829 results about "Diagnostic model" patented technology

The invention relates to the technical field of equipment fault intelligent diagnosis, in particular to an equipment fault intelligent diagnosis method and system based on a Modbus protocol. The method comprises the following steps: acquiring real-time operation data from target industrial equipment through a Modbus protocol, dynamically adjusting an initial sampling frequency based on an equipment operation state, and performing multiple verification and compensation correction on the acquired data to obtain a stable data stream; performing multi-scale decomposition and feature enhancement processing on the stable data stream, extracting a time-frequency domain mixed feature set, and constructing a feature evolution trajectory; inputting the feature evolution trajectory into a double-branch diagnosis model integrating equipment state prediction and fault classification, and outputting an equipment health degree score and fault type probability distribution; and constructing a dynamic fault threshold curved surface, carrying out multi-dimensional fusion decision by combining the equipment health degree score and the fault type probability distribution, and generating a graded fault early warning and maintenance strategy. According to the invention, the accuracy, timeliness and adaptability of industrial equipment fault diagnosis can be greatly improved.

The invention discloses a multi-agent large-model disease diagnosis knowledge reasoning system based on data dual drive, and relates to the technical field of artificial intelligence assisted medical diagnosis. The system collects patient symptom follow-up records, laboratory test results, observation diagnosis probabilities and expert diagnosis recommendation results in a multi-source manner; time sequence evolution characteristics are extracted, a time sequence diagnosis sensitivity coefficient is calculated, and early recognition of disease risks is achieved; in combination with anti-fact simulation and statistical reasoning, a causal consistency coefficient is obtained and is used for verifying causal reasonability of observation diagnosis and contrast results; based on agent group consensus analysis, calculating a game consistency coefficient for judging the credibility of a diagnosis conclusion; positioning and multi-level verification are carried out on abnormal reasoning steps and knowledge fragments, so that the reliability and safety of a result are guaranteed; continuous optimization of the diagnosis model is realized through a log analysis and knowledge backflow mechanism; according to the invention, the accuracy, interpretability and safety of disease diagnosis can be obviously improved.

The invention discloses a multi-mode self-learning diagnosis and early warning method and system for a power distribution system, and relates to the technical field of intelligent operation and maintenance of power systems. According to the method, a visible light image, an infrared thermal image, a sound signal, an environmental parameter and an electrical parameter of the power distribution equipment are collected through a multi-mode sensor, and time synchronization and feature extraction are carried out; multi-modal features are constructed into a hypergraph structure, and cross-modal feature fusion is realized by using a graph attention mechanism; adopting a strategy of combining self-supervised pre-training and supervised fine tuning to carry out multi-objective joint optimization on the fused features to obtain a self-learning diagnosis model; the system inputs multi-modal data in real time during operation, outputs an equipment operation state and a health degree index, and realizes early warning and fault alarm through threshold comparison. According to the method, deep fusion and adaptive learning of multi-source information can be realized, high-precision diagnosis, real-time early warning and online updating capabilities are realized, and the intelligence and safety of a power distribution system are remarkably improved.

The invention provides a bearing fault diagnosis method based on dynamic hypergraph convolution and spatial-temporal feature fusion. The method comprises the following steps: acquiring a training data set; the training data set comprises a vibration signal and a fault type; constructing a bearing fault diagnosis model based on dynamic hypergraph convolution and spatial-temporal feature fusion; the bearing fault diagnosis model comprises a multi-scale feature fusion module, a dynamic hypergraph learning model, a spatial-temporal feature fusion module and a full-connection classification layer; training the bearing fault diagnosis model based on the training data set; and inputting a to-be-diagnosed vibration signal into the trained bearing fault diagnosis model based on dynamic hypergraph convolution and spatial-temporal feature fusion to obtain a bearing fault type. According to the bearing fault diagnosis method based on dynamic hypergraph convolution and spatial-temporal feature fusion, the problem that the bearing fault diagnosis accuracy is low due to the fact that an existing bearing fault diagnosis method is insufficient in the aspects of multi-damage-degree distinguishing, dynamic feature correlation modeling and physical rule fusion is solved.

The invention discloses a motor current fault diagnosis method based on a de-noising diffusion probability model, and belongs to the technical field of mechanical equipment state monitoring and fault diagnosis, and the method comprises the steps: obtaining an original motor current signal sample, carrying out the wavelet transformation, obtaining a time-frequency grayscale image, and obtaining a time-frequency grayscale image; dividing the sample into a training sample used for diffusion model training and a test sample of a fault diagnosis model; constructing a diffusion model DDPM, carrying out training by adopting the training sample, and generating a pseudo sample based on the trained diffusion model; constructing a fault diagnosis model MAF-Cnet, and training the MAF-Cnet based on the training sample and the pseudo sample to obtain the trained MAF-Cnet; and inputting a test sample into the trained MAF-Cnet for diagnosis to obtain a motor current fault diagnosis result. The method solves the core problem that the generalization ability of the diagnosis model is insufficient due to scarcity of motor fault samples, improves the diagnosis accuracy, and is wider in application scene.

The invention discloses a motor fault diagnosis method and system based on voiceprint analysis, and relates to the related field of motor fault diagnosis technology, and the method comprises the steps: collecting sound signals, vibration data and working condition parameters during the operation of a motor, carrying out the preprocessing, separating the voiceprint features of the motor through a harmonic vector analysis method, and removing the irrelevant sound source interference; obtaining a pre-training comparison learning model through a small amount of motor fault data in combination with data enhancement, fault feature analysis and similarity calculation; constructing and training a motor fault diagnosis model, taking the motor voiceprint features, the vibration data and the working condition parameters as input, embedding a pre-training comparison learning model to learn fault information in the motor voiceprint features, extracting fault features through a time delay neural network, inputting motor operation data which are collected and preprocessed in real time into the trained model, and performing motor fault diagnosis. And outputting a judgment result of the motor fault type. The problem that an existing motor fault diagnosis model excessively depends on labeled data is solved, and model generalization is improved.

The invention relates to the technical field of rotating machinery health monitoring and fault diagnosis, and discloses a diversion sealing intelligent diagnosis method and system.The diversion sealing intelligent diagnosis method comprises the steps that an original monitoring data set is collected; performing working condition self-adaptive preprocessing on the original monitoring data set; extracting multi-scale time-frequency-space cooperation features, and performing dimension reduction by using a feature selection method; training by utilizing physical consistency constraint and a small sample learning method to obtain a small sample diagnosis model; inputting the optimized feature vector into a diagnosis model for anomaly detection, failure mode recognition and severity evaluation; a sealing performance degradation model is established, degradation model parameters are estimated, and the remaining service life is predicted; integrating the diagnosis model and the residual life prediction model into an intelligent diagnosis system, and adopting online real-time diagnosis to obtain a diagnosis report; according to the invention, the problems of incomplete monitoring information, difficult early fault detection and lack of life prediction capability in diversion sealing diagnosis are effectively solved.

The invention discloses a fault diagnosis method and system for a rotating machine bearing, and belongs to the technical field of fault diagnosis. The method comprises the following steps: acquiring a to-be-diagnosed vibration signal of the rotary mechanical bearing; inputting the to-be-diagnosed vibration signal into a pre-constructed bearing fault diagnosis model, and outputting a fault diagnosis result of the rotating machine bearing; the bearing fault diagnosis model comprises a feature extraction network, a GMM feature enhancement module, a projection distillation module and a dynamic extensible classifier which are connected in sequence. According to the method, catastrophic forgetting can be effectively relieved, continuous diagnosis of newly-occurring accidental faults can be achieved, in the initial task, the model learns and identifies different fault types through a fault bearing data set collected in advance, a basis is provided for the subsequent increment task, the increment task is composed of a plurality of stages, and in each stage, the fault bearing data set is subjected to fault detection. The model enhances playback of old knowledge through historical category pseudo features generated by a Gaussian mixture model, and aligns feature representations of new and old models by using a projection distillation module.

The invention provides an online rail fault diagnosis method and system based on knowledge transfer learning, and belongs to the technical field of crossing of intelligent monitoring and artificial intelligence of railway infrastructures. The method comprises the steps that S1, a server trains a model framework through a source domain data set to obtain a teacher diagnosis model; based on the target domain data set, training the teacher diagnosis model by adopting a mixed training strategy to obtain a student diagnosis model; s2, acquiring real-time multi-modal monitoring data from a target domain line by the edge computing equipment, compensating to obtain corrected data, and dynamically selecting the most important feature subset from the corrected data to form a simplified feature set; and S3, inputting the simplified feature set into a student diagnosis model to obtain a student fault diagnosis result and confidence thereof, and introducing a D-S evidence theory to generate a student fault diagnosis report. The method has the advantages that the accuracy, the real-time performance, the cross-domain adaptability and the overall system safety of railway track fault diagnosis are greatly improved.

The invention provides a double-path causal fusion circuit breaker fault diagnosis model optimization method and system, and the method comprises the steps: carrying out the staged signal index extraction of obtained working condition data in the switching-on and switching-off process of a circuit breaker, obtaining an original signal segment, and taking the original signal segment as an input; taking a fault classification result corresponding to the original signal segment as output, training the fault diagnosis model, and obtaining a trained to-be-optimized fault diagnosis model, the genetic annealing algorithm is utilized to dynamically optimize the to-be-optimized hyper-parameters of the obtained to-be-optimized fault diagnosis model by adopting the preset composite fitness function to obtain optimized hyper-parameters, and the optimized hyper-parameters are substituted into the to-be-optimized fault diagnosis model to obtain an optimized fault diagnosis model, so that the limitation of a single optimization algorithm is overcome, and the optimization efficiency is improved. Effective improvement of the model is realized, and the diagnosis capability of circuit breaker faults and causal chain fracture faults is further improved.

The invention discloses an intelligent inspection and fault diagnosis method for power equipment and related equipment, and the method comprises the steps: carrying out the preprocessing of multi-source data, and obtaining an adaptive diagnosis model and a trend prediction model through the matching of a diagnosis-prediction model according to the specific model, working condition and data type of the current equipment through the matching of a diagnosis model and a prediction model; performing anomaly diagnosis on the multi-source data by using the matched diagnosis model to obtain abnormal data; and finally, deep fusion with multi-dimensional information such as the historical state, the real-time load and the external weather of the equipment is carried out, and a matched prediction model is driven to carry out comprehensive analysis, so that sequential and personalized prediction of fault evolution is realized, the crossing from post-event alarm to pre-event early warning is completed, and the reliability of fault evolution is improved. And an operation and maintenance closed loop from accurate diagnosis to advanced prediction is also formed, and the adaptive capability of the system to different power transmission, power transformation and power distribution scenes is comprehensively enhanced.

The invention provides a training method of a power system fault diagnosis model, a fault diagnosis method and a device, and the training method of the power system fault diagnosis model comprises the steps: obtaining fault common parameters among various types of equipment fault data, the fault generality parameter is used for representing change information of amplitudes at defect frequencies corresponding to a normal frequency domain signal and a fault frequency domain signal of the fault data; constructing a common parameter distribution model according to the fault common parameter and the type of the equipment fault data, and performing fault simulation on the normal data of the equipment based on the common parameter distribution model to obtain a virtual fault sample; and performing iterative training on the deep learning model by taking the normal data of the equipment and the virtual fault sample as training samples and taking the sample fault type as a label to obtain a power system fault diagnosis model. According to the method, the prediction performance of the power system fault diagnosis model is improved, and then the power system fault diagnosis accuracy is improved.

The invention discloses a marine storage tank emergency cut-off valve intelligent fault prediction method based on edge calculation, and relates to the technical field of industrial equipment intelligent operation and maintenance. Comprising the following steps: S1, determining a feature vector: synchronously acquiring multi-modal data through a multi-source sensor array, and performing signal processing on the multi-modal data to obtain a corresponding feature vector; s2, constructing a diagnosis model: constructing a sample data set according to the feature vector, and constructing a hybrid diagnosis model according to the sample data set; and S3: model processing: taking the multi-modal data as the input of a final CNN-LSTM hybrid network model, outputting to obtain a corresponding confidence coefficient, and determining a corresponding early warning mechanism according to the confidence coefficient. According to the method, the false alarm rate and the missing report rate can be reduced, and early-stage accurate recognition of potential faults such as abrasion and jamming is achieved.

The embodiment of the invention discloses a coal mine multi-source geological data dynamic diagnosis system and method based on a knowledge graph, and the system comprises a data collection module which is used for collecting and preprocessing multi-source heterogeneous data, and obtaining a standardized database; the data fusion module is used for determining a geological knowledge map, performing multi-source data knowledge extraction on the standardized database, performing knowledge fusion and conflict resolution, obtaining a knowledge triple and updating the geological knowledge map in real time; the intelligent diagnosis and decision module is used for identifying abnormal events in the standardized database, and performing graph traversal and evidence fusion based on the geological knowledge graph to obtain a diagnosis conclusion; a geological situation is adapted to obtain a diagnosis model, and an optimized diagnosis model is obtained through an incremental learning mechanism; and the decision application module is used for performing three-dimensional visual presentation on the diagnosis conclusion and the geological knowledge map, generating a diagnosis report, updating the geological knowledge map based on the feedback data flow and optimizing the diagnosis model. According to the invention, the accuracy and real-time performance of dynamic diagnosis can be improved.

The invention relates to the technical field of fault diagnosis models, and discloses an adaptive AI fault diagnosis model fusing reinforcement learning and an industrial equipment predictive maintenance system. Comprising an industrial equipment data acquisition and preprocessing module, a reinforcement learning-fused adaptive fault diagnosis model module, an equipment health degree evaluation and residual life prediction module, a predictive maintenance decision and execution module and a system management and integration module, and the output end of the industrial equipment data acquisition and preprocessing module is electrically connected with the input end of a self-adaptive fault diagnosis model module fusing reinforcement learning. According to the system, data during equipment operation are effectively collected, the equipment health degree evaluation module is matched to convert the feature deviation degree into 0-100 visual scores, the health trend visualization unit displays changes through a broken line diagram and a thermodynamic diagram, fault risk points are marked, historical backtracking and multi-equipment comparison are supported, non-professional personnel can also rapidly judge the equipment state, and the equipment health degree evaluation module is matched to convert the feature deviation degree into 0-100 visual scores. And the equipment management efficiency is improved by 30%.

The invention discloses a power equipment fault intelligent diagnosis method and system based on vision and language processing, and relates to the technical field of power diagnosis, and the method comprises the steps: data collection and preprocessing: collecting panoramic multi-modal data of power equipment of a transformer substation, and carrying out the preprocessing of the data; carrying out data vectorization processing, and respectively carrying out feature extraction and vectorization on the preprocessed visual data and text data; constructing a cross-modal attention fusion diagnosis model, and realizing cross-modal feature collaboration; model training: training the cross-modal attention fusion diagnosis model; and the fault intelligent diagnosis and operation and maintenance application is used for outputting a quantitative health degree score to the power equipment and generating a structured operation and maintenance report. According to the invention, through preprocessing and model fusion, the situation of an information island in the past is changed, the comprehensiveness and accuracy of diagnosis are remarkably improved, a comprehensive equipment health degree analysis and operation and maintenance suggestion report is generated, and the efficiency and accuracy of substation equipment fault diagnosis are improved.

The invention discloses an electrical complete equipment state monitoring and early warning system based on multi-parameter intelligent sensing, belongs to the technical field of electrical equipment state monitoring, and can clearly point out a specific fault mode (such as contact resistance increasing overheating) and a possible position (such as an A-phase bus connection point). Through multi-parameter time sequence feature fusion and an intelligent diagnosis model, deep mining of a fault source is realized, the operation and maintenance efficiency is greatly improved, and the maintenance work is turned from blind troubleshooting to accurate disposal. Weak precursor signals of early and slow faults can be captured by extracting depth time sequence characteristics (such as temperature rise rate and dominant frequency offset rate) strongly related to a fault evolution mechanism. The AI model is utilized to learn complex modes of these precursor, and early warning can be given out before the equipment performance is obviously degraded, so that predictive maintenance of'nipping in advance 'is realized, and unplanned shutdown and major accidents are effectively avoided.

The invention relates to an artificial intelligence diagnosis auxiliary method and device based on a medical image, equipment and a medium. According to the method, standardized images and interested area masks are extracted from medical images to serve as basic data, in combination with a pathological causal atlas matrix constructed by medical domain knowledge, the atlas matrix is utilized to guide an attention mechanism in a deep neural network to generate a causal-associated weighted feature map and attention distribution; further eliminating the influence of confusion variables through adversarial training and causal intervention loss processing so as to obtain a robust diagnosis model, and finally performing path search and confidence calculation on attention distribution and a pathological causal map based on an analysis result of the model on a target image. And a diagnosis decision path and a visual interpretation report conforming to clinical causal logic are generated, so that the false correlation feature interference is effectively inhibited while the diagnosis accuracy is ensured, and the transparency and clinical credibility of a model decision process are remarkably improved.

The invention discloses an early auxiliary diagnosis method and system for neuropsychiatric diseases based on a brain-like multi-modal large model. The method specifically comprises the following steps: 1) collecting clinical historical data of a patient and preprocessing the clinical historical data; 2) performing feature extraction and fusion on the preprocessed data by using a brain-like mechanism to obtain a fusion feature vector; 3) constructing a brain-like multi-modal hybrid expert diagnosis large model, and processing the brain-like multi-modal hybrid expert diagnosis large model by using knowledge distillation and compression to obtain a lightweight brain-like diagnosis model; 4) inputting the fusion feature vector into a lightweight brain-like diagnosis model to obtain a prediction diagnosis result; 5) retraining the lightweight brain-like diagnosis model according to the predicted diagnosis result; and 6) performing feature extraction and fusion on the clinical data of the patient to obtain a target fusion feature vector, and inputting the target fusion feature vector into the optimal lightweight brain-like diagnosis model to obtain a final diagnosis result. According to the multi-modal model auxiliary diagnosis method, the multi-modal model auxiliary diagnosis accuracy is improved.

The invention relates to a physical knowledge-guided model interpretability analysis method and diagnosis system, and belongs to the technical field of oil well fault diagnosis, and the method comprises the steps: collecting sensor data in an indicator, carrying out the standardization processing of the data, and obtaining a preprocessed grayscale image, and taking the preprocessed grayscale image as an oil well fault diagnosis offline data set; constructing an oil well working condition intelligent diagnosis model guided by physical knowledge based on improved EffcientNet, and taking a well fault diagnosis offline data set as model input; optimizing parameters of the oil well working condition intelligent diagnosis model by adopting a multi-task cooperative training mechanism based on uncertainty weighting to obtain an optimized oil well working condition intelligent diagnosis model; performing performance quantitative evaluation on the optimized oil well working condition intelligent diagnosis model by adopting a multi-dimensional index; oil well working conditions are monitored and diagnosed in real time, a result is output, and abnormity is responded. According to the invention, accurate and explainable intelligent diagnosis of the real-time working condition of the oil well is realized.

The invention discloses a constant-speed and variable-speed induction motor acoustic fault diagnosis method based on a Transform-SE attention mechanism and a convolutional neural network, and belongs to the field of sound signal processing. And the data is converted into a two-dimensional time-frequency graph through short-time Fourier transform so as to construct a data set. Then, the data set is used for training a hybrid diagnosis model which is jointly constructed by a convolutional neural network, a Transform module based on Patch and an SE module; the CNN is used for extracting local time-frequency features, the Transform module captures a cross-regional global dependency relationship, and the SE module adaptively enhances key channel features. According to the method, local details and global context information can be effectively fused, and stable and high-precision identification of various motor faults is realized under complex working conditions including constant speed, variable speed, no-load and full load.

The invention discloses a power equipment multi-band signal comprehensive detection method, which comprises the following steps: deploying a multi-band sensor, and synchronously coupling and collecting an original composite signal; distributing a unified clock signal to each monitoring point based on an optical fiber synchronous network, and controlling an acquisition channel to synchronously acquire an original composite signal; preprocessing and performing frequency band separation on the original composite signal, and outputting a plurality of sub-frequency bands; and extracting signal features from the sub-bands, outputting a multi-dimensional feature vector to a pre-trained deep learning diagnosis model, outputting a combined diagnosis result, and calculating spatial position coordinates of the discharge source. Electrician frequency, overvoltage and partial discharge signals are integrally acquired through the multi-frequency-band sensor, high-precision time alignment acquisition of multi-parameter signals is realized in combination with a subnanosecond optical fiber synchronization technology, intelligent analysis is performed by adopting a double-branch deep neural network for parallel processing of time domain and frequency domain characteristics, and the accuracy and the reliability of the system are improved. And the combined diagnosis precision and the early warning capability of complex insulation defects and overvoltage events are obviously improved.

The invention provides a high-power heavy-duty gearbox transmission device fault diagnosis method based on multi-mode deep learning, and belongs to the technical field of gearbox fault diagnosis of deep learning. The method comprises the following steps: firstly, deploying a multi-modal sensor array at a key measuring point of equipment, and constructing a multi-modal high-fidelity special data set suitable for a high-power heavy-load gearbox scene; secondly, constructing a graph neural network for dynamically coupling equipment physical topology and complex environment influence to perceive propagation characteristics of a fault in a spatial dimension, and capturing a slow evolution rule of the fault in a time dimension in combination with a time Transform network; further, a collaborative attention fusion mechanism is designed, and cross-modal deep fusion is realized; and finally, through the trained optimal diagnosis model, a clear fault type and a confidence score are output. According to the method, high-precision recognition of early weak faults under the heavy load working condition is achieved, and the dynamic prediction and early warning capacity of latent faults is remarkably enhanced.

The invention relates to the technical field of industrial equipment predictive maintenance and fault diagnosis, in particular to a multi-motor coupling vibration intelligent diagnosis method and system. According to the technical scheme, the method comprises the following steps: generating a coupled vibration simulation data set with an accurate fault tag through a parameterized fault simulation module based on collected vibration data of multiple motors in a normal operation state and physical parameters of motor equipment; according to the invention, cold start of the diagnosis system under the condition of no historical fault sample is realized; a deep reinforcement learning agent is used for processing a space-time coupling signal, and a layered reward mechanism is combined, so that the decoupling diagnosis precision and the early warning capability are remarkably improved; through the online self-adaptive learning module, the system can be finely adjusted in real time according to field feedback to quickly adapt to the state of individual equipment; and the simulation-model evolution module continuously optimizes the simulator and the diagnosis model by using the accumulated real data to form a self-iterative closed loop.

The invention provides an AI-driven new energy equipment fault early warning and self-healing method and system, and the method comprises the steps: obtaining multi-source physical data of new energy equipment, carrying out the preprocessing, and extracting a key feature quantity reflecting the health state of the new energy equipment; inputting the key characteristic quantity into a constructed diagnosis model for fault diagnosis to obtain a diagnosis result; if the diagnosis result shows that a fault exists, logic judgment is conducted according to the diagnosis result and a preset intelligent self-healing strategy, and whether self-healing operation is allowed to be executed or not is determined; if the self-healing operation is allowed to be executed, a standardized control instruction is generated and sent to an equipment executing mechanism, and the equipment executing mechanism is driven to complete the self-healing operation; and if the self-healing operation is not allowed to be executed, the diagnosis information, the early warning report and the disposal suggestion are pushed to the operation and maintenance monitoring end, so that accurate prediction, fusion diagnosis and safe self-healing of the fault are realized, and the operation and maintenance efficiency and the equipment reliability are improved.

The invention discloses a learner error concept diagnosis method, system and device based on reverse reasoning chain generation and a storage medium, and belongs to the technical field of error concept diagnosis. The method comprises the steps of obtaining learning interaction data; inputting the learning interaction data into a pre-trained error concept diagnosis model to obtain a student error concept diagnosis result; wherein the error concept diagnosis model comprises a standard reasoning chain generation module, an error reasoning chain generation module and a diagnosis module; based on the question and the standard answer, a standard reasoning chain generation module generates a standard answer reasoning chain; based on the question and the student error answer, an error reasoning chain generation module generates an error answer reasoning chain through an attention mechanism, a neural network layer and a pre-acquired error question knowledge set; and the diagnosis module performs sequence comparison on the standard answer reasoning chain and the error answer reasoning chain to obtain a student error concept diagnosis result. According to the invention, accurate positioning of key error steps of question solving of students is realized.

The invention provides an electric power metering equipment fault diagnosis method and system based on a knowledge base, and belongs to the technical field of electric power metering equipment operation and maintenance, and the method comprises the steps: obtaining a large amount of historical monitoring data of electric power metering equipment, and storing the historical monitoring data in the knowledge base; constructing a multi-dimensional fault knowledge graph based on the knowledge base; the method comprises the following steps: collecting real-time state panoramic data of electric power metering equipment including an actual topological relation, real-time environment parameters and real-time operation data through an edge computing node, extracting equipment operation characteristics, and constructing a multi-dimensional state matrix in combination with a multi-dimensional fault knowledge graph; performing anomaly scoring on the multi-dimensional state matrix to obtain an anomaly score, and inputting the multi-dimensional state matrix into the fault diagnosis model based on the anomaly score to obtain a fault diagnosis report; and performing optimization iteration based on a feedback result of the fault diagnosis report. According to the invention, the accuracy, efficiency and intelligent level of fault diagnosis of the electric power metering equipment can be greatly improved.

The invention discloses a valve inner leakage detection method based on multi-source information fusion, and particularly relates to the field of valve inner leakage detection.The valve inner leakage detection method comprises the steps that firstly, multi-dimensional information of dynamic response of a valve body and the state of a driving system is synchronously collected, and high-quality basic data is constructed through noise reduction, alignment and abnormal correction preprocessing; extracting time domain, frequency domain and time-frequency domain characteristics and valve rod displacement, servo torque and current characteristics, and integrating the characteristics into high-dimensional characteristic vectors; then training a hierarchical diagnosis model, learning a health state feature boundary by a feature-level fusion model, and establishing a fault recognition rule by a decision-level fusion model through dual-channel classification and evidence fusion; and finally, during online detection, preliminarily screening anomalies through the model, finely identifying faults, and outputting a report containing a valve identifier, an operation state, an inner leakage level and confidence. According to the method, through multi-source information cooperation and hierarchical diagnosis, the inner leakage detection precision and the anti-interference capability are improved, and a reliable basis is provided for valve operation and maintenance.

The invention provides a pneumonia CT image diagnosis model training method, diagnosis method and equipment, and the training method comprises the steps: inputting a 3D chest CT image into a multi-task deep learning model, enabling a shared encoder in the model to extract multi-scale feature data, and enabling a connection module and a decoder to obtain pneumonia focus region prediction result data according to the multi-scale feature data, the classification head obtains pneumonia diagnosis type prediction result data according to the multi-scale feature data; determining the joint loss of the model in the current iteration round and updating model parameters; and if the current multi-task deep learning model satisfies a training termination condition, outputting the current model as a pneumonia CT image diagnosis model. According to the method, the problems of low model feature utilization rate and low pneumonia diagnosis process efficiency caused by incapability of simultaneously completing focus segmentation and type classification due to task simplification of an existing pneumonia diagnosis model can be solved.

The invention discloses a transformer mechanical fault diagnosis method and device and a storage medium, and belongs to the technical field of deep learning, and the method comprises the steps: obtaining a to-be-diagnosed vibration signal of the surface of a transformer box body, and obtaining a corresponding to-be-diagnosed mode component; inputting the modal component to be diagnosed into a pre-trained fault diagnosis model to obtain a fault diagnosis result; the fault diagnosis model training method comprises the steps of obtaining a training sample set; wherein the training sample set comprises a historical modal component and a fault category label corresponding to the historical modal component; the training sample set is input into a pre-constructed fault diagnosis model, a trained fault diagnosis model is obtained, an encoding module of the fault diagnosis model carries out time-frequency domain feature extraction and time-frequency domain attention weighting on the input data to obtain time-frequency domain fusion features, and the time-frequency domain fusion features are input into the fault diagnosis model; spatial topological features are obtained through image feature extraction and image attention weighting, step-by-step feature re-calibration is carried out on time-frequency domain fusion features, and the fault diagnosis accuracy is remarkably improved.