167 results about "Fault probability" patented technology

The invention relates to the field of mechanical equipment health management, in particular to a large sliding bearing fault detection and evaluation method, device and system. Comprising the following steps: collecting multi-source sensing data, and constructing a comprehensive data set; constructing a state space model based on a sliding bearing physical mechanism; the multi-source sensing data and the state space model are fused through Bayesian filtering, and hidden state parameter posterior distribution is dynamically estimated; generating a virtual fault sample by using a generative adversarial network in combination with a physical rule base; designing a Bayesian space-time sequence diagnosis model based on an attention mechanism, and generating fusion health state features; processing and fusing the health state features by using a degradation process model, and predicting the remaining service life of the bearing; and based on the health state, the fault probability and the remaining service life, setting multi-stage early warning threshold values, and triggering intelligent early warning. According to the method, the defect that a single model is insufficient in adaptability and generalization ability under complex working conditions is overcome, and the accuracy and reliability of fault detection are remarkably improved.

The invention discloses a fault tracing and positioning method in an FTU section, and belongs to the technical field of distribution automation fault positioning. The method comprises the following steps: synchronously acquiring current abrupt change signals of multiple FTU sections, reconstructing a transient waveform through EMD decomposition and cubic spline interpolation, extracting wavelet packet energy characteristics, and generating multi-dimensional transient characteristics in combination with wave head polarity and timestamps; fusing the power distribution network topology and traveling wave time delay to construct a space-time correlation graph, introducing virtual nodes to compensate communication interruption, dynamically assigning node attributes and marking a reflection path; based on graph neural network cooperative training, iteratively aggregating neighborhood information and dynamically optimizing edge weights, and generating candidate section fault probability distribution; and judging a conflict level by using information entropy, carrying out multi-level digestion in combination with polarity matching and time delay consistency, and outputting a high-confidence positioning result. According to the method, the problems of difficulty in multi-FTU cooperative positioning, poor communication interruption adaptability, inaccurate feature fusion and the like are solved, and the accuracy and robustness of power distribution network fault tracing are remarkably improved.

The invention discloses a power equipment fault prediction system based on big data analysis. The method comprises the following steps: acquiring initial equipment multi-dimensional data; constructing a dynamic topology network of the power equipment, including a dependency relationship between the equipment and a fault propagation path, performing embedded learning on the dynamic topology network by using a GNN graph neural network, and extracting equipment collaboration features in the initial equipment multi-dimensional data; a multi-task learning framework is constructed in combination with the equipment cooperation features to predict the equipment fault probability and the remaining service life, and an equipment health index is obtained; and acquiring environmental parameters, dynamically adjusting a fault judgment threshold based on the equipment health index and the environmental parameters, generating a prediction result, integrating the prediction result with an SCADA system, and triggering graded early warning. And the influence of environmental factors on the operation state of the equipment is fully considered. Under different environmental conditions, the equipment fault risk can be judged timely and accurately.

The invention discloses an electric energy meter detection assembly line fault diagnosis and prediction method based on multi-modal time sequence analysis. The method comprises the steps of collecting multi-modal data including electric energy meter visual data, time sequence sensor data and text log data in real time; performing cross-modal fusion of time sequence alignment on the multi-modal data to generate joint feature representation; performing joint optimization of fault diagnosis and prediction; performing fault diagnosis based on the joint feature representation, and outputting a current fault type and probability; predicting a future fault probability based on the equipment state continuous evolution model; in response to batch conduction characteristics which are output by the prediction model and reach a preset abnormal value, triggering recalculation of the associated modal data; correcting an initial condition of the equipment state continuous evolution model according to the fault type obtained through re-calculation; and dynamically adjusting a diagnosis decision threshold according to the prediction confidence output by the corrected equipment state continuous evolution model.

The invention discloses an on-line monitoring and fault early warning system for the running state of a dynamic compression-shear testing machine, belongs to the technical field of fault diagnosis, and aims to solve the problems of poor adaptability to multiple motion modes, lagging fault early warning and fuzzy fault positioning in the prior art. According to the system, core collaborative link fault sensitive point monitoring parameters are matched according to a current motion mode, a dynamic threshold value is generated to construct a fault judgment threshold value system, real-time data subjected to cyclic division are collected and loaded to generate a time sequence data set, a reference candidate range state is judged based on the threshold value, and a fault judgment reference library is constructed; and executing deviation analysis prediction trend through the reference library, generating a compensation instruction, identifying potential faults in combination with a threshold value, an actual value and a prediction value, calculating a link fault probability, and completing diagnosis. According to the invention, monitoring adaptability and accuracy can be improved, compensation in advance and accurate fault early warning are realized, and stable operation and test accuracy of equipment are guaranteed.

The invention discloses a diesel generator turn-to-turn short circuit fault protection method and system based on multi-parameter characteristics, and relates to the technical field of intelligent fault diagnosis of power equipment, and the method comprises the steps: carrying out the feature extraction of operation state monitoring data, carrying out the integration according to a time sequence, and generating a real-time feature sequence set; performing spatio-temporal feature coding and fusion on the real-time feature sequence set to generate a multi-dimensional spatio-temporal feature map; mapping the comprehensive matching score set into fault confidence according to a linear relation, obtaining a fault confidence sequence, judging a fault level in combination with a characteristic amplitude overrun condition, and generating a fault diagnosis result set; and executing hierarchical response based on the fault diagnosis result set, generating a hierarchical protection action execution record, and generating a short-circuit fault protection report in combination with the fault diagnosis result set. According to the method, quantitative similarity analysis of real-time features and standard modes is realized, the fault probability is accurately evaluated through a multi-parameter weighted fusion mechanism, and the reliability and interpretability of a diagnosis result are improved.

The invention discloses a printing equipment fault detection method, equipment, a medium and a product, which are applied to the field of artificial intelligence, and comprise the following steps: collecting hardware parameters and software parameters of target printing equipment, and generating target equipment characteristics based on the hardware parameters and the software parameters; inputting the target equipment features into a pre-trained fault detection model to obtain a fault probability output by the fault detection model; and determining a target fault level according to the fault probability, and calling a target standard process in the maintenance strategy library based on the target fault level. By collecting parameters and generating target equipment features, equipment operation state information can be comprehensively captured, and multi-dimensional data support is provided for fault detection. The fault probability is determined through the fault detection model, quantitative evaluation of the fault probability can be realized by means of the advantage of double-model fusion, and the prediction accuracy is improved. By determining the target fault level and calling the corresponding standard process, hierarchical management and accurate operation and maintenance are realized, and the equipment maintenance efficiency and reliability are improved.

The invention discloses a fault analysis method and system for an intelligent power distribution network, and relates to the technical field of power distribution network fault diagnosis, and the key points of the technical scheme comprise the following steps: determining a target region which needs fault analysis and comprises a target detection node in the intelligent power distribution network, collecting network topology data, environment parameters and historical fault data of the target area in the historical period; extracting a target detection node as well as a first adjacent node and a second adjacent node which are distributed adjacent to the target detection node from the target area; according to the network topology data, the environmental parameters and the historical fault data, extracting a regional association factor influencing the fault diffusion range of the first adjacent node and the second adjacent node; and predicting the operation condition of the target detection node in the current period according to the operation fluctuation condition of the target detection node in different historical periods to obtain a current state prediction value. The method has the effect of accurately analyzing the operation state and fault probability of the target detection node and the adjacent nodes.

The invention relates to the technical field of cableway fault monitoring, solves the technical problems that in the prior art, the difference between a fault prediction result and the reality is large, nonlinear data is difficult to predict accurately, and the prediction result is inaccurate, and particularly relates to a cableway monitoring management method and system based on artificial intelligence and edge calculation. The method comprises the following steps: S1, obtaining original data of a cableway monitoring system, preprocessing the original data to obtain alignment data, capturing dynamic features through time sequence dependence, providing feature importance interpretation, organically combining time sequence prediction and feature contribution by a weighted fusion mechanism to generate health indexes, and obtaining health indexes of the cableway monitoring system; and the continuous health state can be mapped into a quantifiable fault probability, and finally real-time early warning is realized through threshold triggering, so that the interpretability of a model output result is improved, independent optimization and fault traceability are supported, and the prediction precision and the reliability of operation and maintenance decision are remarkably improved.

The invention relates to the technical field of power distribution network fault monitoring, in particular to a fault recognition method and system based on an intelligent fusion terminal, and the method comprises the steps: obtaining an instantaneous multi-dimensional electrical data set at each moment, and constructing an input sample with the current moment as an end point, inputting the input sample into the trained long-short-term memory model to calculate a first fault probability of the input sample; inputting the input sample into a trained optimal fuzzy clustering model to calculate a second fault probability of the input sample; and distributing respective weights for an output result of the long and short term memory model and an output result of the optimal fuzzy clustering model, carrying out weighted fusion on the first fault probability and the second fault probability to obtain a comprehensive fault probability of the input sample, and judging whether the power distribution network has a fault according to the comprehensive fault probability. According to the invention, through multi-source information fusion, model collaborative optimization and dynamic weight distribution, the fault identification precision and response speed of the power distribution network under complex conditions are effectively improved.

The invention discloses a fault detection method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of data processing. The method comprises the steps that under the condition that a target system breaks down, fault warning information and a target knowledge graph of the target system are acquired, and the target knowledge graph comprises a plurality of nodes, potential fault probabilities of the nodes, fault propagation probabilities and edges between the nodes; determining a fault sub-graph of the target system according to the fault alarm information and the target knowledge graph, wherein the fault sub-graph is a sub-graph composed of abnormal nodes in a plurality of nodes in the target knowledge graph; and determining a root cause node in the plurality of abnormal nodes according to the association relationship of the plurality of abnormal nodes in the fault sub-graph, the potential fault probability and the fault propagation probability, and generating and displaying a fault root cause analysis result according to the root cause node and the target fault root cause probability thereof so as to efficiently and accurately determine the fault root cause.

The invention discloses an equipment fault diagnosis method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence. The pre-training joint reasoning model is used for comprehensively analyzing the multi-dimensional data to generate an equipment fault probability prediction result, a composite fault mode can be effectively recognized, dynamic working condition changes can be adapted, meanwhile, tracing analysis is conducted on a fault propagation path in combination with the graph neural network, the effectiveness of feature extraction and modeling is improved, and therefore the fault probability prediction result is obtained. The technical problems that in an existing equipment fault diagnosis system, a threshold model is difficult to recognize a composite fault, a physical model cannot adapt to a dynamic working condition, and the fault traceability of a correlation analysis model is limited can be solved, and the purposes of improving the accuracy and adaptability of equipment fault diagnosis, enhancing the fault traceability and improving the reliability of equipment fault diagnosis are achieved. And the technical effect of promoting predictive maintenance to develop to higher-level intellectualization is achieved.

The invention relates to the related technical field of robot fault detection, in particular to an industrial robot real-time fault detection method and system, and the method comprises the steps: analyzing the operation state of an industrial robot based on a communication state signal, determining a motion domain and sensing domain synchronization factor, configuring a cross-domain feature vector and a performance feature vector, and carrying out the fusion, the deep belief network is used for drawing up the fault probability graph and identifying the feature identifier to achieve fault reminding, the technical problems that a fault response strategy is fixed, complex and changeable industrial scene requirements are difficult to adapt, and fault reminding cannot be effectively conducted in time are solved, cross-domain feature vectors and performance feature vectors are constructed, and the fault reminding efficiency is improved. The method has the technical effects that the serial control sequence is dynamically verified, multi-scale decomposition is combined, signal delay fluctuation and retransmission frequency are accurately extracted, a deep belief network is used for fusing time sequence and spatial features to identify fault types, fault reminding is carried out through a fault probability distribution map, and the operation safety of the industrial robot is guaranteed.

The invention discloses a disk fault prediction method and device, and relates to the technical field of data processing, and the method comprises the steps: obtaining the target feature data of a target disk, and predicting the fault probability of the target disk in a future target time period through a preset disk fault prediction model according to the target feature data of the target disk, outputting the target prediction probability, predicting the fault probability of the target disk in the future target time period, and determining the feature contribution degree of each feature data based on a preset disk fault prediction model and the target feature data when the target prediction probability is determined to be greater than a first preset threshold value; furthermore, a preset fault analysis model is adopted to determine a target fault reason according to the target feature data and the feature contribution degree of each feature data, and the target fault reason is sent to the client, so that a user can grasp the running state of the target disk and the fault reason of which the fault probability exceeds a threshold value in advance, and the interpretability of the disk fault is improved.

The invention relates to the technical field of supercomputing system operation and maintenance, and discloses a method for resetting an intelligent operating system of a supercomputing system node, which comprises the following steps of: 101, acquiring data of each computing node of a supercomputing system in real time, transmitting the data to a monitoring center through an RDMA (Remote Direct Memory Access) high-speed network for retention to form historical operating data, the historical operation data comprises historical index time sequence data and historical fault label data; 102, a three-dimensional array is generated in the historical operation data through a sliding window method, the three-dimensional array comprises sample information, time information and feature information, and the information in the three-dimensional array is spliced in sequence; and step 103, constructing a fault prediction model, inputting the three-dimensional array into the fault prediction model, and outputting a fault probability by the fault prediction model. According to the method, the fault prediction model is constructed, the node data of the supercomputing system is collected and processed in real time, the fault occurrence probability can be predicted, and an intelligent decision basis is provided for resetting of the supercomputing node operating system.

The invention discloses an automatic instrument fault prediction method based on fuzzy logic, and belongs to the technical field of industrial automation and equipment fault diagnosis. Comprising the following steps: generating a preprocessed sensor data set; constructing a feature space fusing multi-dimensional information; constructing a three-layer fuzzy reasoning architecture comprising an input layer, a reasoning layer and an output layer; mapping membership function parameters and rule weights in the three-layer fuzzy reasoning architecture into a parameter optimization space comprising a parameter adjustment action, a rule weight optimization action and a reasoning structure adjustment action; self-adaptive adjustment of the membership function parameters is achieved; and calculating the fault probability according to the current optimized membership function parameter, and evaluating the optimization effect of the current parameter configuration in combination with the multi-target reward function. According to the method, through combination of multi-time window dynamic monitoring, multi-type membership function design and a strict hard-soft constraint mechanism, accurate evaluation and stable prediction of the equipment fault probability are realized.

The present application relates to the technical field of computers, and in particular to a fault root cause locating method, a fault root cause positioning system implementing the method, and a computer-readable storage medium and a computer program product. The method comprises: acquiring an architecture topology graph and abnormal alarm information of an application system; on the basis of the architecture topology graph and the abnormal alarm information, constructing a troubleshooting logical tree, wherein in the troubleshooting logical tree, a logical relationship between nodes is used to indicate a potential fault propagation link between configuration components in the architecture topology graph; performing qualitative analysis on the troubleshooting logical tree, so as to identify a potential fault point that causes a fault; performing quantitative analysis on the troubleshooting logical tree, so as to calculate a fault probability and the degree of influence of each potential fault point; and on the basis of results of the qualitative analysis and the quantitative analysis, determining a root cause fault point, and acquiring a fault propagation link of the root cause fault point.

The invention discloses a fault diagnosis and self-healing control method, system, equipment and medium for a flexible interconnection device of a power distribution network, and belongs to the technical field of fault diagnosis and control of the power distribution network, and the method comprises the steps: building a system state vector, collecting operation parameters of the power distribution network, and carrying out the weighted fusion; performing quality inspection on the original data based on the acquired operation parameters, and dynamically adjusting model parameters through digital twin synchronization and model parameter updating; deep learning is carried out to carry out multi-level fault feature extraction, and multi-scale feature fusion is carried out; a fault mode identification module is started, and fault probability is calculated for fault classification; evaluating the severity of the fault according to a fault diagnosis result, selecting an optimal control strategy, and carrying out self-healing control; and fault early warning is started to estimate a future fault occurrence probability, and early warning information of different levels is issued to perform preventive maintenance. According to the invention, full-process automation and intelligentization from data perception and intelligent diagnosis to active control and prospective maintenance are realized.

The invention discloses a port equipment fault early warning method based on multi-source heterogeneous data and related equipment, and relates to the field of port equipment fault early warning. Sensor time sequence data, operation task data, maintenance log text and equipment image data are subjected to synchronous association and joint modeling, so that the defect of one-sided fault feature representation caused by isolated utilization of a single data source in the prior art is overcome, and organic unification of a multi-dimensional state and deep internal relation mining are realized; and the recognition capability of the model on early weak fault features and the basic credibility of fault probability prediction are remarkably improved.

The invention discloses an all-working-condition simulation method fusing fault prompt words and time evolution fault data, and belongs to the technical field of wind power simulation, and the method comprises the steps: generating a thermodynamic diagram of a detection point through a physical field simulation model according to equipment and operation working conditions of a wind generating set; according to the original text of the maintenance log of the wind power plant, performing analysis processing through a semantic knowledge model to obtain fault semantics; unifying the thermodynamic diagram and the fault semantics into a shared space, and constructing a fault knowledge memory pool; querying a fault knowledge memory pool according to the thermodynamic diagram to generate a prompt vector, and performing fault prediction according to the prompt vector to obtain a fault probability; and carrying out dynamic weighted fusion on the fault probability and the fault semantics through attention to obtain a fault diagnosis decision covered by all working conditions of the wind generating set. According to the method, all working conditions of the wind power plant are simulated according to physical field fault data and fault semantics, and fault priori knowledge and key information are provided by using fault cues.

The invention discloses a dew-point meter measurement data processing method and equipment, relates to the technical field of industrial automatic measurement and control and fault diagnosis, and aims to construct a dynamic sensing window with a variable form to preprocess dew-point meter time sequence data, calculate fault probability entropy in real time and detect instantaneous abnormality. And a window form is decided in combination with the fault-window form mapping library, and adaptive switching is carried out to obtain an anomaly recognition result. And selecting a corresponding algorithm from the correction strategy library to correct the abnormity. According to the method, a dynamic sensing window with a variable form is constructed, and adaptive switching among panoramic, sniping and multi-focus forms is realized by taking the fault probability entropy calculated in real time as a drive. By means of a built-in fault-window form mapping library, abnormal symptoms and fault physical mechanisms are associated, multiple concurrent faults are separated, root causes are deduced, and decision space explosion is avoided. And on the basis of a diagnosis result, a correction strategy library targeted algorithm is called to correct abnormity, and an identification-diagnosis-correction intelligent closed loop is formed.

The invention provides a fault diagnosis method and system based on brake noise feature analysis, and belongs to the technical field of fault diagnos.The method comprises the steps that multi-modal sensing data in the braking process is obtained and preprocessed; feature extraction is carried out on the preprocessed multi-modal sensing data to obtain a braking noise signal feature vector, a brake vibration signal feature vector and a working condition parameter signal feature vector, then fusion is carried out, a deep fusion feature vector including context information is generated, a fault diagnosis model is input, and a fault diagnosis result is obtained. Obtaining an initial fault probability corresponding to each fault mode; in response to the condition that at least one initial fault probability is greater than a preset fault threshold, generating a candidate fault state set; and if a certain fault state in the candidate fault state set continuously appears in continuous N sampling moments and the trend stability of the corresponding fault probability sequence is greater than a preset stability threshold, determining the fault state as a final fault state at the current moment.

The invention relates to the field of fault analysis, and discloses an electrical equipment fault analysis method and system based on big data. The method comprises the following steps: extracting a starting current spectrum and a steady-state current spectrum in a non-salt-fog environment from a historical library, and training corresponding fault diagnosis models by using a one-dimensional convolutional neural network and a two-dimensional convolutional neural network respectively; the method comprises the following steps: acquiring a real-time starting current frequency spectrum, environmental parameters, equipment operation duration, salt mist corrosion characteristic parameters and conductive ion conductivity parameters, compensating the real-time starting current frequency spectrum, eliminating pseudo harmonic peaks and baseline offset distortion caused by corrosion of copper ions by salt mist and corrosion products thereof, and obtaining a compensated starting current frequency spectrum; in the starting stage, the fault probability weight is identified through full-frequency scanning, and FPGA resources are dynamically allocated; and acquiring a steady-state frequency spectrum for fault detection in an operation stage. According to the method, the influence caused by the salt mist environment is eliminated, the fault misjudgment rate is reduced, and the resource occupancy rate is reduced.

The invention discloses a fault prediction method and device for a numerical control machine tool, and the method and device have the following advantages: collecting various types of data, including multi-source process parameter data and processing image data, comprehensively covering all aspects of the operation of the numerical control machine tool, fully mining the data value through an innovative data preprocessing and feature extraction method, and improving the fault prediction efficiency of the numerical control machine tool. The operation state of the machine tool can be described more accurately, and fault prediction accuracy is improved; a unique dynamic space-time attention network architecture can adaptively focus key space-time characteristics, capture dynamic association between data and early-stage weak symptoms of faults, and is more sensitive to perception of fault characteristics, so that the prediction performance is improved; fusing fault probabilities: fusing the two output probabilities to obtain a result, and keeping stable prediction precision under different machine tools and working conditions; and multi-stage early warning and decision support: multi-stage fault early warning and detailed fault reason analysis reports and maintenance suggestions provide all-around decision support for enterprises, and reduce production loss and maintenance cost.

The invention relates to a safe atomic power fault detection self-healing method and device, electronic equipment and a storage medium, which are applied to the technical field of system security, and the method comprises the following steps: obtaining index data of a target instance; analyzing the index data, and determining current fault information; inputting the index data into a risk prediction model for fault prediction to obtain predicted fault information, the predicted fault information comprising a fault probability and a risk index; if the current fault information comprises an abnormal index and / or the fault probability is greater than a preset fault probability, determining a target fault type based on the abnormal index and / or the risk index; determining a fault level based on the target fault type; and determining a fault self-healing strategy based on the fault level. The method has the effect of improving the timeliness and accuracy of safe atomic power fault detection self-healing.

The application discloses a cross-working condition control equipment fault detection system based on causal correction and full-space modeling. The system comprises a control equipment detection instrument, a control equipment fault database, a data processing module, a full-space fault modeling module, a causal correction module and a control equipment fault display and control module. The full-space modeling module and the causal correction module respectively solve the problems of data sparsity and sample selection bias existing in traditional methods, and are intended to realize unbiased estimation of fault probability under multiple working conditions.

The application relates to the technical field of fault diagnosis, and provides a high-frequency transformer fault diagnosis method and system, which comprises the following steps: collecting a target signal with a time stamp and extracting corresponding features, simultaneously relying on a transformer structure, material parameters and physical rules to build a digital twin model, simulating insulation and structure degradation equivalent working conditions, solving multi-physical field data and generating multi-physical field mechanism samples; then, the mechanism samples and field measured data are fused through a generative adversarial network to expand the fault sample data set and solve the sample scarcity problem; in the running stage, the digital twin model is updated in real time through parameter online inversion, a feature dynamic graph representing multi-physical coupling is constructed by combining the parameter deviation of internal mechanism degradation and the multi-source features of external working conditions, finally, the feature aggregation and time sequence reasoning are completed through the graph neural network and the time sequence neural network trained offline, the fault probability is output, and the optimal diagnosis result is determined; thereby, the fault recognition accuracy and the robustness in the running stage are improved.

This invention provides a fault identification method for test equipment based on diagnostic semantic adaptation, belonging to the field of test equipment operation status monitoring technology. It includes: S1, collecting multi-measurement channel sensor signals and image information generated during the test and performing preprocessing; S2, performing measurement channel mapping, unit conversion, range matching, and normalization processing on multi-source asynchronous data; S3, determining the fault probability of the test equipment, obtaining the fused fault confidence level, and generating a structured test equipment fault diagnosis record package; S4, analyzing the fault types of the test equipment and executing the test equipment fault identification alarm program. This invention uses an edge-side temporal fault discrimination network to perform real-time fault screening on a unified state vector, and employs a multimodal transfer diagnostic network for fault verification and incremental learning, forming a parameter optimization closed loop to improve the accuracy and robustness of fault identification.

The application provides a method and device for analyzing faults of industrial power supply maintenance equipment. The method provided by the application comprises the following steps: determining historical faults of the industrial power supply maintenance equipment; screening root nodes of fault trees from the historical faults; determining associated components and external conditions of faults for each root node of the fault trees; taking each associated object in the associated components and the external conditions as a fault tree child node under the root node for each root node of the fault trees, and constructing a fault tree of the industrial power supply maintenance equipment, wherein a state of the associated object is taken as a state value of the fault tree child node; calculating an importance weight of each part according to a working principle of the industrial power supply maintenance equipment; calculating a fault probability of each root node of the fault tree based on the importance weight, and predicting a fault occurrence situation of the industrial power supply maintenance equipment. The method realizes comprehensive construction of the fault tree and accurate prediction of the fault occurrence.

The present application belongs to the field of marine hydraulic system, and particularly relates to a marine hydraulic system fault diagnosis system and device, comprising the following steps: constructing a knowledge base based on a fault tree structure; obtaining fault phenomenon description keywords and performing a first matching with the knowledge base; based on the first matching result and the first reasoning fault diagnosis result, continuing to obtain fault phenomenon description keywords and performing a second matching with the knowledge base; repeating the steps until a component-level fault is matched, then outputting the fault diagnosis result and recording it into weight analysis. The present application can greatly improve the diagnosis efficiency and accuracy based on fault tree and fault probability matching and reasoning. The present application has high integration and is convenient to carry; non-invasive measuring elements are adopted, which can non-contact measure sound emission, vibration, rotating speed, temperature and other signals, and can intelligently judge the fault according to the signals. Moreover, the present application can reduce the dependence on related personnel and reduce the difficulty of marine hydraulic system fault diagnosis.