438results about How to "Improve fault diagnosis efficiency" patented technology

The invention relates to a multifunctional comprehensive type electric control automobile fault diagnosis system. The multifunctional comprehensive type electric control automobile fault diagnosis system comprises a vehicle-mounted network, a vehicle communication interface (VCI) system and personal computer (PC) diagnosis software. The system comprises two working modes: an off-line mode and an on-line mode. Under the off-line mode, the VCI system is connected with the vehicle-mounted network; fault diagnosis of a plurality of protocols and different module types is realized by the VCI system; functions of reading a fault code, removing the fault code, reading a frozen frame, reading a data stream and reading module information are realized; a diagnosis result is displayed by a liquid crystal display screen; and a function of storing diagnosis data is achieved. Under the on-line mode, the VCI system is connected with the vehicle-mounted network; the PC diagnosis software is connectedwith the VCI system; and the fault diagnosis of the plurality of protocols is realized. Besides the functions provided by a diagnosis protocol, a diagnosis application module also provides functions of monitoring data of the vehicle-mounted network and generating a diagnosis result report.

An equipment fault diagnosis method successively comprises fault diagnosis training steps and fault diagnosis operation steps. The method focuses on a data form characteristic essence and combines a multi-dimensional segmentation fitting algorithm and an optimized dynamic time warping algorithm based on equipment fault data to carry out pattern expression of modeling and distance threshold extraction, and extract form characteristics from the found equipment abnormity data to carry out mode matching, so that an equipment data fault type can be identified and a reason diagnosis function is realized. In this way, the difficulties in current fault diagnosis technologies that similarity degrees among the fault data can hardly be described efficiently and accurately can be solved.

The invention provides a photovoltaic module fault diagnosis method of a deep convolution generative adversarial network. The method comprises the steps of establishing a mathematical model of a photovoltaic module; carrying out fault image acquisition on the photovoltaic module; setting a part of fault data as a training sample; constructing a training model of the deep convolutional adversarialnetwork; the generator G inputting a noise vector and outputting a pseudo image through a deconvolution layer; the discriminator D inputting a real sample and a pseudo sample, extracting convolution features through convolution operation, and obtaining the probability of the real sample; optimizing a weight parameter through a back propagation algorithm, then starting the next cycle, and outputting a test image every 300 cycles; and inputting the real sample and the obtained test sample into a classifier to classify fault types, thereby realizing fault diagnosis. According to the fault diagnosis method, a large number of fault pictures are generated by using the deep convolutional network, and a fault image database is expanded, so that fault classification is more detailed, and fault diagnosis is more accurate.

The invention relates to a rules-based intelligent system for grid fault diagnosis, comprising a real-time data acquisition module, a data receiver, a preprocessing module, a working database, a knowledge base, an inference engine and a command generator. The real-time data acquisition module acquires real-time data information of a grid and sends it to the data receiver; the data receiver performs reasonableness testing and encoding; the preprocessing module performs formatting and information fusing and sorting and stores the information in the working database; the working database sends a command to the inference engine; the inference engine sends an inference verification request to the knowledge base; the knowledge base acquires data from the working database and performs data matching on the basis of a grid CIM (common information model) according to knowledge rules in the knowledge base built; the inference engine performs inference analysis according to the data in the working database, system state and knowledge in the knowledge base. The system has the advantages that a self-learning function is achieved, checking and error correcting is facilitated and grid fault diagnosis is more efficient.

The invention provides a device fault reporting and fault diagnosis method and system. The method comprises steps: S1, a fault reporting terminal transmits comprehensive fault information of an intelligent device to a cloud server according to a preset fault reporting mode; S2, according to a preset fault analysis rule, the cloud server analyzes the comprehensive fault information of the intelligent device and a corresponding maintenance scheme is acquired from the database of the cloud server; and S3, the cloud server returns the maintenance scheme generated in the step S2 to the fault reporting terminal. fault reporting mode in various channels such as automatic fault reporting, code scanning fault reporting and purely manual fault reporting are adopted, fault reporting under various conditions of the intelligent device can be realized, and according to the received comprehensive fault information, multiple diagnosis methods such as high-precision feature information matching retrieval, rule engine and text similarity comparison rule are adopted, a maintenance scheme with strong pertinency can be acquired as much as possible, and a user and an engineer can perform accurate and efficient maintenance conveniently.

The invention discloses a system for quantitative management of software defects, which comprises a defect prediction and evaluation module, a process fault diagnosis module and a software defect mending cost estimating module. The defect prediction and evaluation module is used for evaluating and predicting the amount of software defects. The process fault diagnosis module is used for simulating the propagation process of software process faults, expressing fuzzy fault knowledge and providing a target-drive-oriented backward reasoning mechanism and software product fault diagnosis. The software defect mending cost estimating module is used for researching a defect mending cost predicting method so as to calculate mending cost and accurately estimate the defect mending cost. By the system, intelligent evaluation on software defects is realized, efficiency and accuracy in software process fault diagnosis are improved, software process is more controllable, and development process is more highly mature.

The invention discloses an equipment fault diagnosis method based on multidimensional segmentation fitting. The method successively comprises a fault diagnosis training step and a fault diagnosis operation step. The method realizes mode expression and distance threshold extraction functions of modeling through combining a multidimensional segmentation fitting algorithm and an optimized dynamic time bending algorithm by focusing on the essence of data form characteristics on the basis of equipment fault data, and realizes equipment data fault type identification and cause diagnosis functions by performing mode coupling through extracting form characteristics of discovered equipment abnormal data, thereby solving the problem of incapability of efficiently and accurately describing the similarity degree between fault data by use of a conventional fault diagnosis technology.

The invention discloses a neural network-based subway train fault diagnosis device and a neural network-based subway train fault diagnosis method. A lower computer classifies acquired subway train state information according to a functional unit, concentrates and summarizes data, and sends the data to an upper computer; the upper computer receives, processes and stores the subway train state data summarized by the lower computer; the upper computer comprises a data acquisition module and a neural network module; the data acquisition module finishes the classification of the acquired subway train state data; the lower computer acquires real-time data information of a subway train; and when the subway train fails or is to fail, the neural network module of the upper computer performs corresponding judgment and pre-judgment according to the output of a radial basis function neural network established during training and outputs fault information to a fault diagnosis result module. By the embodiment of the invention, the technical problems of insufficient acquired and analyzed data volume, low data processing efficiency and a complicated calculation process in the prior art can be well solved.

The invention discloses a method for analyzing and diagnosing failure. The method comprises the following steps: acquiring failure diagnosing information and data information of the adopted analysis method, wherein the failure diagnosing information comprises a diagnosing object and a failure reason; providing the failure diagnosing information for a maintenance terminal, and receiving feedback information determining whether the failure diagnosing information is correct from the maintenance terminal; and according to the feedback information, counting and storing the data information comprising the analysis method and the failure diagnosing information. In addition, the invention also discloses a system for analyzing and diagnosing the failure. The technical proposal can improve the efficiency of analyzing and diagnosing the failure.

A box-type substation intelligent online failure diagnosis system comprises an electric parameter collection module, a non-electric-parameter collection module, a switch value collection module, a data processing module, a micro-processor module, a failure diagnosis module, a high-voltage switch cabinet failure tree, a transformer room failure tree, a low-voltage switch box failure tree, a GPRS module, a monitoring center, a data output module and a warning module. The substation intelligent online failure diagnosis system has the advantages that operation state data of a box-type substation in real time can be collected and warnings are given out if abnormal-condition data occur so that workers can predict probable failures; failure symptom data can be timely and precisely collected so that online failure diagnosis can be carried out, the failures can be timely eliminated, and failure diagnosis efficiency is improved; a failure diagnosis method based on a failure tree analysis method is adopted, searching efficiency of failure diagnosis knowledge is improved, meanwhile readability of the failure diagnosis knowledge is also improved, and maintenance of failure diagnosis procedures is facilitated.

The invention discloses an intelligent gear defect analysis method based on fractional wavelet transform and a BP neutral network. The intelligent gear defect analysis method includes: taking transform order as a variable to perform fractional Fourier transform on gear vibration signals to determine optimal order, and performing fractional wavelet transform on the gear vibration signals under the optimal order for denoising to realize separation of useful component and background noise of the gear vibration signals; calculating feature parameters of the signals after being denoised to form a group of feature vectors which are used for representing features of gear vibration after denoising; averagely dividing the feature vectors into two groups which serve as a training sample and a testing sample respectively, and inputting the feature vectors into the BP neutral network for learning and classifying. By the intelligent gear defect analysis method, background noise mixed in the gear meshing vibration signals is inhibited well, useful signal component related to defects is retained, and gear defect features can be extracted effectively; self learning and classifying capability of the BP neutral network is utilized, so that defect mode of gears can be quickly recognized qualitatively with high accuracy.

The invention belongs to the field of transformer fault diagnosis, and particularly relates to a transformer fault diagnosis system and method based on digital twinning, the transformer fault diagnosis system is composed of a physical system module, a digital twinning module and a fault diagnosis module, and the method specifically comprises the following steps: creating a three-dimensional model of the transformer by using the physical system module and acquiring transformer operation state data acquired by a sensor; using the digital twinning module to create a transformer digital twinning model, and generating analog data and calibration of the digital twinning model; and performing fault diagnosis of the transformer by using the fault diagnosis module. According to the invention, the physical entity of the transformer is combined with the virtual model, the digital twin model is corrected according to the state monitoring data obtained by the sensor and the simulation data of the twin model, the characteristic parameters are extracted, and the fault type is diagnosed by using the BP neural network algorithm. The possible reasons of the fault are analyzed, the maintenance cost and period of the transformer are reduced, the fault diagnosis efficiency is improved, and the transformer can operate safely and reliably.

The invention provides diagnosis method and device for an electrifying fault of a computer motherboard. The method comprises the steps of supplying power to the motherboard and determining whether a programmable logic chip works; if so, outputting at least one enable signal which is sequenced according to a preset time sequence according to the connection condition of the programmable logic chip and a plurality of power conversion chips so as to enable the power conversion chips to work; detecting level switching signals output by the plurality of power conversion chips through the programmable logic chip; determining the work from a circuit which generate the at least one enable signal to circuits between the successful level conversion signals of the corresponding power conversion chips is normal if the level conversion signals are valid, and otherwise, determining that the fault occurs in the circuit section. With the adoption of the diagnosis method for the electrifying fault of the computer motherboard, the difficulty and workload at the repair of the motherboard can be greatly decreased; the diagnosis method is fast and convenient; the fault can be accurately located to the level of some circuit generating the level signal.

The invention discloses a transformer fault diagnosis method, and the method comprises the steps: step1, a vibration signal of a transformer is acquired, and noise reduction preprocessing is performed on the vibration signal; step2, EMD decomposition is performed, obtained IMF components are selected according to set critical values, so that the IMF components with low amplitude are removed can be prevented; step3, wavelet analysis is performed, and feature vectors after de-noising are obtained; step4, a three layers BP neural system is constructed, feature vectors extracted from the wavelet analysis serves as input vectors of BP neural network training to train, and a fault signal is outputted. According to the invention, methods such as the wavelet analysis and the like are adopted to remove interference signal in the fault signal, transformer internal fault occurrence and development multi-process and multi-fault multiple modes are diagnosed through the neural network, the transformer fault can be quickly and accurately diagnosed, the fault diagnosis efficiency is improved, the service life of the transformer is prolonged, the unnecessary costs is reduced, and the cost is saved.

The invention discloses a method for analyzing analog circuit fault propagation characteristics, comprising the following steps of: acquiring circuit response curve clusters under the condition that each analog circuit node is normal and circuit response curve clusters under the node fault state; dividing the fault mode according to the matched degree of the circuit response curve clusters under the node fault state and the circuit response curve clusters under the normal condition; constructing an analog circuit fault propagation network according to the fault mode; calculating the clustering coefficient C and average characteristic path length of the analog circuit fault propagation network; and calculating the degree distribution of the analog circuit fault propagation network and then selecting measurable points according to the degree distribution. The invention carries out preference on the measurable points of a fault circuit according to the scale-free network characteristic and the non-uniformity characteristic which are showed by the circuit fault propagation characteristics, thereby further increasing the fault diagnosis efficiency and accuracy degree.

The invention discloses a gear machining surface topography analytical method based on a gear machining simulation model. The gear machining surface topography analytical method is characterized by establishing the simulation model based on the gear grinding machining, obtaining an ordinary process of processing a gear surface topography simulation model through deduction, substituting dynamic information of an axis of movement collected by simulation or a sensor installed inside a machine tool during the processing of gear grinding, and obtaining the simulated gear grinding processing surface topography. The gear machining surface topography analytical method based on the gear machining simulation model is used for predication of gear grinding surface quality and is further used for quantitative evaluation of influence of the axis of movement on the gear grinding surface quality, and tracing of the errors of gear working accuracy and surface waviness and roughness and provides a theoretical basis and an implementation method of gear grinding surface quality and fault diagnosis efficiency of a gear grinder.

The invention discloses a power transformer fault diagnosis method based on acoustic characteristics and a neural network, and the method comprises the following steps: employing a sound collection device to collect and obtain sound signals when a power transformer is in each state, and recording the corresponding relation between the collected sound signals and each state of the power transformer; preprocessing the acquired sound signals; Establishing and training a GRU neural network model; and collecting a sound signal of the power transformer to be diagnosed, preprocessing the sound signal, inputting the preprocessed sound signal into the trained GRU neural network model, and completing fault diagnosis of the power transformer to be diagnosed according to an output result of the GRU neural network model. According to the method, the frequency domain characteristics of the power transformer are extracted from the sound signals generated when the power transformer runs, the frequencydomain characteristics of the power transformer are used for training the threshold circulation unit neural network, operation is relatively simple, cost is low, and online monitoring is easy to achieve.

The invention provides a fan gear box fault diagnosis model establishing method used for establishing a fan gear box fault diagnosis model. The method comprises a step of obtaining a vibration signal of a fan gear box and then carrying out smoothing and denoising processing on the vibration signal, a step of decomposing the processed vibration signal and extracting the characteristic vector of the vibration signal, a step of dividing the characteristic vector of the vibration signal into a training data set and a testing data set, and a step of using a Drosophila algorithm to optimize a parameter of a radial basis function (RBF) neural network model, inputting the characteristic vector of the vibration signal in the training data set to obtain the optimal value of the parameter, generating the fan gear box fault diagnosis model based on a radial basis function neural network and carrying out test. In the scheme, the optimization algorithm is introduced for the characteristic of the RBF neural network, through introducing the artificial intelligence analysis technology, the extracted characteristic value is processed further, thus the efficiency of fault diagnosis is improved, and stop losses caused by faults are reduced.

The embodiment of the invention provides a remote diagnosis method and system for network equipment, the network equipment and a cloud server. The remote diagnosis method of the network equipment comprises the steps that function configuration is carried out according to an acquisition task defined by a cloud server, and the acquisition task is a task determined by the cloud server according to afault diagnosis rule in an expert knowledge base; diagnosis data is acquired according to the function configuration; and the diagnosis data is sent to the cloud server, so that the cloud server analyzes the diagnosis equipment according to the fault diagnosis rule to judge whether the network equipment is abnormal or has a fault. The method is used for solving the technical problems that an existing remote network diagnosis method is not flexible enough and low in diagnosis efficiency.

The invention discloses a method for analyzing reliability of a turbine blade disk system of an aircraft engine. The method comprises the following steps of: establishing a system chart; establishing a system dynamic bayesian network and a system failure-mode dynamic bayesian network model; discretizing and transforming the dynamic bayesian network into multiple static bayesian networks; structurally decomposing the static bayesian networks into simply-connected regional networks and multiply-connected regional networks; performing bidirectional derivation on the simply-connected regional networks by a static bayesian network inference method; and performing bidirectional derivation on the multiply-connected regional networks by a bucket elimination method to respectively solve the failure rate of the turbine blade disk system, namely a system element, of the aircraft engine, and the fault rate of each failure mode. According to the method for analyzing the reliability of the turbine blade disk system of the aircraft engine, the problems of complicated expression, low computational efficiency, combinatorial explosion and the like, which are caused when traditional reliability analyzing methods are used for analyzing large-scaled, complicated and dynamic structures, are solved, and the computational efficiency is enhanced.

The invention relates to a wind tunnel operation fault diagnosis system based on a distributed architecture. The wind tunnel operation fault diagnosis system belongs to the technical field of aerospace ground thermal protection and insulation tests, and is used for performing real-time monitoring and state judgment on an operating state of a combustion gas flow supersonic wind tunnel test system,triggering a general control fault decision-making processing subsystem to alarm or coordinate subsystems to shut down by steps according to a set fault processing strategy when the subsystems judge that an abnormal situation occurs, effectively ensuring safety of processing equipment in the field, and guaranteeing reliable operation of the test. The wind tunnel operation fault diagnosis system provides a technical guarantee for the state monitoring and fault diagnosis of wind tunnel equipment, provides software and hardware support for stable operation of the wind tunnel system, can respond to the fault timely since a fault response speed reaches ms level, and greatly improves the efficiency and reliability of fault diagnosis.