dimensional digital model. The method comprises the following steps: S1, constructing a multi-level scene based on spatial levels of a road traffic system and designing functions of the multi-level scene; s2, defining autonomous levels of the traffic system, and describing the perception capability, decision logic and execution precision of each terminal device of the vehicle road cloud of each level; s3, according to different attributes of traffic entities, designing a perception-transmission-decision-control four-stage traffic information circulation process and realizing unambiguous collaboration among different intelligence subjects; and S4, converting the standardized and defined information model into a plurality of instantiation units, and deploying the instantiation units into computing entities of various end-edge-cloud traffic subjects to support actual operation of a traffic service scene. According to the method, the problems of difficult cross-domain collaboration, non-uniform information models and insufficient global optimization caused by non-uniform intelligent level of traffic subjects in the prior art are effectively solved, and methodological support is provided for design, verification and implementation of a vehicle-road cloud integrated system.

The invention discloses a ship pipeline system model generation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a pipeline schematic diagram and a specification configuration file after receiving a modeling instruction for a pipeline system, determining an element model of a part forming the pipeline system from a model library according to the pipeline schematic diagram, according to the pipeline schematic diagram and the specification configuration file, the primitive model is adopted to generate an initial pipeline system model, and the initial pipeline system model is adjusted to obtain a target pipeline system model when a model adjustment instruction is received. The initial pipeline system model is generated by triggering the modeling instruction, and the target pipeline system model is obtained by triggering the adjustment instruction to adjust the initial pipeline system model, so that a designer does not need to manually model and adjust the model for multiple times according to a pipeline schematic diagram, and the modeling efficiency of the pipeline system model is improved; the design progress of the pipeline system is accelerated; and the design quality is improved.

The invention discloses a nonlinear adaptive control system design method and device based on a pseudo-inverse matrix, and relates to the field of adaptive control, and the method comprises the steps: S1, constructing a controlled object state-space equation comprising matching uncertainty and non-matching uncertainty; non-matching uncertainty is converted into matching uncertainty through pseudo-inverse transformation; s2, introducing the state vector into a regression vector to obtain an expansion regression vector, and obtaining an uncertainty function based on the expansion regression vector; s3, constructing a state observer, and obtaining a state observation value of the controlled object; s4, taking the difference between the state observation value and the state actual value as the excitation of the adaptive law, and updating the parameters of the uncertain function; s5, constructing a self-adaptive control law by taking the estimated value of the uncertain function as input; and S6, filtering an output signal of the adaptive control law through L1 to obtain a final control law. Through the expansion regression vector comprising the state vector, accurate compensation of the uncertain function is realized, and the self-adaptive efficiency is improved.

The invention belongs to the technical field of avionics system design, and particularly relates to an integrated task computer and a backup upgrading method thereof. The comprehensive task computer comprises a core processor and a FLASH memory, the FLASH memory is provided with a starting mirror image file and an application mirror image file from low to high according to addresses, the starting mirror image file is internally provided with a first boot loader, a first PL end bit stream and a system configuration program from low to high according to the addresses, and the application mirror image file is internally provided with a second boot loader, a second PL end bit stream and a system configuration program from low to high according to the addresses. The system configuration program is internally provided with a bootstrap program of the application mirror image file and an identification module for identifying whether the application software is upgraded or not; and the application mirror image file is provided with a second boot loader, a second PL end bit stream and an application software program from low address to high address. According to the invention, the online upgrading function of the equipment master control software and the underlying firmware thereof is realized, and the stability and convenience of the system are enhanced.

The invention provides an automatic software development system based on multi-agent cooperation, and the system comprises a demand analysis agent which is used for receiving a natural language demand input by a shared working area, generating a demand specification document containing an acceptance standard based on the natural language demand, and sending the demand specification document to the shared working area; the detailed design agent is used for receiving a demand specification document input by the shared working area, performing system design based on the demand specification document, generating a design specification document and sending the design specification document to the shared working area; the project development agent is used for receiving a design specification document input by the shared working area, performing code development based on the design specification document, generating an executable code and sending the executable code to the shared working area; and the shared working area is used for storing and forwarding the natural language demand input by the user and the output of the demand analysis intelligent agent, the detailed design intelligent agent and the project development intelligent agent. The development efficiency can be improved, the labor cost is reduced, and the software quality is improved.

The invention relates to the technical field of automatic advanced control theory and application, and provides a non-matching disturbance suppression method and equipment based on an extended compensation function observer, and the method aims at a non-integral chain system with non-matching disturbance, carries out the order expansion processing of the non-integral chain system, and obtains an extended system for displaying and presenting the order derivative of the non-matching disturbance. Designing an expansion compensation function observer according to the expansion system, performing error analysis on the expansion compensation function observer, and selecting gain of the expansion compensation function observer according to a convergence principle of an expansion error equation; and a model compensation control strategy is designed according to the extended compensation function observer and the state error feedback, so that the non-matching disturbance of the non-integral chain system is inhibited. According to the method, the non-matching disturbance of which the order derivative approaches zero can be estimated, so that the limitation on the disturbance is greatly relaxed, and an anti-disturbance control solution with higher precision and wider applicability is provided.

The invention discloses an atmospheric turbulence phase screen generation method based on layered physical constraints, and belongs to the crossing field of optical communication and artificial intelligence. According to the method, a diffusion probability model is combined with layered atmospheric physical constraints, independent physical constraint loss functions are established for a boundary layer, a troposphere and a stratosphere of the atmosphere, and it is ensured that a generated phase screen conforms to turbulent flow statistical characteristics of all layers through power spectrum density constraints and structure function constraints; enhancing feature learning of each layer of phase screen by adopting a physically guided attention mechanism; and designing a time-dependent constraint weight strategy, and adaptively adjusting the physical constraint strength in the diffusion denoising process. The method solves the technical problems that the vertical layering difference is ignored, the physical consistency is insufficient, and the generation quality depends on a large amount of labeled data in the existing method, is particularly suitable for high-fidelity atmospheric turbulence modeling of a satellite laser communication link, and can also be widely applied to the fields of free space optical communication system simulation, adaptive optical system design and the like.

The application provides a virtual modeling-based flight control ICD protocol simulation verification system and a flight control system, comprising a network topology modeling module, a virtual bus modeling service module, an ICD modeling service module, a processing algorithm modeling service module and an ICD simulation running monitoring module, and each module cooperatively realizes a full-process closed loop from ICD analysis to virtual bus simulation verification. The application completes network construction of the system by simulating the commonly used system network bus in the design stage, and in combination with the data processing algorithm, the business data interaction between the system nodes can be simulated in the system design front end, the ICD design problem is identified, the compatibility verification of the ICD and the hardware bus interface is completed in the design front end, the rework waste caused by the design mismatch problem is reduced, and the reliability and delivery efficiency of the system are improved.

The application discloses a train braking system distributed cooperative analysis platform, which comprises a system simulation area, a data acquisition area, a data intelligent analysis area and the like. The data acquisition area acquires vehicle data and transmits the vehicle data to the system simulation area. The system simulation area outputs vehicle simulation data through model-in-loop simulation, rapid control prototype simulation and hardware-in-loop simulation according to the vehicle data. The data intelligent analysis area performs fault diagnosis on a train braking system according to the vehicle data and the vehicle simulation data, and outputs a solution to eliminate faults according to a diagnosis result. The application takes an electronic brake control unit, a pneumatic brake control unit, a basic brake unit and other key components as main control objects, establishes a train braking system distributed cooperative analysis platform based on model simulation and big data analysis, and solves problems existing in system design, system test verification and system operation and maintenance.

The invention discloses an electron beam additive manufacturing method for an integrated copper-chromium contact-conducting rod assembly, and belongs to the technical field of copper-chromium contact manufacturing. The electron beam additive manufacturing method comprises the steps that S1, a special powder system is designed and prepared, specifically, contact area powder and conducting rod area powder are prepared and subjected to drying treatment; s2, digital modeling and support design: establishing an integrated copper-chromium contact-conducting rod assembly model by using three-dimensional software and slicing; S3, fusing and integrally forming by using an electron beam powder bed: printing an integrated copper-chromium contact-conducting rod assembly in a vacuum chamber of the electron beam powder bed, and S4, a printing post-treatment process is carried out, specifically, returning treatment, hot isostatic pressing treatment and machining treatment are carried out on the integrated copper-chromium contact-conducting rod assembly printed piece. According to the printing post-treatment process, the residual stress of the integrated copper-chromium contact-conducting rod assembly can be effectively eliminated through the printing post-treatment process; and the problems of macroscopic cracks and part warping caused by high residual thermal stress can be effectively avoided.

The invention discloses a hydraulic structure risk assessment method based on a multilevel dynamic fuzzy Bayesian network, and relates to the technical field of hydraulic engineering safety monitoring, and the method comprises the following steps: recognizing risk factors of a hydraulic structure, and building a hierarchical hydraulic structure risk assessment system; a Bayesian network risk probability model is constructed based on a risk assessment system, nodes in the model correspond to indexes of each layer of the assessment system, and edges among the nodes are connected according to a causal relationship among the indexes. According to the invention, accurate and dynamic management and control of hydraulic structure risks are realized. In the aspects of data processing and risk judgment, multi-source monitoring data such as displacement, seepage and water level are classified and integrated according to an index layer, a criterion layer and a target layer through hierarchical evaluation system design, the isolation problem of traditional single data monitoring is avoided, the data collaboration value is fully mined through logic association among the layers, and the risk judgment accuracy is improved. And the risk assessment does not depend on one-sided information any more.

A dynamic SLAM robustness improvement method for a degraded motion scene is characterized in that on the basis of an ORB-SLAM2 architecture, a lightweight target detection thread is introduced, YOLO-FASTEST with high reasoning speed and small model size is combined with an NCNN reasoning framework, efficient semantic perception is realized, and prior information is provided for dynamic point elimination. According to the method, the epipolar constraint and the degradation consistency constraint are further fused, a dynamic judgment mechanism fusing camera motion prior residual modeling and Bayesian reasoning is provided, dynamic feature judgment under degradation motion is achieved, and the applicability defect of traditional geometric constraint in a degradation motion scene is effectively overcome. Meanwhile, the system designs a multi-index-driven key frame insertion strategy, the pose change amplitude, the image entropy change and the constraint pixel proportion are jointly considered, and the mapping efficiency and the real-time performance are improved.

The invention belongs to the field of product top-layer system design and modeling, and discloses an interactive feedback-oriented product top-layer system design method, which comprises the following steps of: constructing a multi-layer model based on a demand R, a function F, a behavior B and a structure S, establishing a knowledge graph for representing a semantic relationship between layers and between nodes on the same layer by using weighted directed edges, forming a layer-by-layer mapping matrix by using edge weights, and constructing a layer-by-layer mapping model; realizing weight decomposition from the demand to the structural unit; a constraint hypergraph is constructed on the node set, and structural unit combination constraints are depicted through mutual exclusion, dependency, collaboration and conflict hyperedges; physical parameters of the structural units are normalized into performance vectors, weighted aggregation is carried out according to weights, legality judgment and performance correction are carried out in combination with a hypergraph, a system-level performance evaluation result is obtained, candidate configuration schemes are compared and optimized according to the result, and a product configuration scheme meeting requirements and constraint conditions is formed. The method provides a model basis for subsequent product structure configuration optimization based on interactive feedback.

The invention relates to the technical field of building energy conservation and green buildings, and discloses a design parameter optimization method for a tropical zero-carbon building integrated system. According to the method, an input correlation-output uncertainty-global sensitivity three-dimensional analysis framework is constructed, through high-fidelity simulation modeling, Latin hypercube sampling and Gaussian process proxy model construction and verification, and in combination with Pearson correlation analysis, Monte Carlo propagation and Sober sensitivity calculation, a dominant parameter set and key interaction items are accurately recognized, and the accuracy and the reliability of the system are improved. And finally, solving the optimal low-carbon parameter combination by adopting a sequential quadratic programming algorithm under the engineering constraint. The system comprises twelve functional units such as a meteorological acquisition unit, a parameter definition unit and a simulation modeling unit, and outputs a parameter list which can be directly used for enclosure construction, unit type selection and photovoltaic arrangement. According to the method, scientificity and implementability of parameterization design of the tropical zero-carbon building are improved, annual net carbon emission can be reduced through actual measurement, and intelligent decision support is provided for the building double-carbon target.

The invention discloses a deep reinforcement learning environment construction and reservoir intelligent scheduling decision method and system, and relates to the technical field of water resource management and intelligent control. Compared with a traditional scheduling method, the power generation income is improved by 12.8%, and the comprehensive benefit is improved by 25%; the constraint violation rate is greatly reduced: through an intelligent constraint processing mechanism, the constraint violation rate is reduced to 2.1% from 7.2% of a traditional method; the performance reduction range of the system under the extreme hydrological condition is controlled within 8.2% through a multi-algorithm fusion framework; due to an end-to-end learning mechanism, the system has self-learning and self-adaptive capabilities, and a scheduling strategy can be continuously optimized; an interpretability analysis tool is integrated, so that the trust degree of engineering technicians to the intelligent scheduling system is improved; the system design fully considers engineering application requirements, and supports progressive deployment and man-machine cooperative scheduling.

An anomaly detection method includes determining state variables of an industrial control system based on a system design of the industrial control system; determining invariants governing the state variables based on the system design; receiving historical measurement data of the state variables of each invariant from the industrial control system; constructing a set of behavioural models for each invariant using a set of machine learning algorithms and the historical measurement data of the respective state variables, the behavioural models representing normal behaviour of the respective state variables; predicting measurement data of the state variables of each invariant using the behavioural models and the historical measurement data of the respective state variables; receiving current measurement data of the state variables during operation of the industrial control system; and detecting the anomalies based on deviations between the current measurement data and predicted measurement data of the state variables of each invariant.

The application discloses an airplane hydraulic servo actuating system simulation method based on digital twinning, and the method comprises the following steps: (1) constructing a digital twinning hydraulic simulation model and a digital twinning three-dimensional visual model of an airplane hydraulic servo actuating system physical system; (2) storing simulation model output data of a monitoring point of the digital twinning hydraulic simulation model and sensor acquisition data of the airplane hydraulic servo actuating physical system in real time and synchronously to form twinning data; (3) comparing and analyzing the simulation model output data and the sensor acquisition data, iteratively optimizing the digital twinning hydraulic simulation model through a model optimization module, and simultaneously performing three-dimensional visual demonstration on the working condition of the airplane hydraulic servo actuating virtual model. The application can provide a simulation modeling and optimization method for airplane hydraulic servo actuating system design, and provide a reference for research and verification of virtual-real mapping technology of the airplane hydraulic servo actuating system based on digital twinning.

The invention discloses a model-based civil aircraft integrated modular avionics resident system design method. The method comprises the steps of S1, resident system demand modeling and demand confirmation based on a customized MBSE method; s2, performing resident application software function logic modeling based on a Simulink model; s3, performing qualitative security analysis on the resident system based on the function scene and the fault combination; the input of the step S1 comes from a technical protocol of a resident system issued by a host, and through modeling iteration, the demand of the resident system is captured and issued to the step S2; s2, feeding back a system design problem identified in the modeling process; the step S1 synchronously sends the demand of the resident system to the step S3, and at the same time, the step S3 feeds back the identified security demand and constraint to the step S1 to support system demand iteration. According to the invention, an efficient, replicable and landing design thought is provided for the integrated modular avionics residence system, the system design efficiency is improved, and the verification cost is reduced.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are configured to detect and characterize power quality issues (PQIs) by independently training artificial intelligence (AI) and machine learning (ML) models on each power quality issue and sequentially deploying them is disclosed. A multi-tier architecture includes PQI agents that are deployed reliably to monitor the power quality issues in reduced time. The multi-tier architecture includes the capability for the models to dynamically update on new data to adjust to the constantly changing conditions of the power grid. An extensible power-quality-issue-aware detection system generates data-driven anomaly scores to guide engineers and others in performing root case analysis (RCA) on power quality events associated with a facility or equipment. The system is designed for seamless integration with various power quality monitoring systems of different sensitivity or thresholds used to identify different classes of power quality issues.

The invention provides a flight control ICD protocol simulation verification system based on virtual modeling and a flight control system. The flight control ICD protocol simulation verification system comprises a network topology modeling module, a virtual bus modeling service module, an ICD modeling service module, a processing algorithm modeling service module and an ICD simulation operation monitoring module, and all the modules cooperate to achieve a whole-process closed loop from ICD analysis to virtual bus simulation verification. According to the method, network construction of the system is completed by virtually simulating a common system network bus in a design stage, service data interaction between system nodes can be simulated and ICD design problems can be identified at a system design front end by combining a data processing algorithm, compatibility verification of the ICD and a hardware bus interface is completed at the design front end, and the design efficiency is improved. Reworking waste caused by the design mismatching problem is reduced, and the reliability and delivery efficiency of the system are improved.

The invention discloses an underwater wireless power transmission system parameter identification method based on machine learning, which comprises the following steps: constructing a data set through finite element simulation, and obtaining original input parameters including geometry, electromagnetism and position offset and corresponding key output parameters; feature engineering is executed, and derived features with physical significance are extracted; performing standardized preprocessing on the data; for each key output parameter, independently training an XGBoost regression model; carrying out five-fold cross validation on the training set by adopting a Bayesian optimization algorithm, and carrying out independent hyper-parameter optimization on each XGBoost model; and carrying out interpretability analysis on the trained agent model by utilizing SHAP analysis, quantifying the contribution degree of each input feature to a prediction result, and providing physical insight. According to the method, high-precision prediction of the electromagnetic parameters under the complex working condition is achieved, complex electromagnetic field calculation is avoided, the system design efficiency is remarkably improved, and the efficiency and interpretability of intelligent optimization design of the UWPT system are remarkably improved.