1214results about How to "Realize analysis" patented technology

The invention relates to the field of temperature control, in particular to an automatic control method and system for a constant-temperature test room. The method comprises the following steps: acquiring real-time indoor operation monitoring parameters and external environment multi-dimensional data of a constant-temperature test room; performing indoor operation state analysis on the real-time indoor operation monitoring parameters, and constructing a laboratory dynamic state space model; carrying out multi-time-point environment temperature fluctuation calculation on the external environment multi-dimensional data, and carrying out nonlinear correlation learning to generate indoor state-environment nonlinear correlation characteristics; carrying out dynamic temperature evolution simulation on the laboratory dynamic state space model based on the indoor state-environment nonlinear correlation characteristics, and carrying out dynamic temperature evolution prediction to obtain temperature prediction values of a plurality of regions; constant-temperature deviation compensation calculation is carried out on the temperature prediction values of the multiple areas, then intelligent temperature control compensation is carried out, and an intelligent temperature control strategy is constructed; according to the invention, efficient and accurate constant-temperature automatic control is realized.

The invention relates to the technical field of data analysis, and discloses a business data analysis method, device and equipment based on big data and a storage medium, the method comprises the following steps: collecting and preprocessing original log data to obtain standardized log data, and performing adaptive multi-modal feature extraction to obtain comprehensive feature representation; inputting a heterogeneous graph neural network to carry out anomaly detection and multi-level root cause analysis to obtain a hierarchical anomaly event; executing task scheduling and resource allocation of reinforcement learning to obtain a task allocation scheme; performing deep learning enhanced root cause reasoning and knowledge graph construction on the task allocation scheme to obtain a system state diagram and a causal relationship; and generating a multi-dimensional task data analysis report. According to the method, comprehensive analysis, anomaly detection, root cause reasoning and intelligent scheduling of log data are realized. The reliability and performance of the system can be improved, and more intuitive and accurate decision support can be provided for operation and maintenance personnel.

The invention discloses a multi-point ditch flow monitoring method, and particularly relates to the field of branch ditch flow monitoring, which is used for solving the problem of complex branch ditch flow monitoring and optimization, and comprises the following steps of: constructing a branch ditch topological connection relation matrix, generating a flow characteristic curve in combination with flow and water level time sequence data, and marking interference points; generating an interference incidence matrix by utilizing two-channel interaction analysis, extracting upstream and downstream flow offset and disturbance propagation characteristics, judging an interference dominant mode according to a difference degree, and respectively calculating a flow offset compensation matrix and a disturbance propagation correction matrix; the recursive optimization model realizes segmented correction and reduces error residual errors, combines spatial-temporal feature clustering to identify abrupt change sections and generate a high-risk area key monitoring list, extracts refined data based on a high-frequency acquisition strategy to analyze abnormal causes, generates a dynamic correction result by using a prediction model, and updates a traffic balance data set. The multi-mode interference is accurately corrected, the flow distribution is optimized, and the monitoring precision and the system stability are improved.

The invention relates to the field of inductive control of illuminating lamps, in particular to an inductive control system of an inductive LED illuminating lamp. The method comprises the following steps: the lighting scene module is used for identifying all LED lighting lamps in an area; calculating node positions of all the LED lighting lamps in the area one by one, and identifying use scenes in the area to construct a plurality of LED lighting scene sub-areas; the ambient light feature module is used for acquiring ambient light parameters of a scene sub-region; performing light spatial distribution tracking on the ambient light parameters of the scene sub-regions, and performing ambient light state feature mining to generate ambient light comprehensive state features; and the multi-area lighting cooperation module is used for carrying out dynamic light source output parameter adjustment and multi-area lighting cooperation smoothing on the plurality of LED lighting scene sub-areas based on the environment light comprehensive state characteristics so as to generate multi-area lighting cooperation control parameters. According to the invention, rapid and accurate induction control of the LED illuminating lamp is realized.

The invention discloses an SCL field safety accident analysis and early warning method and system, a medium and a program product, and the method comprises the steps: carrying out the distributed cleaning and feature extraction of multi-source heterogeneous monitoring data, and obtaining a multi-dimensional time sequence feature flow; constructing a dynamic association network of a security state; identifying a key influence factor chain, and establishing a semantic analysis model; constructing a safety threshold system; evaluating the multi-dimensional time sequence characteristic flow by using a safety threshold system; when the multi-dimensional time sequence characteristic flow triggers early warning, performing tracing analysis by using a semantic analysis model to obtain a root event triggering the early warning, and simulating the development trend of the root event based on a preset evolution model; determining a predicted risk range and a risk type according to the tracing cause analysis result and the accident development trend; and the corresponding accident early warning scheme is matched in the preset database according to the risk range and the risk type, and the accident early warning scheme is sent to the monitoring terminal, so that the accuracy of judgment and classified early warning of different types of safety accidents is improved.

The invention discloses an intelligent water quality monitoring system and method based on a turbidity sensor, and relates to the technical field of water quality monitoring. Data acquisition nodes are arranged in a water area to be monitored, data are acquired by using the turbidity sensor and an intelligent water quality monitoring equipment group, an environment data set S is constructed, and preprocessing is performed; acquiring a turbidity change coefficient # imgabs0 # according to a turbidity data set in the preprocessed environment data set S, performing primary evaluation, marking abnormal data acquisition nodes, acquiring a particulate matter dynamic index KL and a pollution index WR according to a particulate matter data set and an organic pollutant data set in the environment data set S, and performing secondary evaluation according to the turbidity change coefficient # imgabs1 # and the turbidity change coefficient # imgabs0 # in combination with the particulate matter dynamic index KL and the pollution index WR. Acquiring a comprehensive water quality score Q, performing secondary evaluation, and constructing a water quality prediction model to predict the water quality change and regulate and control the water quality for the data acquisition nodes which are normally evaluated for the second time; the intelligent level of water quality monitoring is improved, the accuracy of water quality monitoring is enhanced, and the safety of water quality is ensured.

The invention relates to the field of production fault analysis, in particular to a fault monitoring analysis method and system for lubricating oil production. The method comprises the following steps: acquiring a multi-dimensional working monitoring parameter and an omnibearing working image; performing abnormal outlier filtering processing on the multi-dimensional working monitoring parameters, and performing time sequence evolution simulation to generate time sequence state evolution data; performing continuous frame optical flow motion analysis on the omnibearing working image, performing dynamic parameter mapping based on time sequence state evolution data, and constructing a dynamic production twinborn model; obtaining a preset production standard demand log; carrying out dynamic process deviation detection based on a preset production standard demand log dynamic production twinborn model, and carrying out production fault analysis so as to obtain stage production fault data; performing potential fault traceability speculation on the staged production fault data to obtain an abnormal fault potential node; and constructing a potential fault mark twinborn model based on the abnormal fault potential nodes. According to the invention, efficient and accurate fault analysis of lubricating oil production is realized.

The invention discloses a cable joint health state assessment method and system based on multi-dimensional data fusion, and relates to the technical field of cable state assessment, and the method comprises the steps: collecting cable joint operation parameters, unifying a time sequence, and forming a two-dimensional matrix; performing spectral analysis on the operation parameters, and calculating energy characteristics of each sub-band by applying multi-stage wavelet decomposition; and constructing a Bayesian network structure, and calculating probability distribution according to the energy characteristics of the sub-bands. According to the method, spectral analysis is carried out through Fourier transform, the effect of identifying main frequency components and noise characteristics in signals is achieved, the effect of extracting energy characteristics of the signals in different frequency ranges is achieved by decomposing a two-dimensional matrix into a plurality of sub-bands by applying multi-stage wavelet decomposition, and the method has the advantages of being simple in structure and convenient to operate. By constructing a Bayesian network structure and defining feature nodes and state nodes, the health state evaluation of the cable can be dynamically updated according to data collected in real time.

The invention discloses a battery thermal runaway detection system based on an early warning function, and relates to the technical field of battery thermal runaway, and the system comprises a supervision center which is used for carrying out the real-time supervision of the data information of a plurality of batteries, carrying out the early warning of the time data of the battery thermal runaway, and facilitating the timely issuing of warning information and notification announcements, and a monitoring device which is used for monitoring the data information of a plurality of batteries. The monitoring device is used for collecting thermal runaway parameters of each detection node of a plurality of batteries, the thermal runaway parameters comprise battery voltage, temperature, current and pressure, and the protection device is used for carrying out delayed protection operation on the monitoring device. The battery thermal runaway detection system based on the early warning function establishes a thermal runaway early warning model by fusing multi-parameter data of heat, force, electricity and the like and historical data of a thermal runaway phenomenon and by utilizing various learning algorithms, monitors battery parameters and sets simple judgment standards and threshold values such as a non-working state current threshold value and the like, so that the battery thermal runaway early warning model is established. Early detection of battery thermal runaway is realized, and monitoring and early warning effects are achieved.

The invention discloses an intelligent power distribution room safety monitoring management system, which comprises the following steps: checking states of a sensor, a gateway and a camera, and collecting environment data through the sensor; preprocessing the collected data, identifying a smoke area by using a YOLOv5 model, and starting a linkage safety mechanism according to abnormal environmental parameters; performing personnel detection by using a YOLOv5s model, capturing and analyzing a behavior track through a SimAM mechanism, and realizing multi-target tracking and abnormal behavior detection; grading the abnormal events based on a rule classifier, and triggering equipment linkage control; and storing the data in an NoSQL database, analyzing a trend to predict potential dangers, and optimizing a YOLOv5 model through historical data. The system can monitor the environment and personnel safety conditions in the power distribution room in real time, has efficient response capability and a trend prediction function, and can be widely applied to the field of safety monitoring of intelligent power grids and industrial environments.

The invention provides a live pig health monitoring method based on multi-source information fusion, and the method comprises the steps: collecting the sound data of a live pig in a natural environment, carrying out the classification and preprocessing of the sound data, forming a sound sample data set, inputting an LSTM neural network model, and carrying out the training, and obtaining a sound detection model; acquiring a live pig attitude image to obtain an attitude sample data set, and inputting the live pig attitude sample data set into the YOLOv5s model for training to obtain an attitude detection model; inputting live pig sound data collected in real time, preprocessing the data, and inputting the data into the sound detection model to obtain sound features; inputting live pig attitude images collected in real time into the attitude detection model to obtain attitude features; measuring the body temperature of the live pig by using an infrared temperature sensor, measuring the weight of the live pig by using a weight sensor, and fusing the sound feature, the posture feature, the body temperature and the weight to obtain a fusion vector; and inputting the fusion vector into a random forest classifier for decision making, and determining the health state of the live pig. According to the method, multi-modal data are fused, comprehensive evaluation and diagnosis of the health condition of the live pigs are facilitated, and the accuracy and robustness of the whole monitoring system are further improved.

The invention relates to the technical field of data processing, and discloses a cross-border trade data intelligent processing method and system based on an intelligent port. The method comprises the steps of performing functional model hierarchical processing on cross-border trade business data, obtaining a functional module calling relation network, performing process template construction processing, obtaining a dynamic process assembly rule base, performing service burying point processing, obtaining a user behavior analysis data set, performing guide strategy construction processing, and obtaining a user behavior analysis result set; and obtaining a service guidance rule base, carrying out knowledge graph construction processing, obtaining a service knowledge inference rule set, and carrying out cross-border trade data processing to obtain a port service intelligent decision scheme. According to the method, intelligent processing of cross-border trade data is realized, a complete technical chain from data acquisition, behavior analysis to decision support is constructed, accurate business guidance and intelligent decision support are provided, and the problems of low business processing efficiency, inaccurate service guidance, weak decision support capability and the like in the prior art are solved.

The invention relates to the technical field of road maintenance and management, in particular to a pavement internal disease analysis method and system based on artificial intelligence. Five core processes of multi-layer sensor network real-time data acquisition, multi-modal data fusion and deep learning feature extraction, dynamic environment and use mode combined disease prediction and analysis, intelligent prediction and decision support system, and real-time disease condition evaluation and report generation are carried out. Through the technical means, comprehensiveness and timeliness of data acquisition, accuracy of disease identification and prediction, scientificity of a maintenance strategy and optimization of resource allocation are realized; the finally generated disease current situation report provides a detailed disease distribution diagram, disease type analysis and disease severity evaluation, comprehensive, accurate and timely disease information is provided for maintenance personnel, and the efficiency and effect of pavement maintenance and management are remarkably improved.

The invention relates to the technical field of image classification, in particular to a fetal heart monitoring image classification method and system based on a neural network. The method comprises the following steps: acquiring a fetal heart monitoring image, generating a standard monitoring image through Gaussian noise elimination and spatial domain normalization, then performing multi-channel convolution on the standard image to extract image convolution features, obtaining standard fetal heart features through compression regular optimization, performing morphological reconstruction to generate a fetal heart dynamic model, and finally obtaining the fetal heart dynamic model. Baseline features are identified based on historical data, then periodic variation quantification and safe floating range derivation are performed on fusion features, and finally a multi-scale discrimination framework is constructed to realize intelligent classification of fetal heart monitoring images. The fetal heart monitoring image classification method is more stable and more accurate.

The invention discloses a landslide susceptibility evaluation method and system based on multi-source data and deep learning. The landslide susceptibility evaluation method combines an SBAS-InSAR technology, remote sensing image analysis, a deep learning algorithm, a TRIIGRS-SCOOPS3D coupling model and MASSFLOW simulation. The method is used for high-precision landslide prone area identification, potential landslide position prediction and three-dimensional landslide process simulation, and is especially suitable for landslide disaster risk management and emergency response in mountainous areas.

The invention relates to the technical field of geological disaster evaluation, in particular to a mine geological disaster risk comprehensive evaluation method considering spatial distribution characteristics. The method comprises the following steps: acquiring mine multi-source spatial data; performing mine geological disaster risk distribution analysis on the mine multi-source spatial data to generate a mine geological risk distribution map; performing spatial region potential disaster probability analysis on the mine geological risk distribution map to generate mine geological distribution disaster probability data; and performing high-complexity spatial region screening on the mine geological risk distribution map through the mine geological distribution disaster probability data to obtain high-complexity spatial region data. According to the method, multi-source data are integrated, spatial distribution characteristics are emphasized, active and inactive areas are distinguished, ecological and water body changes are analyzed, and the accuracy and comprehensiveness of mine geological disaster risk comprehensive evaluation are improved.

The invention discloses a 3D printing process intelligent control method and system based on real-time feedback, and relates to the technical field of 3D printing, a data acquisition module collects a printing layer surface image and printing data in real time, constructs an image data set and a printing data set, and performs cleaning and standardization processing on the data in a preprocessing module; the image analysis module analyzes surface defects of a printing layer by using a convolutional neural network, generates a defect score D, compares the defect score D with a preset defect score threshold D1, evaluates the state of the printing layer and triggers early warning, and the comprehensive evaluation module calculates a crack generation probability Z by combining printing data and the defect score; and the intelligent control module compares the crack generation probability Z with a preset crack generation probability threshold value Zl, evaluates the printing state and feeds back and controls printing parameters according to a result, so that crack and structure defects in the printing process are effectively prevented and reduced, and the printing precision and the finished product quality are improved.

The invention relates to the technical field of target detection, and discloses a personnel state recognition method and system based on target recognition detection. The method comprises the steps of performing parameterization processing on collected original image data to obtain intelligent BIM data; performing multidisciplinary data exchange processing on the intelligent BIM data to obtain target detection data; performing intelligent posture analysis processing on human body information in the target detection data to obtain optimized posture data; behavior recognition processing is carried out on the optimized attitude data to obtain behavior analysis data, and the behavior analysis data comprises violation behavior types, climbing state judgment and risk level evaluation; performing fuzzy logic evaluation processing on the behavior analysis data to obtain safety compliance data; and performing intelligent early warning processing on the safety compliance data and the real-time monitoring data to obtain full-life-cycle management data. According to the invention, the efficiency of personnel state recognition based on target recognition detection is improved.

The invention discloses a multi-robot task scheduling method, system and device and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the role definition of a robot, collecting environment information in real time, and constructing a dynamic environment model; according to the dynamic environment model, identifying current tasks to be executed, evaluating urgency, complexity and resource requirements of each task, and forming a priority list; disassembling a high-priority task in the priority list into sub-tasks, and assigning a role and a task allocation scheme of the robot; a biologically inspired self-organizing algorithm is adopted, the robot exchanges information according to the state of the robot and task requirements, and a task allocation scheme is dynamically adjusted; the robot exchanges information according to the own state and the task demand, and dynamically adjusts the task allocation scheme, so that the flexibility and adaptability of task allocation are realized, the change of environment and state can be responded in time, and task delay caused by insufficient resources is avoided.

The invention relates to an Internet of Things equipment intelligent management platform based on edge computing, and aims to realize efficient and intelligent management of Internet of Things equipment through an edge computing technology. According to the platform, the edge nodes are deployed near the data source, so that local processing and storage of the data are realized, the data transmission delay is remarkably reduced, and the response speed of the system is improved. And the platform is provided with an intelligent management module, so that the equipment state can be monitored in real time, faults can be predicted, repair operation can be automatically executed, and the stability and reliability of the system are enhanced. And a self-adaptive data stream processing algorithm is adopted, and the data stream is dynamically adjusted according to a real-time network state and equipment requirements, so that the high efficiency of data processing is ensured. The secure transmission module protects the data transmission process through an end-to-end encryption technology, and prevents data leakage and tampering. The cloud-side collaborative resource scheduling system realizes optimal allocation of resources, and a user-defined rule engine provides high flexibility and personalized management strategies to meet different user requirements.

The invention discloses a multi-modal-based emotional state evaluation method, which comprises the following steps: S1, collecting multi-modal data of a user to be tested, the multi-modal data comprising voice data, facial micro-expression data and facial heart rate data; s2, constructing a multi-modal deep neural network, inputting the multi-modal data into the multi-modal deep neural network, and dynamically adjusting the weight of the modal data by the multi-modal deep neural network by using an attention mechanism so as to output and obtain fusion features; and S3, judging the emotional state of the to-be-detected user based on the fused features. Accordingly, the invention further discloses a multi-mode-based emotional state evaluation system, and the multi-mode-based emotional state evaluation system can be used for implementing the emotional state evaluation method, so that the physiological status of the patient is more accurately and comprehensively considered, the emotional state of the patient is evaluated, and the accuracy of the emotional state evaluation is improved. Therefore, professional psychologists are assisted in diagnosing depression.

The invention provides a machine learning-based multi-dimensional auxiliary decision analysis method and system for power supply of a distribution network. The method comprises the following steps of: S1, acquiring historical data and historical electrical load data of the distribution network; s2, obtaining a power supply demand prediction model through the long and short term memory network and the historical data of the distribution network; s3, obtaining a load change model through a time sequence prediction algorithm and historical electrical load data; s4, identifying the real-time operation data of the distribution network based on the output of the steps S2 and S3 to obtain a power supply capacity change trend and a load margin; s5, establishing a comprehensive objective function based on the output in the step S4, performing optimization solution on the objective function through a genetic algorithm, and outputting an optimal power supply decision scheme; and S6, executing the output of the step S5, monitoring the power supply operation parameters of the distribution network in real time, and dynamically adjusting the optimal power supply decision scheme based on the power supply operation parameters of the distribution network. According to the invention, the reliability of distribution network power supply is improved, and the dynamic adjustment and optimization of the distribution network power supply decision scheme are realized.

The invention relates to the technical field of intelligent lock recognition, in particular to an intelligent lock image feature recognition method and system based on deep learning. The recognition method comprises the following steps: constructing a multi-branch deep neural network model, wherein the multi-branch deep neural network model comprises a backbone network, a feature extraction branch and a feature fusion branch; a framework training model is used to learn identity recognition, attitude estimation and environment perception tasks; and identifying the comprehensive feature representation by using a trained framework training model, and generating a control instruction of the intelligent lock according to an identification result. According to the intelligent lock image feature recognition method based on deep learning provided by the invention, comprehensive analysis of multi-dimensional information such as identity, posture and environment is realized by constructing the multi-branch deep neural network model.

The invention discloses an intelligent network traffic anomaly detection and automatic isolation system, which comprises a data acquisition module, a preprocessing module, an intelligent traffic analysis module, an anomaly detection engine, an automatic isolation execution module and a visual monitoring and alarm platform, by introducing a deep learning algorithm and a multi-dimensional anomaly detection algorithm, deep mining and comprehensive analysis of network traffic can be realized, feature information is automatically learned and extracted from mass data, an accurate traffic behavior model is constructed, and abnormal behaviors in the traffic are detected in real time. And full-process automatic processing from data acquisition, preprocessing, intelligent analysis to automatic isolation is realized. When abnormal traffic is detected, the system can automatically execute isolation measures and monitor the isolation purpose in real time, and compared with a traditional method based on a rule base or threshold judgment, the method is higher in detection accuracy and real-time performance.

The invention relates to the technical field of smart city management, in particular to a city physical examination spatio-temporal data dynamic aggregation and decision support system which comprises a data acquisition module, a data preprocessing module, a spatio-temporal data aggregation module, an index calculation module, a dynamic analysis module and a decision support module. Wherein the data acquisition module is used for acquiring multi-source heterogeneous original city operation data; the spatio-temporal data aggregation module is used for aggregating the data according to a specified time window and a specified space unit; the index calculation module is used for extracting a core index reflecting a city health state; the dynamic analysis module is used for predicting the future change trend of the core indexes; and the decision support module is used for generating an urban governance strategy optimization scheme. According to the method, through dynamic integration and space-time correlation analysis of multi-source heterogeneous data, the urban operation trend is accurately predicted, a targeted treatment optimization scheme is generated, and the comprehensiveness of urban physical examination and the scientificity of decision support are remarkably improved.

The invention provides a ground surface settlement monitoring method and system fusing Beidou and InSAR data. The method comprises the following steps: receiving positioning data from a Beidou satellite system and earth surface deformation data acquired by a synthetic aperture radar interference measurement system; based on the positioning data and the earth surface deformation data, correcting the earth surface deformation data according to the environmental factors through a space-time fusion model to obtain corrected earth surface deformation data; by means of the corrected surface deformation data, a multi-stage analysis technology is adopted, the development trend of surface subsidence is determined, a surface subsidence distribution diagram is generated, and the surface subsidence distribution diagram is used for displaying spatial distribution characteristics of surface subsidence; and according to the ground surface settlement distribution diagram, the future ground surface settlement condition is monitored by using the space-time fusion model, and a ground surface settlement monitoring report can provide a scientific basis for early warning and prevention of geological disasters. The ground surface settlement monitoring efficiency and monitoring effect are improved.

The invention relates to a UWB-based man-machine real-time positioning method in a long-distance tunnel hole. The method comprises the following steps: S1, collecting original ranging information of integrated signal characteristics; s2, correcting an original distance based on signal quality; s3, carrying out NLOS signal identification based on SVM (Support Vector Machine); s4, NLOS ranging error elimination based on an error distribution fitting model; s5, preliminarily resolving a tag position stake number; s6, label position correction based on Kalman filtering; and S7, determining a man-machine position based on label matching. According to the invention, the UWB positioning system is used for positioning and tracking personnel machinery in a hole, so that real-time transmission and analysis of man-machine position pile number information in the hole are realized, and management personnel can timely and accurately master man-machine operation positions; according to the man-machine real-time positioning method, the influence of the complex construction environment in the tunnel hole is reduced, and the man-machine positioning precision and stability in the tunnel hole are effectively improved.

The invention discloses a method for calculating the insulation field intensity of a transformer under the influence of moisture and temperature distribution, and relates to the technical field of electric power engineering, and the method comprises the steps: constructing a multi-physical field coupling simulation platform for monitoring and analyzing the temperature, humidity and electric field distribution in the transformer; setting a humidity sensitive element array, collecting humidity data, and transmitting the humidity data to a central processing unit for processing; constructing an insulation prediction model through a deep neural network algorithm, inputting the insulation prediction model based on historical humidity, historical temperature and insulation state data to complete training, and predicting a change trend of insulation field intensity under a specific working condition; processing the real-time data, inputting the processed real-time data into the insulation prediction model to obtain a real-time insulation state prediction value, and dynamically adjusting parameters of the insulation prediction model; an abnormity early warning mechanism is established based on a real-time insulation state prediction value, and once an insulation state abnormity is detected, the system immediately starts early warning to inform operation and maintenance personnel to check and maintain.

The invention discloses a tunnel apparent disease detection method. The method comprises the following steps: collecting three-dimensional point cloud data in a tunnel through a moving vehicle carrying a three-dimensional laser scanner; calculating a depth value according to a Z value of the three-dimensional point cloud data, and mapping the depth value to a gray scale range of 0-255 to obtain a gray scale image; identifying a gray value abrupt change area in the gray image through an edge detection algorithm to obtain an abrupt change crack area on the surface of the tunnel lining; performing gray segmentation on the gray value mutation region to obtain a water leakage region, and performing connected domain analysis on the water leakage region to obtain the area of the water leakage region; identifying a gray value mutation region according to a region growing algorithm to obtain a lining surface layer layering region; according to a template matching method, a drainage ditch area in the gray level image is identified; and marking tunnel cracks, water leakage, lining surface layer peeling and drainage ditch damage areas. According to the invention, the three-dimensional laser scanning and image processing technology is adopted to detect the apparent diseases of the tunnel, so that the disease maintenance efficiency is improved.

The invention discloses an AI classroom behavior collaborative analysis method and system. The method comprises the following steps: acquiring classroom environment data in real time; preprocessing the classroom environment data to respectively obtain target student video data, target student audio data, target student action data and target student expression data; performing feature extraction on the target student video data, the target student audio data, the target student action data and the target student expression data to respectively obtain expression features, voice content features, action features and posture features; performing comprehensive processing on the expression features, the voice content features, the action features and the posture features to obtain comprehensive features; performing multiple recognition on the comprehensive features, and performing post-processing on an initial recognition result obtained by recognition to obtain a target recognition result; and performing quantitative evaluation on the target identification result to generate a behavior analysis report. According to the invention, behaviors of students can be accurately identified and evaluated in real time, and classroom management and teaching optimization levels are effectively improved.