1577results about How to "Efficient identification" patented technology

The invention relates to the technical field of data processing, and discloses a coal and gas outburst dynamic monitoring and intelligent early warning method and device. The method comprises the following steps: collecting and preprocessing multi-source sensor data arranged in a target area to obtain a multi-dimensional data set; performing multivariable time sequence analysis on the multi-dimensional data set to obtain coal seam gas outburst risk prediction data; based on coal seam gas outburst risk prediction data, performing dynamic risk assessment and spatial interpolation processing on the multi-dimensional data set to obtain real-time risk distribution data of the target area; performing multi-dimensional threshold analysis on the real-time risk distribution data to obtain preliminary early warning data; performing multi-modal information fusion on the preliminary early warning data to obtain target early warning data; and performing intelligent decision tree analysis on the target early warning data to obtain a target early warning scheme. According to the invention, the accuracy and reliability of dynamic monitoring and intelligent early warning of coal and gas outburst are improved.

The invention discloses a photovoltaic cleaning robot based on automatic path planning and an operation method thereof, relates to the technical field of robots, and solves the problem of cleaning blind spots in an existing cleaning robot and the endless loop risk of a path planning algorithm. According to the invention, the surface information of the photovoltaic panel is accurately captured through the multispectral acquisition module, a high-resolution and high-definition comprehensive image is generated through the data fusion processing module, then dirt is accurately identified on different scales by using a multi-scale pyramid structure and an adaptive feature fusion mechanism, and an attention mechanism and environmental perception data are combined, so that the real-time performance of the system is improved. The recognition threshold is dynamically adjusted, and misrecognition and missing detection are reduced; and finally, enabling the robot to autonomously learn in a complex environment and optimize an obstacle avoidance strategy through a dynamic obstacle avoidance algorithm based on deep reinforcement learning. The intelligent level and the cleaning effect of an existing photovoltaic cleaning robot are greatly improved.

The invention discloses a park sweeper positioning and environment mapping method based on multi-sensor fusion. The method comprises the following steps: S1, preprocessing multi-modal data acquired by a plurality of sensors; s2, extracting and fusing semantic features and geometric features in the multi-modal data preprocessed by the plurality of sensors; s3, performing geometric feature extraction and recognition on the point cloud data by using a VoxelNet point cloud processing algorithm; s4, performing pose estimation and track plotting by fusing multi-sensor data; s5, identifying places where the motor sweeper repeatedly passes through through loopback detection, and correcting accumulated errors; and S6, constructing a three-dimensional environment map by fusing the laser radar, the visual features and the IMU data, performing global optimization by applying a map optimization technology, correcting errors, improving map precision, and updating the map in real time. According to the invention, the autonomous navigation capability of the sweeper is enhanced, the sweeping efficiency and safety are improved, and the sweeper is suitable for various complex and dynamic park environments.

The invention provides a risk control early warning method and system based on bank flow analysis, and relates to the technical field of computers, bank flow data of a target user in a bank system is collected, the collected bank flow data is fused with multi-source cross-domain data, and time sequence data of transaction behaviors is generated according to a time sequence; performing data feature extraction on the time sequence data to obtain transaction features; constructing a framework of a risk prediction model, and obtaining the risk prediction model through training and verification; real-time flow data of a target user in a bank system is monitored in real time, a trained risk prediction model is utilized to evaluate transaction behaviors of clients in real time, an anomaly detection result of an anomaly detection model is combined with output of the risk prediction model, a comprehensive risk score is formed to identify potential risks, and an early warning mechanism is triggered. Through deep analysis of bank flow data, real-time risk monitoring and early warning are realized, and potential financial risks can be effectively identified.

The invention discloses an intelligent bidding and tendering information identification method, which relates to the technical field of engineering management, and comprises the following steps: standardizing and preprocessing a bidding and tendering information document format; constructing a natural language processing model special for the bidding and tendering field; training a multi-level information extraction model based on deep learning; carrying out cross-document information integration and correlation analysis; performing anomaly detection and verification based on rules; semantic understanding and sentiment analysis; automatic subject matter description and technical specification extraction; a real-time dynamic monitoring and information updating mechanism; the invention discloses a graph-based decision support and recommendation system. According to the intelligent bidding and tendering information identification method, efficient and intelligent identification of bidding and tendering information is realized by constructing a natural language processing model specially aiming at the field of bidding and tendering. The bidirectional coding capability of BERT and the sequence modeling capability of LTM are combined, and a hierarchical attention mechanism is introduced, so that the model can accurately identify various key information in bidding and tendering documents.

The invention relates to the technical field of unmanned aerial vehicle detection, in particular to a monitoring and early warning system and method for countering unmanned aerial vehicle detection interference, and in the monitoring and early warning system, a signal receiving module independently receives electric signals of multiple unmanned aerial vehicles through array space stations; the abnormal signal detection module performs feature extraction, and detects abnormal signals by using frequency feature change and a spectrum analysis technology; the time difference of arrival detection module calculates the time difference of arrival of each space station to the abnormal signal, and the angle of arrival detection module analyzes and determines the angle of arrival through a space covariance matrix; the cross positioning module synthesizes the time difference and the angle information to determine the position of the abnormal unmanned aerial vehicle; and the adaptive interference suppression module identifies the type of an abnormal unmanned aerial vehicle by using a feature extraction result and a machine learning model, selects a suppression strategy, controls an array space station to align to the position of the abnormal unmanned aerial vehicle, realizes efficient suppression, and protects normal operation of a legal unmanned aerial vehicle and other aerial equipment at the same time.

The invention provides a high-density RFID tag group scanning system based on a multi-antenna array and beam forming, and relates to the technical field of the Internet of Things. The system comprises a multi-antenna array, an RFID reader-writer, a beam forming unit, a signal processing unit, a feedback unit and a data management unit. Through a digital beam forming technology, the system dynamically adjusts the direction and width of a beam, and achieves the precise scanning of a target area. And in combination with real-time signal feedback, a density peak clustering algorithm and a gradient descent algorithm are adopted to optimize beam parameters, so that the recognition efficiency is improved. The system further utilizes an anti-collision algorithm to dynamically adjust frame parameters, and performs logic grouping based on spatial positions and type characteristics of tags, so that signal collision and missed reading rates are remarkably reduced. Meanwhile, the data management unit stores and outputs the label data in a classified mode, and intelligent management capacity is provided for multi-scene application.

The invention relates to the technical field of glass detection, and discloses a method, a device and equipment for detecting glass after light sweeping. The method comprises the following steps: collecting multi-source original sensing data of glass to be detected, carrying out signal denoising, synchronous transformation and multi-scale glass feature extraction on the multi-source original sensing data, and carrying out feature combination, feature dimension reduction compression, region segmentation and region contour reconstruction on the multi-scale glass features to obtain an initial defect region set; performing spatial-temporal feature combination of multi-source features on the initial defect region set to obtain an enhanced defect feature set; and constructing a region similarity matrix corresponding to the enhanced defect feature set, performing defect category judgment and multi-dimensional glass quality scoring on the region similarity matrix to obtain glass quality evaluation data, performing process association on the glass quality evaluation data, and generating a final detection report of the to-be-detected glass. According to the method, the result accuracy of quality detection on the glass subjected to light sweeping is improved.

The invention relates to the technical field of flow anomaly identification, and discloses a flow anomaly identification method for a numerical control machine tool protocol, which comprises the following steps of: 1, multi-source data acquisition: acquiring various types of data from a numerical control machine tool and a control system thereof by arranging a data acquisition module, the data sources include network protocol flow data, machine tool sensor data, operation log data and equipment environment data, and the data formats of the data sources are kept uniform; the collected original data is subjected to standardization processing, the problems of data dimension inconsistency, noise interference and missing values are solved, and alignment of the data on a time axis is guaranteed through a synchronization algorithm; through a multi-source data acquisition and high-precision sensor system, the real-time monitoring of the flow of each key fluid system of the numerical control machine tool is realized. And by combining a plurality of feature extraction methods, the traffic anomaly can be effectively identified.

The invention provides an electrocardiogram data anomaly recognition method, device and equipment based on deep learning and a storage medium. An original electrocardiogram signal of a patient is collected, and a target electrocardiogram signal is obtained through multi-stage preprocessing. And identifying an abnormal signal in the target electrocardiogram signal by using a deep fusion learning model, and generating a preliminary identification result. And then, the preliminary recognition result is combined with a pre-trained machine learning model, mixed model processing is performed through a stack generalization fusion method, a Bayesian network is constructed based on the detailed information of the patient, a reasoning result with context sensing is obtained, and a target recognition result is finally generated. And generating an abnormal report according to the target identification result, and storing and displaying the abnormal report to the user in a classified manner according to a predefined standard. According to the method, high precision and personalized diagnosis of anomaly detection are ensured, and the reliability and efficiency of electrocardiogram analysis are improved.

The invention discloses a risk assessment and prediction method based on a network security situation awareness system, and relates to the technical field of network security. According to the risk assessment and prediction method based on the network security situation awareness system, a current network potential risk data set is obtained, and a current network potential risk assessment value is obtained through comprehensive analysis based on the obtained current network potential risk data set; acquiring a current network traffic data set, and based on the acquired current network traffic data set, performing comprehensive analysis to obtain a current network traffic evaluation value; comprehensively analyzing the current network potential risk assessment value and the current network flow assessment value to obtain a network security risk coefficient and a network security risk level; by comprehensively analyzing the current risk and flow data, a more comprehensive, real-time and dynamic network security management scheme is provided, potential threats can be effectively identified, and the early warning capability is improved. The problem that the existing network security situation awareness system is inconvenient to comprehensively reflect the network security situation is solved.

The invention discloses a craniocerebral injury degree diagnosis auxiliary system based on a medical image, and relates to the technical field of medical treatment, a primary judgment module can accurately judge whether a patient has the risk of interstitial encephaledema or not by analyzing the accumulation degree of interstitial fluid in white matter and quantitatively calculating a penetration anomaly coefficient Syxs, the ability of early risk screening is provided, and the risk of interstitial encephaledema can be accurately judged. Potential problems can be recognized in time before disease deterioration, a clinician is prompted to intervene rapidly, and therefore the prognosis effect of a patient is remarkably improved. When the risk of interstitial encephaledema exists, the type diagnosis module further distinguishes lesion types (such as brain contusion or other injuries) by extracting related distinguishing features in a multi-modal feature set, calculates a locking coefficient Sdxs, and provides a scientific quantitative basis for diagnosis of lesion types based on specific features of the lesions. According to the accurate type diagnosis method, diagnosis errors can be reduced, and reliable support is provided for clinical decision making.

The invention relates to the technical field of fault detection for a wireless communication network, and discloses a fault detection method for the wireless communication network. By collecting data of base station signal strength, network delay, data packet loss rate and user equipment signal quality, the problem of insufficient fault detection caused by a single index is solved. Through multi-dimensional data acquisition, the system can comprehensively evaluate network performance, the fault detection accuracy is improved, and different fault types can be effectively identified especially in a complex fault mode. By storing the data according to the time sequence, the problem of time sequence chaos is avoided, and accurate detection of time-varying faults is ensured. The comprehensive data vector generated by each time of sampling comprises a plurality of network performance indexes, so that the fault detection and positioning capability is improved. Abnormal values are eliminated through data preprocessing, the data quality is ensured, an accurate basis is provided for subsequent analysis, and the reliability of a detection result is ensured.

The invention relates to the technical field of financial data processing, in particular to a data processing method and system based on financial information bills. The data processing method comprises the following steps: acquiring multi-modal financial information bill data; and performing bill modal decomposition on the multi-modal financial information bill data to generate financial information bill modal decomposition data. Bond information price income prediction needs a large amount of financial data, such as market interest rate, bond expiration date, face interest rate and the like, the data are similar to the data form of bill modal decomposition, and a more accurate model can be obtained through standardization and feature extraction of multi-modal data. Therefore, valuable input is provided for bond price and income prediction. According to the invention, through multi-modal data fusion, counterfeited feature comparison modeling, abnormal bill clustering analysis and dynamic risk assessment, the security and accuracy of financial bill identification are improved.

The invention discloses a multi-modal data fusion student mental health early warning method and system. The method relates to the technical field of property detection, and comprises the following steps: collecting student psychological health data, analyzing the student psychological health data, and comprehensively analyzing, optimizing and adjusting the student psychological health early warning method. The student psychological health data is acquired and processed, the student psychological health data is analyzed, the student psychological health data image quality evaluation index and the student psychological health data fusion network volatility evaluation index are obtained, and the student psychological health early warning method is comprehensively analyzed, optimized and adjusted. The accuracy of the student psychological health early warning data quality is improved, and the problem that the accuracy of the student psychological health early warning data quality is insufficient in the prior art is solved.

The invention relates to a transformer voiceprint anomaly detection method based on a generative adversarial network, and the method comprises the steps: obtaining voiceprint data, and carrying out the preprocessing of the voiceprint data, and obtaining the preprocessed spectrum data; constructing an abnormal voiceprint detection model; inputting the preprocessed spectrum data into an abnormal voiceprint detection model for training; and obtaining voiceprint data to be detected and preprocessing the voiceprint data to be detected, inputting the preprocessed voiceprint data to be detected into the trained abnormal voiceprint detection model, and outputting a detection result. According to the method, unbalanced distribution of normal voiceprint data and abnormal voiceprint data can be balanced, the generalization ability of the model is enhanced, and the model can keep high detection performance when processing a small amount of abnormal data; according to the method, the distinguishing capability of the abnormal voiceprint is enhanced, the abnormal voiceprint can be effectively recognized in a complex noise environment, the influence of noise and interference factors is reduced, and the detection accuracy is improved; fine-grained features in the voiceprint signals can be captured, extraction of the features is further optimized, and therefore abnormal voiceprints can be recognized more accurately.

The invention relates to the technical field of software application testing, in particular to an automatic intelligent testing system and method for software application. The method comprises the following steps: acquiring test environment parameters of software to be tested, calculating a dynamic waiting time reference value, and generating waiting mechanism configuration data; performing element positioning information collection and element positioning strategy generation on a user interface of the software application based on the waiting mechanism configuration data to obtain element positioning configuration data; performing conditional waiting strategy processing according to the element positioning configuration data and the waiting mechanism configuration data to generate conditional waiting mapping data; and performing visual AI auxiliary positioning processing according to the conditional waiting mapping data to generate visual positioning feature data. Through real-time monitoring of test environment parameters, the system automatically calculates and configures appropriate waiting time, so that the test process can flexibly adapt to various operation environments.

The invention discloses a harmonic traceability method based on a harmonic power direction of an electric power system, which belongs to the technical field of electric power quality of the electric power system and comprises the following steps of: constructing matrixes of fundamental waves and harmonic signals, initializing active and reactive power deviation values of nodes, and adopting a decoupling algorithm combined with a Jacobian matrix iteration method to carry out harmonic traceability. And sequentially calculating the fundamental wave voltage and each harmonic current, and finally obtaining the power flow direction and judging the harmonic source attribute. When harmonic power flows from a load to a power grid, the node is identified as a harmonic source; and when the harmonic power flows to the load from the power grid, identifying the node as a harmonic receiving point. An equivalent circuit model is used for separating harmonic influences of a linear load and a non-linear load, and a real-time monitoring technology is combined to realize dynamic tracking and accurate positioning of a harmonic source. The method is low in calculation complexity, excellent in convergence performance and suitable for a modern power distribution network scene where distributed energy and power electronic equipment are widely connected, the harmonic suppression efficiency is remarkably improved, and the safety and stability of power grid operation are ensured.

The invention belongs to the technical field of bridge and road crack recognition, and discloses an improved semantic segmentation network construction method and system for bridge and road crack recognition. According to the method, a convolution block, a down-sampling layer and an up-sampling layer in a UNet network are improved, a novel space-channel attention mechanism is introduced, jump connection and a U-shaped structure in the UNet network are reserved, an improved semantic segmentation network is constructed, and crack recognition is carried out. According to the invention, a highly-specific crack semantic segmentation network model with stronger generalization ability and higher precision is designed, on CRACK500, SDNET2018 and CFD public data sets, IoU is 73.3%, F1 reaches 82.6% and is far higher than that of other models, and the method is suitable for detecting cracks on bridge body structures such as road surfaces and bridge towers of bridges.

The invention discloses a data processing and quality evaluation method for efficiency test data of an electric drive system. The method comprises the following steps: acquiring an original electric drive efficiency test data set; performing noise reduction on the original electric driving efficiency test data set through a probability distribution-based data noise reduction method to obtain a noise-reduced electric driving efficiency test data set; carrying out the first abnormity detection and processing of the noise reduction electric drive efficiency test data set through a DBSCAN model, and obtaining a preliminary screening electric drive efficiency test data set; carrying out the second anomaly detection and processing of the preliminary screening electric drive efficiency test data set through an LOF algorithm model and an iForest algorithm model, and obtaining a preprocessed electric drive efficiency test data set; and performing quality evaluation on the preprocessed electric drive efficiency test data set through the constructed six-tuple data quality model. According to the invention, effective noise reduction and abnormity detection can be carried out on the efficiency test data of the electric drive system, so that the data quality is improved.

A three-dimensional target detection and tracking method fusing multi-sensor information belongs to the technical field of computer vision, and can make up for the defect of a single mode by collecting camera and radar image information and fusing camera images and laser radar point clouds. Multi-target tracking is carried out by using a multi-data coupling method of 2D + 3D data, a remote object is identified through a camera, when the object enters an induction range of the laser radar, the laser radar can carry out more accurate positioning, and position estimation of the target in a 2D image is corrected by using a more accurate 3D position provided by the laser radar. The method is used for solving the problems of inaccurate target identification, target shielding and the like under complex road conditions; a traditional single-mode three-dimensional target detection algorithm cannot effectively fuse the advantages of multi-sensor data and is difficult to accurately identify objects in a distance or under a complex road condition.

The invention discloses an electric power fault diagnosis and prediction system based on big data, particularly relates to the field of intelligent diagnosis of an electric power system, and aims to solve the problems of fault response delay and insufficient diagnosis precision. Localized intelligent diagnosis of power faults is realized, and stable operation and rapid recovery of a power system are guaranteed; a priority classification and sorting uploading mechanism is combined to ensure that key data is transmitted preferentially, diagnosis errors caused by delay are reduced, and the analysis stability of a central dispatching center is enhanced; through comprehensive judgment of a global deviation aggregation index and a trust stability harmonic measurement index, accurate classification of local node diagnosis controllability is realized, more accurate key data is guaranteed to be obtained, finally, the fault response capability of a system and the safety of a power system are improved, and powerful technical support is provided for intelligent diagnosis and maintenance.

The invention relates to the technical field of railway power supply and distribution, particularly provides an operation and maintenance management method and system for railway power supply and distribution, and is used for solving the problem of low operation and maintenance management efficiency caused by poor accuracy of fault identification and positioning. The method comprises the following steps: receiving equipment operation data of a railway power supply and distribution system collected by a sensor network through the Internet of Things; inputting the data into a pre-trained graph neural network model, and identifying a fault equipment identifier and a fault mode; determining a target fault propagation path according to the fault equipment identifier, the fault mode and the multi-level power supply and distribution knowledge graph; wherein the multi-level power supply and distribution mapping knowledge domain comprises an equipment level mapping knowledge domain, a region level mapping knowledge domain and a system level mapping knowledge domain which are associated with one another; according to the target fault propagation path, a fault severity evaluation model is adopted to predict the fault severity, a corresponding operation and maintenance management report is determined, and corresponding processing is carried out according to the operation and maintenance management report. According to the technical scheme provided by the invention, the operation and maintenance management efficiency is improved.

The invention relates to an STON1 gene molecular marker primer related to chicken double-yolk egg traits and application of the STON1 gene molecular marker primer, and belongs to the technical field of biology. The STON1 gene molecular marker is a 7867409th basic group of a chicken reference genome GRCg7b version chromosome 3, the basic group is mutated into A or G, and the genotypes are A / A, A / G and G / G. The double-yolk egg ratio of the G / G genotype chicken is higher than that of the A / G and A / A genotype individuals, and the double-yolk egg ratio of the A / G genotype chicken is higher than that of the A / A genotype individuals. A forward and reverse primer pair is used for amplifying a fragment containing the molecular marker site, Sanger sequencing is carried out on an amplification product, the genotype of an individual is rapidly and accurately identified to serve as a genetic marker for chicken breeding, and the chicken with the higher proportion of double-yolk eggs is bred; the double-yolk egg traits can be efficiently and accurately detected, the breeding accuracy and breeding efficiency of the chicken double-yolk egg proportion are improved, and the method has important value for chicken breeding and production.

The invention discloses an industrial equipment operation monitoring and early warning system based on an infrared temperature distribution technology, and the system comprises a temperature distribution image correction module which calculates a compensation coefficient of heat reflection on the surface of industrial equipment, and obtains a temperature distribution image after the reflection effect is corrected; the image displacement correction module is used for correcting temperature distribution image offset caused by displacement of the displacement component of the industrial equipment; the temperature abnormal area identification module is used for identifying a temperature abnormal area; the temperature anomaly region maintenance strategy making module is used for making a maintenance strategy of the temperature anomaly region; the temperature imbalance area identification module is used for identifying a temperature imbalance area in the non-temperature abnormal area; the temperature imbalance area maintenance module is used for formulating a preventive maintenance strategy of a temperature imbalance area; and the maintenance strategy execution and optimization module is used for continuously optimizing the maintenance strategy according to the maintenance task execution result. According to the method, the efficiency and effect of industrial equipment maintenance work are improved by combining an infrared thermal imaging technology and a multi-data correction and analysis method.

The invention discloses a time series data anomaly detection model construction method and an anomaly detection method and system, and the method comprises the steps: reconstructing time series data through employing a model constructed based on a TCN-LSTM-CMA auto-encoder, and generating reconstructed data; calculating a reconstruction error by comparing the time sequence data and the reconstruction data before and after reconstruction; and according to the calculated reconstruction error, carrying out anomaly detection by adopting an isolated forest algorithm, and identifying abnormal data in the time series data. The invention provides a brand-new TCN-LSTM-CMA auto-encoder model construction method, and the method is combined with an isolated forest method to carry out time series data anomaly detection. According to the method, the defects of an existing anomaly detection method in the aspects of precision, adaptability and robustness are overcome. The method has a wide application prospect in the aspect of time series data anomaly detection in the fields of industrial monitoring, network security and the like.

The invention discloses a hyper-spectral image lithology identification method and equipment based on spatial and spectral characteristics, and relates to the technical field of image information processing.The hyper-spectral image lithology identification method based on spatial and spectral characteristics mainly comprises the steps that hyper-spectral data of a research area is preprocessed to obtain a hyper-spectral sample data set; dividing the hyperspectral sample data set according to a preset proportion and performing data enhancement processing to obtain a training set, a verification set and a test set; constructing a lithology identification model by using an advanced convolutional neural network model; training and verifying the lithology identification model by using the training set and the verification set to obtain a trained lithology identification model; and obtaining a lithology identification result by using the trained lithology identification model according to the test set. According to the hyperspectral image lithology identification method and device based on the spatial and spectral features, the accuracy and efficiency of hyperspectral image lithology identification can be improved.

The invention relates to the technical field of computers, and provides a document digitization method and device, electronic equipment and a readable storage medium. The method comprises the following steps: converting original data into a to-be-processed electronic document in a specified format; performing primary page classification processing on the to-be-processed electronic document to obtain a primary page classification result; based on the primary page classification result, determining a page information extraction strategy for the to-be-processed electronic document; extracting key information elements and a page text set from the to-be-processed electronic document based on a page information extraction strategy; and performing structured processing on the key information elements and the page text set to obtain structured data corresponding to the to-be-processed electronic document, and storing the structured data. According to the method, deep intelligent digital processing can be carried out on the original data from different data sources, the processing efficiency is high, and subsequent data processing analysis and retrieval utilization are facilitated.

The invention relates to the technical field of obstacle detection, in particular to a laser point cloud-based obstacle framing method in a converter station scene, which comprises the following steps of: based on a converter station environment, performing three-dimensional scanning through a laser radar, collecting point cloud data, performing noise filtering on the data, performing spatial alignment of the data, and obtaining processed point cloud data. According to the invention, three-dimensional scanning is carried out through the laser radar, the scanning angle and the resolution are adjusted, the coverage rate and the precision of the point cloud data are optimized, the point cloud data are mapped to the adjacent grid center, the data structure is simplified, the point cloud data are horizontally cut, the linear features of the electric wire are identified, and the obstacle identification process is optimized. Through combination of spatial statistical analysis and clustering analysis, the accuracy and the meticulous degree of obstacle recognition are improved, and the obstacles are framed by constructing a bounding box of each obstacle, so that three-dimensional space positioning and form recognition of the obstacles are realized.

The invention relates to the technical field of stamping part surface detection, in particular to a stamping part surface detection method and a welding slag cleaning device.The detection method is based on three-dimensional point cloud data processing, is not affected by environment light changes, can more accurately separate a defect area from a background, and is high in detection accuracy. The welding slag can be effectively identified even at a complex geometrical shape or a deep concave position, comprehensive detection of a stamping part with a complex shape can be realized, and the accuracy and the efficiency of detection are remarkably improved; by presetting the basic threshold value and dynamically adjusting according to the reflection characteristics, it can be guaranteed that the stamping part can obtain stable detection and cleaning results under the detection conditions of different light environments.