471results about How to "Reduce noise interference" patented technology

The invention relates to the technical field of respiratory monitoring, in particular to a respiratory signal monitoring method, device and system for a patient. The method comprises the following steps: analyzing distribution characteristics of extreme points on a respiration signal curve to obtain an initial respiration anomaly factor between adjacent extreme points; according to the time change characteristics between different adjacent extreme points and the change trend of the data points between adjacent moments, the noise influence degree between the adjacent extreme points is obtained, and a corrected breathing anomaly factor between the adjacent extreme points is obtained; obtaining a trend characteristic factor of each similar extreme point according to a change trend between adjacent similar extreme points and the corresponding breathing anomaly fluctuation factor; the data credibility between the adjacent extreme points is obtained; and filtering the breathing gas volume to obtain a filtered breathing gas volume, and obtaining a filtered breathing curve. Noise interference is considered, and the accuracy of respiration monitoring is improved by obtaining relatively accurate respiration signal data of the patient.

The invention discloses a mining area unmanned vehicle multi-mode competitive collaborative fusion sensing method, and relates to the technical field of fusion sensing, and the method comprises the following implementation steps: employing infrared thermal imaging and visible light image fusion to forward sense an obstacle, employing an ultrasonic radar and a laser infrared distance measurement sensor to sense a near-area obstacle, and employing a laser infrared distance measurement sensor to sense the near-area obstacle; whether an obstacle approaches or not is judged according to distance measurement information of sensors at four corners and four sides; a laser radar, a depth visible light imaging head and an inertial measurement unit are fused to perceive obstacles, and six modes are fused to construct a complete environment perception domain. According to the multi-mode competitive collaborative fusion perception method for the unmanned carrying vehicle in the mining area, posture changes are detected and tracked in real time, the angle of a vehicle steering engine is adjusted in advance, it is guaranteed that an image can accurately reflect an actual scene, the precision of state prediction of the carrying vehicle is further improved, and the safety and reliability of operation of the unmanned carrying vehicle in the mining area are improved.

The invention discloses a power grid communication equipment fault identification method and system based on multi-source heterogeneous data characterization learning. The method comprises the following steps: firstly, collecting various complex multi-source heterogeneous data containing fault power grid communication equipment and preprocessing the complex multi-source heterogeneous data; extracting deep semantic features by using a pre-trained feature extraction network and obtaining a feature vector sequence; capturing time features of the feature vector sequence through a bidirectional long-short-term memory network, and obtaining complete sequence feature representation through a full connection layer; performing low-rank multi-modal fusion on the complete sequence feature representation in combination with cross-modal Transform to obtain three types of output splicing construction joint representation, and obtaining a fusion feature by using a self-attention mechanism; and finally, constructing a fault identification model by using the fusion features. Through innovative data preprocessing and data fusion technologies and in combination with an advanced deep learning model, fault-related characteristics can be automatically learned from multi-source heterogeneous data, and intelligent identification of the fault state of the power grid communication equipment is realized.

The invention discloses a cable fault positioning method and system based on reflected wave decomposition and kurtosis sorting, and aims to solve the problem that a cable fault is difficult to detect under a low impedance change rate. The method comprises the steps of transmitting an incident excitation signal to a cable to obtain a first reflection signal in the cable; an improved VMD algorithm is adopted for decomposition to obtain K IMF components, and the IMF with the maximum kurtosis is selected as a second reflection signal; acquiring a time-frequency distribution curve of the second reflected signal by using short-time Fourier transform and frequency spectrum redistribution technologies; and constructing a two-dimensional energy-time curve by extracting an energy value and time under the frequency of the maximum energy amplitude point, and determining a fault position. The system is composed of an incident excitation module, a decomposition module, an STFT-RSP module and a fault positioning output module, and the positioning method is achieved. According to the method, the limitation of a traditional spread spectrum time domain reflection positioning method in cable fault detection is effectively overcome, and an efficient and accurate instructive technology is provided for cable fault positioning and detection.

The invention discloses an urban green land vegetation extraction method based on an unmanned aerial vehicle multispectral remote sensing image. Comprising the following steps: 1) determining an image acquisition area, and performing unmanned aerial vehicle path planning; 2) performing data acquisition through an unmanned aerial vehicle to obtain a high-resolution multispectral image; (3) splicing the acquired images through measurement software Pix4D mapper 4.4 to generate a digital orthoimage; and 4) combining the orthoimages of the spectral bands by using ENVI 6.0 software to obtain images of five bands including blue, green, red, red edge and near-infrared. According to the method, a background area which does not meet the vegetation spectral reflectivity characteristic is effectively inhibited, and the abnormal phenomenon that the reflectivity of a red-edge wave band is lower than that of a red wave band or higher than that of a near-infrared wave band is also solved, so that noise interference is effectively reduced; meanwhile, no obvious intersection phenomenon exists between the gray statistical characteristic values of the vegetation and the non-vegetation characteristics, and the accuracy of green land vegetation collection is improved.

The invention discloses a sea ice target detection method based on multi-dimensional feature extraction, and the method specifically comprises the following steps: S1, data preprocessing: carrying out the denoising of an original sea ice image through a Gaussian filter, carrying out the multi-scale analysis of the sea ice image through an image pyramid, and obtaining sea ice images under different scales; s2, local feature extraction: extracting texture features of each local region by using a gray-level co-occurrence matrix; s3, performing enhanced texture feature processing on the extracted texture features through a directional filter and an enhancement algorithm to obtain final texture feature data; and S4, performing feature fusion on the obtained multi-dimensional features and the texture features to form a comprehensive feature image, and obtaining a classification result of the sea ice target. According to the sea ice target detection method, through multi-scale analysis, image representation is obtained under different scales by using an image pyramid transformation method, changes and expressions of texture features under different scales are captured, and the stability of sea ice target detection is improved.

The invention relates to the technical field of numerical control machine tool cutter state monitoring, and discloses an intermittent turning cutter service life monitoring and evaluating system based on multi-sensor fusion. The detection and evaluation system is composed of a data acquisition module, a noise data preprocessing module, a noise feature analysis and mode recognition module, a tool life prediction module and a multi-source data fusion module. According to the method, noise, vibration and temperature data are integrated, a weighted average algorithm is adopted, noise interference of a single sensor is reduced, the accuracy of cutter state evaluation is improved, filtering, smoothing and signal enhancement technologies are used, high-frequency noise is removed, data fluctuation is smoothed, useful signals are enhanced, data quality is improved, and data of all the sensors are standardized; the weight is calculated according to the reliability and the precision, weighted average fusion is carried out, fused high-quality data is generated, and the beneficial effect that errors caused by interference caused by noise in service life monitoring during cutting of the cutter are avoided is achieved.

The invention relates to the technical field of object recommendation, and provides an object recommendation method and device, electronic equipment and a readable storage medium. The method comprises the following steps: performing session division processing on a user historical behavior feature vector to obtain at least one user historical session vector; processing each user historical session vector and the attribute vector corresponding to the to-be-recommended object based on an attention mechanism to obtain each self-attention vector; performing gating mechanism processing on each user historical session vector and each self-attention vector to obtain each gating vector; performing fusion processing on each gating vector to obtain a user interest vector; determining a recommendation score corresponding to the to-be-recommended object according to the user attribute vector, the user interest vector and an attribute vector corresponding to the to-be-recommended object; and determining the target object data displayed to the user based on the preset recommendation score threshold value and the recommendation score, thereby improving the accuracy of user interest prediction and enhancing the capture ability of dynamic interest changes of the user.

The invention relates to the technical field of radio orientation, in particular to a measuring method capable of tracking and recording motion trail information of a vibrating rod, which comprises the following steps: arranging at least four UWB (Ultra Wideband) base stations, fixing UWB transmitters at the joint of the vibrating end of the vibrating rod and a rubber tube, and fixing IMU (Inertial Measurement Unit) sensors at the vibrating end of the vibrating rod; according to the data output by the UWB transmitter and the IMU sensor, the position and posture of the vibrating rod in the detected target mold are calculated through a positioning algorithm, and the motion trail of the vibrating rod is further calculated; and according to the vibrating time, the vibrating area and the vibrating area overlapping degree of the vibrating rod, the vibrating state of the concrete is analyzed. The UWB technology and the IMU technology are fused, so that high-precision positioning of the vibrating rod can still be kept under the ground where wireless signals such as GPS signals cannot be transmitted, and the vibrating quality can be conveniently detected and evaluated.

The invention relates to the technical field of paint surface detection, in particular to a UV resin coating paint surface defect detection method and system.The method comprises the steps that a paint surface image set shot by light sources at different angles is subjected to reflective point removal treatment, and a fused to-be-detected image facilitating defect detection is obtained; segmenting the to-be-detected image of the paint surface before and after cleaning, calculating a similarity index of the segmented image, and detecting whether an uncured defect exists or not according to a preset similarity threshold value; acquiring and processing data of the segmented image to obtain a segmented region uniformity index, and detecting a color non-uniformity defect according to a preset threshold value; establishing an MSF-CRA-YOLOv5 model to carry out defect detection on the paint surface to be detected, wherein the defect detection comprises a defect type and a defect position; designing a plurality of loss functions in the total loss function, and designing a loss function in a prediction stage for accurate positioning of a bounding box; and finally obtaining a detection result and generating a detection report. According to the method provided by the invention, the efficiency of detecting the paint surface defects of the UV resin coating is improved.

The invention belongs to the technical field of computer application, and relates to an operation inspection equipment fault detection method and system based on an improved deep learning model, and the method comprises the steps: obtaining original data, employing EEMD to decompose the original data for feature enhancement, obtaining a decomposition signal, carrying out the noise reduction of the decomposition signal, and obtaining a feature signal after noise reduction; according to the feature signals after noise reduction, a deep learning model is constructed based on Resnet and a dynamic Transform encoder, and the prediction probability of each fault category is output; a ZOA optimization algorithm is used to optimize hyper-parameters of a deep learning model, an optimization model is obtained, the performance of the optimization model is evaluated, an optimal model is obtained, and the prediction probability of each fault category is output, so that false report and missing report of faults can be effectively reduced in a fault detection task, potential safety hazards caused by the fact that the faults are not found in time are reduced, and the fault detection efficiency is improved. Therefore, the stability and reliability of the power system are improved.

The invention relates to the technical field of footwear products, in particular to a wrap yarn surface defect detection method and system. Firstly, a composite grating image is collected and projected to the surface of wrap yarn to obtain a light intensity function; and obtaining a wrapped phase based on the light intensity function. Secondly, performing preliminary unwrapping by adopting an optimized MSE algorithm to obtain phase data; performing phase recovery by using Fourier transform processing; performing phase adjustment according to the phase difference to obtain an unwrapped phase; phase distribution corresponding to the unwrapped phase is obtained, error calculation is carried out on the phase distribution and expected phase distribution, a phase value is adjusted, and phase unwrapped data are obtained. Then, calculating an absolute phase by using a nonlinear model; and calculating the gradient of the data in the absolute phase, calculating the amplitude of the gradient according to the size and direction of the gradient, and determining the position of the defect by applying threshold processing. And finally, performing morphological post-processing on the defect image, extracting defects, and realizing detection of the surface defects of the wrap yarn. According to the invention, the accuracy and efficiency of wrap yarn surface defect detection can be improved.

The invention provides a mixed precursor chemical gas identification method based on feature construction, and relates to the technical field of mixed gas identification, and the method comprises the steps: determining a division criterion of a transient response stage and a steady-state response stage through a working mode of fixed temperature modulation as an inverted step wave; and taking the average value in the steady-state response stage as the characteristic of the structure, establishing a sample library of the structure characteristic and the mixed gas concentration, and fitting the relationship between the structure characteristic and the mixed gas concentration by using a regression model with a simple structure, so that the function of identifying the mixed precursor chemical gas by using the simple model is realized. The current situation that the model for identifying the mixed precursor chemical gas is more complex and the algorithm scale is more huge is changed, and the working efficiency of mixed gas detection is improved.

A heart ultrasound image segmentation method based on a state space model and feature interactive perception relates to the field of image segmentation, and a dual perception state space enhancement module DPSSEM uses two SSM modules and combines the two SSM modules with SAM and CAM respectively, so that more information can be obtained from two dimensions of space and channel, and the image segmentation efficiency is improved. The dual perception state space enhancement module DPSSEM carries out fine interaction and fusion among different feature maps, the feature identification capability and expression capability are significantly enhanced, the accuracy and robustness of a heart structure in ultrasound image segmentation are effectively improved, and the feature interaction perception decoding module FIPDM carries out multi-feature processing branch and interaction operation, so that the accuracy and robustness of the heart structure in ultrasound image segmentation are effectively improved. And performing multi-path refinement and enhancement on the extracted features in a decoding stage.

The invention discloses a recommendation method fusing a knowledge graph and sentiment analysis, which comprises the following steps of: constructing a data set, processing comment text data in the data set to obtain a triple, processing the triple by adopting linear transformation to obtain a user embedded vector and a project embedded vector, and constructing the user embedded vector and the project embedded vector. Coding the comment text data through a pre-training language learning model to obtain a probability distribution value of sentiment analysis, fusing the user embedding vector and the item embedding vector, and connecting the obtained context representation of the comment text data with the corresponding probability distribution value of sentiment analysis to obtain a matching score of the user and the item, and performing matching prediction verification on the matching score of the user and the item to obtain the accuracy of the matching score of the user and the item. According to the method, sentiment analysis is introduced, and the sentiment analysis can help to identify the sentiment attitude of the user to the item or the content, so that the preference of the user is more accurately captured, and the matching degree of recommendation and the satisfaction degree of the user are improved.

The invention discloses a meat product foreign matter on-line detection method and system, and belongs to the field of visual detection.The detection method comprises the steps that a fixed detection area is set, a multi-mode sensor is installed above the fixed detection area, and the multi-mode sensor collects data and transmits the data to a data processing center through a wireless network; the data processing center decompresses and preprocesses the received data and fuses the image data twice to obtain a final fused image; according to the feature information in the final fusion, extracting fusion feature data; analyzing the feature data by using a support vector machine, and judging whether foreign matters exist or not and classifying the types of the foreign matters; a detection result is fed back to a production line control system in real time, and meat products containing foreign matters are positioned and removed. According to the method, the multi-mode sensor and an efficient data analysis technology are combined, and the accuracy and the real-time performance of meat product foreign matter detection are effectively improved.

The invention relates to a touch all-in-one machine interaction control method and device, computer equipment and a medium, and the method comprises the steps: receiving image data through a preset video stream protocol, and obtaining a corresponding image data stream; acquiring a real-time network bandwidth condition, and then performing adaptive compression processing on the image data stream based on the real-time network bandwidth condition, and dynamically adjusting image transmission parameters; comprehensively analyzing the image data stream by using a deep learning algorithm, extracting operation characteristics of a user, generating an output control instruction based on the operation characteristics, and further controlling and adjusting image display and / or an equipment state; content information is extracted from the image data stream, and content analysis is carried out by adopting a corresponding content analysis strategy according to the content information, so that real-time display and / or storage are / is carried out according to the analyzed content; and obtaining a user interaction behavior, generating a corresponding adjustment feedback instruction based on the user interaction behavior, and performing personalized adjustment on the user interface. The method has the effect of improving the image transmission quality.

The invention discloses a vibrating wire sensor fault diagnosis and repair method, system and device, and a storage medium. The method comprises the steps of collecting an output signal of a vibrating wire sensor; amplitude values of all the collected output signals of the vibrating wire sensor are amplified, and a band-pass filter circuit is used for filtering; inputting the amplified and filtered data into a pre-constructed fault diagnosis and recognition model, and performing feature extraction and classification so as to recognize the vibrating wire sensor with the fault and the fault type of the vibrating wire sensor; according to the fault type, different modes are selected to repair the vibrating wire sensor with the fault; the diagnosis result and the working state of the fault diagnosis and recognition model and the real frequency of the repaired vibrating wire sensor are displayed; and storing all the data for subsequent analysis and iterative updating of a fault diagnosis and recognition model. According to the invention, fault diagnosis and online real-time monitoring can be accurately and effectively carried out on the vibrating wire sensor, and the vibrating wire sensor with faults can be rapidly repaired.

The invention discloses a method for characterizing and evaluating marine corrosion under a paint layer based on pulsed eddy current thermal imaging and a BEMD noise reduction method, and belongs to the technical field of marine corrosion detection. The method comprises the following steps: detecting a marine corrosion sample by adopting pulsed eddy current thermal imaging ECPT, and obtaining a corrosion image sequence of surface heating and cooling of the corrosion sample with different corrosion degrees; a BEMD method is adopted to separate the corrosion image layer by layer, an intrinsic mode function IMF corresponding to noise is removed, and the corrosion image is reconstructed; and comparing the corroded area and the non-corroded area of the corrosion image after noise removal, and evaluating the corrosion degree of the marine corrosion test sample. Through accurate corrosion characterization and evaluation, a scientific basis can be provided for corrosion protection design of an ocean structure, engineers are helped to take protection measures in time, the service life of ocean facilities is prolonged, and economic losses caused by corrosion are reduced.

The embodiment of the invention discloses a commodity classification method and device based on an artificial intelligence model, and the method comprises the steps: obtaining commodity data containing a to-be-classified commodity, and the commodity data comprises text data, image data and user behavior data; performing feature extraction and feature fusion on the commodity data to obtain a multi-modal feature vector; constructing a commodity association network, and updating the commodity association network in real time by using a dynamic network updating algorithm according to the commodity data to obtain commodity association information; constructing a semantic knowledge graph generation model, and generating a commodity classification candidate set by using the knowledge graph generation model according to the multi-modal feature vector and the commodity association information; and according to the commodity classification candidate set, using the commodity classification model to classify the to-be-classified commodity, and obtaining a classification result of the to-be-identified commodity. According to the commodity classification method, the accuracy, adaptability and real-time performance of commodity classification are improved.

The invention provides a traffic flow prediction method based on space-time decomposition and an attention mechanism. The method comprises the following steps: firstly, decomposing original traffic flow data into a low-frequency trend item and a high-frequency event item through Fourier transform and inverse transform thereof, and introducing time embedded information to enhance the expression ability of time sequence characteristics; secondly, for a trend term, constructing a trend processing branch by using time convolution, a time attention module and a trend category learning module, and emphatically extracting trend information of a single node; for an event item, a time convolution and multi-time slice space attention gating module is adopted, an event processing branch is constructed, and event influence and spatial dependence between different nodes are emphasized to be captured. And finally, performing weighted fusion on the features of the trend item and the event item through an adaptive fusion module to obtain a more accurate and robust traffic flow prediction result. The method can improve the prediction precision while effectively processing the spatio-temporal information, and is suitable for flow prediction in a complex traffic scene.

The invention discloses a multi-feature multi-modal fusion tight gas reservoir yield deep learning prediction method (MMF), which improves deep learning performance through dynamic production data dimension reduction, data quality enhancement, VMD and other optimization input and LSTM fusion, and belongs to an artificial intelligence method in the technical field of oil-gas exploration and development. The method comprises the following steps: firstly, eliminating production dynamic factors having no important influence on the cumulative yield by using Granger causality test; inputting the screened features into a KF (Kalman filter) to carry out optimization estimation; performing VMD on the optimized cumulative yield to obtain a plurality of groups of sub-modal sequences; finally, multi-modal prediction and fusion are carried out based on LSTM, a prediction result of the cumulative yield is obtained, and compared with RNN, LSTM, GRU, KF-LSTM, CNN-LSTM and CNN-GRU, the R2 of MMF is improved by 0.73%-12.84%; according to the method, through dynamic feature selection, filtering, modal decomposition and deep learning, data representation is optimized, the understanding of the model on dynamic data is enhanced, and the uncertainty, the nonlinear relation and the interpretability among gas well production data are mined, so that the prediction accuracy is improved.

The invention provides an intention recognition method based on unmanned aerial vehicle cluster three-dimensional trajectory analysis, and relates to the field of group behavior recognition of unmanned aerial vehicle clusters. Through preprocessing the three-dimensional trajectory, the consistency of the trajectory in time and space dimensions is ensured, the stability and quality of data are improved, the subsequent intention recognition process is more accurate and reliable, through the improved HDBSCAN algorithm, the direction information of the trajectory is effectively recognized, and the clustering structure is dynamically adjusted under different density levels, so that the accuracy of intention recognition is improved. And the intention identification of the unmanned aerial vehicle in different group scales and complex task scenes is more accurate. In combination with a deep learning network, the method can better capture the time dependency relationship of a three-dimensional track, improves the analysis capability of a complex behavior mode in an intention recognition process, improves the accuracy and reliability of a recognition result, and improves the recognition efficiency in complex scenes such as multi-unmanned aerial vehicle cooperative combat. More effective identification of the unmanned aerial vehicle cluster intention is realized, and the intention identification performance is greatly improved.

The invention relates to the technical field of tuning data of filters, provides a tuning control method of a distributed microwave filter, and aims to solve the problem of difficulty in nonlinear relation and multivariable convergence between a debugging model and an actual model in a filter tuning process. The method comprises the steps of data preprocessing, spectrum analysis, error correction, tuning model construction and optimization and the like, a target frequency component and an interference frequency component in a signal are identified through a fast Fourier transform algorithm, a tuning model is optimized through a genetic algorithm, an optimal tuning parameter is calculated, and if the performance of a filter does not reach a target, the tuning parameter is calculated. According to the method, the accuracy of filter tuning control is improved, and the adaptability and the stability of the filter are enhanced.

The invention discloses a pedestrian crossing tolerance time prediction method under a signal control condition. The method comprises the following steps: calculating a risk score of each pedestrian sample in a pedestrian crossing data set through a random survival forest model; carrying out tolerance grouping on the pedestrian samples by using a K-means clustering algorithm in combination with the risk score, and generating a data set of a plurality of tolerance; dividing the data set of each tolerance into a training set and a test set; a Stacking integration model is constructed; performing hyper-parameter tuning on each primary model through a Bayesian hyper-parameter optimization algorithm; inputting the training set into each primary model for training according to five-fold cross validation, and outputting a prediction result of each primary model; integrating the prediction result of each primary model and the true value of the tolerance time into a new training set and a new test set, inputting the new training set and the new test set into the meta-model, and outputting a corresponding tolerance time prediction value; and realizing tolerance time prediction of a single pedestrian through the trained Stacking integrated model. According to the invention, the accuracy of pedestrian crossing tolerance time prediction can be improved.

The invention relates to a four-motor traction control method, device and equipment and a readable storage medium, and belongs to the field of control over vehicle transmission systems.The method comprises the steps that the target wheel speed of each wheel is calculated by obtaining the actual vehicle speed of a target vehicle at the current moment and the actual wheel speed and the wheel acceleration of each wheel; calculating the wheel speed change rate correction amount of each wheel based on the wheel acceleration of each wheel at the current moment and a plurality of historical wheel accelerations of each wheel at a set historical moment; determining the slippage control adjustment amount of each wheel and judging whether slippage occurs or not; if the wheels slip, target motor torque of the wheels is calculated based on the wheel speed change rate correction amount of the wheels and a preset motor torque calculation rule, and traction force of the wheels is controlled based on the target motor torque. According to the method, the effects of improving the traction force control precision and stability of the vehicle under different road conditions, reducing the slipping phenomenon and improving the driving safety and comfort are achieved.

The invention discloses a visual positioning method and system based on multi-modal information fusion, and belongs to the field of computer vision. The method comprises the following steps: acquiring an RGB image and a depth image in the same scene, extracting semantic features from the RGB image through a multi-modal feature extraction network, and extracting structural features from the depth image; performing weight distribution and deep fusion on the semantic features through a feature balance module to obtain final multi-modal fusion features; predicting three-dimensional scene coordinates of each two-dimensional pixel point and uncertainty corresponding to the three-dimensional scene coordinates on the basis of the final multi-modal fusion features; and calculating the six-degree-of-freedom pose of the camera based on the predicted coordinates. According to the method, the problems of texture dependence and structure fuzziness in the existing single-mode visual positioning method are solved.

The embodiment of the invention discloses a mobile handwritten signature recognition method and device based on image processing and a medium, and relates to the technical field of handwritten signature recognition, and the method comprises the steps: obtaining the handwritten signature image information of a handwritten signature input in a mobile terminal, and carrying out the image analysis of the handwritten signature image information, determining a current dynamic threshold value corresponding to each pixel unit; based on the current dynamic threshold value corresponding to each pixel unit, binarization processing is carried out on the handwritten signature image information, a corresponding binarized signature image is determined to extract multi-dimensional signature features of the binarized signature image, and the multi-dimensional signature features comprise image features, dynamic features and geometric features; according to the multi-dimensional signature features and a pre-constructed signature recognition model, carrying out signature recognition on the handwritten signature, and determining recognition information of the handwritten signature; the method of dynamically adjusting the threshold value can significantly reduce errors in the binarization processing process, thereby improving the accuracy of subsequent signature recognition.

The invention relates to the technical field of metal button surface defect real-time detection methods, in particular to a metal button surface defect real-time detection method based on dry deep learning, which comprises the following steps: acquiring a to-be-detected metal button image and preprocessing the to-be-detected metal button image to obtain a to-be-detected metal button image; and inputting the preprocessed image into a deep learning network model to extract a defect region, optimizing and verifying the extracted defect region, and finally generating a statistical result of defect detection. According to the method, dynamically regulated progressive boundary construction, adaptive gradient mapping, Gaussian fitting detail enhancement, multi-dimensional difference correction factors, sectional defect region generation and other algorithms are innovatively introduced in sequence, so that boundary recognition and detail optimization are progressive layer by layer. The innovative multi-stage optimization design enables the data output of each step to be connected with the subsequent steps, guarantees the continuity and consistency of defect detection, and avoids the problems of boundary error and information loss caused by algorithm independence in a traditional method.

The invention discloses a shield tunnel settlement prediction method based on artificial intelligence. The method comprises the steps of data acquisition, data optimization, construction of a shield tunnel settlement prediction model, model optimization and settlement prediction. The invention relates to the technical field of tunnel construction monitoring, in particular to a shield tunnel settlement prediction method based on artificial intelligence. According to the scheme, data cleaning is carried out by defining a dimension refining distance function and calculating gravitation between data, potential relations between the data are deeply mined, noise interference is reduced, and the accuracy and reliability of the data are improved; by designing a mapping function, a circulation control layer, a depth correlation layer and a loss function, the recognition and prediction precision of the model on a complex settlement mode is improved; model parameters are dynamically searched by designing an intervention factor, defining an adaptive step length, performing bidirectional iterative search and gradually adjusting search, so that the search efficiency is improved, time consumption and a loss value of model training are balanced, and the model is more efficient and stable.