125 results about "Diagnosis methods" patented technology

The application relates to an excitation system fault recording and event record analysis and diagnosis method and system, belonging to the field of excitation systems. The method comprises collecting recording files and event sequence records of the excitation system; performing multi-domain feature extraction based on the recording files to obtain a multi-domain feature tensor; performing space-time causal structure learning based on the multi-domain feature tensor and the event sequence records to output a causal adjacency matrix, a causal diagram and a time delay matrix; performing double-channel interpretable fault classification based on the multi-domain feature tensor, the causal diagram and an event time tag list E in the event sequence records to output a fault type label M and an attention space-time heat map; performing counterfactual causal tracing to obtain a root cause variable set and a causal propagation path, and outputting a diagnosis report. The application realizes intelligent diagnosis of the excitation system with signal analysis capability, causal reasoning capability and diagnosis interpretability.

The present application discloses a bearing fault diagnosis method and system based on knowledge enhancement and multi-path distillation, which relates to the fields of intelligent operation and maintenance and industrial equipment health management. The method includes obtaining sensor signals and visual image data of the bearing operation; based on an asynchronous dual-channel architecture, correspondingly extracting signal features of the sensor signals and image features of the visual image data, and performing time synchronization on the signal features and the image features; using a multi-modal bottleneck Transformer module to fuse the synchronized signal features and the synchronized image features; based on a maintenance knowledge graph dynamically constructed from a bearing maintenance manual, combining a text generation model to map the fused features to a semantic space and generate a fault diagnosis report. The present application can improve the recognition accuracy, real-time performance and interpretability of diagnosis results of bearing faults.

The application discloses a kind of micro-impact test bench fault diagnosis method, device, equipment and storage medium, belong to equipment state monitoring technical field;Method includes obtaining the multi-source monitoring data of micro-impact test bench;Extract the time-domain statistical characteristics and frequency-domain statistical characteristics of each kind of monitoring data, and the fusion of each statistical characteristics extracted, form the feature vector representing the health state of micro-impact test bench;The feature vector is input into the diagnosis model trained in advance, to obtain the fault information of micro-impact test bench output by the diagnosis model. Through the multi-source monitoring data such as electrical data, mechanical component mechanical response data and motion data when impact occurs of micro-impact test bench, based on the information complementarity between the multi-source monitoring data, more comprehensive master equipment operating state, solve the problem that existing micro-impact test bench fault diagnosis accuracy is low.

The application provides a multi-agent medical auxiliary diagnosis method based on dynamic semantic perception reward, comprising: processing the current object's visit description and historical case memory information to obtain a multi-modal composite state; inputting the multi-modal composite state into a multi-modal large model for forward feature extraction to obtain a final hidden state, and determining the activation probability of each expert in a plurality of expert agent libraries according to the final hidden state by using a linear projection head; according to the activation probability of each expert, selecting an expert routing chain containing a main responsibility expert and a collaborative expert, sequentially calling the specified expert agent in the routing chain, obtaining an initial diagnosis result by the main responsibility expert agent according to the multi-modal composite state, and obtaining a supplementary result by the collaborative expert agent according to the multi-modal composite state and the initial diagnosis result; and generating a predicted auxiliary diagnosis result according to the initial diagnosis result and the supplementary result, which contains the probability of the object suffering from each type of preset disease, an auxiliary diagnosis and treatment report and a comprehensive confidence.

The application is suitable for the technical field of vehicle electronic diagnosis, and provides a vehicle dynamic diagnosis method and device based on cache data, a terminal equipment and a storage medium, which comprises the following steps: obtaining a vehicle model configuration code corresponding to a vehicle to be diagnosed; wherein the vehicle model configuration code is used to represent the vehicle model version and configuration information of the vehicle to be diagnosed; in the case that the diagnosis cache data of the vehicle to be diagnosed is stored locally, obtaining the first vehicle model configuration information corresponding to the vehicle to be diagnosed from the diagnosis cache data according to the vehicle model configuration code; wherein the diagnosis cache data is used to represent a diagnosis data set corresponding to all configurations of the vehicle to be diagnosed; determining the first diagnosis data of the vehicle to be diagnosed from the diagnosis cache data according to the first vehicle model configuration information; and executing the first diagnosis data to diagnose the vehicle to be diagnosed. The above method can effectively improve the diagnosis efficiency of the vehicle and meet the actual needs of efficient automobile diagnosis.

A multi-source heterogeneous data driven large rotating machinery fault diagnosis method, which first collects one-dimensional data composed of low-frequency vibration signals, medium-frequency vibration signals and temperature signals, and two-dimensional data composed of operation images at the same time, then fuses the one-dimensional data and two-dimensional data by Bayes theorem to obtain a diagnosis result, at the same time, obtains a diagnosis result B according to the low-frequency vibration signals and medium-frequency vibration signals, and obtains a diagnosis result C according to the temperature signals, then sums up the diagnosis results A, B and C according to the weighted summation method to obtain the final diagnosis result, if the final diagnosis result is greater than or equal to 0.5, it is judged that there is a fault, if it is less than 0.5, it is judged that there is no fault. The design not only monitors multiple signals, but also has good fault diagnosis effect.

The application discloses a transformer operation state self-diagnosis method and system, relates to the technical field of state diagnosis, and comprises the following steps: acquiring and analyzing relevant data in the working state according to test conditions; judging the primary side circuit element state according to the primary side data and an RLC circuit step response time constant formula; calculating the voltage stability according to the secondary side data; calculating the delay duration of the tap switch and the damage degree of the tap switch according to the primary side data; dividing and outputting the state grade; and predicting the first fault time point according to the delay duration and a preset delay duration. The application realizes predictive maintenance by predicting the first fault time point, avoids power failure accidents caused by sudden failures, comprehensively integrates various data of the primary side and the secondary side, combines specific analysis of a circuit model and key components, forms a multi-dimensional and systematic diagnosis system, and realizes comprehensive, intelligent and fine management of the transformer operation state.

The application discloses a kind of based on multiple type signal dry vacuum pump working state intelligent diagnosis method and system, specifically related to vacuum pump monitoring technical field, by synchronous acquisition encoder pulse and vibration acceleration signal, equal-angle resampling establishes angular domain sequence, by pulse interval calculation instantaneous angular velocity and angular acceleration and combined with moment of inertia to obtain actual inertia moment, based on screw profile and ideal compression model generates theoretical aerodynamic load moment and difference integration obtains leakage flux index, corrects rotor dynamics aerodynamic term and iteratively inverts unbalance eccentricity, exports health status and fault grade.The application adopts angular domain alignment to make criterion consistent under speed fluctuation and working condition change, constructs leakage flux index by difference integration of aerodynamic load and inertia moment, and iteratively inverts physical unbalance eccentricity with residual error, so that leakage and unbalance have distinguishable physical quantity representation, improve evaluation consistency and traceability.

The embodiment of the present specification provides a diagnosis method, device, system, electronic equipment, storage medium and program product. In the embodiment of the present specification, a first diagnosis list is determined based on the chief complaint information of a user, and at least two first suspected diagnoses are selected from the first diagnosis list. Related candidate questions are determined for the at least two first suspected diagnoses to form a candidate question set; a large language model is used to select a candidate question that can change the confidence of the at least two first suspected diagnoses from the candidate question set as a first inquiry question; and the first inquiry question is fed back to the user for the chief complaint information.

An abnormality diagnosis device according to the present invention includes: an operational signal collecting unit that collects a plurality of sensor signals; an in-operational-segment operational signal extracting unit that extracts a sensor signal for each predetermined operational segment of equipment from the plurality of sensor signals collected by the operational signal collecting unit; a signal level acquiring unit that acquires a signal level for each predetermined frequency band for each operational segment with respect to the sensor signal for each operational segment extracted by the in-operational-segment operational signal extracting unit; a degree-of-deviation calculating unit that calculates the degree of deviation of the signal level for each operational segment and each frequency band acquired by the signal level acquiring unit from the signal level of the same equipment, the same operational segment, and the same frequency band during normal operation; and an abnormal part specifying unit that specifies an abnormal part of the equipment on the basis of the degree of deviation calculated by the degree-of-deviation calculating unit.

The application discloses a car fault diagnosis method, device and equipment and a storage medium, relates to the technical field of car fault diagnosis, and can output accurate structured parameter packages by performing entity extraction and intention recognition on unstructured fault description texts, thereby laying a data foundation for subsequent retrieval and scoring; based on parallel double-retrieval modes of symptom sets and component sets, candidate maintenance scheme sets can be efficiently obtained from heterogeneous knowledge sources; in combination with multi-dimensional quantitative scoring of a multi-dimensional weight vector, a time attenuation coefficient, a component co-occurrence weighting factor and a component overlap rate, and in cooperation with a screening and sorting mechanism of a safety gate threshold, the economy and timeliness of maintenance schemes are balanced under the premise of safety priority. The dependence of the diagnosis process on artificial experience is reduced, the accuracy of fault positioning and the rationality of maintenance scheme recommendation are improved, the optimal maintenance combination is quickly generated in a complex car fault scene, and the time cost and labor cost of fault diagnosis are effectively reduced.

The application discloses a kind of coupling exception dynamic diagnosis method, device, equipment and storage medium.Therein, the dynamic diagnosis method includes: obtaining the power generation of range extender, engine actual speed, generator actual speed, generator set speed;When power generation is constant in preset time, according to power generation, engine actual speed, generator actual speed, generator set speed and preset power generation-speed deviation corresponding relation judges whether coupling bolt is abnormal;When coupling bolt is abnormal, coupling is overhauled.The technical scheme of the application, by obtaining the power generation, engine actual speed, generator actual speed, generator set speed, in combination with preset power generation-speed deviation corresponding relation, the characteristics of speed dynamic fluctuation after coupling bolt fracture are identified, according to the characteristics, coupling abnormal diagnosis is carried out, when judging coupling bolt is abnormal, timely overhauling is carried out, to avoid causing range extender further damage.

The invention belongs to the technical field of transformer fault detection, and discloses a transformer fault diagnosis method and related device.The transformer fault diagnosis method comprises the steps that primary side power data and box surface vibration data of a to-be-diagnosed transformer are collected, and primary side data and vibration data are obtained; comparing the primary side data with a preset power data threshold value, and judging whether the primary side data is abnormal or not; if the abnormity judgment result of the primary side data is abnormal, outputting and obtaining an electrical operation state fault diagnosis result of the to-be-diagnosed transformer; if the abnormity judgment result of the primary side data is normal, performing feature extraction on the vibration data to obtain vibration feature data; inputting the vibration characteristic data into a pre-trained support vector machine model for fault diagnosis, and outputting a mechanical health state fault diagnosis result of the to-be-diagnosed transformer; according to the invention, through multi-dimensional data acquisition, a multi-level diagnosis process and an advanced data processing algorithm, accurate and rapid identification of the transformer fault is realized.

This invention provides a method and system for diagnosing the health status of elevator equipment, belonging to the field of equipment health status diagnosis technology. Specific steps include: determining the elevator status diagnosis interval; collecting multi-source parameters for each day within the interval; inputting the multi-source parameters and simulation values ​​output by the finite element method into a trained LSTM model; outputting the predicted values ​​of the indicator parameters for the next day and their prediction confidence levels; obtaining the residual values ​​of the predicted elevator status indicator parameters for the next day and correcting them through compensation weights; constructing a three-level evaluation framework; converting the corrected indicator parameters into membership values ​​and constructing a matrix; and outputting the final health level of the elevator through fuzzy transformation. This invention effectively eliminates the interference of original data errors and temporal residuals, achieves effective connection between indicator parameter prediction, residual correction, and health evaluation, strengthens the synergistic empowerment effect of the correction and evaluation stages, and makes the health evaluation results more consistent with the actual operating status of the elevator.

The present application relates to the technical field of generator set, specifically to a generator set monitoring and early warning diagnosis method based on principal component analysis and random forest, comprising: collecting historical operation data of the unit, extracting data characteristic values, and forming a data characteristic set by using principal component analysis; using a random forest model to construct a health state evaluation model according to the data characteristic set; calculating the dynamic reference value of the data characteristic set through the health state evaluation model, setting the deviation threshold value by using the dynamic reference value, and constructing an early warning model; forming a unit monitoring and early warning sheet according to the deviation value of the unit measuring point and the preset deviation threshold value, intelligently tracking the abnormal situation of the unit through an abnormal tracking mechanism; and analyzing the unit operation state by using a unit knowledge graph module according to the unit monitoring and early warning sheet, and outputting operational specification guidance to the operating personnel for adjustment. The present application realizes intelligent tracking and real-time operation guidance of the abnormal situation of the unit, significantly improving the efficiency of fault handling and the safety of unit operation.

In one embodiment, in a diagnosis method of an electrolysis unit, an impedance of the electrolysis unit is measured in each of a first frequency range and a second frequency range lower in frequency than the first frequency range. In the diagnosis method, a resistance value of each of a first resistance component in which influence on the impedance becomes dominant in a first frequency range and a second resistance component in which influence on the impedance becomes dominant in a second frequency range is calculated based on measurement results of the impedance, and degradation and operation of the electrolysis unit are determined based at least on a calculation result of each of the resistance values of the first resistance component and the second resistance component.

The application relates to the technical field of hydropower station equipment fault diagnosis application, and discloses an intelligent diagnosis method, system, equipment and medium for hydropower station equipment fault knowledge. The method comprises the following steps: collecting multi-dimensional operation data in real time, and constructing a dynamically updated multi-dimensional attribute knowledge network; based on the network and real-time data, training a diagnosis model that fuses a graph neural network and causal reasoning; deploying the trained model on edge nodes and the cloud to form a distributed diagnosis system; calculating the overall risk level of the equipment according to the system output; when the risk level continuously exceeds a threshold value, automatically triggering corresponding emergency instructions. The application realizes closed-loop fault processing from data fusion, knowledge updating, intelligent diagnosis to edge collaboration and emergency control, and improves the diagnosis accuracy, adaptability and response efficiency.

A machine tool component fault early warning and diagnosis method based on open set adversarial learning, after preprocessing and field construction of collected machine tool component monitoring data, an open set adversarial fitting network capable of self-adaptive fitting of classification decision boundary and hypothesis space boundary is constructed, dynamic adversarial learning strategy is used to ensure network training stability, Nash equilibrium of deep feature mapping module and boundary integrated fitting module is realized, open set fusion decision technology is used to fuse the output labels of multiple samples on the open set adversarial fitting network, accurate machine tool component fault early warning and diagnosis is realized. The present application includes both labeled data and unlabeled data in model training, which can diagnose both healthy operation type and fault type within the hypothesis space, and identify abnormal operation type outside the hypothesis space, breaking through the limitation of the prior art that can only identify a few fault types, which is of great significance to ensure the operation reliability of machine tool components.

The present application relates to a kind of sintering mixer cylinder abnormal self-diagnosis method, the method comprises the following steps: S1, a kind of speed measuring device suitable for the working characteristics of cylinder, and can realize anti-slip, anti-weld interference self-resetting, S2, a kind of rotating speed abnormal self-diagnosis device, S3, design a kind of speed measuring device abnormal self-diagnosis method;The technical scheme is ingenious, compact structure, determines using the rotational speed of the on-line continuous measurement cylinder, and using the mode of abnormal self-diagnosis to ensure the reliability of speed measuring device.

The application discloses a disease diagnosis method and system based on an adversarial convolutional neural network and gait data, relates to the technical field of medical signal processing, and comprises the following steps: inputting normalized gait kinematic data into a feature extractor to perform feature extraction and obtaining gait features; calculating identity adversarial loss, prototype contrast loss and classification loss in the training process of an adversarial convolutional neural network model based on the gait features; performing parameter optimization on the adversarial convolutional neural network model based on the identity adversarial loss, the prototype contrast loss and the classification loss, and obtaining a trained adversarial convolutional neural network model; obtaining original gait kinematic data of an unknown patient, inputting the original gait kinematic data into the trained adversarial convolutional neural network model to perform disease diagnosis, and obtaining a diagnosis result. The application effectively solves the problem that a deep model is prone to identity-pathology confusion under a small sample condition, and significantly improves the generalization ability and diagnosis robustness of the model on an unseen patient.

A fine-grained strabismus diagnosis method and system using a graph neural network based on causal feature selection, and a device and a medium. The method comprises: acquiring nine facial photographs of a patient, and performing image preprocessing on each of the nine facial photographs, in order to construct a nine-gaze-position image; using an object detection algorithm to detect an orbital region in each gaze position in the nine-gaze-position image, in order to extract feature variables of each gaze position that are related to fine-grained strabismus diagnosis; using a causal feature selection algorithm to select from among the feature variables related to each gaze position key feature variables having a direct causal relationship with fine-grained strabismus diagnosis; and inputting the key feature variables of each gaze position into a graph neural convolutional network model, and performing training and optimization with a strabismus disease dataset by means of a propagation formula, in order to output a fine-grained diagnosis result. Unrelated details are removed from entire facial images, and main eye regions are extracted to construct a nine-gaze-position image, thereby reducing the computational cost; and a causal feature algorithm is used to extract key feature variables of each gaze position, and a graph neural convolutional network model is used to learn the key feature variables of each gaze position, thereby making the graph neural convolutional network model more interpretable, and thus realizing fine-grained strabismus diagnosis.

Provided is a sarcopenia diagnosis method executed by a sarcopenia diagnosis device operated by at least one processor, the sarcopenia diagnosis method comprising the steps of: monitoring gait propulsion variability on the basis of gait data collected during walking; and diagnosing early signs of sarcopenia when the gait propulsion variability is not smaller than a threshold value.

This invention discloses a multimodal state perception and fault diagnosis method based on equipment identification guidance. The method includes: acquiring multimodal information of the power equipment under test to obtain multimodal perception data; performing time synchronization, spatial alignment, and data normalization processing on the multimodal perception data; automatically identifying the power equipment based on visible light imaging information to obtain equipment type information and / or key structural location information; selecting a multimodal fusion and diagnosis strategy matching the corresponding power equipment according to the equipment type information, and jointly analyzing the multimodal perception data; and outputting the state assessment result and / or fault diagnosis result of the power equipment based on the joint analysis result. By using equipment identification results as a priori constraints to guide the multimodal information fusion and diagnosis process, this invention achieves differentiated state perception and fault diagnosis for different types of power equipment, improving detection accuracy and engineering applicability.

The application discloses a partial discharge diagnosis method and system based on local similarity, a storage medium and a computing device. The method first constructs a merging matrix and a label matrix, extracts partial discharge sample data, constructs pulse repetitive partial discharge (PRPD) data into a two-dimensional contrast matrix, and adds the two-dimensional contrast matrix into the merging matrix. Secondly, for the to-be-diagnosed data, PRPD data is extracted, a filtering threshold is calculated according to the amplitude, filtering processing is performed to generate filtered PRPD data, and then a to-be-diagnosed matrix is constructed. Finally, by traversing the elements in the merging matrix, the matrix total similarity of the to-be-diagnosed matrix and each contrast matrix is calculated, the index of the element with the highest similarity is recorded, and the element in the corresponding label matrix is extracted as the final diagnosis result.

The application discloses a blower bearing fault diagnosis method based on a multi-source feature fusion transfer model. The method synchronously collects multi-source operation data by deploying a sensor network on a target blower and extracts fusion features, and simultaneously trains a basic diagnosis model by using complete fault data of a laboratory benchmark blower. When deployed, the similarity of the feature distribution of the target blower and the benchmark blower is quantitatively evaluated to determine the feasibility of transfer, and the model is safely fine-tuned and lightened based on the screened source domain knowledge. Finally, the optimized model is deployed to the edge side of the target blower to realize real-time diagnosis. The method effectively reduces the dependence on the historical fault data of a new blower, realizes rapid, safe deployment and precise self-adaptation of the diagnosis model, improves the timeliness of fault early warning, and guarantees the safe operation of the blower.