572 results about "Spatial positioning" patented technology

The invention discloses a welded pipe conveying abnormity prediction method and system based on large model reasoning, and aims to solve the problems that multi-source data is difficult to align, cross-station false correlation is caused, prediction lacks executable positioning and time sequence, and linkage control reliability is insufficient. Event alignment is carried out by taking a controller edge signal and an encoder zero position as time anchor points, a production line topology semantic graph containing time delay, capacity and interlocking attributes is constructed, and topology reachability and physical time delay constraints are applied in a self-attention long sequence model to carry out multi-step rolling prediction. And outputting a risk probability, refining the risk probability to spatial positioning of a roller way section or a shaft and the minimum executable intervention time, and generating a risk interval in combination with uncertainty estimation and calibration so as to drive an upstream beat self-adaptive speed reduction, shunting or stopping strategy. The technical effects of improving accuracy and interpretability, reducing false alarm and missing alarm, ensuring that linkage can be executed in advance and meeting edge time delay budget are achieved.

The invention discloses a multi-source image data fusion-based fine decoration air crack seepage quality problem detection method and device, and solves the technical problem of how to carry out comprehensive, high-precision and intelligent detection on the fine decoration surface air crack seepage quality problem. Comprising the following steps: 1) receiving visible light image data, thermal infrared image data and three-dimensional laser point cloud data of a target refined decoration surface acquired from visible light acquisition equipment, thermal infrared imaging equipment and three-dimensional laser scanning equipment respectively; 2) carrying out feature extraction on the visible light image data, the thermal infrared image data and the three-dimensional laser point cloud data; 3) obtaining point cloud projection coordinates, and then performing association fusion on the first two-dimensional feature and the second two-dimensional feature with corresponding three-dimensional features to generate fusion point cloud data containing multi-source features; and 4) based on the fused point cloud data, carrying out defect classification identification and spatial positioning to obtain a detection result. And comprehensive and high-precision detection of the quality problem of air crack seepage of the finely-decorated surface is realized.

The invention belongs to the technical field of pipe network monitoring control, and particularly relates to an urban pipe network leakage detection method and system.The urban pipe network leakage detection method includes the steps that firstly, data are collected at key nodes and pipe sections of a pipe network through a data collection module, and a four-dimensional original data set with spatial positioning attributes is formed; the preprocessing module adopts an improved Kalman filtering algorithm containing a pipe network material attenuation coefficient to reduce noise, and outputs high-quality data; the space-time fusion module is combined with GIS pipe network topological data, the topological weight is calculated through a node degree centrality algorithm, and a time attenuation mechanism and adjacent node features are fused to generate a comprehensive feature matrix; the dynamic judgment module judges suspected leakage based on a multi-parameter weighting model and a sliding window dynamic threshold value; the positioning engine module positions a leakage point through a two-factor algorithm of signal time difference and improved hydraulic model residual error; and finally, the linkage control module starts secondary acoustic verification, valve control, early warning and maintenance scheduling instructions are automatically generated after confirmation, and closed-loop management from detection to disposal is achieved.

The invention relates to the technical field of robot control, and discloses an industrial robot adaptive control method and system based on multi-modal sensor fusion, and the method comprises the steps: collecting multi-modal original data, and carrying out the time-space alignment; capturing space-time semantic association of visual textures, tactile pressure distribution and force sense fluctuation in the multi-modal data through a multi-head attention mechanism guided by a physical model, and performing space-time registration; a CNN-LSTM hybrid model is adopted to extract visual texture features and time sequence tactile features in the physical information enhanced multi-modal feature matrix; and carrying out dynamic weight distribution on the fusion feature vectors with physical consistency by utilizing a weight distribution model driven by element reinforcement learning to generate dynamic weighted fusion features. According to the method, the spatial positioning precision of the industrial robot in a precise assembly scene is greatly improved, the contact force control stability is greatly improved, and the control robustness in a complex operation scene is remarkably enhanced.

The invention relates to the technical field of auxiliary training, and discloses an AR auxiliary training system for improving the diagnosis and treatment capability of general practitioners on undifferentiated diseases, and an immersive training environment is constructed by adopting an augmented reality technology. The system comprises an environment sensing module, a space positioning module, a case data module, a virtual rendering module, an interactive acquisition module, an intelligent response module, a state control module and an evaluation calculation module. The environment sensing module adopts an RGB-D camera and an inertial measurement unit to collect environment and head movement data of a user; the spatial positioning module determines a virtual patient placement position based on an SLAM algorithm; the virtual rendering module renders a three-dimensional virtual patient in a real environment; the interaction acquisition module supports voice and gesture multi-mode interaction; the intelligent response module generates an intelligent patient answer; the evaluation calculation module carries out comprehensive evaluation from three dimensions. The invention provides a highly immersive and intelligent training environment, and has the advantages of low cost, reusability and high standardization degree.

The invention relates to the technical field of data processing, in particular to an engineering geological survey data processing method and system, and the method comprises the following steps: obtaining hole site space positioning and lithologic boundary information, collecting a structure segment sequence, extracting resistance change direction classification disturbance behaviors, recognizing node sequence conflicts, and judging hydrological turning positions. Identifying the corresponding relation between the structural section and the water level track, and generating a structural section water level merging mapping table. According to the method, the spatial information, the lithology identification, the sampling level and the penetration resistance of the drilling structure sections are collected and serialized, disturbance identification and non-sampling section classification are performed based on the resistance change trend between the sections, and node conflicts are identified in combination with the numbering relation and the lithology combination; continuous modeling and classified merging of geological information on the spatial level are achieved, the linkage adaptability of data in a multi-dimensional analysis scene is enhanced, misjudgment interference caused by information isolation is avoided, and dynamic recognition and hydrological response analysis of a geological structure are supported.

The invention provides a time-space evolution data processing method and system applied to tunnel deformation analysis, and the method comprises the steps: obtaining a time sequence monitoring sequence of different monitoring dimensions in a tunnel construction process, constructing a time-space evolution correlation model of tunnel deformation based on the time sequence monitoring sequence, and analyzing a dynamic coupling relation between structure response data and geological environment action data, generating a space-time correlation feature matrix, generating a feature evolution sequence of tunnel deformation based on the space-time correlation feature matrix, and performing nonlinear mutation feature extraction on the feature evolution sequence to obtain a mutation feature index set; according to the sudden change characteristic index set and a preset accumulated deformation rate threshold value, performing dynamic division of tunnel deformation safety levels, generating a safety level division result, and based on the safety level division result and the spatial distribution data of the tunnel construction section, executing spatial positioning and boundary contour extraction of the potential risk damage area. And obtaining a risk damage area distribution map. According to the invention, the tunnel construction safety risk can be accurately evaluated and effectively controlled.

The invention provides a rock and soil construction quality monitoring and diagnosing method, which comprises the following steps of: modeling historical engineering events and expert rules, constructing an event causal atlas prototype containing weights, and realizing event sequence feature extraction and real-time causal atlas dynamic updating in combination with on-site multi-modal sensing data and construction logs; neural symbol reasoning and tensor completion technologies are adopted to predict a novel causal relationship, and a causal atlas structure is perfected through space, time and logic consistency verification; a multi-layer risk early warning mechanism is set, a causal map local risk assessment and event chain propagation are combined, spatial positioning early warning signals are generated in a grading manner, closed-loop backtracking optimization is supported, causal reasoning accuracy and early warning efficiency are improved, construction process risk identification and dynamic early warning can be realized, and the engineering safety management level is improved.

The invention relates to a gesture recognition and projection fusion non-contact interaction method and device, equipment and a medium. The method comprises the steps of obtaining multi-user gesture original image data, extracting geometric features and boundary features of a hand contour after image preprocessing and noise removal, and generating recognition result data; secondly, on the basis of three-dimensional coordinate information in the recognition result, a tracking trajectory is analyzed through trajectory continuity, a user identity identifier is matched in combination with a user identity feature library, and user space positioning information is generated; then, a three-dimensional track point sequence is extracted from the user space positioning information, an initial projection area is divided by adopting a dynamic area segmentation algorithm, and an operation area mapping relation is formed; and finally, analyzing the operation area mapping relation to extract gesture action features, generating a control instruction set in combination with a preset rule, and scheduling a conflict instruction to generate an instruction execution sequence. By adopting the method, the scene limitation of traditional contact type interaction can be broken through, and the stability and practicability of non-contact interaction in a multi-user environment are improved.

The invention relates to an X-ray weld defect intelligent detection method based on weld line perception and reversible domain mapping, which comprises the following steps: collecting a gray X-ray image of a weld region, and carrying out joint labeling on a weld center line track and a defect mask to construct a standardized training data set; designing a weld line sensing hybrid neural network architecture; performing end-to-end training on the network by using a joint loss function formed by detection task loss and center line consistency constraint to realize collaborative optimization of defect category discrimination and spatial positioning; and deploying the trained model in an automatic welding quality detection system, performing forward reasoning on X-ray images acquired in real time, and continuously outputting defect detection results with accurate category, position and form information in combination with a post-processing strategy of weld direction clustering. According to the invention, stable and accurate identification of slender and weak-texture weld defects under the condition of bent welds is realized, and automation and reliability of nondestructive detection of welds are remarkably improved.

The invention provides a three-dimensional target detection method and device based on radar mixing points and image fusion. The method provided by the invention comprises the steps of obtaining radar point cloud data and image data collected under the same timestamp; constructing a mixed point cloud based on the radar point cloud data, and extracting radar aerial view features based on the mixed point cloud; determining image aerial view features based on the radar point cloud data and the image data; and fusing the radar aerial view features and the image aerial view features based on a channel attention mechanism and a space attention mechanism to obtain comprehensive features, and performing three-dimensional target detection based on the comprehensive features. The method and the device provided by the invention are used for solving the problems of radar sparsity, insufficient image fusion, inaccurate spatial positioning and the like in the existing method, and the overall performance of three-dimensional target detection is remarkably enhanced.

The invention discloses an electric power system multi-source forced oscillation positioning method based on a graph attention network and variational mode decomposition. The method comprises the following steps: acquiring power grid topology data of a target electric power system and attribute data of each node; inputting the power grid topology data and the attribute data of each node into a pre-trained target network model, wherein the topology perception space decoupling network processes the power grid topology data and the attribute data of each node and outputs the energy contribution degree of each node; the frequency domain time decoupling network processes the attribute data of each node and the corresponding energy contribution degree and outputs a synchronous machine component and a fan component; and the physical constraint oscillation classification network processes the synchronous machine component and the fan component and outputs a multi-source forced oscillation positioning result. According to the invention, the modeling of the electrical connection relation between the power grid nodes is realized through the topology perception space decoupling network, and the decoupling of the synchronous machine and the fan component is realized through the frequency domain time decoupling network, so that the precision of oscillation source space positioning is improved.

The invention discloses a farmland soil moisture content real-time surveying system and method based on unmanned aerial vehicle multispectral imaging. The method comprises the steps that multispectral sensor parameters are configured, and an unmanned aerial vehicle flight scanning path is planned; a space coordinate system and time synchronization mechanism is established, and high-precision positioning and time synchronization are achieved; collecting and calibrating visible light, near-infrared and short-wave infrared original image data to form a spectral signal set; calculating an image signal-to-noise ratio, screening a low-quality image, and executing noise suppression; extracting timestamp information from the suppressed image, performing spatial positioning, and establishing a spatial corresponding relation database; calculating time synchronization precision and performing image correction; evaluating the spatial resolution according to the distortion coefficient; calculating a comprehensive quality parameter, comparing the comprehensive quality parameter with a threshold value, and obtaining a soil moisture content distribution parameter when a condition is met; a farmland moisture state map is generated, partition marking is carried out according to a multi-level standard, a monitoring result is output, and high-precision and real-time monitoring of the farmland soil moisture content is achieved.

The invention relates to the technical field of underwater positioning, in particular to an AUV (Autonomous Underwater Vehicle) three-dimensional pose joint estimation method and system based on multi-modal layering, and the method comprises the steps: distributing a historical observation sequence to corresponding independent convolutional neural network branches according to modals, carrying out the local time sequence feature extraction through each branch, and carrying out the local time sequence feature extraction; outputting local time sequence characteristics of each mode; performing hierarchical feature fusion based on local time sequence features of each mode, inputting global fusion features into a double-branch regression head, respectively decoding through a position regression branch and an attitude regression branch, and outputting a three-dimensional position increment and an attitude increment; and constructing a loss function by using the three-dimensional position increment and the attitude increment, training to obtain an optimal model, and deploying the optimal model to an AUV platform, thereby breaking through the limitation that the traditional method only focuses on a two-dimensional plane or separately estimates the attitude, completely covering the full-space positioning demand of the AUV three-dimensional maneuvering task, and improving the integrity and consistency of the attitude estimation.

The invention provides a GIS insulation defect evaluation method and device and electronic equipment, and relates to the field of data processing. According to the method, a cross-modal synchronous data stream formed by an ultrahigh frequency sensor and a mechanical vibration sensor on a GIS (Geographic Information System) is obtained, event slicing is firstly carried out, multi-dimensional features are extracted, and candidate events are screened in combination with a sparse labeling library; and generating a propagation time delay window and a path priority table by using a three-dimensional geometric model, completing cross-modal pairing and time registration, outputting a registration result, performing array manifold sparse reconstruction separation, and eliminating multipath interference to obtain purification components. And constructing a cross-modal event chain graph based on the purification components, executing spatial positioning and physical quantity inversion under the constraint of the chain graph, and finally generating a defect evaluation report in combination with a historical labeling result, thereby realizing high-precision detection and evaluation of GIS insulation defects. By implementing the technical scheme provided by the invention, the accuracy of insulation defect evaluation can be improved.

The invention relates to the technical field of radar testing, in particular to a radar testing system and method based on multi-mode dynamic reconstruction. The system comprises a multi-mode radio frequency link dynamic reconstruction module, a baseband signal processing module, a space positioning module, an intelligent diagnosis and visualization module and a closed-loop crosslinking control module. According to the invention, integration of three working modes of target simulation, power measurement and T / R assembly test is realized through multi-mode radio frequency link dynamic reconstruction, automatic identification and diagnosis of T / R assembly faults are realized through the intelligent diagnosis and visualization module, and the test precision is ensured through high-precision space positioning. Seamless switching among the modes is realized through closed-loop cross-linking control, and the efficiency and precision of radar testing are remarkably improved.

The invention provides a construction project quality detecting and monitoring method and system, and relates to the technical field of data processing.The method comprises the steps that spatial positioning sensors are deployed at steel structure beam column welding joints, a concrete core shear wall root pouring area and a curtain wall top cantilever connecting end; welding acoustic emission frequency domain signals of beam-column joints, concrete vibration energy distribution waveforms of the root of the shear wall and dynamic load stress spectrums of the cantilever connecting ends are collected respectively, and a spatial heterogeneous original data set is generated; acquiring three-dimensional coordinates of positioning sensors on a steel structure beam column welding node, a concrete core shear wall root pouring area and a curtain wall top cantilever connecting end so as to construct a dynamic space reference frame, and calculating a deformation feature vector of the dynamic space reference frame; the deformation feature vector comprises a reference frame area change gradient value, a frame side vector fluctuation coefficient and a space included angle offset entropy value. According to the invention, the real-time performance of construction project quality monitoring is improved.

The invention relates to the technical field of ship underwater positioning, in particular to a dynamic space positioning method and system for a sensor chain body of a ship drag chain, and the method comprises the steps: dispersing the drag chain into a plurality of hinged rigid sections in a two-dimensional inertial reference system, connecting the sensor chain body to the tail end, and taking the motion of a ship as a traction point boundary; according to the given traction speed, the initial pitch angle, depth and tension distribution are obtained through static balance; calculating local speeds in the sections according to translation and rotation states of upstream nodes of all the sections, obtaining distributed hydrodynamic loads in combination with fluid parameters, establishing moment balance equations at all the upstream nodes, and forming a second-order ordinary differential equation set with a pitch angle as an unknown quantity; and numerical solution is carried out under a unified time step length, and the mass center positions of each node and a sensor chain body are obtained according to geometric recursion, so that dynamic positioning in an inertial reference system is realized. According to the invention, the precision and reliability of underwater target motion analysis and target tracking can be improved.

The invention relates to the technical field of image processing, and discloses a house quality detection method and system based on a live-action three-dimensional model. The method comprises the following steps: converting an OSGB format live-action three-dimensional building model into a body coordinate system and carrying out quality evaluation, carrying out semantic segmentation on a standardized model to obtain a component geographic entity set, establishing an independent local coordinate system of each component to form a single three-dimensional model set, generating a multi-view projection feature image set based on a normal vector distribution planning view angle, and carrying out multi-view projection on the single three-dimensional model set. And detecting defects by adopting a 3D-YOLO-BuildingDefect algorithm, and carrying out inverse transformation to obtain three-dimensional space defect distribution and a quality grade evaluation result. The technical problems that a traditional two-dimensional detection method is insufficient in spatial positioning precision, incomplete in detection coverage rate and insufficient in geometric information utilization are solved, and the spatial positioning accuracy of house quality detection and the comprehensiveness of defect recognition are improved.

A power transmission tower grounding resistance non-contact measurement method based on the electromagnetic coupling principle comprises the following steps that transmitting and receiving electromagnetic coupling coils are arranged around an iron tower grounding body, and geometric calibration and spatial positioning of a measurement area are completed by combining grounding grid structure parameters and soil conduction characteristics; injecting a high-frequency alternating-current excitation signal into the transmitting coil, and synchronously acquiring the amplitude and phase response of the induced voltage at a receiving coil end; carrying out filtering processing on the induction signal by adopting a time-frequency analysis and phase decoupling algorithm, and solving a function relationship between electromagnetic response and grounding impedance by combining a coupling equivalent model; based on experimental calibration data and scene parameters, a nonlinear mapping model of induction response and grounding resistance is constructed, and real-time inversion calculation is carried out by combining a solving result obtained in the third step. According to the invention, the real-time accurate measurement of the grounding resistance under the conditions of no power failure and no wire breakage is realized, and the safety, the operation convenience and the anti-interference capability in a complex environment in the measurement process are obviously improved.

The invention relates to the technical field of focus labeling, in particular to a medical image focus labeling method and system based on deep learning, and the method comprises the steps: collecting a multi-modal medical image, and carrying out the noise reduction and contrast enhancement preprocessing to obtain a medical enhanced image; segmenting a focus area through a deep convolutional network and generating a focus labeling mask image; and performing post-processing optimization on the mask image, inputting an optimization result into the sub-pixel level annotation generation model, and outputting a high-precision focus annotation coordinate sequence. According to the method, image quality and focus visibility are improved through multi-modal preprocessing, accurate segmentation is realized by using a deep convolutional network, traditional pixel-level precision limitation is broken through in combination with post-processing and a sub-pixel-level model, the problems of noise interference, contrast difference and boundary blur are effectively solved, and focus labeling fineness and spatial positioning precision are remarkably improved.

The invention discloses a physical object three-dimensional positioning method and system based on video data, and relates to the technical field of three-dimensional positioning. The method is used for solving the problems of low object space positioning precision, unstable pose estimation and poor time sequence continuity in a video scene. Firstly, an input video stream is analyzed, an object segmentation mask is generated, feature points are extracted, camera motion parameters are calculated through inter-frame matching, and a scene sparse three-dimensional point cloud is reconstructed; a candidate three-dimensional bounding box is generated according to the segmentation mask and the point cloud, an optimal bounding box is selected by combining geometric matching degree and feature similarity evaluation, and a preliminary three-dimensional positioning result of the object is obtained; a positioning result and historical frame motion data are fused, a space-time constraint optimization model is constructed, and the six-degree-of-freedom pose of the object is solved; and finally, neural radiation field representation is established based on the pose, the pose and neural parameters are optimized through combination of micro rendering and back propagation, continuous and accurate updating of the three-dimensional position of the object is realized, and the positioning stability and robustness in a dynamic scene are improved.

The invention relates to the field of image recognition, in particular to a remote sensing image ultra-small target detection method based on improved YOLO. An improved feature fusion structure R-AFPN is provided, a higher-resolution detection branch is added on the basis of a traditional feature pyramid, a bidirectional feedback and double-tower structure is adopted, and full interaction of shallow and deep features is achieved. The point can be widely applied to all target detection networks with feature pyramids. A space-time density sensing dynamic convolution module ST-DyConv and a packaging form C2fSTDyConv thereof are provided, and three-branch parallel weighted fusion is guided through standard convolution, dynamic deep convolution and MLP density, so that a convolution kernel adaptively changes along with local target density. The point can be independently applied to any CNN trunk or Neck, and the dense small target characterization capability is improved. A double-branch coordinate-channel mixed attention module DCMA is provided, coordinate information is coded in the horizontal / vertical direction and fused with channel attention, and the pixel-level space positioning capacity is remarkably enhanced. The point is high in universality and can be inserted into various deep networks. An NWD + WIoU + DFL composite loss function combination form is adopted, and ultra-small target bounding box regression is specially optimized. The point is completely decoupled from a network structure and can be directly used for all target detection models.

The invention discloses a user behavior analysis feedback method for immersive digital interaction, and relates to the technical field of man-machine interaction, and the method comprises the steps: obtaining interaction state data of a target user in an immersive digital interaction environment, and constructing a user state sequence according to the interaction state data; dividing the user state sequence into a plurality of analysis units according to a preset time length, determining a current behavior mode of the target user according to a state density value in each analysis unit and a state transition value between adjacent analysis units, and generating a feedback control signal corresponding to the current behavior mode; and according to the feedback control signal and the current position of the target user in the immersive digital interaction environment, generating spatial positioning feedback content and rendering the spatial positioning feedback content to the immersive digital interaction environment. According to the method and the device, accurate recognition of the user behavior mode is realized, differentiated spatial positioning feedback is generated according to different behavior modes, and the problem that the user behavior state is difficult to perceive and guide in real time in an immersive environment is solved.

The invention relates to the technical field of power system power quality analysis and control, and discloses a power distribution network power quality multi-disturbance-source positioning and traceability analysis method, system and device and a medium, and the method comprises the steps: optimally configuring a monitoring point network according to a power distribution network topological structure; collecting three-phase voltage and current data of each monitoring point, and extracting multi-dimensional features after preprocessing; identifying disturbance types by adopting a hierarchical classification strategy, and separating composite disturbance; the disturbance information and the time sequence of each monitoring point are fused, and accurate space positioning of harmonic waves and transient disturbance sources is realized by combining parameters of the power distribution network; establishing a disturbance propagation model, and analyzing a propagation path and an influence range; and finally, generating a comprehensive traceability report containing a positioning result, disturbance characteristics, influence evaluation and governance suggestions, and calculating the overall traceability confidence. According to the method, the problems of accurate positioning and tracing in a multi-disturbance-source coexistence scene are effectively solved, and the positioning accuracy and the recognition reliability are improved.

The invention discloses an intelligent industrial system real-time defect detection and visual quality evaluation system and method based on a self-supervised visual Transform, and relates to the technical field of automatic visual detection and defect recognition in industrial manufacturing. The characterization capability of the visual Transform and the labeling efficiency of self-supervised learning are combined, and effective visual detection independent of labeling training data is realized. A hybrid Transform-convolutional backbone network, a multi-target SSL strategy and a hardware optimization deployment mechanism are integrated, so that the method is simultaneously suitable for high-precision defect positioning and real-time processing of an edge manufacturing system. And the abnormal scoring and positioning module is used for identifying and spatially positioning defects of different scales and types by utilizing the learned potential features. By providing a solution which is extensible, does not need to be labeled and has real-time capability, long-term challenges in the field of industrial visual inspection are solved, and the requirements of industrial 4.0 and 5.0 ecosystems are met.

The invention provides a plastic toy surface defect detection method based on machine vision, and the method comprises the steps: firstly collecting and standardizing a plastic toy surface multi-parameter original image, and carrying out white balance correction and histogram equalization to improve the image quality; secondly, decomposing image frequency domain features by applying multi-scale wavelet transform, and enhancing defect area spatial positioning and texture sensing capabilities by combining cross guidance of frequency domain and spatial domain attention mechanisms; and inputting the fused features into a lightweight convolutional neural network to extract a high-discrimination feature vector, executing defect classification and position regression, and introducing an adaptive mechanism to dynamically optimize a decomposition scale and an attention strategy according to recognition confidence and detection history. The method is suitable for automatic surface quality detection under a complex background.

The invention discloses a wallboard defect detection method, device and equipment based on visual positioning and a medium. The method comprises the steps of collecting three-dimensional point cloud and two-dimensional image data of a wallboard through a visual positioning unit, extracting fastener mounting hole feature points in the point cloud, matching the feature points with corresponding hole site theoretical coordinates of a pre-stored CAD digital model, adjusting the three-dimensional point cloud according to the feature points, and obtaining a three-dimensional point cloud space aligned with a CAD digital model space. And correcting two-dimensional image distortion by adopting pre-calibrated parameters, mapping the two-dimensional image distortion to the aligned three-dimensional point cloud space, generating texture enhanced three-dimensional detection data, and inputting the texture enhanced three-dimensional detection data into a pre-trained deep learning classification model for defect detection. According to the invention, through automatic space positioning and multi-dimensional data fusion, the problems of difficult positioning and low precision of large component detection are solved, the defects of missing holes, fastener missing and the like are accurately identified by means of deep learning, and the management and control efficiency and reliability of large wallboard assembly quality are significantly improved.

The invention discloses a road subsidence detection method and system based on a deep learning model. The method comprises the following steps: acquiring continuous image sequence data of a to-be-detected road; inputting the continuous image sequence data into a deep learning model; extracting multi-scale visual features of each frame of image in the continuous image sequence data through an encoder network in the deep learning model, and fusing the multi-scale visual features of each frame of image to generate a fused feature map corresponding to each frame; through a time sequence analysis network in the deep learning model, time sequence modeling is carried out on the continuous multi-frame fusion feature map, dynamic deformation features of the road surface are captured, and a road subsidence area is identified based on the dynamic deformation features; and through a decoder network in the deep learning model, carrying out spatial positioning and contour reconstruction on the road subsidence area, and outputting a detection result containing the position and contour information of the road subsidence area. According to the method, the road subsidence detection precision and robustness are improved, and large-range road network automatic continuous monitoring is realized.

The invention belongs to the technical field of tunnel matching construction early warning, and particularly relates to a process collaborative operation early warning system based on tunnel large-machine matching construction, which performs multi-source cross validation on process events uploaded in tunnel large-machine matching construction by fusing space positioning information and real-time operation state signals of corresponding responsible equipment of the process events. According to the method, credible judgment on the authenticity of an original process event is realized, meanwhile, the process event passing cross verification is taken as a node, a process dependency network is constructed based on the sequence dependency and parallel cooperation relationship between the processes, and the time sequence coupling logic of multiple processes is explicitly described; and after the collaborative deviation is identified, recursively deducing a conduction path of the delay under the constraint of a sequence chain and parallel by taking a deviation node as a starting point. Therefore, early warning is upgraded from single-point overtime judgment to global evaluation based on full-link influence, a prospective basis is provided for active scheduling, and meanwhile, early warning triggering depends on actual influence diffusion, so that early warning timeliness and accuracy are improved.