6117 results about "Deep neural networks" patented technology

The invention discloses a cross-modal information fusion and retrieval method and system driven by semantic comprehension, and the method comprises the steps: obtaining text, image and audio original data, and extracting an initial feature set of each modal through a deep neural network; dynamically distributing each modal weight coefficient based on an attention mechanism, and performing weighted fusion on the initial feature set to obtain cross-modal fusion feature representation; through a cross-modal semantic association analysis model, high-dimensional semantic association features are extracted from the fusion feature representation, and semantic enhancement feature vectors are generated; constructing a cross-modal semantic graph network based on the vector, complementing missing modal features, and generating an optimized multi-modal feature set; and inputting the optimized feature set and the query sample into a contrast learning model, calculating a semantic similarity score, and generating a cross-modal retrieval result sorting list according to the score.

The invention relates to the technical field of hydraulic engineering safety monitoring, and particularly discloses a hydraulic engineering dam safety monitoring and early warning method and system, which realize comprehensive perception and accurate early warning of the health state of a dam structure through a composite sensing technology and an intelligent analysis algorithm. A micro-mechanical resonance sensor and a distributed optical fiber sensor are cooperatively deployed, and an interface and structure integrated three-dimensional monitoring network is constructed; a three-dimensional interface stripping characteristic spectrum is constructed based on a time-frequency conjoint analysis technology, and the bonding degradation state between the sensor and the dam body is accurately identified; a strain field anomaly distribution matrix is established through spatial correlation modeling, precise positioning of internal damage is realized, a dual-channel feature fusion network and a deep neural network evaluator based on an attention mechanism are designed, and multi-dimensional correlation analysis is performed on an interface state and structural damage features; and finally, realizing progressive response from data verification and multi-source verification to emergency linkage through a three-level linkage early warning decision tree.

The present invention relates to the field of industrial intelligent predictive maintenance, and in particular to an interpretable deep feature fusion network-based industrial intelligent predictive maintenance method, comprising: acquiring gearbox vibration data comprising noise; performing preliminary extraction and noise suppression on features of the acquired data by establishing an interpretable feature extraction module having a physical information constraint; integrating multi-scale features comprising long-distance and local dependencies by means of a dual-branch feature fusion module having global and local feature fusion capabilities; performing dimensionality reduction on a high-dimensional feature and generating an output by means of a classifier to obtain a final fault identification result; and performing interpretability analysis on a diagnosis process of a model. In the present invention, by embedding the signal processing technology having a well-defined physical theory support into a deep neural network, the interpretability and reliability of model inference results are effectively improved while the fault identification accuracy of the model is improved.

The invention discloses an intelligent multi-modal virtual digital human interaction system based on an AI language large model. The system comprises a high-authenticity face generation module; the high-authenticity face generation module uses an AdaAN network, based on adaptive feature fusion and voice driving and time sequence modeling of voice features, feature information related to voice is extracted, the extracted voice features are processed through a deep neural network, it is ensured that the voice and facial expressions are highly aligned in time and space, and the face recognition accuracy is improved. Collecting a bio-electricity signal, mapping the signal to facial muscle movement, generating a final facial expression, and interacting with a user; the system further comprises an intelligent interaction module, a training optimization and efficient generation module, an efficient integration module, a multi-modal data acquisition module, an AI large model core processing module, a digital human image generation and driving module, an interaction scene adaptation module and a feedback optimization module. The invention further discloses a multi-mode digital human interaction method which has wide application value.

The invention relates to the technical field of automation, in particular to an automatic monitoring and optimizing system for a fine chemical production process, which comprises the following steps of: extracting time-frequency domain fusion characteristic quantity of stirring torque power time sequence fluctuation data in real time through an incidence matrix construction module, dynamically inverting a thixotropic index by combining a deep neural network model, and optimizing the stirring torque power time sequence fluctuation data; the problem that a traditional method is difficult to perceive material rheological characteristics in real time is solved. The dynamic coupling analysis module analyzes the material viscosity change rate based on the thixotropic index, fuzzy PID control is adopted to generate a stirring speed adjusting instruction dynamically matched with the viscosity and a jacket temperature compensation value, and the defects of uneven mixing and local overheating caused by lagging adjustment of process parameters are overcome; the multi-target collaborative optimization module locks the mass optimization weight in the viscosity sudden change stage, rapidly stabilizes the reaction condition through a feed-forward compensation algorithm, dynamically balances the stirring power consumption and the heat transfer efficiency based on Pareto frontier search in the steady state stage, and solves the conflict between the mass and the energy efficiency target.

The invention provides an enterprise employee behavior analysis and safety risk early warning monitoring method and system, and relates to the technical field of enterprise risk management, and the method comprises the steps: collecting employee terminal operation behavior data, building an activity thermal distribution diagram based on office area grid behavior association intensity, and training a behavior evaluation model. And inputting the behavior scoring matrix into a deep neural network to extract target behavior characteristics, calculating an abnormal behavior risk weight coefficient in combination with a department security policy, performing classification and analyzing a risk diffusion probability, and generating a risk situation index to determine an early warning level. Starting a response strategy according to the early warning level, blocking high-risk early warning in real time, tracking associated accounts, establishing a risk association map, identifying potential risk propagation nodes and performing active protection, finally generating an early warning report and feeding back effective protection rules to a behavior baseline model, and realizing continuous optimization of a risk early warning mechanism. And the accuracy and effectiveness of safety risk early warning in the enterprise are improved.

The invention provides a pressure-bearing equipment damage mode identification and risk assessment method and system, and relates to the technical field of safety engineering, and the method comprises the steps: collecting multi-source sensor data and image data, inputting the data into a deep neural network after preprocessing and feature extraction, extracting spatial features through a convolutional layer, and extracting time sequence features through a recurrent neural network. And using the attention mechanism to fuse the features to identify an injury pattern. And then, constructing a multi-level evaluation index system, performing combined weighting by adopting an analytic hierarchy process and an entropy weight method, inputting weights into an improved Bayesian network model based on a D-S evidence theory, dynamically updating a conditional probability table by the model by utilizing a deep neural network and a fuzzy inference rule, and finally obtaining a risk evaluation result. According to the invention, the damage mode of the pressure-bearing equipment can be effectively identified, risk assessment is carried out, and assessment precision and reliability are improved.

The invention discloses an intelligent water quality regulation and control system and method based on multi-parameter real-time monitoring, and belongs to the technical field of water quality monitoring. According to the intelligent water quality regulation and control system, the water quality data of the water body is obtained in real time through the multi-parameter sensor array, and the monitoring regulation and control server can quickly generate an abnormal report and a water quality regulation and control scheme. The data processing module performs feature extraction on the water quality data to obtain target features; the water quality evaluation module is used for accurately evaluating the water quality by using a pre-trained deep neural network model; the abnormity identification module can timely judge whether the water quality has a pollution risk and generate an abnormity report; and the regulation and control module generates a water quality regulation and control scheme by adopting a multi-objective optimization algorithm. The system realizes real-time performance, accuracy and intelligence of water quality monitoring, can quickly respond to water quality changes, effectively reduces pollution risks, and improves the efficiency and effect of water quality regulation and control.

The invention discloses an industrial equipment fault prediction method based on multi-modal data, and belongs to the technical field of specific calculation models, and the method comprises the steps: carrying out the preprocessing according to the collected multi-modal data of the operation of industrial equipment, so as to unify the format of the multi-modal data, and obtaining the structural data; extracting features of the structured data one by one according to data categories, and obtaining a multi-modal fusion feature through a dynamic fusion mechanism; according to the multi-modal fusion features, a fault prediction classification score is obtained through a deep neural network model to perform fault prediction; and when the drift parameter of the multi-modal data is greater than a preset threshold value, performing incremental training on the deep neural network model through the multi-modal data collected in real time to update parameters of the deep neural network model. Through multi-modal data unified processing, dynamic feature fusion, deep neural network modeling and an online learning mechanism, the problems of insufficient multi-modal data fusion, prediction uncertainty quantization deficiency, poor model adaptability and the like are solved.

The invention relates to the technical field of mobile energy storage vehicles, and discloses an AI-based mobile energy storage vehicle running state monitoring and analysis system which comprises a main controller, an AI monitoring coprocessor and a state analysis coprocessor. The main controller calls a monitoring analysis instruction and sends the monitoring analysis instruction to the state analysis coprocessor; an AI monitoring coprocessor dispatches a state analysis instruction and processes multi-modal data; and the state analysis coprocessor analyzes the parameters to generate a reference monitoring signal, cooperatively monitors the battery temperature, the charging and discharging efficiency and the load fluctuation in real time, and generates an abnormal correction signal and a state control instruction in combination with an analysis optimization mode. The system realizes accurate analysis of multi-source data and dynamic control of the energy storage unit through data preprocessing, feature dimension reduction and deep neural network prediction, improves monitoring accuracy, dynamic adaptability and intelligent level, and ensures safe and efficient operation of the mobile energy storage vehicle.

The invention relates to the field of road traffic, in particular to a multi-feature fusion fatigue driving detection method and a fatigue driving detection system. The method comprises the following steps: extracting facial features from a face image of a driver; extracting vehicle features from the vehicle driving parameters of the vehicle driven by the driver; and fusing the facial features and the vehicle features to judge whether the driver is in fatigue driving. Extracting facial features by designing a CNN model; extracting basic convolution features; extracting local convolution features; extracting global convolution features; performing pooling operation; aggregating global features; and carrying out dimensionality reduction mapping. A self-encoder is designed to extract vehicle characteristics; a symmetric deep neural network structure is adopted, and high-dimensional time sequence data is compressed to a low-dimensional potential space through nonlinear mapping; through combination and matching of the CNN model and the auto-encoder, the technical defects of feature redundancy, noise interference, information loss and suboptimal decision existing in an existing multi-feature fusion fatigue driving detection system are thoroughly solved.

The invention discloses a deep neural network model-based backfill compaction degree quality evaluation method, which comprises the following steps of: acquiring various physical characteristics of soil in a compaction process in real time through a multi-source sensor, and performing data labeling and time-space adaptive normalization processing; based on the position information of the multi-source sensor and the multi-source sensing data, adopting an improved empirical mode decomposition and stochastic resonance enhancement method, and fusing same-order mode components of the multi-source sensor to obtain an intrinsic mode function related to the compactness; in combination with graph convolution operation, stochastic resonance gating, multi-scale time sequence attention, a mixed loss function, a dynamic course learning strategy and the like, training the deep neural network model; and based on the trained model, carrying out backfill compaction degree quality evaluation on the to-be-detected area. According to the method, by collecting multi-source data in real time and combining advanced technologies such as space-time adaptive normalization, empirical mode decomposition and dynamic adaptive graph convolution, efficient and stable backfill compaction degree evaluation is achieved.

The invention provides a mesoscale convection parameter optimization method and system based on a genetic algorithm, and relates to the technical field of weather forecast, and the method comprises the steps: modeling a rainfall evolution state through a Sheng differential equation, inferring and recognizing power system parameters in combination with variation, and extracting features through a space-time heterogeneous graph neural network and a diffusion probability model; the parameter threshold is corrected by adopting the physically guided neural network, and the optimization objective function is constructed through the deep neural network to realize parameter optimization, so that the accuracy of rainfall forecasting can be improved, the forecasting error can be reduced, and the method has relatively strong adaptability and generalization ability.

Disclosed in the present invention is an improved deep learning model-based refrigeration unit fault detection method. The method uses an LOF algorithm to remove outliers from a fault dataset, and then uses ADASYN technology to solve the problem of data imbalance. In addition, in respect of the problems that existing refrigeration unit fault diagnosis deep learning models are prone to network degradation, and refrigeration unit fault diagnosis models generally lack weighting critical features, the present invention first alleviate, on the basis of ResNet, the problem of network performance degradation which is prone to occur in deep neural network training processes, and then integrates a CBAM for capturing critical features in fault data, so as to improve the feature extraction capability of a network. Experimental results show that the LOF-ADASYN-ResNet-CBAM method provided by the present invention effectively diagnoses refrigeration unit faults.

The invention relates to the technical field of user behavior analysis, and discloses a user behavior intelligent analysis and management system based on a big data technology. The system comprises a user behavior data acquisition module for acquiring behavior data in a multi-dimensional scene; the behavior feature intelligent recognition module is used for extracting features by using a deep neural network and a time sequence analysis algorithm and generating a map; the behavior pattern dynamic analysis module is used for analyzing pattern changes through dynamic clustering and a hidden Markov model; the abnormal behavior autonomous detection module is used for detecting anomalies based on the multi-dimensional anomaly score and an adaptive threshold value; and the behavior management intelligent optimization module is used for optimizing a management strategy by utilizing a reinforcement learning algorithm. In addition, a behavior data archiving module is further arranged to guarantee safe storage of data. The system can comprehensively collect and analyze user behavior data, accurately detect abnormity, intelligently optimize a management strategy, improve user experience, system safety and operation efficiency, and have wide application value in multiple fields.

The invention relates to a higher education personalized hierarchical teaching method and system based on artificial intelligence, and the method comprises the steps: obtaining multi-dimensional learning data, carrying out the time-space alignment processing, and generating a synchronous multi-dimensional data set; performing spatial-temporal feature fusion and time sequence modeling on the data set by using a deep neural network, and constructing a dynamic student portrait; analyzing knowledge mastery degree features in the portrait through a semantic analysis model, and generating a personalized resource recommendation sequence in combination with the knowledge graph; based on the sequence and the portrait, planning a personalized learning path by using a path reasoning algorithm; and carrying out teaching hierarchy binding on the personalized resource recommendation sequence and the learning path to form a hierarchical teaching scheme. Accurate teaching support is provided for individual differences of students, and the teaching effect and learning experience are effectively improved.

The invention provides an enhanced generation method based on question matching retrieval, and belongs to the field of matching generation, and the method comprises the following steps: S1, a semantic feature coding stage: carrying out real-time feature extraction and vector space mapping on a natural language query input by a user by adopting a deep neural network model, generating high-dimensional distributed representation with semantic representation capability; s2, a knowledge base intelligent retrieval stage: executing multi-dimensional semantic matching in the vectorized knowledge base based on an approximate nearest neighbor search algorithm, and screening out a candidate knowledge set highly related to query semantics through a similarity measurement function; s3, retrieval matching results are automatically associated to the structured knowledge base through the established semantic-knowledge mapping relation, the preprocessed standardized response content is directly obtained, and the response content adopts a multi-modal data organization form and comprises a structured data entity and retains a rich text expression form.

The invention discloses a speech recognition and natural language processing integration method and system, and the method comprises the steps: carrying out the multi-modal data fusion according to a speech signal of a user, context text information and environment sensor data, and obtaining a fused multi-modal feature vector; inputting the multi-modal feature vector into a speech recognition model based on an adaptive deep neural network, and performing speech-to-text processing to obtain text output; inputting the text output into a semantic analysis model based on a graph neural network, and performing context semantic analysis and user intention recognition to obtain semantic representation of the user intention and a confidence score of the semantic representation; and according to the semantic representation and the confidence score thereof, dynamically adjusting parameters of the speech recognition model and the semantic analysis model by using a feedback optimization technology based on reinforcement learning, and generating a model optimization strategy. According to the embodiment of the invention, the accuracy of speech recognition and the semantic comprehension capability of natural language processing can be improved.

The invention discloses a keyboard key defect detection method and system based on machine vision, and the method comprises the following steps: collecting the multi-modal data of keyboard keys, and carrying out the fusion preprocessing of reflection component separation, dynamic gamma correction and multi-modal constraint alignment; constructing a double-flow deep neural network for defect detection, wherein the first branch network adopts an improved U-Net architecture embedded with a CBAM attention module to extract texture features; the second branch network adopts a PointNet + + architecture to process three-dimensional geometrical characteristics; realizing cross-modal feature association through a feature fusion layer, wherein a fusion weight is adaptively adjusted according to a material type; and outputting a detection result based on the cascade classifier, wherein the method comprises the following steps: positioning a suspected defect area by a first-stage YOLOv5 network; the second-stage ResNet50 network is used for completing defect classification; and the dynamic threshold segmentation algorithm adjusts the judgment boundary according to the material type. According to the invention, high-precision and high-efficiency detection of keyboard key defects is realized.

The embodiment of the invention provides an end-to-end automatic driving control method and device based on multi-camera fusion, and multi-view target detection and tracking are realized through spatial transformation and coordinate mapping by combining front wide-angle camera information and left and right wide-angle camera information. A multi-view feature fusion network architecture is designed, the multi-view feature fusion network architecture comprises three sub-networks of feature extraction, dynamic weight distribution and feature fusion, and the fusion weight is dynamically adjusted based on image definition, detection confidence and view overlapping degree. A geometric consistency constraint between visual angles and a reconstruction loss function are introduced, a deep neural network model is constructed, abnormal conditions such as camera shielding are effectively handled, and an accurate control instruction is output. According to the method, the defects of the traditional technology in the aspects of multi-view information fusion, shielding processing and the like are overcome, and the sensing ability and the control reliability of the automatic driving system are remarkably improved.

The invention provides a new energy photovoltaic dynamic inspection method and system based on artificial intelligence, and relates to the technical field of photovoltaic power station intelligent inspection. Inspection is triggered according to weather early warning, performance warning or timed tasks; initial path planning is carried out by combining terrain, weather and historical data, and the path is updated by dynamic obstacle avoidance through an RRT * algorithm; multi-modal data, including visible light images, infrared thermal imaging, EL detection data and positioning data, are acquired during inspection of the unmanned aerial vehicle; the unmanned aerial vehicle data and the ground sensor data are integrated to generate a unified fault feature matrix; positioning a defect area in real time by using a deep neural network, judging a defect type and dividing a fault level; and finally, the health degree of the photovoltaic system is scored according to the fault level, and the safe operation trend is analyzed. The multi-modal data real-time fusion and dynamic path planning are realized, the fault identification precision and the inspection efficiency are improved, the manual inspection cost and risk are reduced, and powerful support is provided for intelligent operation and maintenance of a photovoltaic system.

The invention relates to the technical field of data center heat dissipation, and particularly provides a single-phase and two-phase immersion liquid cooling method and system based on AI intelligent decision, and the method comprises the steps: injecting coupled data into a dynamic feature extraction engine, and outputting a thermodynamic state evolution tensor which comprises the characteristics of a temperature change rate, a load-heat flux density coupling coefficient and the like; the thermodynamic state evolution tensor is input into the deep neural network model, the temperature and pressure matched with the current thermodynamic state evolution tensor are calculated, and a closed-loop control instruction set capable of being executed by equipment is generated; a closed-loop control instruction set is injected into an execution mechanism set, execution mechanisms execute power reconstruction and flow channel switching according to instructions, gaseous fluorinated liquid is liquefied and flows back through an efficient condenser in a two-phase mode, and heat dissipation mode self-adaptive switching and heat cycle reconstruction are achieved. The system comprises a server, an AI algorithm controller, a cooling liquid storage device, a condenser, a circulating pump, an electric valve, a pressure release valve and a temperature sensor. The heat dissipation efficiency and the system reliability are remarkably improved.

The invention relates to the technical field of water conservancy project detection, and discloses a water conservancy project safety detection early warning method based on artificial intelligence. The method comprises the following steps: acquiring multi-modal monitoring data of a key part through a distributed sensor network, and extracting a dynamic feature sequence in a preset time period through space-time alignment and noise filtering; inputting the image into a deep neural network fused with an attention mechanism, constructing a multi-scale space-time correlation map through hierarchical feature learning, and generating a high-dimensional representation of an engineering structure state; historical accident case data is used as a supervision signal, a hybrid expert model is used for performing multi-task training on high-dimensional representation, and the contribution weight of each monitoring index to the safety risk is obtained; combining real-time environment parameters and structural response characteristics to construct a dynamic threshold adjustment model, adaptively updating an early warning threshold according to a risk probability, and screening out key risk factors of which the contribution weights are greater than the updated threshold; and on the basis of spatial and temporal distribution characteristics, through graph neural network node association reasoning, multi-source early warning information is fused to generate a graded early warning result.

The invention discloses a three-dimensional stomatognathic model reconstruction system based on multi-modal data fusion. The system comprises a multi-modal data input unit, a template deformation reconstruction unit, a registration fusion unit, a multi-source data integration unit and an output unit. Through fusion processing of a CBCT image, an oral cavity vision measurement model and facial scanning data, a body deformation algorithm is adopted to couple biomechanical characteristics to realize craniojaw template deformation, and a non-rigid ICP algorithm is combined for dynamic regulation and control to realize facial template adaptation. A deep neural network is innovatively constructed to segment CBCT gingival data, the CBCT gingival data is fused with an oral cavity vision measurement model, and high-precision tooth reconstruction is realized by applying a differential geometry multi-scale curvature field segmentation and adversarial edge optimization technology. Through a composite registration strategy combining adaptive rigid registration and non-rigid registration, an occlusal plane constraint mechanism and an orbital curvature extreme point matching algorithm are innovatively introduced, finally, multi-source data high-precision registration fusion is realized, and a three-dimensional oral-jaw system model with anatomical structure integrity and clinical precision can be generated.

The invention discloses an electromechanical equipment health assessment and early warning method based on multi-mode dynamic perception, and belongs to the field of intelligent operation and maintenance of electromechanical equipment. The problems that in the prior art, a single physical quantity cannot comprehensively reflect the equipment state and a traditional signal processing algorithm cannot adapt to the equipment degradation mode change are solved, a panoramic sensing system covering multiple physical fields such as vibration, temperature and noise is constructed through a multi-mode sensor network and a dynamic weight fusion algorithm, and the multi-physical-field multi-physical-field panoramic sensing method is applied to the multi-physical-field multi-physical-field panoramic sensing system. The problem of isolated island of traditional single-dimensional monitoring information is solved; through a physical-depth mixed feature extraction architecture, combining interpretable engineering features with abstract features extracted by a deep neural network to form a health assessment model with mechanism transparency and mode generalization ability; through deep integration of the digital twin platform and the RPA technology, the manual inspection frequency and workload are reduced, the fault recognition accuracy is promoted to increase year by year, and continuously optimized intelligent operation and maintenance ecology is formed.

The invention relates to a proton exchange membrane fuel cell (PEMFC) high current density performance prediction method, system, equipment and medium. The method comprises the following steps: establishing a multi-physical field coupling model which comprehensively considers complex processes such as electrochemical reaction, proton conduction, gas diffusion and heat transfer, and describing the change of each physical quantity by adopting a partial differential equation based on a basic physical law; performing grid division and numerical discretization on the proton exchange membrane fuel cell model; selecting model parameters, and verifying the model through experimental data of different working conditions; inputting actual working condition parameters into a model to predict performance, and analyzing a simulation result; using a convolutional neural network, a recurrent neural network and an auto-encoder to extract features from different types of data and fuse the features to form a comprehensive feature vector; a deep neural network prediction model is constructed, and a cross entropy loss function and an Adam optimizer are adopted for training; dropout, L1 and L2 regularization, k-fold cross validation and transfer learning are utilized to optimize the model, and the generalization ability is improved; the system, the equipment and the medium realize high current density performance prediction of the proton exchange membrane fuel cell (PEMFC) based on the method; the prediction precision is improved, the experiment cost is reduced, the internal mechanism can be deeply understood, and powerful support is provided for design optimization, operation management and fault diagnosis of the fuel cell.

The invention relates to the technical field of medical systems, and particularly discloses an anesthesia complication prediction model construction method based on deep learning, and the method comprises the following steps: S1, obtaining multi-source heterogeneous anesthesia medical data; s2, constructing a multi-modal feature fusion module; s3, designing a hierarchical deep neural network architecture which comprises sub-networks for processing different modal data in parallel and a full-connection prediction layer fusing multi-modal features; s4, continuously outputting a complication probability curve in a sliding time window mode by adopting a dynamic risk trajectory prediction mechanism instead of a single static prediction result; and S5, deploying a clinical real-time decision interface, and mapping a prediction result to an anesthesia monitoring equipment alarm system in real time. A bidirectional LSTM + 1D-CNN hybrid encoder and a cross-modal attention mechanism are adopted, time sequence dependence of physiological signals and spatio-temporal characteristics of operation events are synchronously captured, deep semantic fusion of multi-source data is achieved, and the characterization capacity of a model for precursor characteristics of complications is improved.

The embodiment of the invention provides a project research and development data key information processing method and device. A research and development content recognition system and a self-adaptive research and development knowledge graph are constructed. Unified processing and time sequence alignment of text, voice and image contents are realized through multi-modal information decomposition and fusion. Semantic completion and error correction are carried out based on research and development of a semantic analysis model, a knowledge graph structure is dynamically constructed and optimized, and a structured document with a traceability relation is generated. The system adopts a deep neural network model to extract research and development key information, constructs a multi-level document framework, and realizes intelligent conversion from research and development data to a project application document. According to the method, the defects of the traditional technology in the aspects of multi-modal information processing and knowledge structure optimization are effectively overcome, and the research and development data management and project declaration efficiency is remarkably improved.

The invention discloses a municipal road pavement crack multi-modal fusion detection method, which belongs to the technical field of pavement crack detection, and comprises the following steps: S1, obtaining visible light images, infrared thermal imaging and three-dimensional laser scanning data in multi-modal data, generating a time-unified and space-aligned multi-modal data set based on the three-dimensional laser scanning data; s2, extracting a visible light image and an infrared thermal image from the multi-modal data set, and obtaining features corresponding to the visible light image and the infrared thermal image to obtain a multi-modal feature set; and S3, inputting the multi-modal feature set into a deep neural network, and carrying out weighted integration on feature vectors through multi-layer convolution operation to obtain a crack detection result with three-dimensional coordinates. The municipal road pavement crack multi-modal fusion detection method solves the problem that an existing pavement crack detection method is low in accuracy and reliability.