2953 results about "Network module" patented technology

The invention relates to the field of power equipment data processing, in particular to a steam turbine vibration fault diagnosis system fused with deep learning. Comprising a dynamic knowledge base construction module, a working condition adaptive data synchronization module, a knowledge-guided heterogeneous feature fusion module, a dynamic structure neural network module, an online self-optimization weight distribution module and a knowledge-enhanced coupling fault reasoning module. The dynamic knowledge base construction module updates the multi-modal knowledge graph through an incremental knowledge distillation mechanism, and generates an interpolation strategy template and a frequency band sensitivity matrix; the working condition self-adaptive data synchronization module dynamically calls an interpolation algorithm based on a rotating speed fluctuation mode to realize time sequence alignment optimization of multi-source sensor data; the system effectively solves the problems of time scale asynchronism and feature heterogeneity in multi-source heterogeneous data fusion through a knowledge-driven and data-driven closed-loop interaction mechanism, and realizes accurate diagnosis and early warning of steam turbine vibration faults under complex working conditions.

The invention belongs to the technical field of data detection, and particularly relates to an efficient data anomaly automatic detection and alarm system. The detection and alarm system comprises a sensor and data acquisition device, a data processing and analysis module, an alarm module, a monitoring center and visual interface, a communication and network module, a storage and backup module, an intelligent decision support module and a user feedback and adjustment module. According to the system, data can be monitored and analyzed in real time, abnormity can be quickly found, an alarm is given, manual monitoring requirements are reduced, data misjudgment is avoided, data accuracy is ensured through data cleaning and processing, an intelligent decision support module provides optimization suggestions based on AI, and a user can adjust rules to adapt to requirements. The system has the functions of data processing, anomaly recognition and trend prediction, the monitoring center visually displays the state, the storage and backup module ensures long-term storage of data, the automatic mechanism improves the response speed and the operation benefits, and the adaptability is high.

The invention discloses a capacitor appearance intelligent defect detection method based on YOLO-NAS and Transform fusion, and belongs to the field of artificial intelligence and industrial automation, a lightweight backbone network is combined with MobileViT, a feature extraction architecture is optimized through NAS, and the global feature expression ability is improved; a Transform-FPN (Fabry-Perot Networking) is introduced to realize multi-scale feature fusion; instructing student model learning by utilizing high-order features of the teacher model through feature distillation; optimizing small target and irregular defect detection precision by adopting an improved positioning loss function; and the Soft-NMS and the DIOU-NMS are combined, and the calculation complexity is reduced through model pruning and hybrid quantization, so that the real-time detection deployment of the embedded equipment is realized. According to the capacitor appearance intelligent defect detection method based on YOLO-NAS and Transform fusion, the problems of missing detection of small targets, difficulty in distinguishing multiple defects and high model calculation complexity are solved by combining a lightweight backbone network, a Transform module, multi-scale feature fusion and an improved loss function.

The invention provides an improved underwater target detection system and method based on RT-DETR, and belongs to the technical field of underwater target detection based on computer vision. The system comprises a backbone network module, a hybrid encoder module, an InerMPDIOU sensing module and a decoder module, the backbone network module performs large separable kernel attention calculation after extracting features based on the large separable kernel attention, and outputs a multi-layer feature map; the hybrid encoder module design comprises a deformable large kernel attention-based in-scale feature interaction unit and an improved cross-scale feature fusion unit; the sensing module introduces a scale factor and an auxiliary bounding box into IoU calculation of an original IoU sensing module, and target query initialization is improved by using query selection sensed by InerMPDIOU. According to the model improvement, adaptation is carried out aiming at the particularity of the underwater environment, the underwater operation efficiency is improved, and the accuracy is improved while the parameter lightweight is realized.

The invention relates to a road disease detection method based on scale difference. The method comprises the steps that after road disease image data are cleaned, a Darklabel marking tool is used for carrying out detailed disease position and category marking on a cleaned image; a deformable convolutional network module DCNv3 is introduced into a network structure based on the preprocessed data, a small-scale detector is added, an attention mechanism CBAM is introduced, the effective receptive field of the model is expanded, the feature extraction capability of targets of different scales is enhanced, and a loss function is improved; and finally, evaluating the training model based on a road disease detection result of an actual engineering scene, verifying the generalization of the training model, and carrying out road disease detection through the evaluated model. Compared with the prior art, the method has the advantages that the influence of environmental interference on a detection result is reduced, so that the accuracy and recall rate of road disease target detection are comprehensively improved.

The invention, which relates to the technical field of structure health monitoring, discloses a sensing data-based on-line intelligent detection system for the whole body and the periphery of a house, comprising: a distributed sensor module, which is composed of a fiber grating sensor array, an MEMS environment sensor and an image acquisition unit, the system is arranged in a house bearing structure, a peripheral foundation, a drainage system and a greening area. The edge computing node module is configured to preprocess sensor data, including noise filtering, temperature compensation and abnormal data marking; the dynamic topology communication network module adopts a LoRaMesh and 5G hybrid networking technology and supports node self-repairing and bandwidth self-adaptive distribution; and the cloud analysis platform module integrates BIM model reconstruction, multi-source data fusion analysis and early warning decision, and outputs structure deformation prediction, an energy consumption anomaly map and a disaster risk assessment report.

The invention relates to the technical field of tunnel engineering construction, and discloses an intelligent material transportation and safety monitoring system and method for shield construction, and the system comprises a visual perception unit, a sensor network module, an AI analysis center module, a safety decision module and a human-computer interaction interface. According to the invention, data acquisition is carried out through the visual perception unit and the sensor network module, multi-target detection operation is carried out on image frames through the AI analysis center module after target identification and track prediction, target types, space coordinates, contour boundaries and confidence coefficients are identified and extracted, and safety judgment and early warning output are carried out. According to the invention, by integrating the multi-view camera equipment and the UWB, GNSS and other sensors and adopting a deep learning target detection algorithm, high-precision identification and continuous tracking can be carried out on construction site personnel, equipment, segments and other key objects, and accurate input is provided for subsequent risk analysis.

The invention discloses a cooperative monitoring device and method for a large deep foundation pit complex supporting system, and relates to the technical field of foundation pit supporting. The device comprises a multi-dimensional sensor network module, a BIM-GIS digital twin platform module, an intelligent analysis and early warning module, a construction collaborative decision module, a data backup and recovery module and a remote monitoring and management module. The method comprises the following steps: step 1, carrying out multi-source data space-time registration; step 2, dynamically constructing a digital twinborn model; step 3, coupling risk assessment; step 4, construction collaborative optimization; according to the technical scheme, the method comprises the following steps of data processing, data quality control and system performance evaluation, through three innovations of deep coupling of multi-source data, dynamic model correction and intelligent collaborative decision making, a'monitoring-analysis-decision-execution 'full closed loop is constructed, technical breakthroughs are achieved in complex working condition adaptability, early warning real-time performance and construction safety, and the method has remarkable engineering application value.

The invention provides a lightweight road damage detection method based on RT-DETR improvement, and the method comprises the steps: obtaining road damage image data, and dividing a data set; a backbone network of the RT-DETR model is modified to be composed of a plurality of multi-scale edge information enhancement modules, a hybrid encoder of the RT-DETR model is modified to be composed of an attention-based intra-scale feature interaction module and a multi-branch cavity convolution pyramid network module, and an RDD-DETR model is obtained after modification; and the RDD-DETR model is trained and is used for road damage detection in the road image data. According to the invention, the end-to-end multi-scale feature extraction and fusion network is used for road damage detection, so that the road damage detection accuracy and detection speed can be greatly improved.

The invention discloses an air pollutant concentration prediction method and related equipment thereof, and relates to the technical field of data processing. The method comprises the following steps: acquiring current pollutant concentration data, current meteorological data and target site geographic position data corresponding to a target environment monitoring site; taking the current pollutant concentration data, the current meteorological data and the geographic position data of the target station as target input data of the prediction model; wherein an input module of the prediction model is used for performing modal decomposition processing on input data to obtain multiple pieces of modal data; the time feature extraction module is used for extracting time feature data; the spatial feature extraction module is used for extracting spatial feature data; the space-time fusion convolutional network module is used for extracting space-time features; the output module is used for outputting a prediction result; determining a prediction result of the air pollutant concentration corresponding to the target environment monitoring station according to the output result; the method achieves the effects of improving the comprehensiveness and accuracy of a prediction result and expanding application scenes.

The invention relates to a biped robot complex terrain self-adaptive gait planning method and a biped robot, and belongs to the technical field of robotics.The biped robot complex terrain self-adaptive gait planning method comprises the steps that a fractional order PID controller is constructed, and the fractional order PID controller comprises a multi-sensor network module, a self-adaptive module and a fractional order calculus control module; constructing a reinforcement learning model for biped robot gait planning, setting a state, an action, a decision and a reinforcement learning reward function of reinforcement learning, performing continuous iteration and optimization adjustment on the reinforcement learning model by using a strategy gradient method, updating strategy parameters, and outputting control parameters of the biped robot; and performing decision fusion on control parameters output by the fractional order PID controller and the reinforcement learning model through a comprehensive loss function to obtain globally optimal biped robot control parameters. According to the method, more accurate gait planning can be provided for the biped robot in complex terrains, and better walking flexibility and adaptability are achieved.

The invention discloses a lung X-ray image segmentation system based on deep learning, which comprises a data preprocessing module, a lung X-ray image segmentation network module, a training module and a segmentation result output module, and is characterized in that the lung X-ray image segmentation network module constructs a lung X-ray image segmentation network based on deep learning, and the lung X-ray image segmentation network is recorded as MSDA-Net; and the training module is used for training the constructed MSDA-Net. A multi-scale feature extraction module is introduced into the network, and expansion convolution and feature fusion methods with different expansion rates are combined, so that the adaptability of the model to a lung region in an X-ray image is enhanced, a key target region in the image is highlighted, irrelevant background noise is suppressed, the significant difference of the lung region in form and size can be effectively handled, and the accuracy of the model is improved. The method improves the recognition capability of a complex and irregular region, and improves the segmentation effect of a target region.

The invention relates to the technical field of aircraft intelligent detection and maintenance systems, and discloses an aircraft defect intelligent evaluation system and method based on multi-modal fusion, and the system comprises a multi-modal data collection module, a tensor construction and decomposition module, a meta-prototype relation network module, a multi-target game optimization module, and a closed-loop feedback module. The method comprises the steps of constructing a five-order feature tensor through multi-modal data synchronous acquisition and space-time alignment, extracting low-rank features through hypergraph block item decomposition, dynamically generating a defect prototype set in combination with meta-learning, generating a maintenance decision by adopting a Nash equilibrium strategy and fusing multi-constraint conditions, and optimizing system parameters through closed-loop feedback. The whole-process intelligentization of aircraft defect detection and maintenance is realized; according to the method, high-precision defect detection is realized through multi-modal data fusion and hypergraph modeling, an intelligent decision is generated in combination with dynamic prototype learning and multi-target game optimization, and continuous self-optimization is performed by means of a closed-loop feedback mechanism, so that the operation and maintenance efficiency and safety of the aircraft are improved automatically in the whole process.

Methods and systems for managing a data processing system are disclosed. To manage the data processing system, a management controller may be included in the data processing system. The management controller may perform managerial functions for the data processing system regardless of whether in band components are compromised, depowered, and / or otherwise non-functional. In addition, to communicate with remote entities, the management controller may utilize a network module of the data processing system. The network module may direct network traffic between in band and out of band communication channels and may operate independently from hardware resources of the data processing system.

The invention relates to the technical field of modern agriculture, and discloses an intelligent yak breeding monitoring system which comprises a sensor network module, a data processing center module, an intelligent analysis module and a remote monitoring terminal module. The sensor network module integrates various sensors and is used for monitoring physical signs, behaviors and breeding environment parameters of yaks in real time; the data processing center module is responsible for receiving, processing and storing original data transmitted by the sensor network; the intelligent analysis module establishes a health assessment model and an environment optimization algorithm based on the processed data, and realizes real-time assessment of the health condition of the yaks and intelligent optimization of the breeding environment; the remote monitoring terminal module provides a user interface and supports remote control and early warning notification functions. The intelligent yak breeding monitoring system aims at solving the problems that an existing yak breeding environment monitoring technology is single in data, insufficient in intelligent degree and difficult to meet the requirements of precise breeding and scientific management.

The invention provides an antenna radio frequency performance test system and method, and relates to the technical field of antenna testing, the system adopts an intelligent signal source module, uses a quantum random number generator to generate a test signal of an ultra-wide frequency spectrum, and an adaptive matching network module can automatically adjust impedance according to impedance characteristics of an antenna to be tested. The space electromagnetic environment reconstruction module accurately simulates various electromagnetic environments through an electromagnetic radiation source and a wave-absorbing material, the multi-dimensional signal acquisition module simultaneously acquires electric field, magnetic field, phase and frequency spectrum information, and the intelligent analysis and diagnosis module analyzes signal data by using an artificial intelligence algorithm and performs fault diagnosis based on a machine learning model. In general, the system and the method improve the comprehensiveness, the accuracy and the intelligentization of the antenna test, and provide a new test solution for the field of wireless communication.

The invention provides a high-efficiency ship automatic control system, and the system comprises a comprehensive control platform which carries out the unified integration of subsystems, sets a target function, and carries out the data sharing, collaborative optimization and global control among the subsystems. The intelligent sensing network module is used for collecting historical data and real-time data; the self-learning control module is used for constructing a control strategy generation model; the ship digital model module is used for constructing a digital model for simulating ship navigation so as to test different ship control strategies; the decision execution module is used for generating and executing a control instruction; and the safety monitoring module detects abnormal behaviors of the ship and gives an alarm. According to the invention, a plurality of subsystem modules can be integrated in a unified manner, data sharing, collaborative optimization and global control are realized, an optimal control strategy can be provided, the cost and risk of actual navigation are reduced, and the control precision, response speed and operation efficiency of a ship are improved.

The invention relates to the technical field of power adapter temperature management, and discloses a gallium nitride power adapter temperature management system comprising a dynamic thermal model module used for accurately predicting the temperature change trend of each key component; the multi-level temperature monitoring network module is used for forming a complete temperature distribution diagram; the multi-device collaborative sensing module is used for generating a sensing result of the whole heat dissipation environment; the self-adaptive air duct structure module is used for optimizing an air flow path; the heat dissipation path module based on swarm intelligence is used for calculating and generating an optimal multi-device collaborative heat dissipation path by applying a swarm intelligence algorithm; the self-adaptive heat dissipation control strategy module is used for realizing multi-target balance optimization of temperature, noise and energy consumption; the problem that heat dissipation is difficult when multiple adapters are used in a centralized mode is solved, heat dissipation efficiency is improved, energy consumption is reduced, and noise is reduced.

The invention discloses an unmanned aerial vehicle track and resource scheduling method based on deep reinforcement learning, and belongs to the technical field of resource scheduling, and the method comprises the steps: carrying out the real-time simulation and optimization of a communication interaction process through employing a digital twin network of a physical network; by minimizing the task completion time delay of all user equipment in the average time slot, the QoE target of task offloading service in the multi-UAV edge network is realized, so that the service efficiency and user experience of the whole network are improved. And aiming at the constructed optimization target, a deep reinforcement learning algorithm is combined with a variational auto-encoder module to solve the problem of mixed action space. Continuous and discrete action spaces are effectively processed, and the decision-making ability of an algorithm is improved. Besides, a graph attention network module is also introduced, so that the unmanned aerial vehicle can adaptively capture the state characteristics of other unmanned aerial vehicles, thereby making a more accurate joint decision. The joint decision-making mechanism can significantly improve the task unloading efficiency and the service quality of the multi-unmanned aerial vehicle edge network.

The invention discloses a semi-supervised medical image segmentation method and device based on SAM guided knowledge distillation, and the method proposes a multi-view collaborative training strategy, employs two different sub-networks to carry out collaborative teaching, and generates a more generalized result. A learnable prompt strategy is provided to dynamically generate prompt information, and an adapter is integrated to finely adjust the SAM and is specially used for a medical image segmentation task; besides, knowledge distillation guided by the SAM is provided, useful knowledge is transferred from the SAM to the two sub-networks, learning can be carried out from prediction of the SAM, and the influence of false labels in the training process is reduced. According to the method, the effect of full supervision can be achieved only through a small amount of annotated data, and the demand quantity of the annotated data is greatly reduced; the generalization ability of a large model is fully utilized, and knowledge distillation of the SAM module is applied to the semi-supervised field for the first time, so that the segmentation performance of the semi-supervised network module is greatly improved.

The invention relates to a server cluster monitoring system based on multi-node collaboration and an implementation method thereof, a dynamic topology network module is configured to reconstruct a connection topology among monitoring nodes in real time according to node performance and link quality, support mixed configuration of a star type, a ring type and a net structure, and realize multi-node collaboration. Multi-dimensional data capture from a physical layer to an application layer is realized through a cross-level index acquisition module based on an integrated hardware sensor interface and a virtualization layer probe, and each node is enabled to perform collaborative reasoning through parameter encryption sharing through a decision model based on federated learning. A monitoring task fragmentation strategy is dynamically adjusted through an adaptive elastic fragmentation unit according to network delay and load fluctuation, and an abnormal event association rule base is updated in real time through an incremental knowledge graph construction unit. High availability and elastic expansion are realized through a multi-node collaborative architecture, the monitoring efficiency is improved in combination with dynamic load balancing and hybrid detection, and an intelligent multi-level response mechanism is constructed to guarantee the service continuity.

The invention relates to the technical field of energy, and discloses a distributed electric power energy storage system and method, and the system comprises a decommissioned battery sorting and modularization module which is used for carrying out the performance evaluation, grading and standardized modularization processing of decommissioned power batteries; the energy storage unit module is used for assembling the retired batteries into an energy storage unit and storing and releasing electric energy; the energy management module is used for monitoring the running state of the energy storage unit and optimizing energy distribution; the communication network module is used for carrying out data transmission and cooperative control between the modules; and the power grid and user interface module is used for interacting the energy storage system with a power grid and a user side. According to the method, the energy scheduling unit can optimize the charging and discharging strategy of the energy storage unit in real time by combining reinforcement learning and federated learning algorithms, and meanwhile, the adaptability of a scheduling model in multiple scenes is improved by utilizing cooperative training of distributed nodes.

The invention relates to the technical field of energy management and carbon accounting, in particular to an intelligent carbon emission monitoring system and method based on the Internet of Things, and the system comprises a distributed sensing network module which collects the energy consumption and emission data of an independent accounting unit in real time; the edge computing module is deployed at a local edge computing node to preprocess the data acquired by the distributed sensing network module; the cloud co-processing module receives the preprocessed data and carries out dynamic accounting and multi-source data fusion; the carbon accounting model module automatically matches accounting requirements according to the industry to which the enterprise belongs and generates a monitoring point layout scheme; and the intelligent visualization module is used for generating a multi-dimensional carbon emission data analysis chart and a compliance report meeting MRV requirements based on data of the edge calculation module, the cloud co-processing module and the carbon accounting model module. Full-process automatic management from data acquisition, real-time monitoring to verification is realized, and the accuracy, integrity and traceability of carbon emission data are ensured.

The invention provides a gas turbine exhaust gas temperature prediction and fault early warning system and method, and relates to the technical field of gas turbine state monitoring and fault diagnosis. The system comprises a data acquisition and preprocessing module used for acquiring and preprocessing data; the dynamic graph construction module is used for constructing graph structure data; the graph neural network module is used for extracting spatio-temporal features through learning; the improved auto-encoder module is used for realizing feature reconstruction by learning normal working condition data and then outputting reconstruction errors to the fault early warning module; the temperature prediction module is used for predicting a future exhaust temperature value; the fault early warning module is used for performing fault judgment and decision; and the result display and output module is used for summarizing analysis results. According to the system, the prediction precision of the exhaust temperature is remarkably improved, the fault detection and early warning capabilities are enhanced, the system has better feature representation capability and adaptability to complex working conditions, and close integration and mutual enhancement of prediction and early warning are realized.

The invention relates to the technical field of high-frequency signal modulation, and discloses a high-frequency carrier synchronization signal modulation system. A carrier distortion compensation module of the system constructs a model based on a historical transmission data set, captures a phase jitter parameter, a spectrum leakage component and a modulation pulse sequence of a transmitting end carrier in real time, and outputs a reconstructed baseband parameter; the multi-dimensional distortion analysis module compares the reconstructed baseband parameter with a receiving end demodulation baseband parameter through composite difference detection, and generates a channel-level distortion coefficient tensor; the topological positioning network module is used for positioning signal out-of-step physical nodes and generating a probability distribution thermodynamic diagram by combining impedance characteristics of transmission nodes and signal path delay information; and the adaptive modulation strategy module starts a multi-band carrier injection mode for the high-probability out-of-step nodes according to the abnormal probability gradient of the thermodynamic diagram, and applies a phase disturbance test to adjacent transmission links. The system can improve the adaptability and accuracy of high-frequency carrier signal synchronous modulation.

The invention discloses an unmanned aerial vehicle autonomous navigation system based on a hierarchical reinforcement learning strategy. The unmanned aerial vehicle autonomous navigation system is suitable for a three-dimensional flight task in an unknown environment. The system comprises a state sensing module, a hierarchical strategy network module, a control execution module, a data classification module and a data playback module. The state sensing module extracts obstacle position information based on a deep neural network, and fuses the target, the obstacle position and the flight state to generate a state vector and a time sequence. The hierarchical strategy network adopts a high-layer DQN to generate a navigation intention, and a low-layer LSTM and PPO are combined to output a continuous control action; the control execution module adjusts the attitude of the unmanned aerial vehicle according to the instruction and performs closed-loop correction. The system introduces a double dynamic memory mechanism (DDM), improves strategy training efficiency and stability through experience classification and proportional sampling, and adopts a multi-target award function guide strategy to optimize convergence among task completion, obstacle avoidance safety and flight rationality. The system has good environmental adaptability and generalization ability, and is suitable for autonomous navigation tasks in complex scenes.

The invention relates to a pig image BDE reconstruction system and method based on differentiatable image rate filtering, and belongs to the field of image processing, and the system comprises an image preprocessing module which is configured to process an original low-bit image; the neural network module acts on the processing and reconstruction tasks of low-bit pig images, the characteristics of each image are collaboratively optimized in a task dividing and conquering mode, and finally a high-quality image is obtained; the loss function module is configured to optimize the network model performance by minimizing the difference between the network output image and the real image; the training module is configured to optimize network model parameters and a learning process by adopting a staged training strategy; and the test and evaluation module is configured to evaluate the image quality through the peak signal-to-noise ratio and the structural similarity index and measure the reconstruction effect of the model. According to the method, a two-stage training strategy is adopted, an image reconstruction task is decomposed into two sub-tasks which cooperate with each other, and spatial resolution enhancement and bit resolution improvement are achieved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as medical health and financial science and technology, and discloses a model quantitative reasoning acceleration method, device, equipment and medium. The method comprises the steps that an input text is divided into a plurality of processing blocks, importance scoring is conducted on the non-first processing block, and calculation precision formats are distributed according to scoring results; determining a unified quantization configuration of each processing block; dividing the network modules into configuration sharing groups, and sharing quantitative configurations of corresponding processing blocks in the groups; and executing block-level quantization inference according to the unified quantization configuration, and generating a model inference result. The quantitative configuration of each processing block is uniformly determined on the basis of the token importance score, and the configuration is multiplexed in the network module group, so that block-level precision distribution and parallel quantitative reasoning are realized, the video memory overhead and the configuration time overhead are greatly reduced while the reasoning precision is guaranteed, and the reasoning efficiency is improved. And the execution efficiency and the video memory utilization rate in the long text reasoning task are effectively improved.

The invention relates to the technical field of water conservancy system design, in particular to a water conservancy informatization data collection and transmission system and method based on a distributed ad hoc network, and the method comprises the steps: deploying monitoring nodes at each monitoring point of a water conservancy project to collect hydrological data and environmental data; peripheral monitoring nodes are automatically found and connected through a distributed ad hoc network module, a multi-hop wireless network is formed, and communication between the monitoring nodes and gateway nodes is achieved. Specifically, a dynamic routing algorithm is adopted to monitor the delay and signal stability of a link in real time and monitor node residual energy, and an optimal transmission path is calculated; when a node or a link has a fault, a routing path is automatically recalculated according to a fault processing strategy, and disaster recovery transmission is realized; the energy consumption of the monitoring node is reduced through a sleep wake-up mode and an energy-aware routing algorithm; and converging the data of each monitoring node at the gateway node, and uploading the data to a cloud data center. And the flexibility and reliability of data transmission are enhanced.

The invention discloses a three-phase permanent magnet synchronous motor full-speed-domain driving control system and a control method thereof. The system is composed of a torque limiting module, a full-speed-domain control neural network module, a current control module, a coordinate transformation module-I, a coordinate transformation module-II, a coordinate inverse transformation module, an SVPWM module, a SiC MOSFET driving module, a full-speed-domain position rotating speed observation module, a weak magnetic feedback module and a three-phase permanent magnet synchronous motor. The control method is used for driving the control system. According to the method, accurate tracing of the optimal dq-axis reference current working point is realized based on deep learning, and accurate control of three operation modes of MTPA, field weakening control and MTPV is realized; an improved mobile vision field estimation algorithm is adopted, and the rotor position and the rotor rotating speed are accurately estimated within the full-speed domain range; the SiC MOSFET is used as an inverter switching tube, and a brand new drive circuit is designed to adapt to the operation condition of the electric vehicle.