2644 results about "Dimensionality reduction" patented technology

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

The invention relates to the technical field of image detection, in particular to a PCBA board defect detection method and system based on image processing, and the method comprises the following steps: carrying out the meshing calculation of a gray scale deviation after a gray scale image is subjected to Gaussian filtering denoising, generating change rate data, carrying out the statistics of a frequency number, constructing a histogram, combining with an Otsu algorithm, and generating a candidate mask; extracting pixels based on a mask, calculating a gradient modulus, screening edge candidate points, carrying out gradient direction connection and morphological processing to generate a complete edge structure, expanding a connected domain through a region growing algorithm, aligning the connected domain with a template contour, and outputting defect coordinates. According to the method, the defect identification sensitivity is improved through combination of gray level image gridding processing and dynamic threshold calculation, a candidate mask is generated through grid gray level change rate statistics and an Otsu algorithm to avoid over-segmentation missing detection, and the contour precision is improved through combination of gradient modulus difference screening and morphological closed operation optimization. The region growing algorithm and template dynamic alignment reduce deformation misjudgment, and staged dimension reduction and feature enhancement reduce calculation complexity and solve resource waste.

The invention provides an intelligent scheduling and control method and device for an integrated energy system. According to the method, power, gas and heat resource operation data are acquired, multi-scale layered modeling is performed according to a time scale and a space scale, and a power resource state space model, a gas resource flow continuity model, a heat resource heat balance model and a multi-energy coupling characteristic constraint model are established; carrying out feature extraction and dimension reduction representation by adopting a deep auto-encoder network; cooperative training of multiple groups of cognitive models is carried out through a split hierarchical federal learning framework, and a global intelligent model is obtained; constructing a neural architecture search network with a hybrid bionic learning rule, setting a hierarchical scheduling target, and generating a hierarchical intelligent scheduling strategy; and a fault-tolerant control mechanism is constructed, and error detection and correction of operation deviation are realized. According to the invention, multi-time scale collaboration, collaborative learning under multi-device group privacy protection and high-reliability fault-tolerant control are realized, and the operation efficiency and reliability of the integrated energy system are remarkably improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as agent autonomous decision making, financial science and technology and medical health, and discloses a multi-modal hierarchical feature fusion and decision making method, device, equipment and medium, and the method comprises the steps: obtaining vision, language and motion data, and carrying out the hierarchical feature extraction to generate a multi-modal initial feature set; feature importance is analyzed, screening and dimension reduction are carried out, and screened multi-modal features are obtained; performing semantic enhancement on the screened multi-modal features to generate multi-modal semantic enhancement features; executing cross-modal attention fusion on the multi-modal semantic enhancement features to obtain cross-modal fusion features; and inputting the cross-modal fusion features into a semantic reasoning network to generate a decision result. According to the method, through multi-level screening dimension reduction, semantic enhancement and cross-modal attention fusion, the model can accurately utilize key feature relationships among multi-modal data, redundant interference is reduced, and semantic reasoning accuracy and decision-making efficiency are improved.

The invention discloses a distribution network tree barrier real-time analysis method and system based on dynamic vision and SLAM. The method comprises the following steps: generating a dynamic visual baseline by cooperatively controlling the translation and flight displacement of an unmanned aerial vehicle holder, and constructing a bionic binocular model to simulate a time sequence image into a binocular image pair; generating a depth point cloud through epipolar correction and stereo matching; key targets are recognized and extracted through a semantic segmentation network, and semantic point clouds are generated; establishing a dimensionality reduction motion model by utilizing pan-tilt stability augmentation, and fusing a visual inertial odometer and RTK data by adopting a filtering or optimization algorithm to realize centimeter-level pose estimation; and finally, performing optimization processing on the semantic point cloud, completing three-dimensional reconstruction based on multi-modal fusion, and outputting a risk assessment result through tree line spacing calculation and safety margin analysis. According to the invention, accurate, efficient and automatic routing inspection and risk early warning of the distribution network tree obstacles are realized.

The invention discloses a wind turbine generator data analysis and fault diagnosis method and system based on big data and artificial intelligence. According to the method, a blade image, a vibration signal, audio data and operation parameters are synchronously acquired through an unmanned aerial vehicle multi-mode sensor and a ground monitoring system, and a multi-source heterogeneous data set is constructed; after the data is classified and preprocessed, image features, vibration time-frequency domain features and operation parameter key value pairs are extracted respectively; dimensionality reduction is carried out by using an auto-encoder, feature-level space-time alignment is realized through an improved DTW algorithm, and a multi-dimensional fault feature matrix is generated; a hierarchical diagnosis model including a GRU auto-encoder, an MLP network and an attention mechanism CNN is constructed, and training is carried out by taking minimization of sub-model deviation as an optimization target; and finally, fusing multi-source features to realize fault classification, and generating a visual diagnosis report. According to the method, efficient fusion and accurate diagnosis of multi-source heterogeneous data are realized, and the accuracy and the real-time performance of fault detection of the wind turbine generator are remarkably improved.

The invention discloses a life prediction method based on health index construction and neural network fusion, and belongs to the technical field of equipment state monitoring and predictive maintenance. According to the method, through multi-source degradation feature extraction, common dynamic principal component analysis (CDPCA) dimensionality reduction, health index construction and normalization, deep learning multi-model modeling, integrated learning fusion and Bayesian optimization hyper-parameter optimization, online health assessment and residual life prediction of the equipment part degradation process are realized. Specifically, the method comprises the following steps: firstly, extracting time domain, frequency domain and time-frequency domain features from a sensor acquisition signal, and performing dimension reduction through CDPCA to obtain effective degradation characterization; then, weighting the main features to construct a health index (HI) curve, optimizing the weight through a genetic algorithm, and then performing normalization; a plurality of neural network models such as CNN, Bi-GRU, Bi-RNN, Bi-LSTM and SRNN are constructed based on the normalized HI sequence, and degradation trend modeling is realized; inputting the output results of the neural networks into an integrated learning module for fusion optimization; and finally, carrying out automatic optimization on the key hyper-parameters of the model by utilizing Bayesian optimization. In the equipment operation process, a normalized HI curve can be calculated in real time and input into the fusion model, and the residual life estimation value of the part is dynamically output. According to the method, high-precision, high-robustness and online life prediction can be provided under complex working conditions, the safety and reliability of equipment operation and maintenance are improved, and the method has wide engineering application value.

The invention provides a compressor flow field reduced-order modeling method and device based on POD and deep learning, and relates to the technical field of compressor flow field modeling, and the method comprises the steps: obtaining three-dimensional transient flow field data of a compressor flow field region under a plurality of working condition parameters, and constructing a flow field data set containing a plurality of time snapshots based on the three-dimensional transient flow field data; obtaining target flow field snapshot data of the compressor based on the flow field data set; performing intrinsic orthogonal decomposition on the target flow field snapshot data, and obtaining a dimension-reduced time coefficient matrix based on the decomposed data; and constructing a training set based on the working condition parameters and the dimensionality-reduced time coefficient matrix, and training a pre-constructed neural network prediction model by using the training set to obtain a target prediction model. According to the compressor flow field reduced-order modeling method, the target prediction model integrated with the flow physical law can be trained and constructed, and the prediction task under the new working condition can be completed by adopting the target prediction model.

The invention discloses a big data privacy protection modeling method and system based on federated learning and a block chain, and relates to the technical field of privacy protection and joint modeling. According to the method, homomorphic encryption, differential privacy, federated learning, secure multi-party computing and block chain technologies are fused, big data privacy protection and joint modeling are realized, encryption and dimensionality reduction are performed on original data through homomorphic encryption and differential privacy, an encrypted training sample of secure privacy is generated, a local model is trained on an encrypted data set through federated learning, and a big data privacy protection result is obtained. The method comprises the following steps: calculating aggregation parameters by using security multiple parties, constructing a verification network in combination with a block chain, ensuring credibility and integrity of model training, and finally, adding noise optimization performance for a global model by using differential privacy, testing generalization ability through cross validation, and determining a deployable privacy protection joint learning model, thereby breaking traditional data islands, promoting cross-mechanism data cooperation, and improving the privacy protection performance. Big data values are released, and data protection regulations and privacy requirements are met.

The invention discloses a mobile terminal streetscape image real-time segmentation method based on a lightweight neural network, and relates to the technical field of image segmentation. The method comprises the following steps: firstly, carrying out 320 * 320 adjustment, Z-score standardization, adaptive histogram equalization and 3 * 3 Gaussian filtering preprocessing on an input streetscape image; then, an improved MobileNetV3 backbone network is used, and a five-scale feature map is output in combination with DropBlock regularization through eight feature extraction stages including depth separable convolution and an SE attention module; multi-scale features are fused through a U-shaped structure, and a fusion feature map is generated through up-sampling, element-by-element addition of dimension reduction low-layer features and an attention gating module; and during reasoning, outputting a segmentation mask by using a convolutional layer, Softmax and a conditional random field, and finally performing knowledge distillation, weight pruning, 8-bit quantization and TensorRT optimization. According to the invention, high-precision real-time street view segmentation is realized, the robustness is high, and the method is suitable for different devices and scenes.

The invention discloses an indoor three-dimensional point cloud semantic segmentation method based on a super voxel Transform architecture, and belongs to the technical field of map making. The method comprises the following steps: acquiring point cloud data of different scenes, preprocessing the point cloud data, and constructing a training sample set; constructing a neural network for indoor three-dimensional point cloud semantic segmentation; training the neural network; and obtaining indoor three-dimensional point cloud data to be segmented, preprocessing the point cloud data, inputting the point cloud data into the trained neural network, outputting a super-voxel category probability and confidence, mapping a super-voxel label back to the original point cloud, and completing semantic segmentation of the indoor three-dimensional point cloud. According to the method, efficient dimension reduction and local feature aggregation of the point cloud are realized through a hierarchical structure of the super voxels, global semantic association is modeled in combination with a self-attention mechanism of Transform, semantic segmentation can be better performed on the indoor three-dimensional point cloud, and various indoor application requirements are met.

The invention discloses a bearing degradation trend prediction method and system based on multi-domain feature dynamic fusion and dimensionality reduction, and the method comprises the steps: collecting full-life vibration signals of a bearing, synchronously marking three stages of health, degradation and fault, constructing multi-dimensional features such as a time domain, a multi-scale frequency domain, a time-frequency domain, and the like; evaluating the cross-stage difference of the features by using double criteria of mahalanobis distance and information entropy, and adaptively adjusting the weight to complete optimization; threshold cutting, linear proportion, Softmax or hierarchical weighting strategy empowerment are automatically selected according to data distribution, and energy is reserved through PCA for dimension reduction. And a TCN-GRU deep network model is constructed. Real-time data are input into the model to predict the degradation state, if errors exceed the limit, feature reconstruction and model retraining are triggered, and full-life-cycle high-precision high-robustness multi-stage continuous online monitoring is achieved. The method aims at solving the problems that the diagnosis precision is limited and the working condition adaptability is insufficient due to the fact that single time domain or frequency domain features are excessively depended and the features of each stage of fault evolution are difficult to comprehensively characterize.

The invention belongs to the technical field of machine vision and precision measurement, and particularly discloses a non-contact part arc parameter high-precision measurement method and system, and the method comprises the following steps: S1, constructing a three-dimensional measurement mobile platform; s2, establishing a dynamic scanning reference; s3, performing spatial pose optimization based on the three-dimensional morphology characteristic parameters of the part, and driving a moving guide rail to dynamically scan the surface of the part to obtain a three-dimensional point cloud image of the part; s4, cutting and screening the point cloud image to obtain an arc region point cloud image; s5, preprocessing the point cloud image of the arc region; s6, carrying out dimension reduction processing; s7, outputting a circle center position vector and a radius calibration value to determine a corresponding circle center coordinate and a radius parameter; s8, constructing a radial deviation evaluation function; and S9, judging that the measured part meets the standard. The non-contact part arc parameter high-precision measurement method and the non-contact part arc parameter high-precision measurement system have the advantages of high precision, high efficiency, automation and the like, and are suitable for arc parameter detection of complex curved surface parts.

The invention relates to the technical field of oil well fault monitoring, and discloses an oil well indicator diagram real-time fault prediction method and system. The method comprises the following steps: acquiring an oil well sensor data stream, buffering and checking data integrity through a sliding window, and aligning multi-channel sensor data by applying a dynamic time warping algorithm to generate a standardized data stream; extracting time domain features based on the data stream, and comparing the time domain features with a historical feature library after principal component analysis dimension reduction to generate a feature difference index; triggering a multi-level threshold strategy according to the difference index, collecting an incremental training data set, finely tuning the model by adopting an elastic weight preserving algorithm, and generating a hot switching ready model; after the model is loaded, a fault probability value is generated through GPU accelerated reasoning, and an early warning event with a timestamp is generated; and finally analyzing the message into an early warning protocol message edge for transmission, and dynamically optimizing system resources based on logs. According to the method, the delay problem of high-frequency data flow is effectively solved, and the fault prediction accuracy and the system response speed are remarkably improved.

The invention provides an intelligent pipe surface quality detection method and system based on machine vision, relates to the technical field of industrial automatic detection and machine vision, and aims to establish a pipe surface feature library and mark shape abnormal features. The method comprises the following steps: collecting an image of a pipe in a bright and dark composite light field, extracting gray and texture features after polarization filtering processing, reconstructing a three-dimensional point cloud covering a mortar layer and a concrete layer by matching a principal component analysis dimensionality reduction fusion feature set with a feature library, and converting the point cloud into a two-dimensional expansion graph through cylindrical projection; a mortar abnormal area and a concrete abnormal area are segmented, the hole volume is calculated through point cloud residual errors in the mortar area, and internal hollowing is detected in combination with acoustic vibration excitation and thermal response; the concrete area locates defects based on point cloud features; according to the sequence of the concrete covering process before the mortar covering process, a correlation model is constructed to match and coincide the defect sites, and the detection result is output, so that the detection automation degree and accuracy can be improved.

The invention discloses an on-load tap-changer vibration fault diagnosis algorithm based on tensor feature and adaptive weighted Stacking integration, relates to the technical field of on-load tap-changer fault diagnosis, and is used for improving the fault diagnosis precision. Comprising the following steps: S1, data acquisition; s2, feature extraction; the method comprises the following steps: extracting multi-scale time-frequency characteristics of an on-load tap-changer vibration signal by using wavelet scattering transform WST, and realizing low-rank decomposition and dimensionality reduction characterization of high-dimensional characteristics by combining a non-negative tensor decomposition model NTF; s3, fault diagnosis; a multi-base learner Stacking integration framework is adopted, and a prediction matrix is generated through K-fold cross validation; through a swarm intelligent optimization algorithm SRA, hyper-parameters and fusion weights of all base learners are adjusted, L2 regularization suppression over-fitting is introduced, and finally fault classification is realized by adopting a logic regression element learner with Softmax cross entropy. According to the invention, through fault diagnosis of multi-model adaptive fusion and optimization, the fault identification precision, stability and on-line monitoring capability are improved.

The invention relates to an AI Agent-driven credit risk early warning strategy automatic evaluation method and device, control equipment and a computer readable storage medium, and the method comprises the steps: obtaining structured financial data, unstructured text data and dynamic time sequence data of an enterprise through multi-source data, carrying out the standardization processing, and outputting a standardized risk data set; based on the standardized risk data set, static financial features, dynamic derivative features and associated network features are extracted, and a high-discrimination feature set is generated through feature screening and dimensionality reduction optimization; a multi-model integration strategy is adopted, the high-discrimination feature set is input into a neural network, a Stacking integration model and a graph neural network, and enterprise risk scores and grades are output; and automatically matching an early warning rule based on the enterprise risk score and the grade, and carrying out real-time monitoring and early warning on enterprise credit according to the early warning rule.

The invention relates to the technical field of machine tool fault diagnosis and maintenance, and discloses a machine tool fault predictive maintenance method based on vibration analysis, which comprises the following steps: collecting vibration, temperature and acoustic emission signals and machine tool working condition parameters through a multi-modal sensor, extracting multi-domain features after preprocessing the vibration signals, and combining the working condition parameters through feature fusion and dimension reduction to obtain a machine tool fault predictive maintenance result. And establishing a fault classification model by using transfer learning, and performing hierarchical optimization. Model parameters are updated in real time based on an online learning mechanism, a fault early warning agent model is constructed to predict fault probability distribution, a dynamic threshold strategy is designed to avoid false report and missing report, and finally, related models and strategies are integrated to edge computing equipment. According to the method, multi-source data are integrated, multiple advanced algorithms are applied, machine tool faults can be accurately predicted, real-time monitoring and maintenance decision output are achieved, the machine tool operation reliability is improved, and the maintenance cost is reduced.

According to the cooling tower early fault early warning method based on vibration state monitoring, vibration signals and working condition labels of key parts of the cooling tower are synchronously collected through multiple channels, and data quality is improved through preprocessing operation such as band-pass filtering and normalization; time-frequency features are extracted in a multi-scale mode through self-adaptive variational mode decomposition and wavelet packet transformation, signal complexity is quantized through energy entropy, and weak fault detection capacity is enhanced; the obtained features are input into a deep belief network after being subjected to principal component analysis dimensionality reduction, and automatic classification and recognition of the equipment operation state are achieved; dynamic early warning grade adaptation is carried out according to an identification result in combination with a working condition label, the environmental adaptability and stability of early warning are effectively improved, the method further has the functions of early warning sample recording and periodic model iterative optimization, and the fault identification precision and robustness in a complex noise environment are remarkably improved.

The invention provides an engineering test method and system for a storage chip and a medium, and belongs to the technical field of semiconductor packaging. The method comprises the following steps: acquiring read-write operation data, temperature data and voltage data of a storage chip in real time through a distributed sensor network, performing dimension reduction and segmentation processing on test data by using a multi-dimensional feature extraction algorithm, extracting statistical features and correlation features, inputting a fault prediction model constructed based on a deep learning algorithm, and performing fault prediction. Fault type and probability prediction is realized; and judging whether the chip has a fault by combining a preset threshold value, if the chip has the fault, accurately positioning a fault area by adopting a dynamic probe test technology, determining a fault time point and a trigger condition through time sequence analysis, and finally generating a fault diagnosis report and providing a repair suggestion. According to the invention, the accuracy and efficiency of fault detection of the storage chip can be effectively improved.

The invention discloses a human body posture estimation method, system and device and a medium, and relates to the technical field of computer vision, and the method comprises the steps: obtaining a to-be-estimated picture containing a human body; the method comprises the following steps of: performing feature extraction and down-sampling on a to-be-estimated picture, performing dimension raising, depth separable convolution operation, channel aggregation operation and dimension reduction on a feature map with down-sampling resolution in an output branch after down-sampling to obtain a local feature map, performing up-sampling reconstruction on the local feature map by adopting dynamic weight interpolation, and fusing an output branch which is not down-sampled to obtain a local feature map; obtaining a first fusion feature; taking the first fusion feature as an initial feature, repeating the step of obtaining the first fusion feature, obtaining a second fusion feature, carrying out fusion to obtain a dual-scale fusion feature, extracting a depth perception feature in the dual-scale fusion feature, carrying out human body posture estimation through the depth perception feature, and obtaining a human body key point heat map. According to the invention, multi-scale and global information is obtained through a lightweight structure, and accurate key point positioning is obtained.

The invention discloses an unsteady flow field dimension reduction and prediction method fusing physical modeling and deep learning, and belongs to the technical field of computer-aided fluid mechanics analysis. According to the method, firstly, a modal coefficient reflecting global dynamics is extracted from an unsteady flow field by using a DMD, and meanwhile, low-dimensional feature representation of a potential space is learned from a flow field snapshot through CVAE; the two types of features have complementarity in physical and statistical meanings, and the complex dynamic evolution law of the unsteady flow field is more effectively represented through the low-dimensional features constructed in a combined mode. On the basis, an LSTM model is used for carrying out time sequence modeling on the joint features, and high-precision prediction of future evolution of the flow field is achieved. The hybrid modeling method provided by the invention improves the dimensionality reduction efficiency and prediction precision of a high-dimensional nonlinear unsteady flow field while keeping physical consistency, and is suitable for intelligent simulation and rapid prediction tasks in a complex flow scene.

The invention belongs to the field of environment monitoring and computer vision, and particularly relates to a water body color recognition regression method and system based on space-time causality and manifold learning, and the method mainly comprises the steps: carrying out the detection of a current target water body video sequence, extracting a water body region, carrying out the high-dimensional feature dimension reduction of the water body region, and obtaining a water body color recognition result; and performing feature extraction on the water body region through a space-time causal feature learning model, fusing the flow shape learning features and the space-time causal features to obtain fused features, and outputting a finally predicted water body color value. According to the method, end-to-end assembly line design of preprocessing-segmentation-feature modeling-regression is adopted, manual intervention is not needed from video input to color prediction, and through cascade cooperation of five core modules (video preprocessing, water body segmentation, manifold learning, time sequence causal modeling and color recognition), the real-time performance of the system is improved. Full-link automation from environmental interference suppression, feature extraction to result output is realized, information loss of intermediate links is avoided, and recognition efficiency and robustness are improved.

The invention relates to the technical field of injection molding, and discloses a plastic part injection mold regulation and control system and method based on a complex curved surface and a thin-wall structure, and the plastic part injection mold regulation and control system based on the complex curved surface and the thin-wall structure comprises a mold modeling module, a temperature modeling module, a control modeling module, a control optimization module and a control execution module; the plastic part injection mold regulation and control method based on the complex curved surface and the thin-wall structure comprises the steps that a mold three-dimensional model and thermal control area mapping are built, a heat conduction model is built, modal dimensionality reduction is conducted, a target temperature field and a performance function are combined, optimal temperature regulation and control are achieved through a predictive control algorithm, real-time feedback is matched, and a heating and cooling unit is driven. And dynamic closed-loop control of the mold thermal field is realized. According to the method, thermal control precision and energy consumption efficiency are optimized through Galerkin modal dimension reduction, model predictive control and a weighted performance function, global closed-loop temperature control is achieved by combining mapping of a three-dimensional area and a heating and cooling unit of the mold, and system safety and stability are enhanced.

The invention discloses a recommendation system and method for keeping semantic integrity based on a large language model. According to the method, user-article interaction data and text information are fused, a prompt template of a user and an article is constructed, a configuration file with rich semantics is generated by utilizing a large language model, and initial embedded representation is extracted. Then, two-stage dimensionality reduction transformation is carried out through principal component analysis and a multi-layer perceptron, semantic information is reserved, and low-dimensional embedding is generated; on the basis of the embedding, cosine similarity is calculated, a user-user and article-article similar graph is constructed, and final embedding representation is generated through graph convolutional network coding. Meanwhile, collaborative filtering is combined to capture an interaction relationship and optimize a joint learning target, including recommendation loss, cross-modal comparison loss and regularization terms, so as to align semantics and collaborative filtering embedding, and finally generate a high-precision personalized recommendation result. The method effectively improves the semantic comprehension ability and recommendation accuracy of a recommendation system, and is suitable for various recommendation scenes.

The invention belongs to the technical field of data processing, and particularly relates to a hidden ore body evaluation and positioning method based on multi-source data processing. The method mainly aims at the problems of incompleteness and isomerism of multi-source geological data in acquisition, fusion and modeling. Comprising the following steps: acquiring hyperspectral, geochemical and magnetic anomaly multi-source data of an evaluation area; intelligently complementing missing modal data by using a generative adversarial network based on geological constraints and modal outburst to form a complete multi-source data set; an unsupervised clustering algorithm combining geological correlation and entropy weight analysis is adopted to construct high-confidence-coefficient pseudo-label data, and knowledge mining of unlabeled samples is achieved; feature purification and dimension reduction are carried out through multi-modal feature fusion and hierarchical principal component analysis, and key feature vectors representing the existence of the ore body are extracted; and finally realizing space prediction of the concealed ore body by utilizing the classification model. According to the method, a high-quality data basis and a unified processing framework are provided for intelligent recognition of the hidden ore body, and efficient and accurate positioning of the hidden ore body is achieved.

The invention discloses an industrial robot predictive maintenance method and system based on multi-source data fusion, and the method comprises the steps: synchronously collecting vibration, current, temperature, acoustic and visual signals through multiple types of sensors, carrying out the filtering, correction and normalization processing, and constructing a multi-modal feature set; cross-modal alignment is realized through time compensation, after dimensionality reduction, a mechanical vibration group, an electrical performance group, a thermodynamic group and a motion precision group are divided, mahalanobis distances of the groups are calculated based on a historical health reference to serve as local anomaly degree scores, weights are dynamically adjusted according to the change rate, and the weights are combined into a preliminary health index. And introducing a nonlinear amplification mechanism to enhance high-value response, adaptively switching smooth intensity according to a degradation trend, and outputting a comprehensive health index. According to the method, comprehensive perception and dynamic evaluation of the operation state of the practical training platform are realized, multi-source heterogeneous information is effectively fused, the limitation of single signal monitoring is overcome, and the anomaly recognition accuracy is remarkably improved.

The invention discloses an underground engineering lining disease detection system based on point cloud, and belongs to the technical field of underground engineering detection. In order to solve the technical problems that an existing underground engineering lining disease detection method is low in detection precision, low in automation degree and the like, underground engineering point cloud data to be detected and corresponding position information are collected, and an improved PointNet + + model is adopted for disease recognition. According to the method, original three-dimensional coordinates of a point cloud are expanded into seven-dimensional point cloud data containing coordinates, normal vectors and reflection intensity, the normal vector standard deviation of points in a neighborhood of each candidate point is calculated to serve as local geometric complexity, a local geometric complexity index is fused into sampling distance measurement, then a multi-scale local neighborhood is constructed by combining sphere query, and therefore the multi-scale local neighborhood is obtained. And extracting geometric features, texture features and deformation features by using a PCA feature dimension reduction technology, carrying out feature fusion based on a normal vector weighting mechanism, finally obtaining disease type classification based on a network model, and calculating the size and position of the disease.

The invention provides a medical image segmentation method and system, computer equipment and a storage medium, and belongs to the field of image processing, and the method comprises the steps: extracting preliminary features of a medical image through depth separable convolution, and splicing the preliminary features with original image residuals to obtain a preliminary feature map; after an encoder performs average pooling dimension reduction, local details and global contour features of a dimension reduction feature map are extracted by using left and right branches of a lightweight convolution module LDB, then a downsampling feature map is obtained through channel attention CA weighted fusion, and attention is calculated in combination with a self-attention mechanism module EMHA to obtain a depth feature map and a bottleneck feature map; the decoder weights the depth feature map by means of a channel and space attention to obtain a CBAM enhanced feature map, upsamples the bottleneck feature map and then splices the bottleneck feature map with the CBAM enhanced feature map, features are extracted through an LDB module, and finally a pixel-level segmentation result is output through upsampling and deconvolution, so that image segmentation achieves the effects of high quality, low complexity and low operand.

The invention relates to the field of computer vision, in particular to an image feature recognition method based on computer vision, which comprises the following steps of: preprocessing an input image, removing image noise and correcting image gray deviation to obtain a preprocessed image; performing multi-scale feature extraction on the preprocessed image, obtaining image local texture features and global contour features under different scales, performing dynamic weight fusion, calculating dynamic fusion weight based on a feature response value and a local complexity factor, and performing dimension reduction processing on fusion features through a principal component analysis algorithm to obtain a target feature set; and matching the reference features, calculating the Euclidean distance between the target feature set and the reference features, determining an adaptive matching threshold, judging a matching result, and completing image feature recognition. According to the method, through adaptive filtering and gray level equalization preprocessing, Gaussian pyramid multi-scale feature extraction and dynamic fusion and adaptive threshold matching, feature extraction accuracy, characterization capability and recognition robustness are improved.