6614 results about "Data pre-processing" patented technology

A multimodal intelligent agent system for dynamic environmental monitoring and user-centered support, consisting of: a multimodal sensor module configured to continuously acquire environmental and behavioral data from multiple input modalities, including at least one visual sensor, at least one acoustic sensor, at least one environmental conditions sensor, and at least one proximity or motion detection sensor, each generating modality-specific data streams representing visual images, audio waveforms, physical environmental parameters, and motion signatures within a monitored environment; a data preprocessing and fusion subsystem that is operationally coupled with the multimodal sensor module and configured to normalize, temporally align, and transform the modality-specific data streams into high-dimensional feature embeddings using a variety of encoders, wherein the visual encoder uses convolutional or vision transformer architectures, the audio encoder uses a spectral-temporal feature extractor, and the sensor encoder transforms raw analog data into context vectors suitable for multimodal alignment; a multimodal processing unit consisting of a transformer-based large language model (LLM) trained on paired multimodal datasets and configured to perform semantic fusion, context abstraction, and inference across the aforementioned aligned multimodal feature embeddings to generate a contextual understanding of environmental and behavioral states; an adaptive agent controller coupled to the multimodal inference processing unit and configured to instantiate, manage, and terminate a variety of task-specific intelligent agents, each agent being a software unit configured to perform a specialized function selected from meeting summarization, behavioral analysis, misplaced object detection, or environmental anomaly identification, with the agents dynamically interacting with the inference engine to retrieve contextually relevant multimodal embeddings for task execution; a personalization and adaptive learning subsystem consisting of a user preference database and a neural memory structure configured to update and refine model parameters based on user-specific interaction history, thereby enabling personalized output generation, prioritization of recommendations, and long-term behavioral adaptation; and An output generation interface is operationally connected to the adaptive agent controller and configured to produce multimodal output in textual, visual, and auditory form. The interface is capable of displaying human-readable summaries, notifications, and visual reconstructions of identified entities or environmental states.

The invention discloses a multi-modal visual fusion complex scene small target detection tracking method and system, and relates to the technical field of unmanned aerial vehicle target tracking, and the method comprises the steps: employing a visible light camera, an infrared thermal imager and a laser radar sensor which are carried on an unmanned aerial vehicle platform, and synchronously collecting RGB images, thermal infrared images and point cloud data; the consistency of the multi-modal data is ensured through data preprocessing and space-time alignment; constructing a lightweight double-branch network to extract multi-scale features, generating a fusion feature map by adopting adaptive weighted fusion, and generating depth information by utilizing point cloud to assist in scale estimation; a small target detection head is designed based on the fusion feature map, and precise detection is realized in combination with a feature pyramid network, adaptive scale prediction and a context awareness suppression mechanism; furthermore, through multi-mode cooperative tracking, including target association, spatio-temporal context modeling, trajectory prediction and a re-detection mechanism, tracking continuity is ensured.

The invention discloses a stamping part forming precision dynamic monitoring system based on digital twinning, and particularly relates to the field of general monitoring and adjusting systems, and the stamping part forming precision dynamic monitoring system comprises a digital twinning modeling module, a twinning simulation prediction module, an intelligent function coupling decision module and a physical execution closed loop feedback module; the digital twinning modeling module collects stamping related data through a multi-source sensor, and constructs and dynamically updates a geometric, physical and behavior three-level digital twinning body after preprocessing; the twinborn body simulation prediction module is based on three-stage twinborn bodies and is combined with parameter initialization, double-source simulation, result fusion and threshold decision to realize pre-judgment of forming precision; the intelligent function coupling decision-making module generates a targeted regulation and control instruction through a basic regulation and control function and a dynamic coupling mechanism according to the precision out-of-tolerance signal and the physical data; and the physical execution closed-loop feedback module completes instruction execution, state perception and model correction through iterative loop, realizes dynamic monitoring of the forming precision of the stamping part, and improves the forming precision stability and the production efficiency of the stamping part.

The invention discloses a coal mine power supply intelligent monitoring system based on the Internet of Things, belongs to the field of coal mine power supply monitoring, and aims to solve the problems that an existing coal mine power supply intelligent monitoring system is lagged in response, high in false alarm rate and large in manual dependence degree. According to the invention, through the end-side global sensing module, the data advanced analysis module, the edge data processing module, the data transmission module, the cloud data analysis and model construction module and the fault early warning and closed-loop control module, the real-time acquisition of the equipment state is realized by deploying multiple types of intelligent sensors; local data preprocessing and abnormal pre-judgment are carried out by combining edge computing nodes, an equipment health degree model is established by adopting a time sequence data association analysis algorithm, closed-loop control of overload prediction, electric leakage positioning and energy consumption optimization is realized through multi-source data fusion analysis, and finally a three-level intelligent monitoring system of end side sensing-edge computing-cloud decision is formed. The system response efficiency and accuracy are improved, and the personal labor intensity is reduced.

The invention provides an enterprise process intelligent analysis system based on a large language model. The enterprise process intelligent analysis system comprises a master control scheduling module, a data preprocessing module, a hierarchical analysis module, an insight extraction module, a report generation module and a knowledge retrieval module. The master control scheduling module generates a scheduling plan based on chain thinking reasoning, and dynamically calls each module; the data preprocessing module carries out cleaning and structured conversion on the enterprise event logs and outputs standardized JSON (JavaScript Object Notation) data; the knowledge retrieval module is combined with an RAG technology and a vector database to provide context support for a large language model; the hierarchical analysis module drives a model to execute process discovery and bottleneck identification through a structured cue word template; the insight extraction module converts an analysis result into a commercial insight text containing reasons, influences and suggestions, and has a self-repairing mechanism to guarantee consistency; and the report generation module automatically generates an image-text report. The system can improve the efficiency and accuracy of process analysis.

The invention discloses an illness state tracking management system and method based on a lingual face diagnosis instrument, and belongs to the technical field of traditional Chinese medicine tongue diagnosis and modern information technology fusion. The system comprises a multi-modal data acquisition module, a data processing and analysis module and an augmented reality visualization module; according to the method, illness state tracking is achieved through the steps of multi-modal data acquisition, data preprocessing and feature fusion, personalized digital twinborn model establishment, augmented reality visualization presentation and the like, multi-dimensional data such as tongue picture macroscopic features and tongue surface microorganism distribution can be integrated, dynamic association between the data is revealed, the health state and the intervention effect are visually displayed, and the method is suitable for being popularized and applied. The method is suitable for the fields of traditional Chinese medicine health management and chronic disease monitoring.

The invention provides an electromagnetic field prediction method and device and electronic equipment, and relates to the technical field of electromagnetic field solving. The method comprises the following steps: acquiring historical electromagnetic original data in a field-line coupling scene, preprocessing the historical electromagnetic original data, inputting the preprocessed historical electromagnetic original data into an LSTM-PINN model, and outputting a physical field quantity mapping result; wherein the physical field quantity comprises an electric field component and a magnetic field component; setting a weighted loss function, and performing optimization training on the LSTM-PINN model based on a physical field quantity mapping result and an error of a real physical field quantity corresponding to historical electromagnetic original data to obtain a trained electromagnetic field prediction model; wherein the weighted loss function comprises a data loss function, a physical residual loss function, an initial condition loss function and a boundary condition loss function; and inputting real-time electromagnetic original data into the trained electromagnetic field prediction model to obtain a spatio-temporal distribution electromagnetic field prediction result. The method can effectively extract the spatial distribution features and the time sequence features at the same time, and is suitable for a complex field-line coupling problem.

The invention discloses a field soil heavy metal pollution health risk dynamic assessment and intelligent early warning system, and relates to the technical field of soil environment monitoring. The system comprises a multi-source data acquisition unit, a data preprocessing unit, a risk calculation engine and a visual interaction terminal. The key technical point is that a dynamic field evolution analysis module and an adaptive grid rendering control module are introduced; the dynamic field evolution analysis module constructs a pollution potential energy field matrix representing a pollutant migration trend based on soil heavy metal concentration and hydrogeological parameters, and calculates a space-time gradient change vector of the pollution potential energy field matrix; and the latter dynamically adjusts the grid local density according to the gradient vector module value, and automatically encrypts the computational nodes in the region with severe risk change. In cooperation with a time sequence prediction deduction and feedback correction mechanism, the method can simulate the dynamic evolution of the pollution plume in the porous medium in real time, solves the problems that a migration rule is difficult to capture and the calculation efficiency of a uniform grid is low in traditional static evaluation, and achieves three-dimensional dynamic risk early warning with high precision and low calculation power consumption.

The invention discloses a PLC controller fault detection system, and relates to the technical field of industrial control equipment fault detection.The system is characterized in that PLC operation environment data is acquired through a multi-physical-quantity holographic acquisition module, and after the PLC operation environment data is cleaned and subjected to feature fusion through a data preprocessing module, a fault model is constructed through a multi-physical-quantity fusion model module; the self-adaptive threshold value judgment module dynamically calculates and judges a threshold value and evaluates a state; the fault traceability analysis module constructs a propagation path diagram based on a model and historical cases, and realizes accurate traceability of a fault source and a propagation process; according to the invention, multi-physical-quantity holographic acquisition and feature fusion algorithms are integrated, multi-dimensional parameters are monitored synchronously, a comprehensive feature model is constructed, the fault identification precision is improved, and misjudgment is avoided; dynamic optimization is achieved through self-adaptive threshold judgment, the early warning accuracy is improved, meanwhile, accurate traceability is achieved through an element fault propagation algorithm, a path is optimized in combination with historical cases, the downtime is shortened through full-process intelligent support, and the maintenance cost is reduced.

The invention discloses an RAG intelligent retrieval question-answering system and method based on enhanced metadata, and relates to the technical field of information processing and intelligent retrieval, multi-source heterogeneous knowledge data is preprocessed to obtain unified knowledge data, and structured metadata is extracted from the unified knowledge data based on different text forms; vectorizing a document text in the structured metadata by combining with embedding of the knowledge graph to obtain document representation, and outputting the document representation, the structured metadata and the enhanced keyword set as an enhanced metadata object; labeling a display relationship between different enhanced metadata objects, and constructing to obtain a knowledge database; according to the intelligent knowledge service system and method, restrictive conditions and question intentions are extracted from user questions, mixed retrieval is performed from a knowledge database based on the restrictive conditions and the question intentions, a candidate literature semantic set is output, then structured statistical visualization reports and structured answers are output, and accurate, explainable and multifunctional intelligent knowledge services are achieved.

The invention provides a breakwater monitoring data preprocessing method and system based on Kalman filtering, and relates to the technical field of breakwater structure safety monitoring. The method comprises the following steps: acquiring original motion data of acceleration, inclination and displacement through a motion attitude sensor to obtain an original data sequence; initializing a state vector and an error covariance matrix; dynamically correcting the state transition matrix and calculating a prediction state vector and a prediction error covariance matrix; a Kalman gain is generated; updating a state vector and an error covariance matrix; and extracting the filtered motion data as a preprocessing result. According to the method, the state transition matrix is dynamically corrected by introducing the wave force feedback, so that the Kalman filtering algorithm can adapt to the wave impact environment, noise interference in monitoring data is effectively inhibited, and the accuracy and reliability of key motion parameter data of the breakwater are remarkably improved.

The invention relates to the technical field of environment monitoring, in particular to an intelligent acquisition method based on environment monitoring data fusion, which comprises the following steps: S1, constructing a multi-sensor distributed monitoring network, and acquiring atmosphere, water quality, soil and meteorological environment data; s2, performing data preprocessing, including smoothing, anomaly detection, interpolation and time alignment; s3, carrying out data source, feature and decision three-level fusion, and outputting an environment quality level; s4, constructing a quality index system, monitoring data quality and adaptively optimizing fusion parameters when the data quality is abnormal; s5, performing environment trend prediction and pollution tracing based on a fusion result, and generating early warning information; and S6, constructing a cross-modal causal diagram, reasoning a multi-source causal path, and identifying pollution key factors and source responsibility subjects. According to the invention, through multi-source environment data fusion and cross-modal causal reasoning, high-precision early warning of environment abnormity and intelligent traceability identification of pollution sources are realized.

The invention discloses a multi-source data fusion type intelligent data management system, which comprises a data preprocessing module used for accessing a heterogeneous data source and generating a standardized data frame; the cognitive sub-graph construction module is used for generating cognitive sub-graphs and forming a cross-source evolutionary multi-cognitive hypergraph; the event aggregation module is used for aggregating entities and relationships according to event fingerprints and outputting a multi-source observation chain; the causal checking module is used for performing causal comparison and conflict detection and outputting a checking result, a positioning report and a treatment suggestion; the fusion updating module is used for distributing weights and performing weighted fusion, outputting fusion representation and confidence score, recording conflicts and updating the hypergraph; and the memory pool module is used for storing the hypergraph, the check result and the fusion representation, executing weight adjustment, forgetting and elimination, and outputting a service interface. According to the method, intelligent fusion and dynamic management of multi-source heterogeneous data are realized by constructing a cross-source self-evolution multi-cognitive hypergraph and an active evolution type fusion memory pool.

The invention discloses a complex scene traffic sign detection method and system based on dynamic frequency band focusing and double-domain attention screening. The method comprises the following steps: carrying out data preprocessing and data enhancement on a collected road traffic sign image; a CADPCM module and a CHAttention cross coordination attention mechanism are used to construct a CACHNet backbone network; designing a DWMSN neck network, and establishing a dynamic fusion mechanism of multi-scale features; a CACHNet and a DWMSN neck network are used to construct a CDWN model, and a traffic sign enhancement data set is used to train the CDWN model to determine the optimal model weight thereof. Compared with the prior art, the method has the advantages that the average detection precision is improved by 3.3% while the light weight of the model is maintained by constructing a three-level framework of the feature extraction unit, the attention feature expression enhancement and the dynamic feature fusion, the complex scenes such as illumination variation and shielding can be effectively dealt with, and the method is suitable for popularization and application. And high-precision traffic sign detection support is provided for a vehicle-mounted intelligent auxiliary driving system.

The invention provides a desertification monitoring grading and vegetation extraction method and system, and relates to the field of desertification remote sensing monitoring and ecological assessment, and the method comprises the steps: selecting a multi-temporal satellite image and an unmanned aerial vehicle image which cover a full research region according to a preset condition, and carrying out the data preprocessing of the multi-temporal satellite image and the unmanned aerial vehicle image; the method comprises the following steps: constructing a desertification difference index by fitting a feature space of a vegetation index and a surface albedo by using a multi-temporal satellite image, grading the desertification degree of a research area to obtain a grading result, and locking a key monitoring area in the research area according to the grading result; a vegetation sample image of a key monitoring area is obtained from an unmanned aerial vehicle image, HSL color space conversion and hue optimization processing are carried out on the vegetation sample image, and a normalized vegetation index based on HSL is constructed, so that vegetation information of the key monitoring area is finely extracted, a key desertification disaster area is effectively positioned, and the accuracy of the desertification disaster area is improved. And vegetation information in the region is finely extracted.

The invention belongs to the technical field of artificial intelligence and engineering, and particularly discloses a tunnel deformation prediction method and system based on causal and space-time mixture graph attention, and the method comprises the steps: receiving monitoring data of a tunnel section, carrying out the data preprocessing of the monitoring data, and obtaining a time sequence; fusing the spatial adjacency relation of the monitoring points and the causal analysis result of the time sequence, generating a graph structure containing physical association and causal dependence, and constructing a weighted adjacency matrix in combination with the geological similarity of the monitoring points; inputting the weighted adjacent matrix and the time sequence into the hybrid network model, extracting spatial features and time sequence features, splicing the spatial features and the time features, inputting the spliced features into a full connection layer, and outputting a prediction result; and carrying out interpretability analysis on a prediction result, dynamically adjusting an early warning threshold value based on statistical distribution of prediction errors, and triggering a graded early warning signal for prompting. According to the invention, the prediction precision of tunnel deformation can be improved.

The invention discloses a ground penetrating radar B-scan data augmentation method and system. The ground penetrating radar B-scan data augmentation method comprises the steps that a ground penetrating radar B-scan primary data set is constructed in a simulation mode, and data preprocessing is carried out to construct a ground penetrating radar B-scan data set; constructing a ground penetrating radar B-scan data augmentation primary model based on the U-net network, the residual connection scheme, the jump connection scheme, the convolution scheme and the self-attention scheme, and training to obtain a ground penetrating radar B-scan data augmentation model; and the obtained B-scan data augmentation model of the ground penetrating radar is adopted to carry out data augmentation of the actual B-scan data of the ground penetrating radar. According to the method, augmentation of the B-scan data of the ground penetrating radar can be realized, the reliability is higher, the accuracy is better, and the data augmentation effect is better.

The invention discloses a resting electroencephalogram quality evaluation method and system based on double-branch comparative learning, and the method comprises the steps: collecting an original EEG signal X, carrying out the data preprocessing and data enhancement, generating two different enhanced views, transmitting the two different enhanced views to a double-branch encoder in parallel, respectively extracting a time domain waveform and a time-frequency domain rhythm feature, and carrying out the deep fusion, the fused features X1 and X2 are sent to a projection head, and through a self-supervised contrast learning mechanism, the network weight is optimized by using contrast loss; a small amount of labeled fine-tuning data sets including X and corresponding labels y are adopted, after flowing through a pre-trained double-branch encoder, the fine-tuning data sets are directly sent to a classification head connected with the back of the double-branch encoder so as to output a prediction result of an input data segment, and a mixed loss function including classification loss and comparison loss is adopted for training in the optimization process. According to the invention, a complete online real-time quality control system is established, and end-to-end real-time closed loop from data acquisition to quality evaluation is realized.

The invention discloses a multi-target intelligent optimization method and system for blasting parameters of a strip mine in a high-altitude cold region. The method comprises the following steps: carrying out data acquisition to obtain a parameter data set; performing data preprocessing on the parameter data set to obtain a feature sample set; constructing an initial blasting parameter model based on a machine learning algorithm, and performing hyper-parameter optimization on the model to obtain a blasting parameter model; a multi-objective optimization function is constructed: based on the multi-objective optimization function and the blasting parameter model, solving is carried out in combination with environmental condition constraints, and a pareto optimal solution set is obtained; according to the pareto optimal solution set, a representative solution is selected, a visual scheme is generated, and blasting parameter optimization of the strip mine in the high-altitude cold region is completed. According to the method, temperature, oxygen and frozen soil constraint conditions of the high-cold and high-altitude environment are introduced, blasting safety, lumpiness uniformity and the explosive utilization rate are considered at the same time through multi-target collaborative optimization, the method can adapt to the extreme environment, meanwhile, the one-sidedness of single-target optimization is avoided, and the intelligent level of blasting design and implementation is greatly improved.

The invention discloses a medical image segmentation method based on TransUNet, and belongs to the technical field of medical image segmentation. The method comprises the steps of firstly performing data preprocessing on an original image to obtain preprocessed data; and a DCA attention module is used at a jump joint, so that the problem that a semantic gap exists between characteristics of an encoder and a decoder due to the fact that a simple jump connection scheme is difficult to capture a multi-scale context is solved. The semantic difference leads to redundancy between low-level and high-level features, and finally the segmentation performance is limited. Secondly, a multi-scale boundary sensing module is added to the top layer of the encoder, so that the neural network can better segment the boundary of the target image in the training process; and inputting the preprocessed data into the improved TransUNet model to train the medical image, and outputting an image segmentation result.

The invention provides a self-adaptive semantic-driven data set field matching method and system, and the system comprises a data preprocessing module which is used for carrying out the cleaning, standardization and preliminary analysis of an input data set, and extracting a field name, a data type, a field description and a data sample; the deep semantic representation modeling module is used for constructing a field-level semantic representation vector; the multi-level similarity calculation module is used for comprehensively calculating the grammatical similarity, the semantic similarity and the statistical similarity among the fields, dynamically adjusting the weight of the similarity of each level by adopting a weighted fusion algorithm, and generating a comprehensive similarity matrix; and the matching result management and application module is used for generating a field matching mapping table and a fusion suggestion according to the comprehensive similarity matrix. According to the method, high-precision automatic matching of data set fields is realized by fusing deep semantic understanding, multi-dimensional similarity calculation and incremental adaptive learning, and the efficiency and accuracy of data set fusion are remarkably improved.

The invention relates to the technical field of digital engineering, and particularly provides a BIM-based engineering construction dynamic three-dimensional visual management method and system, and the method comprises the steps: collecting construction multi-dimensional data, carrying out the correlation mapping with an initial BIM model component after preprocessing, and forming a structured construction element data set; dynamically reconstructing an initial BIM model based on the data set, generating a three-dimensional dynamic twinborn body, and dynamically displaying information such as superposition progress, quality, resources and environment; a prediction analysis model is called to generate progress prediction, quality early warning and resource optimization suggestions, and a final scheme is determined after visual simulation verification; and updating the data set and the twin according to an execution result, and iteratively optimizing the prediction model. According to the scheme, dynamic integration and visual management of construction total elements are achieved, the timeliness, accuracy and intelligent level of construction management are effectively improved through intelligent prediction and closed-loop optimization, the construction efficiency is improved, and the management cost is reduced.

The invention belongs to the technical field of power system load prediction, and relates to a long-range multivariable load prediction method and system based on time-frequency domain collaboration, and the system carries out the normalization and stabilization of a multivariate load time sequence through a data preprocessing module; the feature embedding module performs linear embedding on the block sequence to construct high-dimensional feature representation; the state space coding module extracts long-range dependency features and generates depth time sequence representation; the decoding prediction module maps the coding features into a preliminary prediction sequence; the time sequence alignment module identifies a leading-lagging relation among multiple variables and aligns a time sequence; the frequency domain optimization module realizes frequency domain component fusion based on adaptive filtering; and the model training optimization module is used for performing training and optimization through a signal attenuation loss function. The method can effectively improve the precision and robustness of long-range multivariable load prediction, and especially has obvious advantages in the aspects of processing complex dependency relationships and dynamic time delay.

The invention relates to a bidding document total-factor blind-state desensitization method fusing multi-modal artificial intelligence, and the method comprises the following steps: S1, obtaining an original bidding document package, carrying out the data preprocessing, and obtaining a standardized document set; s2, according to the standardized document set, performing multi-modal content identification and alignment to obtain a multi-modal content library; s3, constructing a sensitive information classification system based on domain expert knowledge and a historical case library; s4, constructing a dynamic rule base according to the sensitive information classification system; s5, according to the multi-modal content library and the dynamic rule library, in combination with deep learning, multi-modal sensitive information intelligent detection is carried out, and a sensitive area set is confirmed; and S6, based on the dynamic rule base, performing intelligent desensitization on the sensitive area set to obtain a desensitized document. According to the method, the risk of sensitive information leakage is effectively reduced while the bidding file expression effect is improved.

The invention discloses a multi-modal abnormal data detection and restoration method and system oriented to a power business scene. The method comprises the following steps: collecting multi-source heterogeneous power data, abstracting a power system into a weighted undirected graph, uniformly mapping the multi-source heterogeneous data into a graph signal, and preprocessing the collected data; extracting spatial features of nodes in a topological structure by adopting a graph convolutional network, and capturing a time dependency relationship in combination with a time sequence encoder; identifying various types of data abnormal points through an abnormal scoring function fusing the time sequence prediction error and the neighborhood consistency; a prediction-reconstruction combined repair strategy is adopted, time sequence prediction and neighborhood diffusion estimation are fused, and a preliminary repair value is generated; a lightweight parameter adapter is introduced, a scene feature vector is used as input, a repair weight and a regularization coefficient are dynamically generated, and a repair strategy is automatically adjusted; and performing physical consistency verification on a data result, wherein the physical consistency verification comprises power injection conservation constraint, voltage amplitude range constraint and time sequence continuity constraint.

The invention relates to a water plant intelligent chemical adding amount prediction method based on data preprocessing, and belongs to the technical field of deep learning and intelligent chemical adding. Calculating a theoretical dosage based on historical flow, pH, water temperature and turbidity; dividing a plurality of clusters and splicing to query historical dosage data; weighting and fusing the theoretical dosing amount and the inquired historical dosing amount as a pre-treatment dosing amount; learning the relationship among the flow, the pH, the water temperature, the turbidity and the pretreatment dosage to perform forward feedback optimization; building an alumen ustum image recognition model, classifying alumen ustum, and associating the alumen ustum with corresponding dosage to form a dosage feedback algorithm model; building a dosage feedback model based on the sedimentation tank outlet water quality monitoring data; and correcting the weight in the preprocessed dosage based on the adjusted data of alumen ustum identification and water quality feedback on the dosage. The method can effectively reduce the influence of the dosage data error on the effectiveness of the model, can reduce the complexity of the algorithm model, and improves the robustness of the model.

The invention discloses a multi-condition simulation capacitance detection relay life prediction method, system, equipment and medium, and relates to the technical field of relays, and the method comprises the steps: applying a plurality of simulation conditions to a relay through a programmable driving power supply, simulating the complex conditions in actual operation, and collecting the multi-dimensional parameters of the relay in real time in the execution process of the simulation conditions, extracting characteristic parameters from the collected multi-dimensional parameters, carrying out data preprocessing on the characteristic parameters, constructing a life prediction model, carrying out prediction calculation and reliability grade evaluation on the residual life of the relay by utilizing the life prediction model, and carrying out reliability grade evaluation on the residual life of the relay by monitoring capacitance change between contacts of the relay. And early performance degradation early warning is carried out in combination with a prediction result. According to the invention, through fusion of multi-working-condition simulation, hybrid modeling and capacitance detection, full-chain optimization from data acquisition, accurate prediction to early warning is realized, and the accuracy, timeliness and engineering application value of relay life prediction are improved.

The invention belongs to the technical field of computer vision and digital video processing, and discloses a video object segmentation method based on query adaptive attention and discriminative memory, which comprises the following steps: step 1, constructing a video data set and preprocessing data; step 2, constructing a video object segmentation model combining multi-scale semantic feature integration and query adaptive discriminant enhancement, and training the video object segmentation model; step 3, video object segmentation reasoning; performing target segmentation reasoning on the preprocessed video sequence, outputting a frame-by-frame target segmentation mask, and generating a time sequence tracking result; 4, exporting, deploying and applying the model; through lightweight network design and a discriminative memory optimization strategy, the model is deployed to edge equipment, and real-time segmentation and visualization are realized. According to the method, on one hand, comprehensive target representation is provided on multi-scale feature extraction, and on the basis of the characteristic that only high-confidence target features are stored, error propagation is avoided, and the long-term segmentation stability of the method is ensured.

The invention provides a highway engineering quality real-time monitoring method and system based on digital twinning, and the method comprises the steps: collecting construction data, and carrying out the preprocessing of the construction data, and obtaining a behavior time sequence and a coverage rate index sequence; constructing a behavior graph, performing quality prediction on each behavior segment node through a graph neural network to obtain a predicted quality score, and performing coverage rate index sequence correction to obtain an actual quality score; mapping the actual quality score to a spatial position to obtain a spatial quality tensor, wherein the spatial position is a three-dimensional position obtained by combining equipment position data and a compaction horizon number; performing structural consistency analysis on the spatial quality tensor, identifying and marking a topology abnormal region, and outputting a structural consistency scoring tensor; and generating a visual twin layer based on the spatial quality tensor and the structural consistency scoring tensor, and performing graph level labeling and section mapping on the abnormal region.

The invention discloses a laser radar and multispectral polarization imaging fused target identification system and method. The system comprises a sensor configuration and data preprocessing module, a cross-modal feature extraction and fusion module and a multi-task output and optimization module. The sensor configuration and data preprocessing module performs time-space synchronization processing on the collected original optical signals and laser signals in the environment to obtain multispectral image data and laser radar point cloud data; the cross-modal feature extraction and fusion module performs feature extraction and fusion enhancement processing on the multispectral image data and the laser radar point cloud data, and outputs high-dimensional semantic enhancement point cloud representation containing image semantics and point cloud geometry; and the multi-task output and optimization module processes the high-dimensional semantic enhanced point cloud representation and outputs a three-dimensional target recognition result, target speed information and a pixel-level depth map. Through module design and data processing, the defects in the prior art are overcome, and the accuracy of target recognition is improved.