698 results about "Location prediction" patented technology

The invention provides a civil air defense engineering concealed conduit leakage positioning method based on acoustic characteristics, and belongs to the technical field of civil air defense engineering. An acoustic signal acquisition network is constructed by deploying a high-sensitivity hydrophone array, and signals are preprocessed by using a time division multiple access technology and a pulse compression technology; and carrying out time-frequency analysis by applying wavelet transform to extract acoustic features. A time reversal mirror technology is introduced to identify direct propagation and multipath reflection signals, a fluid acoustic coupling propagation equation is constructed to analyze a leakage sound source mechanism, and pipe network topological information and a sound wave speed correction function are combined to compensate a measurement error. Wherein the deep learning pipe network acoustic propagation multi-modal model is fused with a pipeline structure encoder, an acoustic feature extractor and a position prediction decoder, and high-precision leakage positioning and degree evaluation in a complex environment are realized through a three-stage pre-training strategy; the technical problem that it is difficult to accurately locate the position of a leakage point in the complex pipe network environment of civil air defense engineering is solved.

The invention provides a control method for optimizing operation of high-power short-pulse microwave equipment, and aims to improve the accuracy of microwave interference signals, the energy utilization efficiency and the system adaptability. The method comprises the following steps: firstly, acquiring position information, motion trail data, electromagnetic scattering characteristics and environmental electromagnetic parameters of a target object; and then, according to the target position prediction data, the electromagnetic scattering characteristics and the environmental electromagnetic parameters, generating a microwave pulse waveform control instruction. And controlling the phased-array antenna array to generate a directional microwave beam based on the control instruction and the target position prediction data. And collecting real-time response data of the target, dynamically updating the target motion trend prediction model according to the real-time response data, and recalculating microwave pulse signal parameters. And finally, according to the updated signal parameters and the target position prediction data, adjusting the transmitting power, the working time sequence and the beam direction of the phased-array antenna array so as to maintain the optimal interference effect, reduce unnecessary energy consumption and improve the stability and adaptability of the system.

The invention discloses a chip defect weak supervision semantic segmentation method based on YOLO and a diffusion model, and the method comprises the steps: collecting a chip defect weak supervision data set, carrying out the weak supervision manual marking, and constructing a chip defect image weak supervision data set; constructing and training a target detection model based on the chip defect image weak supervision data set; obtaining a to-be-detected chip defect image, inputting the to-be-detected chip defect image to the trained target detection model for defect position prediction, and outputting a chip defect area positioning image; inputting the chip defect area positioning image into a diffusion model for image reconstruction, and outputting a chip reconstruction image; and performing difference value comparison and thermodynamic diagram analysis on the to-be-detected chip defect image and the chip reconstruction image, and outputting a pixel-level precision chip defect semantic segmentation result. According to the method, the model is trained by using the low-precision weak supervision annotation data, so that high-precision semantic segmentation is realized, the training cost is reduced, and the practicability of the model is improved.

A method and system for analyzing fault data features of an active distribution network. The method comprises: analyzing a voltage variation after a fault in an active distribution network and analyzing a single-phase ground fault (S1); acquiring distribution network fault data by means of analog simulation (S2); and establishing a fault location prediction model to analyze fault data features and realize fault localization (S3). In the method, a voltage variation after a fault in an active distribution network is analyzed, the voltage variation is equivalently represented using an injected current, a single-phase ground fault is analyzed, and the localization of a fault point is realized. By simulating a current variation during an actual fault injection process by means of an injected current function, a model can more closely reflect an actual operating state, thereby enhancing the authenticity of fault simulation and the accuracy of prediction. A complex relationship between a current variation and node impedance is deeply analyzed by means of a complex information filtering function, and more refined fault features are extracted, thereby optimizing the precision of fault localization, and enhancing the adaptability of the model to different fault scenarios.

The invention discloses a time-space state enhanced XGBoost-LSTM-based vehicle position prediction and abnormity early warning method, system and device, and a medium. The method comprises the steps of obtaining a road section traffic flow sequence, constructing an EM clustering model, classifying traffic flow sequence samples in the EM clustering model, and constructing a time state matrix; determining a physical static adjacency matrix, a dynamic steering ratio adjacency matrix and a road section flow dynamic similarity matrix between the road sections, and constructing a spatial state matrix after weighted fusion; an XGBoost-LSTM model is constructed, and model training is carried out; and inputting the constructed time state matrix and space state matrix into the trained XGBoost-LSTM model, and carrying out real-time vehicle position prediction and abnormity early warning. According to the method, the vehicle position prediction precision can be improved, the data acquisition threshold is reduced, the use scene of the prediction method is expanded, and meanwhile, a new dynamic evaluation standard is provided for abnormal event early warning.

The invention discloses a video monitoring abnormal behavior identification method and system based on edge AI, and relates to the technical field of intelligent video analysis, and the method comprises the steps: carrying out the frame segmentation processing of a video monitoring data stream, obtaining a video frame sequence, building a target trajectory prediction model, predicting the position region of a current frame, and generating target position prediction data; performing multi-scale feature extraction on the video frame sequence, performing fusion matching on a target feature vector and target position prediction data, and constructing an enhanced feature matrix; carrying out weight distribution on the key behavior characteristics by adopting an attention mechanism, setting a dynamic threshold adjustment mechanism, and dynamically adjusting an abnormal behavior judgment threshold according to the personnel density; and inputting the adjusted feature data into an abnormal behavior classifier for identification and judgment, outputting an abnormal behavior identification result, and generating an abnormal event report. According to the method, the abnormal behavior detection accuracy in a complex monitoring scene is improved, the false report and missing report rate is reduced, and the millisecond-level real-time response capability is realized.

The invention discloses a ship shore-end intelligent management method, system and device and a storage medium, and the method comprises the steps: carrying out the ship position prediction based on an electronic chart, the current navigation state data of a ship, and the current environment data, and obtaining the information of a to-be-docked ship according to the future position information of the ship, constructing a port operation knowledge graph based on the information of the ships to arrive at the port, the equipment data of the ships approaching and leaving the port, the historical tug operation data and the port data, and predicting the tug workload demand based on the port operation knowledge graph; taking tug operation data as a state space, taking a tug scheduling strategy and a cargo stacking layout adjustment strategy as an action space, taking maximization of wharf operation efficiency as a reward target, and adopting a reinforcement learning method and a simulated annealing method to carry out wharf operation scheduling optimization to obtain an optimal wharf operation scheduling strategy. According to the method, the port working efficiency is improved, manual interference is not needed when the wharf operation scheduling strategy is obtained, and autonomous decision-making can be completely achieved.

The invention relates to the technical field of cloth flaw detection and deep learning, in particular to an MAC-YOLO-based cloth flaw detection method, which comprises the following steps of (1) constructing an MAC-YOLO network, and improving the MAC-YOLO network based on a YOLOv8 network; (2) collecting a cloth surface image data set, carrying out defect type labeling on defect images, and randomly dividing the data set into a training set and a test set according to a proportion of 8: 2; (3) the training set is used for training the MAC-YOLO network, an AdamW optimizer is adopted, a learning rate strategy is adjusted in stages, and a loss function comprises binary cross entropy loss of classification branches and distribution focus loss and complete intersection-to-union ratio loss of regression branches; and (4) detecting the input cloth surface image by using the trained MAC-YOLO network, and outputting the category and position prediction map of the flaws.When the extreme length-width ratio image data is processed, various flaws can be accurately detected.

The invention provides a tunnel fire behavior inversion method based on multi-modal fusion and physical constraint, and aims to solve the problem that the position and power of a fire source are difficult to invert accurately in real time in traditional fire behavior monitoring. According to the method, data, temperature distribution images and physical parameters of distributed temperature sensors in a tunnel are collected, and a spatial-temporal feature fusion network is constructed; designing an information leakage prevention training mechanism, and adopting a modal random discarding and sensor shielding technology to avoid overfitting of the model to a specific input mode; a physical constraint loss function is introduced, and the temperature gradient, the maximum temperature rise and the longitudinal attenuation law are combined to ensure the physical rationality of an inversion result; a coarse-fine two-stage position prediction framework is adopted, and meter-scale precision positioning of the position of a fire source is achieved. According to the invention, the power and position of the fire source can be inversed accurately in real time, and reliable technical support is provided for intelligent monitoring and emergency rescue of tunnel fire.

The invention provides a robot positioning prediction method and device, a medium and equipment, and relates to the field of industrial robot motion control. According to the method, on one hand, a physical-data double-branch collaborative network is designed, meanwhile, a DH parameter method is used for predicting and obtaining a theoretical position coordinate of a target robot, an improved Transform network is used for predicting and obtaining a coordinate compensation value of the target robot, so that a theoretical value and the compensation value are decoupled, and the limitation of single model establishment is avoided; and then, the two are fused, and high-precision end point location prediction for the target robot is realized by combining priori knowledge of robot kinematics and nonlinear expression ability of deep learning. And on the other hand, a spatial physical information mixed loss function is provided, and a spatial topological structure output by the DH model is used to guide the distribution of predicted values of the whole position prediction model, so that the geometric rationality of target robot end point location prediction is improved.

The invention provides an unmanned aerial vehicle intelligent decision-making method and system based on deep reinforcement learning, and relates to the technical field of intelligent decision-making, and the method comprises the steps: obtaining a landing region image and depth information through a visual sensor, processing feature representation and three-dimensional environment description through a risk perception type strategy gradient algorithm, and adaptively constructing an information association relationship. According to the method, feature fusion, optimal landing position determination, dynamic obstacle trajectory prediction and track point sequence generation are realized, a control strategy is optimized when the environment is suddenly changed, safe and efficient landing of the unmanned aerial vehicle is realized, and the safety and adaptability of landing of the unmanned aerial vehicle are improved.

The invention relates to the technical field of thermal power plant environmental protection, in particular to a real-time early warning and operation evaluation system of a thermal power wet desulphurization device, which comprises a real-time early warning subsystem and an operation evaluation subsystem, and the intelligent data collector performs preliminary screening and storage. The intelligent diagnosis module analyzes parameters, judges possible fault types and positions, the prediction model adopts a deep neural network, inputs a diagnosis result and outputs a real-time slurry pH value, density and density difference at a slurry outlet of an absorption tower, the intelligent evaluation module evaluates a final alarm level, and the decision scheme module generates a processing suggestion. The intelligent control execution module converts the data into a control signal, the field alarm module gives out a corresponding alarm, the intelligent query module displays a decision recommendation level on a webpage, the establishment of a prediction model comprises data sampling, model establishment, verification application and update optimization, and the prediction precision is remarkably improved.

The invention relates to the technical field of valve leakage detection, and particularly discloses an ultrahigh pressure gas valve leakage detection method and system. According to the method, a unified leakage feature vector is obtained through multi-source acquisition and processing; capturing a time sequence dependency relationship, and determining a micro leakage mode; carrying out abnormal peak detection to obtain a preliminary leakage probability; combining the initial leakage probability with real-time environmental parameters, and dynamically adjusting a judgment standard; comparing the unified leakage feature vectors through a judgment standard, fusing position coordinate triangulation positioning, judging whether micro crack leakage occurs or not, and obtaining leakage position estimation; the historical data sequence is fused, the micro crack development trend is predicted, and the early warning level is determined; and generating a corresponding response signal according to the early warning level, and outputting micro crack leakage early warning. Multi-source data fusion, dynamic threshold adjustment and position prediction can be carried out, the accuracy and robustness of micro crack leakage detection are remarkably improved, and efficient guarantee is provided for safe operation of a pipeline.

The invention relates to the technical field of unmanned aerial vehicle monitoring and trajectory processing, and discloses a low-altitude unmanned aerial vehicle dynamic trajectory tracking and predicting method based on multi-base-station cooperation. The method comprises the steps that signal parameters are obtained through multi-base-station collaborative observation, and a multi-modal position prediction set is generated; and performing classification and scoring according to the spatial distribution characteristics of the candidate points and the historical track points, and screening out an optimal prediction position point. And inputting the optimal prediction point and the historical trajectory into a generative model, and dynamically adjusting the number of trajectory points by analyzing the point distribution probability to form a preliminary smooth trajectory. And performing physical feasibility verification and fine adjustment on the trajectory according to kinematics constraints to obtain a final smooth continuous trajectory. And matching degree calculation is carried out by fusing alternative trajectories generated by a multi-kinematic model, and the most probable target trajectory is identified. According to the method, the robustness of trajectory prediction and the structural rationality of the generated trajectory in a complex observation environment are improved.

The invention provides a power transmission line icing detection method, device and equipment based on deep learning. The method comprises the following steps: obtaining a power transmission line diagram with a suspected icing area; an icing initial feature extraction model is called to process the power transmission line diagram, multiple first multi-scale icing initial feature maps are obtained, and the multiple first multi-scale icing initial feature maps are composed of intermediate results and final results output by the model; an icing deep feature extraction model is called to process the multiple first multi-scale icing initial feature maps, multiple second multi-scale icing deep feature maps are obtained, and the multiple second multi-scale icing deep feature maps are composed of intermediate results and final results output by the model; and calling an icing position determination model, performing prediction processing on the plurality of second multi-scale icing deep feature maps by using a plurality of prediction heads in the icing position determination model, and determining position prediction information of an icing area in the power transmission line map.

The invention discloses a traffic scene risk identification method and device considering dynamic and static information fusion, and a storage medium. The method comprises the steps of 1, obtaining a traffic scene high-precision map and a time sequence track of each vehicle; track points in the time sequence tracks are converted into a high-precision map coordinate system, lane matching is carried out, and a time sequence track high-precision map of each vehicle is obtained; 2, predicting vehicle positions, and extracting dynamic and static characteristics of each vehicle time sequence track; 3, fusing the dynamic and static features of each vehicle to obtain a fused feature; inputting the fusion features of all vehicles into a risk factor prediction model to predict and obtain dynamic and static risk factor prediction results; on the basis of prediction errors between dynamic and static risk factor prediction results and corresponding real results, combined with vehicle position prediction errors, calculating a comprehensive risk value of the traffic scene; the equipment and the storage medium are used for implementing the method. The method provides a new thought for traffic risk identification.

The invention relates to a complex medium inversion imaging method and system guided by a physical information neural network, and the method comprises the steps: constructing a two-dimensional grid model of a block structure with different medium distributions, obtaining out-of-plane displacement data at grid points through staggered grid finite difference, and forming a wave field full-waveform data set; constructing a physical information neural network, wherein the physical information neural network comprises a first feed-forward network for modeling a mapping relation of a displacement field of the sample, a second feed-forward network for modeling a velocity field of the sample, and a residual network; based on the wave field full-waveform data set, training a physical information neural network by taking minimization of compound loss as a target; and taking the space-time coordinates of the sample as input, and utilizing the trained physical information neural network to obtain predicted displacement and sound velocity of the corresponding position of the space-time coordinates, so as to realize inversion imaging of sound velocity medium distribution. According to the method, the ultrasonic propagation model of the complex medium can be quickly and accurately established under the condition that a small amount of marked data is used.

The invention relates to the technical field of anti-collision systems, in particular to an offshore wind power construction safety pre-warning system based on AIS (automatic identification system) data, which comprises a ship dynamic uncertainty modeling module for acquiring AIS signal updating frequency and positioning precision marks of a target ship and generating a ship future position probability ellipse. According to the invention, the position coordinate, the speed value and the course angle of the ship are obtained in real time based on the AIS data, the reliability and the motion trend of ship position prediction are determined by combining the AIS signal updating frequency and the positioning precision mark, and the future position probability ellipse of the ship is accurately generated; a protection area is dynamically constructed, comprehensive calculation is carried out in combination with the spatial relation between a ship future position probability ellipse and the positions of surrounding fan pile foundations, and a hourly dynamic collision risk index sequence is obtained; and further according to the statistical deviation between the current motion state of the ship and the standard parameter of the function partition, combining with path difference analysis to obtain a navigation abnormity comprehensive index.

The invention discloses an unmanned aerial vehicle navigation method and related equipment based on a visual language model, and the method comprises the steps: carrying out the thinking chain construction of an initial training data set, generating high-quality thinking chain data, and constructing a target training data set according to the initial training data set and the high-quality thinking chain data; based on a supervised fine tuning method and a reinforcement learning method, training the initial visual language model according to the target training data set to obtain a candidate visual language model; deploying the target visual language model passing the model verification to an unmanned aerial vehicle navigation control system; and generating a reasoning result and a target position according to the natural language instruction of the user through the target visual language model, and predicting a target action sequence according to the target position by adopting a foresight mechanism, so that the unmanned aerial vehicle executes the target action sequence. Complex natural language instructions can be accurately understood, spatial reasoning is carried out in combination with environmental semantics, accurate target positioning and path planning are achieved, and the method can be widely applied to the technical field of unmanned aerial vehicle control.

The invention discloses a stacked LSTM trajectory prediction method based on an attention mechanism in a multi-modal environment. The method comprises the following steps: aligning modal data through a sliding window mechanism; designing a three-layer stacked LSTM (Long Short Term Memory) network structure, namely an AS-LSTM network structure; the first layer LSTM inputs inertial measurement unit IMU feature splicing PointNet + + extracted point cloud feature, the second layer LSTM inputs first layer linear processed hidden state splicing CNN extracted image feature, and the third layer LSTM inputs second layer linear processed hidden state splicing GPS feature; and an attention mechanism is added to the hidden state output by the third layer of LSTM to calculate a dynamic weight, and the position prediction at the next moment is output through a Dense layer. And by taking the mean square error and the decision coefficient as evaluation indexes, constructing an objective function for minimizing the prediction error. And an objective function value lower than that of other LSTM prediction methods can be obtained after NCLT data set training.

The invention provides a video coding method and device, electronic equipment and a storage medium, relates to the technical field of image processing, in particular to the field of video coding and the like, and can be applied to application scenes such as video live broadcast and the like. The specific implementation scheme is as follows: acquiring a reference frame which is adjacent to a current frame and has established initial ROI hierarchical division; multiplexing a motion vector generated by the reference frame in a motion compensation time domain filtering process, and determining an ROI position predicted value of the current frame; extracting feature points of the five sense organs of the current frame, and correcting an ROI position predicted value based on a feature point spatial topological relation in the initial ROI; respectively configuring differential quantization parameters for the corrected main face region, the corrected secondary face region and the corrected background region; dynamically allocating a three-layer area code rate according to a real-time network bandwidth; and outputting the coded frame of the current frame and the associated ROI level metadata. According to the scheme, the coding efficiency and quality can be improved.

The invention provides a relay ad hoc network communication method and system based on a mobile terminal, and relates to the technical field of relay ad hoc network communication of the mobile terminal.The energy supply rate is monitored in real time through a mobile terminal integrated kinetic energy converter, the energy sustainable index is calculated, and the distance between adjacent nodes is estimated; constructing an energy-geography combined gradient field in a multi-dimensional space, dynamically adjusting weight coefficients of energy and geography by nodes according to network density, generating a comprehensive gradient vector, and correcting the geography gradient field by using motion data acquired by an IMU (Inertial Measurement Unit) so as to improve the accuracy of position prediction; when the relay link fails, the upstream node can broadcast the request again and trigger the updating of the local gradient field, and the surrounding nodes refresh the gradient field according to the latest information and select a new relay node; meanwhile, gradient information is embedded into a data packet head, when a node energy sustainable index is lower than a threshold value, an energy attenuation factor is introduced, a relay task is quitted in time, a high-energy node takes over, and therefore network energy consumption is balanced.

The invention relates to the technical field of dynamic visual target motion tracking control, in particular to a dynamic visual target motion tracking control method and system based on deep learning, and the method comprises the steps: synchronously collecting continuous multi-frame target scene image data through a visual multi-frame collection module; and performing time sequence association and memory fusion on target features in continuous multi-frame target scene image data through a cross-frame feature memory fusion module, and constructing a target feature model. According to the invention, the current and historical stable features are dynamically fused through the cross-frame feature memory fusion module, time sequence association is realized in combination with the long and short-term memory network, and the problem of slow feature model updating under target deformation and shielding is solved; the deformation-shielding bimodal recognition module accurately recognizes a scene state, provides a basis for the multi-branch Kalman filtering prediction module, enables the multi-branch Kalman filtering prediction module to call a corresponding branch, corrects a prediction equation through a compensation factor, and improves the position prediction accuracy.

This disclosure relates generally to encoding and decoding of 3-dimensional (3D) mesh and specifically to encoding and decoding order and dependency between 3D positions of 3D vertices and 2D positions of 2D texture coordinates of a 3D mesh. In particular, the various embodiments in this disclosure provide a novel method and device to enhance lossless compression of 3D mesh models. The disclosed method and device prioritize encoding texture coordinates before encoding 3D positions. The disclosed method and device further employ angle-preserving position prediction. The disclosed approaches aim to optimize the compression process of 3D meshes by leveraging an inherent correlation between 3D structures and their corresponding 2D texture mappings.

The invention provides a target position prediction method and device based on Kalman filtering, equipment and a medium, and relates to the technical field of space optical communication. The method comprises the following steps: setting an initial state of a Kalman filter according to an initial position of a target light spot; the predicted value of the target light spot at the T moment is calculated by using the predicted value of the Kalman filter at the T-1 moment state; obtaining an observation value of the target light spot at the T moment; and correcting the predicted value at the T moment according to the observed value at the T moment to obtain the position information of the target light spot at the T moment.

The invention provides a catheter tip positioning method and system in central venous catheterization and a medium, and relates to the field of medical image data processing. The system comprises a CT center line extraction module, a puncture position prediction module, a catheterization target calculation module, an ultrasonic center line extraction module, an image fusion module, a catheter position projection module and a catheterization completion judgment module. According to the intelligent navigation positioning technology in the central venous catheterization based on ultrasonic, CT and electromagnetic navigation multi-mode fusion, ultrasonic, CT, electromagnetic positioning and deep learning are creatively fused, accurate positioning and real-time monitoring of the tip of the catheter in the central venous catheterization are achieved, and the learning threshold is lowered.

The invention discloses an energy storage system fault database indexing method, and particularly relates to the technical field of fault prediction. The method comprises the following steps: firstly, constructing an energy disturbance vector sequence matrix in a unified time window, extracting features based on a continuous variation rate and energy residual distribution, and generating an energy disturbance feature spectrogram; establishing an energy propagation path atlas in combination with a system module topological relation, and introducing a time sequence consistency identifier; a fault evolution fingerprint is generated through graph embedding coding, similarity index matching is carried out in combination with a standard fault trajectory, and a fault type and a positioning weight are output; real-time energy indexes are further fused, a micro-fault position prediction map is generated, and dynamic early warning is achieved; according to the method, accurate identification and visual positioning of the micro-fault of the energy storage system in a complex scene can be realized, and the operation safety and the intelligent operation and maintenance capability of the system are improved.

The invention discloses a target position prediction method and system based on body surface point cloud data, and relates to the technical field of medical signal processing, and the method comprises the steps: obtaining 4DCT reconstruction point cloud data of a plurality of subjects and body surface point cloud data in a respiratory cycle, and building an in-vivo point cloud data set and a body surface point cloud labeling data set; training a body surface and in-vivo point cloud correlation model by using the body surface point cloud labeling data set and the in-vivo point cloud data set, inputting 4DCT reconstruction point cloud data of the patient and the body surface point cloud contour of the current breathing moment into the trained body surface and in-vivo point cloud correlation model, and obtaining a final prediction phase and a final target region transformation matrix; and in combination with the 4DCT reconstructed point cloud data and the body surface point cloud contour at the current breathing moment, obtaining a predicted position of the in-vivo target region on the body surface point cloud contour at the current breathing moment. According to the invention, the position of the target area can be accurately predicted on the body surface contour, the accuracy of radiotherapy irradiation is improved, and radiation hazards are reduced.

The invention discloses a mechanical arm online calibration method and system. The method comprises the steps that a hydraulic mechanical arm no-load dynamic model based on the Lagrangian method is constructed; the method comprises the following steps: establishing an improved Denavit-Hartenberg kinematic error model; constructing a position prediction model by using a convolutional neural network and training the position prediction model; performing error compensation correction on the predicted position based on the model; online calibration parameters are determined and dynamically adjusted; and iterative optimization is repeated to realize real-time calibration. The system comprises a dynamical model construction unit, a kinematic error model establishment unit, a position prediction model training unit, an error compensation calculation unit, a calibration parameter determination unit and a model iterative optimization unit which work cooperatively. The method and the system can respond to working condition changes in real time, integrate multi-source errors, improve calibration precision, effectively reduce track deviation and guarantee operation quality and stability.

The invention relates to the technical field of wireless charging, in particular to a self-adaptive wireless power transmission system and a receiver free positioning method thereof. The system is characterized in that a transmitting end comprises an inverter circuit, a transmitting end compensation network, a compensation network input detection circuit and an array transmitter, and the array transmitter comprises seven transmitting coils; the receiving end comprises a receiving coil, a receiving end compensation network and a load voltage detection circuit; the control system comprises a position prediction module and a fuzzy PID controller. The position prediction module is used for predicting the spatial position of the receiving coil by measuring a mutual inductance value between the transmitting coil and the receiving coil based on a neural network optimized by a seagull algorithm; and the fuzzy PID controller is used for acquiring the spatial position of the receiving coil, adjusting the excitation mode of the transmitting coil and the phase of an input signal of the inverter circuit, and optimizing the magnetic field distribution to compensate the offset influence. According to the invention, high transmission efficiency can still be maintained when the receiving coil deviates to a certain extent, and the anti-deviation capability is remarkably improved.