717 results about "Adversarial network" patented technology

The invention discloses a dynamic time sequence event equipment system adversarial network construction and recommendation method and device, and relates to the field of killing network design, and the method comprises the steps: constructing an initial detection-command and control-strike warning network; a dynamic time sequence event on the battlefield is continuously monitored, when the event type of the dynamic time sequence event is an equipment state event, the initial detection-command-strike warning network is updated, and when the event type of the dynamic time sequence event is a chained event, a closed detection-command-strike link set containing an enemy target is generated; the closed detection-command-strike link set comprises a plurality of killing chains; based on the multi-dimensional evaluation index system, evaluating each killing chain to obtain an evaluation result corresponding to each killing chain; and according to the evaluation results corresponding to all the killing chains, recommending an optimal interception scheme of an air defense and anti-guide interception action. The method overcomes the problems of large calculation dimension and slow response speed of an existing method.

The invention discloses an artificial intelligence rice water and fertilizer real-time monitoring method and system, and relates to the technical field of agricultural intelligent decision making, and the method comprises the steps: inputting a farmland feature data set into a soil thermodynamic diagram generation model, carrying out the high-resolution reconstruction of the farmland feature data set through a GAN adversarial network, and generating a whole-field high-precision soil thermodynamic diagram; based on the whole-field high-precision soil thermodynamic diagram, a collision relation between the fertilization amount and historical farming data is detected according to an FCL causal algorithm, a preliminary causal diagram is generated, and a causal diagram structure of the fertilization amount and the historical farming data is constructed by adopting a multiple linear regression method; based on a causal diagram structure, the multi-order causal effect of the fertilization amount, the soil parameters and the historical yield is analyzed through a dynamic allocation algorithm, and a water and fertilizer regulation and control strategy is formulated in combination with a multi-objective optimization algorithm. According to the method, the soil thermodynamic diagram generation model is constructed, so that the fuzzy problem of the edge of the field and the salinization area is solved, a high-fidelity soil space state substrate is provided for water and fertilizer regulation and control, and invalid irrigation is reduced.

The invention discloses an optical cable intelligent label full life cycle management method and system, and the method comprises the steps: extracting structured data through an XML analysis engine based on a configuration file, carrying out the semantic analysis of an unstructured text, carrying out the regression quantification of text features through combining symbol quantiles, and constructing a knowledge graph; according to the knowledge graph, dynamically adjusting the character size, the two-dimensional code position and the error-tolerant rate by adopting a generative adversarial network technology according to the optical cable type and the pasting scene, and generating optical cable intelligent labels adaptive to different scenes; collecting a label image, and converting the label image into structured label identification data including an optical cable type, a connection relation and a transmission signal type by adopting a computer vision technology; the identification data and the knowledge graph are compared, consistency is checked, potential abnormity is analyzed, influences are evaluated, and graded early warning is generated; a micro-service architecture system is constructed, data analysis, AI generation, an intelligent recognition engine and knowledge graph service are integrated, and full-life-cycle management is achieved. The intelligent level of full-life-cycle management of the optical cable label is improved.

The invention discloses a landslide risk assessment method based on an extreme rainfall and geology coupling model, and relates to the technical field of geological disasters. Comprising the following steps: S1, constructing a three-dimensional probability density field of a fracture network and a non-Gaussian random field model of a permeability coefficient tensor; s2, setting a physical kernel layer according to the non-Gaussian random field model, setting a data driving layer through space-time Transform coding, and constructing a graph attention network model; s3, generating an adversarial network through physical information, constructing extreme rainfall coupling data, and updating the non-Gaussian permeability coefficient random field model according to the graph attention network model; and S4, acquiring an entropy generation rate according to the mechanical field data, the seepage field data and the temperature field data, and determining a risk level. Physical interpretability grading early warning of landslide risks is realized, and meanwhile, risk space distribution can be visually displayed through a sliding surface probability cloud picture, so that accurate decision support is provided for disaster prevention and control.

The invention belongs to the technical field of data processing, and particularly relates to a hidden ore body evaluation and positioning method based on multi-source data processing. The method mainly aims at the problems of incompleteness and isomerism of multi-source geological data in acquisition, fusion and modeling. Comprising the following steps: acquiring hyperspectral, geochemical and magnetic anomaly multi-source data of an evaluation area; intelligently complementing missing modal data by using a generative adversarial network based on geological constraints and modal outburst to form a complete multi-source data set; an unsupervised clustering algorithm combining geological correlation and entropy weight analysis is adopted to construct high-confidence-coefficient pseudo-label data, and knowledge mining of unlabeled samples is achieved; feature purification and dimension reduction are carried out through multi-modal feature fusion and hierarchical principal component analysis, and key feature vectors representing the existence of the ore body are extracted; and finally realizing space prediction of the concealed ore body by utilizing the classification model. According to the method, a high-quality data basis and a unified processing framework are provided for intelligent recognition of the hidden ore body, and efficient and accurate positioning of the hidden ore body is achieved.

The invention discloses a generative defense method and system for resisting attacks, relates to the technical field of network security, and aims to solve the problems that an existing defense scheme is high in calculation overhead and poor in real-time performance, static defense is easy to bypass, and robustness and accuracy are difficult to balance. The method comprises the following steps: constructing an adversarial network model by taking a pre-trained target model as a discriminator and a generative model as a generator; constructing a total loss function by combining a defensive loss function and an accuracy loss function, generating a defensive benign sample by adding defensive disturbance into a benign sample, generating a defensive confrontation sample by adding defensive disturbance after generating a confrontation sample based on the benign sample, and inputting the three types of samples into a target model to obtain total loss; and training the generative model to convergence by using a back propagation algorithm to obtain a trained adversarial network model for classification of defense disturbance samples. Defense generation network training is completed in the training stage, only defense disturbance needs to be overlaid in the reasoning stage, the real-time requirement is met, the robustness and accuracy of the model can be balanced, and the method is suitable for various attack scenes.

The invention relates to the technical field of cable asset health management and predictive maintenance, and discloses a cable discharge signal blind separation and enhancement processing method based on an adversarial network, and the method comprises the steps: building a multi-modal monitoring data set through collecting mixed signals and environment data in cable operation; blind separation of discharge signals is realized by using the generative adversarial network, and prior information is not needed; identifying the number of potential signal sources through covariance analysis and double-criterion estimation; iterative optimization and signal enhancement are carried out in combination with a graph neural network and variational reasoning; and finally, through multiple cross validation and quality correction, an enhanced signal with high reliability is output. According to the method, the signal processing technology is deeply fused with asset management, risk prediction and operation and maintenance decision, weak discharge signals can be effectively separated and enhanced under the condition of low signal-to-noise ratio, the accuracy and reliability of cable early fault diagnosis are improved, and credible data support is provided for cable asset health state assessment, risk prediction and operation and maintenance decision.

The invention discloses an oil storage tank oil-water interface measurement system and method and a storage medium, and relates to the technical field of oil-water interface measurement, and the system comprises a data acquisition module, a data processing module, a decision support module and a data security module. According to the oil-water interface measuring system and method for the oil storage tank and the storage medium, a three-dimensional sensing network (distributed sensor network) is constructed by adopting a pressure sensor array and phased array ultrasonic scanning technology and combining dielectric property detection of a microwave dielectric constant sensor; the pressure, the dielectric constant, the liquid level and the vibration data in the tank body are obtained, basic data are provided for subsequent processing, the comprehensiveness of data obtaining can be improved through the sensing network, the pressure data are dynamically calibrated through Takagi-Sugeno fuzzy logic, the influence of temperature drift is effectively eliminated, and the accuracy of data obtaining is improved. The ultrasonic signals are subjected to feature enhancement through the generative adversarial network, and the emulsion layer boundary is accurately recognized.

Systems and methods for detecting patterns in data from a time-series and for detecting outliers in network data in an unsupervised manner are provided. In one implementation, a method includes the steps of obtaining network data from a network to be monitored and creating a window from the obtained network data. The method also includes the step of detecting outliers of the obtained data with respect to the window using an unsupervised deep learning process (e.g., using a Generalized Adversarial Network (GAN) learning technique and / or a Bidirectional GAN (BiGAN) learning technique) for enabling the learning of a data distribution. The unsupervised process, for example, does not require manual intervention.

The invention relates to the technical field of satellite communication signal processing, and discloses a broadband satellite signal blind demodulation reconstruction method and system based on sparse representation. The method comprises the following steps: carrying out frequency domain transformation on broadband satellite mixed signals to extract pilot frequency features to construct a beam state feature matrix, inputting the matrix into an adversarial network to generate a beam adaptive sparse dictionary, constructing a topological relation graph according to a Doppler frequency shift set, and carrying out collaborative sparse decomposition to obtain a sparse coefficient matrix; and extracting a code rate candidate set to execute parallel sparse reconstruction, determining an actual code rate through self-consistency verification to obtain a complete signal, analyzing a switching instruction, extracting time sequence statistical characteristics, predicting target domain characteristics, generating a switched sparse dictionary, and executing demodulation. The sparse decomposition precision, the code rate blind estimation accuracy, the cooperative processing efficiency and the switching continuity of the broadband satellite mixed signals are improved.

The invention discloses an energy internet intelligent key node identification and elasticity enhancement method and system, and the method comprises the steps: 1, constructing and dynamically maintaining a semantic enhanced energy internet digital twin super network and a multi-modal knowledge graph, fusing multi-dimensional information, and achieving the self-evolution and dynamic reasoning capability; 2, based on the model, fusing multi-time scale prediction data, and adaptively evaluating the dynamic comprehensive criticality of the node through an intention-function-resource-vulnerability four-layer penetrating traceability model; 3, aiming at the key nodes, generating an intelligent attack strategy by utilizing a generative adversarial network, deducing an information physical cascade failure process by combining multi-agent deep reinforcement learning, and quantitatively evaluating the system elasticity; and step 4, based on an evaluation result, generating a self-adaptive security reinforcement and dynamic reconstruction decision oriented to active immunity and elastic optimization. According to the method, the accuracy and the dynamism of key node identification can be remarkably improved.

The invention discloses a network intrusion detection method based on a self-attention residual generative adversarial network, which belongs to the technical field of network intrusion detection and comprises the following steps: collecting network flow data, and preprocessing the network flow data to obtain real training data; a FARD-WGAN-GP model is constructed and trained, and hybrid pseudo data is generated based on the trained FARD-WGAN-GP model; constructing a time sequence attention detection model; training a time sequence attention detection model based on the real training data and the pseudo data; network intrusion real-time detection is carried out based on the trained time sequence attention detection model; on the basis of the real-time detection result, optimizing the FARD-WGAN-GP model, and on the basis of the optimized FARD-WGAN-GP model, optimizing the time sequence attention detection model; and carrying out network intrusion detection based on the optimized time sequence attention detection model. According to the method, the quality of the generated data is improved, and the detection accuracy is improved.

The invention provides a bar code enhanced image processing method and system based on a generative adversarial network. The method comprises the following steps: acquiring a training set and an initial model; the training set comprises a plurality of training data, and each training data comprises a sample matrix barcode image and corresponding annotation data; the initial model is an adversarial network constructed and generated by a generator model and a discriminator model; performing model training by using the training set according to the initial model and the target loss function to obtain a bar code enhancement model; the target loss function comprises a generator loss function adopting a weighted composite loss technology and a discriminator loss function adopting a binary cross entropy loss technology; and acquiring a data matrix bar code image in a real environment by using an industrial camera, and inputting the data matrix bar code image into the bar code enhancement model to obtain a standard binary bar code. According to the invention, the adversarial training architecture composed of the generator and the discriminator is constructed, so that the bar code decoding success rate is improved.

The invention belongs to the technical field of intelligent detection of new energy equipment, and particularly relates to a solar panel defect detection method and system, computer equipment and a storage medium, and the method comprises the following steps: a lightweight defect preliminary screening and adaptive shooting step: carrying out the recognition and image collection of a solar panel array through a lightweight model at the edge end of an unmanned aerial vehicle; a defect segmentation and type identification step: performing accurate segmentation on the solar panel and the defects through a neural network model, and judging the types and grades of the defects in combination with a feature extraction and classification model; a defect enhancement optimization step: enhancing the defects through an adversarial network; a detection performance evaluation step: quantitatively evaluating the overall performance of the system through a multi-dimensional index; mSAN-Net network segmentation is adopted, so that the defect detection precision is improved; and in combination with a GAN defect enhancement technology, the omission ratio and the false detection rate of weak defects are reduced, so that the fine operation and maintenance requirements of the solar panel are met.

The invention discloses a multi-modal deep learning traceability method and system fusing magnetoencephalogram and electroencephalography, and relates to the technical field of artificial intelligence and neuroimage.Real magnetoencephalogram signals and electroencephalography signals are preprocessed and then input into a traceability model, the probability of occurrence of a source in a corresponding area is predicted, and the traceability of the source in the corresponding area is obtained by combining an imported source partition distance matrix. A final traceability result is obtained; the training process of the traceability model is as follows: constructing a generative adversarial network, and generating a multi-modal neural electrophysiological data set; inputting the multi-modal neural electrophysiological data set into a residual network of a double-branch structure, and performing stage hierarchical extraction and decoupling on magnetoencephalogram signals and electroencephalogram signals respectively; extracting features in different stages by using a multi-scale convolution module, fusing the extracted features, inputting the fused features into a classifier, defining a loss function, and updating trainable parameters of the traceability model; the traceability method improves the accuracy and generalization ability of traceability positioning.

The invention discloses a hardware tool defect online detection system based on AI image recognition, and belongs to the technical field of image generation type adversarial networks. A YOLOv8 detection framework model is trained, a CBAM attention module is specifically added into a YOLOv8-S detection model, feature extraction of a hardware tool rare defect area is enhanced, feature distribution of hardware tool rare defect samples generated by a GAN is fused in a network bottleneck layer, the feature learning ability of the YOLOv8-S detection model for hardware tool rare defects is improved, and the hardware tool rare defect feature extraction method based on the CBAM attention module is obtained. The detection effect on the rare defects of the hardware tool is enhanced, and the problem of model performance bottleneck caused by scarcity of rare defect samples of the hardware tool is solved.

The invention provides a radar signal depth feature extraction method and system based on adversarial sample defense, electronic equipment and a storage medium, and relates to the technical field of radar signal processing.The radar signal depth feature extraction method comprises the steps that a spacecraft synthetic aperture radar original echo signal is collected and converted into a time-frequency feature map, and intra-pulse and inter-pulse features are extracted in parallel to generate a combined matrix; receiving a deception jamming signal by using a polarization radar group, generating a signal data body without polarization influence through complex coherent superposition, inputting the deception jamming signal and the signal data body into a feature decoupling adversarial network, and separating bullet micro-motion target feature data by means of mutual information maximization constraint; and finally, inputting into a multi-scale local attention module to extract multi-band characteristic components, performing adaptive weight coefficient fusion according to power entropy, performing polarization channel energy correction, and outputting anti-interference fingerprint characteristics with micro-Doppler characteristic enhancement, so that anti-interference processing of the spacecraft synthetic aperture radar signals can be realized. And warhead target anti-interference fingerprint features with micro-Doppler feature enhancement characteristics are effectively extracted.

The invention relates to the technical field of drilling data processing, in particular to a drilling crack type prediction method and system based on deep learning and a medium. The method comprises the following steps: acquiring an original data set of a crack scene; training a generative adversarial network model based on the crack scene original data set, generating a crack enhancement sample set, and obtaining an extended crack image data set; performing multi-modal information fusion modeling on the extended crack image data set to obtain multi-modal crack fusion feature data; constructing a crack evolution time sequence model based on the multi-modal crack fusion feature data to obtain time sequence evolution feature embedded data; and performing deep classification reasoning on the time sequence evolution characteristic embedded data to obtain crack type prediction result data. According to the method, through image enhancement, multi-modal information fusion, time sequence evolution modeling and visual path rendering, the accuracy, robustness and dynamic adaptability of crack type prediction are effectively improved, and meanwhile, the interpretability of a result is enhanced.

The invention discloses a semiconductor data detection system and method based on artificial intelligence, and relates to the technical field of semiconductor detection.The method comprises the steps that parameterized revolving door operation is executed through a quantum circuit, a reformed group equation is constructed to generate a physical loss item, and meanwhile a generative adversarial network is constructed through a quantum discriminator and a quantum generator; generating an enhanced data set; constructing a physical topology adjacency matrix according to the enhanced data set, loading a source domain convolutional neural network model and carrying out feature transformation, and generating a physical constraint embedded analysis engine through a dynamic physical graph attention mechanism and lattice differential homeomorphic mapping; deploying a physical constraint embedded analysis engine, processing real-time wafer data, generating a lattice defect tensor and a time-space confidence field, obtaining a confidence score, triggering a process adjustment instruction when the confidence score meets a high confidence condition, and otherwise, storing data which does not meet the condition into a feedback queue; according to the invention, deep coupling of a quantum generation process and a semiconductor lattice physical rule is realized.

The invention discloses a voice data recognition method and system based on an AI voice algorithm, relates to the technical field of AI voice recognition, and solves the problem that the voice data recognition capability is low. The method comprises the following steps: S1, multi-mode cooperative triggering collection: synchronously collecting lip electromyographic signals and voiceprint features through a multi-mode sensor, an activation instruction is generated through feature fusion, and voice acquisition starting is triggered; s2, AI adaptive noise reduction processing: carrying out noise separation on the original audio signal by adopting a generative adversarial network, separating environmental noise features to generate a dynamic noise reduction mask, and keeping the integrity of human voice features; s3, beam dynamic optimization adjustment: analyzing real-time audio quality based on a reinforcement learning algorithm, dynamically adjusting beam pointing and gain parameters of a microphone array, and focusing a target sound source; and S4, semantic association cache enhancement: carrying out real-time semantic analysis on the collected voice data. According to the invention, the voice data recognition capability of an AI voice algorithm is greatly improved.

A system and a method to detect an attack on an IoT network is disclosed. The IoT network includes interconnection of multiple IoT devices. The method includes receiving, by a network connection device, multiple ICMPv6 network packets from IoT devices and outputting multiple output packets; and matching, by a routing device, a network traffic pattern to attack signatures structured as a taxonomy according to which part of a packet is misused. The taxonomy includes a branch to a data plane attack and a control plane attack, respectively. When an IPv6 RPL packet is detected, the method includes checking for generating, modifying, and replaying attacks by an attacker. When a non-RPL packet is detected, the method includes checking for dropping and leaking packet attacks by the attacker. When the attack is detected, the method includes invoking a solution to the attack. The solution includes mitigation of the attack by the attacker.

The invention relates to the technical field of power systems and automation thereof, in particular to a generative adversarial network-based source-load joint scene generation method, which comprises the following steps of: constructing a multi-source time sequence database and extracting weather, time, space and historical state driving factors; establishing a joint probability distribution model based on a vine connection function; taking a numerical weather forecast path and a date type as conditional input, constructing a generative adversarial network embedded with a physical constraint microloss function of the power system, and forming a physical information generator; performing dependent structure fidelity verification on the generated scene by using the joint probability distribution model; generator parameters are fixed, potential space vectors are optimized through a gradient ascending method to maximize power grid risk indexes, and a high-risk source-load joint scene set is generated. According to the technical scheme, accurate generation of the source-load joint scene which is physically feasible and reasonable in statistics and focuses on the high-risk working condition is realized, and the safe operation toughness and the risk early warning capability of the novel power system are remarkably improved.

The invention discloses an audio and video synchronization face video generation method based on LSTM-CBAM, and belongs to the technical field of image processing, and the method comprises the following steps: S1, material acquisition, S2, feature extraction and screening, S3, correlation learning, S4, sequence generation, S5, synchronization determination, and S6, merging output. The LSTM-CBAM audio and video synchronization discriminator deeply captures time sequence association of audio features and face key point changes, a synchronous score feedback mechanism is combined, the problem of poor audio and video synchronization in the traditional technology is effectively solved, the audio and video synchronization accuracy is improved, the generative adversarial network is embedded into convolution block attention, and the audio and video synchronization accuracy is improved. The features of related speaking regions such as lips and lower jaws of the human face can be intensified in a targeted manner, the attribute constraint layer is matched to ensure that the generated human face is consistent with the original attribute, and the defects of weak reality sense and low detail quality of video characters generated by the existing method are greatly improved.

The invention discloses an encrypted domain name resolution protocol simulation and characterization system, and relates to the technical field of network security and network traffic analysis. The invention aims to simulate an encrypted domain name resolution process in a real network environment, collect the flow of the process and extract features to construct a data set, and ensure the quality of the generated data set through data enhancement and a data set evaluation scheme. The system comprises a traffic simulation module, a traffic representation module, a data enhancement module and a data set evaluation module. The flow simulation and characterization module simulates and encrypts domain name resolution flow and extracts a structured feature vector containing 34 side channel features; and the data enhancement and data set evaluation module is used for enhancing a feature set based on a conditional table generative adversarial network CTGAN so as to construct a feature data set which is closer to traffic in a real network environment, and ensuring that the constructed data set has engineering availability and theoretical rationality through evaluation. The system can be used for constructing a current scarce encrypted domain name resolution protocol side channel feature data set, and provides data support for related security detection and research.

The invention provides a forest degeneration process identification and degeneration degree division method based on a time sequence, and relates to the field of forest resource degeneration restoration. The method comprises the following steps: acquiring surface reflectance data, and calculating an NBR index after preprocessing; fitting an NBR time sequence through a LandTrendr algorithm, and extracting sample place time sequence data based on random sampling and visual interpretation; generating an adversarial network and expanding sample point fitting data into a simulation data set in combination with a self-supervised learning technology; training CNN, random forest and BOSSVS time sequence classification models, and constructing a hybrid classification model through an integrated voting strategy; and identifying a forest degeneration process by using a hybrid classification model, and generating a degeneration degree diagram through reclassification. The method can achieve the efficient recognition of the complex degradation process of the forest region, has good time sequence adaptability and regional applicability, and provides technical support for the monitoring and management of ecological restoration of regional forests.

A system, apparatus, and method to generate decoy honeypots by using generated adversarial networks. In some embodiments, a method for generating decoy honeypots, the steps comprising identifying a plurality of network device configurations on a network; instantiating a generative adversarial network comprising architecture properties; generating a plurality of decoy honeypots with the generative adversarial network, wherein the plurality of decoy honeypots imitate the plurality of network device configurations to deceive malicious actors, and wherein the generative adversarial network optimizes a distribution of the plurality of decoy honeypots according to a precision distribution and a recall distribution; activating the plurality of decoy honeypots to the network; and dynamically evolving the plurality of decoy honeypots towards one or more preferences of a network attacker.

The invention discloses a port wave spectrum parametric modeling algorithm based on machine learning, and relates to the technical field of ocean engineering, and high-precision modeling is realized through three steps: step one, constructing a federated learning framework, training sub-models by data parties only sharing parameters, combining homomorphic encryption fusion features and dynamically adjusting weights, and constructing a model; privacy protection type data fusion is realized; a second step of deploying a generative adversarial network at each local node, extracting multi-scale wave features through a frequency domain hierarchical attention branch network, implanting a sea wave energy conservation constraint and optimizing a generator, generating an extreme sample conforming to a physical law, and forming a mixed training data set; and a third step of training a CNN-LSTM basic model, and realizing dynamic optimization of the model through a sliding window, a forgetting factor, Bayesian optimization and performance monitoring reconstruction. The method effectively improves the wave spectrum prediction precision and long-term stability, reduces the maintenance cost, and can be used for scenes such as port ship berthing and disaster prevention early warning.

The invention relates to the technical field of image restoration, in particular to an image restoration system combining an attention mechanism and a generative adversarial network. The input unit receives an input image and a mask image and preprocesses the input image and the mask image; the generation unit generates a repaired image through a coding layer, a double-flow parallel attention bottleneck layer and a decoding layer, the double-flow parallel attention bottleneck layer generates global structure features by using a global context attention module, a mask-guided sparse attention module extracts local texture features, and the global structure features and the local texture features are fused through a self-adaptive gating fusion module; the discrimination unit adopts a multi-scale structure, carries out authenticity judgment on images with different resolutions through parallel sub discriminators, and introduces a gradient map as an additional channel; the training unit optimizes the generative adversarial network by using a composite loss function, wherein the composite loss function comprises adversarial loss, reconstruction loss and multistage frequency loss; the output unit outputs a final restored image; according to the system, the structure consistency and texture fidelity of image restoration are effectively improved.

The invention discloses a wind turbine generator improved domain self-adaptive cross-domain diagnosis method based on uncertainty quantization, and belongs to the technical field of wind turbine generator bearing fault diagnos.The wind turbine generator improved domain self-adaptive cross-domain diagnosis method comprises the steps that variational mode decomposition preprocessing is conducted on collected original fault signals, and the preprocessed fault signals are divided into source domain data and target domain data; constructing a domain adaptive deep adversarial network model based on double-layer attention enhancement, and training the model by using source domain data and target domain data; constructing a KFAC-based posterior uncertainty quantification module, introducing the KFAC-based posterior uncertainty quantification module into the trained adversarial network model, approximating real posterior distribution of model parameters by using Gaussian distribution, and providing an uncertainty estimation result for a diagnosis result; and fault diagnosis is carried out by using the adversarial network model which introduces a KFAC-based posterior uncertainty quantification module, and a diagnosis result is obtained. According to the method, the capability of capturing fault features is improved, and the reliability and interpretability of fault diagnosis are improved.

The invention relates to the technical field of unmanned vehicles, and discloses an unmanned vehicle auxiliary lane changing decision-making method based on multi-modal fusion, and the method comprises the steps: synthesizing a visual image of a densely overlapped vehicle contour through a generative adversarial network, shielding missing laser point cloud, radar signals of clutter interference, and other analog data; samples are expanded in combination with oversampling and transfer learning, and the problem of insufficient sample size is solved. A dynamic attention mechanism is utilized, correlation modes of multi-modal features such as vision, laser and radar in the scene are mainly learned, the scene is quickly recognized through a long-tail scene adaptation module of a meta-learning framework, and decision parameters are dynamically adjusted. In training, a mixed loss function is adopted to reinforce learning, sudden plug triggering is re-evaluated during real-time decision making, and meanwhile, the model is continuously optimized by relying on a feedback iteration mechanism. Finally, the model can accurately identify a plugging scene, the safety space is judged by fusing multi-modal features, dynamic changes are dealt with, and the traffic accident risk caused by plugging is reduced.