153results about How to "Improve fault diagnosis ability" patented technology

The invention relates to a multifunctional remote fault diagnosis system for an electric control automobile. The multifunctional remote fault diagnosis system comprises a remote fault diagnosis service center, PC (Personal Computer) diagnosis client sides and a diagnosis communication device. The remote fault diagnosis service center serves as a key of the system and is mainly used for realizing an automobile fault diagnosis network management function and an automobile remote fault diagnosis assistance function; the PC diagnosis client sides are mainly used for providing specific automobile diagnosis application functions and remote diagnosis interfaces for users with different rights through human-computer interaction interfaces; and the diagnosis communication device is mainly used for realizing the data communication between the PC diagnosis client sides and a vehicle-mounted network and providing diagnosis data service for upper applications. By means of the multifunctional remote fault diagnosis system, with the remote fault diagnosis service center as a core and all PC diagnosis client sides as nodes, an automobile fault diagnosis network is established; automobile diagnosis data sharing is realized by means of the diagnosis communication device; multifunctional automobile remote fault assistance and fault elimination help can be provided; automobile fault information is subjected to statistic analysis; and a reliable automobile quality report is provided for an automobile manufacturer.

The invention discloses a fault diagnosis method of a high-voltage circuit breaker based on a depth belief network, which comprises the following steps: step 1, selecting a data sample required by anexperiment, and dividing the unified standardized sample data into a test sample and a training sample according to a specific proportion; Step 2: building and initializing the DBN deep belief networkfault diagnosis model; Step 3, inputting a large number of unlabeled samples or unlabeled samples in the pre-training set from the bottom of the model, and pre-training the RBM in the model by usinglayer-by-layer unsupervised greedy learning; Step 4: the whole model being fine-tuned by genetic algorithm; Step 5, the fault diagnosis model of the high-voltage circuit breaker obtained by training being classified to the fault samples of the test set in step 1, so as to obtain the fault classification result, and the diagnosis accuracy rate of the model being counted. The invention discloses a fault diagnosis method of a high-voltage circuit breaker based on a depth belief network, which can train a large amount of data samples to realize the fault diagnosis function of the high-voltage circuit breaker.

The invention discloses an overlay convolutional network-based rolling bearing failure mode recognition method and device, and relates to the field of rolling bearing failure diagnosis. The method comprises the following steps of: extracting a time-frequency domain feature of a vibration signal of a state-known rolling bearing; normalizing the obtained time-frequency domain feature of the state-known rolling bearing into a feature pixel according to a CNN network input format; inputting the feature pixel into a CNN network, and adjusting a model parameter of the CNN network through carrying out forward self-learning and gradient descent-based counter-propagation on the CNN network so as to obtain a trained CNN network; and during the recognition of a practical rolling bearing failure mode, extracting high-order features capable of reflecting intrinsic information layer by layer by utilizing the trained CNN network by taking a time-frequency domain feature of a vibration signal of a state-unknown rolling bearing, and inputting results of the feature self-learning into a top classifier layer by layer, so as to realize failure mode recognition of the rolling bearings under multiple working conditions and strong noises.

The invention discloses a power system fault diagnostic method based on a probability Petri net. The power system fault diagnostic method comprises the following steps of: when a power system is in fault, identifying whether fault information is true fault information or not, preprocessing the true fault information, generating a fault suspicious component library, and forming a correlated suspicious component sublibrary; extracting suspicious components in the fault suspicious component library by a monitoring center, and generating a suspicious component fault tree; establishing a probability Petri net model of outgoing lines of the suspicious components in all directions; carrying out fault diagnosis, so as to obtain fault diagnosis results; and judging fault conditions of the suspicious components corresponding to fault diagnosis results, if the suspicious components belong to the associated suspicious components, executing credibility comparison, so as to obtain fault components, and if not, regenerating the fault tree. With the adoption of the power system fault diagnostic method based on the probability Petri net, an optimal function parameter of a transition function is given based on a probability Petri net theory, the unreliability of the components is introduced, and the fault diagnosis method containing credibility evaluation is provided, so that the power system fault diagnostic method is higher in reliability and accuracy, and can be well applied in actual power grids.

The invention provides an intelligent fault diagnosis method for a numerical control machine, which comprises the following steps: (1) determining a fault characteristic parameter set, a fault type set and a sample set; (2) according to the fault characteristic parameter set and the fault type set, establishing a support vector machine model; (3) training and optimizing a support vector machine by utilizing the sample set; (4) detecting a plurality of fault characteristic parameters of the numerical control machine and using the plurality of fault characteristic parameters as a data source of fault diagnosis; and (5) inputting the data source into the optimized support vector machine to obtain a fault diagnosis result. In the invention, according to the occurrence mechanism and the characteristics of faults of parts of the numerical control machine, when the parts of the numerical control machine have the faults, the numerical control machine is detected and detection data is input into the least squares support vector machine after being processed, so that a diagnosis result can be obtained. According to the invention, the rapid and effective fault diagnosis for the numerical control machine is implemented and the intelligent fault diagnosis method also has strong fault diagnosis capacity, high diagnosis rate and low misdiagnosis rate.

The invention discloses a double-flexible-grinding-head magnetorheological polishing device. In the device, a vertical gantry of a bed body and an X-axis are both fixed on a horizontal base; a worktable is fixed on a sliding block of the X-axis; a Y-axis is fixed on a horizontal beam of the vertical gantry; and a first Z-axis and a second Z-axis are arrangedon the Y-axis in parallel. A large flexible grinding head is installed on the first Z-axis; and a small flexible grinding head is arranged on the second Z-axis. A high-flow circulation system connected with the large flexible grinding head and a low-flow circulation system connected with the small flexible grinding head are arranged on a trolley. A control cabinet is arranged at the rear part of the vertical gantry; and a circulation system cabinet and a cleaning system are arranged at the side surface of the vertical gantry. The double-flexible-grinding-head magnetorheological polishing device provided by the invention has the advantages of high accuracy, high rigidness, high stability and high dynamic property. The double-flexible-grinding-head magnetorheological polishing device not only can be used for processing of large-caliber phase elements, but also can be used for high-accuracy processing of large-caliber planar optical elements within the range of full caliber. The optimal matching of the processing efficiency and the processing accuracy can be realized.

The invention discloses a method for hierarchically diagnosing a fault of a rod-comprising oil pumping system based on an indicator diagram. The method comprises two stages, namely a fault distinguishing stage and a fault recognizing stage, and comprises the following steps of: dividing the indicator diagram into a fault class and a non-fault class according to a statistical law of the normal sample at the fault distinguishing stage; and recognizing a fault type of a fault sample by a search tree method for recognizing the fault of the rod-comprising oil pumping system based on the indicator diagram. By the method, the fault diagnosis performance of a fault diagnosis system is improved, a mechanical model of the rod-comprising oil pumping system does not need establishing or resolving, the problem of a training set is solved, and the basic features of the rod-comprising oil pumping system can be reflected.

The invention relates to a transformer fault diagnosis method based on a neural network. The method comprises the following steps: analyzing fault reasons, and extracting a sample set of dissolved gas in transformer oil and a corresponding a fault type inside a transformer; determining the number of Neurons in a neural network hidden layer according to experience and a successive optimization searching method, and building a neural network; adopting an improved Cuckoo optimization algorithm to train the neural network; and finally utilizing the trained neural network to diagnose a fault of the transformer. The entire design method has the characteristics of high search precision and high global search capability, and effectively improves the accuracy of fault diagnosis for a transformer.

The invention relates to a bearing fault mixing intelligent diagnostic method based on second generation wavelet transform and a BP neural network. The bearing fault diagnostic method based on the second generation wavelet transform and the BP neural network includes steps: firstly, using the second generation wavelet transform to resolve a bearing original vibration signal measured by a sensor; secondly, extracting time domain statistical features and frequency domain statistical features from the resolved signal so as to form a combined feature set, and then performing feature evaluation on the extracted feature set so as to obtain a sensitive feature set; using the sensitive feature set as input of the BP neural network for network training, and building a fault diagnostic model based on the BP neural network so as to achieve classification and diagnosis of faults. The bearing fault diagnostic method based on the second generation wavelet transform and the BP neural network and the fault diagnostic model based on the BP neural network are used in the classification and the diagnosis of the bearing faults, and results indicate that the bearing fault diagnostic method based on the second generation wavelet transform and the BP neural network is high in classification and diagnosis accuracy, high in speed and high in efficiency, effectively improves bearing fault diagnostic effects, and is conveniently used in engineering practice.

The invention provides an intelligent online monitoring protection device which comprises an upper computer, a display module, a communication management module, a rotation speed detection module, a key phase module, at least one vibration displacement/speed/acceleration monitoring module, a relay warning protection module and a communication back plate. A back plate bus is arranged on the communication back plate, the communication management module receives original data detected and transmitted by all the function modules and extracts characteristic data, concentrated storage and management are conducted, comparison judging is conducted on the characteristic data and a pre-set threshold range, and the threshold range reflects equipment operation data under the normal state of equipment. The relay warning protection module conducts warning through sound and/or optical signals on the basis of a judgment result of the characteristic data from the communication management module. The intelligent online monitoring protection device is wide in application range, high in data transmission speed, comprehensive in monitoring parameter and good in monitoring real-time performance, multiple channels are provided, the performance of a processor is high and a fault diagnosing function is achieved.

The invention discloses a fault detection method and fault diagnosis method for the non-stationary process of a large coal-fired generator set. The fault detection method and fault diagnosis method for the non-stationary process of a large coal-fired generator set integrate a co-integration analysis method with a sparse variable selection method for fault detection and on-line diagnosis, aiming at the classical non-stationary process of the large coal-fired generator set. The fault detection method and fault diagnosis method for the non-stationary process of a large coal-fired generator set can directly automatically isolate fault variables on line in real time, and do not need any historical fault information at the same time. The fault detection method and fault diagnosis method for the non-stationary process of a large coal-fired generator set effectively solve the problem of difficulty in fault detection and on-line diagnosis during the non-stationary process, thus greatly improving the performance of fault detection and on-line diagnosis during the non-stationary process, being conductive to accurate and quick repair of faults for a field engineer so as to guarantee safety of the large coal-fired generator set and improve the production benefit.

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 invention provides a multi-strategy fault diagnosis system for the carrier rocket test launching process. The multi-strategy fault diagnosis system comprises a data reception and processing module, a fault detection module, a fault locating module, a rule algorithm plug-in, a fault tree algorithm plug-in, a mathematic model algorithm plug-in and a fault criteria storage module. A general carrier rocket fault diagnosis and reasoning framework is established to enable object information and diagnosis strategy to be separated, thereby realizing universal service between data acquisition, data processing and fault diagnosis, providing general basis for concrete applications of different diagnosis and reasoning methods and improving system diagnosis capability.

The invention discloses a system design method for minor fault detection and position of an electrical traction system. The method comprises the following steps: 1) establishing an off-line data model: collecting sensor steady-state operation data of the electrical traction system and carrying out pretreatment on the off-line data; calculating values of a principal component and a residual component in different layers of subspaces of the data obtained after pretreatment and a load vector; determining and calculating a performance index and a probability density function of a principle component analysis method and a fault detection threshold; and 2) on-line fault diagnosis: processing online data; calculating a performance index of the principal component and the residual component in different layers of subspaces; and through the obtained fault detection threshold, constructing a probability matrix and carrying out fault diagnosis through Bayesian reasoning. The method can carry outeffective multi-feature description on tiny signals of an electrical drive device before occurrence of a fault, and can also carry out real-time online fault diagnosis under the condition that the model and parameters of the electrical drive system are unknown.

The invention discloses an industrial process fault diagnosis method for a complex fault. The method comprises the steps of collecting sample data in a normal mode and building a fault monitoring model; solving parameters by using maximum likelihood estimation, thereby obtaining probability density functions of variables i; collecting a to-be-diagnosed sample and calculating a statistical quantity; when it is detected that the fault occurs, calculating deviation factors of the variables, and performing training to obtain conditional probability density functions of the deviation factors, thereby calculating out posterior probabilities; and selecting the variable with the highest posterior probability to perform multi-dimensional reconstruction, thereby finding out the fault variable. According to the method, the calculation amount is small, and the industrial process fault diagnosis can be accurately carried out under the complex fault. The method is remarkable for an industrial process result, and effectively aims at the complex fault problems of small faults, multi-variable simultaneous faults, excessively high variable dimension and the like.

The invention discloses a six-phase permanent magnet fault-tolerant motor system power tube open-circuit fault diagnosis method. The method comprises steps of conducting park vector transformation onthe six-phase current to obtain current vectors in two orthogonal subspaces; and calculating a current vector average value in a period, realizing open-circuit fault detection of the power tube by judging whether the current vector module value average value exceeds a fault threshold or not, and realizing positioning of the fault power tube according to positive and negative polarities of the current vector real part average value and the imaginary part average value. According to the method, additional hardware equipment does not need to be added, the utilization of the zero-sequence orthogonal subspace current vector ensures strong robustness of the fault diagnosis method to the rotating speed and the load sudden change. The fault location only needs to effectively simplify the operationaccording to the positive and negative polarities of the location variable, the method can simultaneously realize the power tube open-circuit fault diagnosis of the permanent magnet fault-tolerant motor system in normal and open-circuit/short-circuit fault-tolerant operation, and the fault diagnosis capability of the permanent magnet fault-tolerant motor system in the case of primary and secondary open-circuit faults is significantly improved.

The invention relates to a DBN-based multi-dimensional time sequence information driven aeroengine gas path fault diagnosis method which comprises the following steps: collecting aeroengine ACARS data; normalization processing, using the wavelet packet transform method to extract the time sequence information of the parameters and using the dynamic time integration method to extract the correlation information between the parameters; vectorizing the time sequence information in the parameters and the correlation information between the parameters and converting the information into one-dimensional vectors; training a fault diagnosis model, wherein the fault diagnosis model firstly extracts the depth features of the input one-dimensional vectors by using BBN and then diagnoses the fault based on the results of the depth feature extraction by using SVM; using the trained fault diagnosis model to identify the faults of the engine sample features extracted from the test set; performing statistics and evaluation on the fault identification result of the fault diagnosis model; and performing fault identification on the aeroengine ACARS data by using the stored fault diagnosis model so as to obtain the diagnosis result. This method can make full use of the multi-dimensional time sequence information of data and effectively process the high-dimensional features of the data.

The invention discloses an integrated DC solid state power controller and a fault decision-making diagnosis method. The controller comprises a power board and a digital control board, wherein the power board is mainly responsible for system state detecting, conditioning, signal uploading and SSPC (Solid State Power Controller) driving and protection control; and the digital control board integrates related circuits for arc fault detection and cable fault detection and location, detects a conditioned system state signal based on multiple sensors, completes local fault diagnosis for the conventional SSPC such as fixed-time-lag power supply overvoltage-undervoltage fault protection, BIT self-checking of the SSPC, inverse-time-lag overload protection and additional local fault diagnosis such as system arc fault detection and cable fault detection and location in a concurrent manner in an FPGA main control module, and finally realizes decision-making diagnosis and health management for thesystem state based on a multi-source technology integration technology. The integrated DC solid state power controller can realize the enhanced system fault detection and health management ability, and improves the system safety, reliability, testability and maintenance.

The invention discloses interactive electronic technical manual (IETM)-based online fault diagnosis equipment and an online fault diagnosis method. The equipment comprises five parts: an IETM content database, an IETM browser, an IETM fault diagnosis engine, an IETM log database and a test execution platform. According to the invention, an IETM is used as a core and a humanized interaction interface of the IETM is utilized to encapsulate a complicated fault diagnosis process, so that it is easy for a user to use and operate; the fault diagnosis engine and a test execution platform are integrated in the IETM, thereby substantially improving the fault diagnosis capability of the IETM; the equipment has a good modularity characteristic, so that it is easy to carry out updating and replacement of the fault diagnosis engine and the test execution platform; and the diagnosis method enables process information of the fault diagnosis and test data to be completely recorded, so that it is beneficial to analyze a fault cause after the fault occurrence. Moreover, the equipment with good portability can be applied to various equipment maintenance working sites; and the equipment enables maintenance personnel to be effectively guided to remove faults, thereby improving equipment maintenance working efficiency.

The invention discloses an universal controller of a spaceflight carrier rocket, comprising a control plate, a time sequence plate and an attitude control plate, wherein the time sequence plate comprises M paths of ignition units; the attitude control plate comprises N paths of attitude control drive modules, N paths of attitude control recovery modules, pressure collection modules and remote -measuring power distribution and interruption modules; the control plate comprises a processor DSP (Digital Signal Processor), a programmable logic controller CPLD (Complex Programmable Logic Device), an isolated power supply, an analogue switch, an isolation amplifier, M paths of time sequence recovery modules, M paths of ignition recovery modules, P paths of indication input modules, M paths of time sequence drive modules, a rudder control output module, a rocket-borne CAN isolation drive module, and a ground CAN isolation drive module. The controller is characterized in that controllers in four cabins are combined into one universal controller and has the advantages of modular design, good universality and strong compatibility.

The invention provides a three-stage feature fusion rotary machine fault diagnosis method based on multi-modal data. The method comprises the steps: obtaining the operation state parameter data of a machine, and obtaining the data of at least two modals; inputting the obtained modal data into a preset neural network model to obtain a final fault classification result; wherein the preset neural network model at least sequentially comprises three stages of first self-feature fusion, mutual feature fusion and second self-feature fusion; according to the method, a three-stage feature fusion method including a one-dimensional convolutional neural network and a two-dimensional convolutional neural network is adopted, multi-scale features are fused and fault diagnosis is carried out, the two-dimensional convolutional neural network extracts correlation between feature mapping maps, an attention mechanism can carry out different weight distribution on the feature maps, and the fault diagnosis accuracy is improved. Important information is highlighted, redundant information is reduced, and the fault diagnosis performance is greatly improved.

The invention provides an aero-engine ignition control system with a monitoring device, and relates to the design technology of aero-engines. The aero-engine ignition control system with the monitoring device is used for controlling ignitor plugs of an engine, on the basis of control through a dual-redundancy ignition relay of an engine electronic controller, a path of ignition relay is added on an interface unit of the engine of aircraft equipment, the relays of each ignitor plug are increased to three, and the ignition function of the engine can be achieved through closing of each relay. The contact state and the front end input ignition voltage quality of the ignition relay installed in an EEC are monitored in real time through the EEC, the contact state and the front end input ignition voltage quality of the ignition relay in an EIU are monitored in real time through the EIU, monitored information is fed back to the EEC through a bus, and the EEC monitors the three ignition relays and outputs a merged current finally. By means of the aero-engine ignition control system with the monitoring device, the reliability of the engine ignition system is improved, testability and the fault diagnosis capability of the engine are improved, and the safety of an aircraft is enhanced.

The invention discloses a spacecraft rendezvous fault diagnosis and filter design method based on event driving, and relates to the spacecraft rendezvous fault diagnosis and filter design method. Theinvention aims to solve the problems of high bus bandwidth occupancy rate and high data transmission energy consumption in the conventional spacecraft rendezvous system. The method comprises the following steps: 1, establishing a state space model of a spacecraft rendezvous system; 2, designing a weighted fault function; 3, designing an FDF gain matrix based on dynamic event driving, and establishing an augmented residual error system under the event driving condition; 4, obtaining a residual signal and control input according to the gain matrix of the FDF; 5, designing a dynamic event drivingmechanism to enable the gain matrix obtained in the step 3 to be established; 6, designing a residual evaluation function according to the residual signal; and 7, designing a residual evaluation function threshold, and completing fault diagnosis of the spacecraft rendezvous system according to the residual evaluation function. The method is applied to the field of spacecraft rendezvous fault diagnosis and filter design.

The invention provides a driving motor fault diagnosis model construction method based on intra-class feature transfer learning and multi-source information fusion, and the method comprises the steps:firstly proposing an improved hierarchical transfer learning method MSTL, which considers the neighbor relation between intra-class samples, maintains the local manifold structure of intra-class data, also can improve the separability of the domain data subjected to transfer learning to different categories, so that the adaptability of the fault diagnosis model to different distribution domain samples is improved; meanwhile, the feature set dimension can be reduced, and the fault diagnosis performance of the fault diagnosis model under variable working conditions is improved. Besides, aimingat the problem that a certain uncertain factor exists in a signal acquired by a single sensor, the D-S evidence theory is adopted to carry out driving motor multi-source information decision-making layer fusion, and secondary D-S evidence fusion is carried out on diagnosis results of vibration and current signals on a model. According to the feature transfer learning method MSTL and the multi-source information fusion diagnosis model provided by the invention, the fault diagnosis accuracy can be improved, and the method has a certain practical value.