44results about How to "Reliable Fault Diagnosis" patented technology

The invention discloses an intelligent fault diagnosis system for an ICNI system, which can improve the maintenance efficiency, carry out intelligent and automatic diagnosis and is applicable to the ICNI system. According to the technical scheme of the invention, a knowledge base and a management module thereof carry out standardization research and mathematical modeling based on a fault tree, an SQL Server database software framework is adopted, a relational database is used for building a logic relation among a fault phenomenon, a fault mode, a detection method, a historical case and a fault tree internal event to form the knowledge base; and a diagnosis information acquisition module interacts with an automatic testing system via Ethernet to acquire diagnosis data from the ICNI system and a testing instrument, a reasoning machine module adopts CBR and RBR hybrid diagnostic reasoning, after comprehensive judgment is carried out on the fault phenomenon inputted by the user, the field knowledge stored by the knowledge base and the diagnosis data from the automatic testing system, a reasoning method is automatically selected to carry out reasoning diagnosis on the fault, a reasoning process and a reasoning result are outputted to an explanation machine module, and a diagnosis report is generated.

The invention discloses a clustering analysis-based intelligent fault diagnosis method for an antifriction bearing of a mechanical system. A diagnosis model is trained firstly, comprising the following steps: collecting standard vibration signal samples of five fault and normal bearing states of an outer ring, an inner ring, a rolling body and a holding frame; decomposing signals, extracting original vibration signals as well as time domain and frequency domain characteristics of decomposed components to obtain an original characteristic set; removing redundancy by means of a self-weight algorithm and an AP (Affinity Propagation) clustering algorithm to obtain Z optimal characteristics; classifying sample statuses by means of the AP clustering algorithm to obtain a well-trained diagnosis model. A fault diagnosis is performed by the following steps: collecting real-time vibration information of a bearing, decomposing the signals, extracting the optimal characteristics determined by the model, importing the AP clustering algorithm to cluster parameters based on the diagnosis model, comparing with the Z characteristics known in the model to obtain a category of a current unknown signal, so as to complete the fault diagnosis. According to the clustering analysis-based intelligent fault diagnosis method disclosed by the invention, both EEMD (Ensemble Empirical Mode Decomposition) and WPT are utilized to decompose the vibration signals, more refined bearing status information can be acquired, the self-weight algorithm and the AP clustering algorithm increase intelligence of the diagnosis, and therefore accurate diagnosis is ensured.

The invention provides an intelligent patrol safety helmet for a transformer substation. The safety helmet comprises a shell and a functional unit, wherein the shell is prepared from modified polypropylene plastic, ultra-high molecular weight polyethylene plastic or polycarbonate plastic; the functional unit comprises a power frequency electric field sensor, a power frequency magnetic field sensor, a thermal infrared imager, an acceleration sensor, a UWB positioning unit, a signal processing and power supply unit, an LED lighting lamp, a display unit, a sound-light alarm unit and a communication unit. The invention provides an intelligent wearing article for transformer substation intelligentization, automation and safety patrol, guarantee is provided for life safety, the safety patrol means of transformer substation equipment is improved, the maintenance quality and the maintenance efficiency of the transformer substation are improved, and convenience is provided for transformer substation maintenance.

The fault diagnosis system includes on site intelligent instrument connected to objects of industrial process, DCS system, and upper device. The DCS system is composed of data interface, control station, and database. The intelligent instrument is connected to DCS system, and upper device. The upper device includes the standardization process module, functional module of pivot element analysis, functional module for supporting classifier of vector machine, failure predication module, signal acquisition module, module for determining data to be diagnosed, and fault diagnosis module. The invention also discloses a fault diagnosis method. The invention discloses fault diagnosis system and method capable of well treating measured non-linear data obtained from small sample with high capability of generalizing model, as well as capable of obtaining good diagnosis result under condition of small sample in industrial process.

Disclosed in the invention is a remote fault analysis and feedback system of an urban rail transit vehicle. The system comprises a vehicle-mounted device system and a ground device system. The vehicle-mounted device system includes a data acquisition module, a data transmitting-receiving module, and an intelligent display terminal; and the ground device system contains a data transmitting-receiving module, a fault analysis module, and a fault knowledge base. According to the invention, the vehicle-mounted device system collects vehicle data and the ground device system receive the data to carry out analyses continuously; diagnosis is carried out based on a fault tree and fault diagnosis steps; and a diagnosis result can be fed back to a vehicle intelligent terminal in real time. Therefore, accuracy and reliability of the fault diagnosis can be improved.

A fault diagnosis system of melt index detection in propylene polymerization producing process includes the scene Intelligent Instrumentation, DCS systems, and PC connected with the propylene polymerization production, and the DCS system consists of a data interface, a control station and a database. The Intelligent Instrumentation, DCS system and PC are connected with each other in order, and the PC includes a standardized processing module, independent component analysis module, support vector machine classifier function module, signal acquisition module, diagnostic data to be identified module and fault diagnosis module. It also proposes a method of fault diagnosis.

An industrial production process diagnostic system based on small wave analysis comprises industrial process object connected on site intelligent meter, DCS system and its upper position control machine with the DCS system made of data interface, control station, data base, the intelligent meter, DCS system and the upper position control machine connected sequentially, with the said upper position control machine composed of standardized handling module, small wave dissolving module, pivot element analysis function module, small wave restructuring module, support vector machine classifier module and diagnostic judging module. It also puts forward a failure diagnostic method. It provides an industrial production process failure diagnostic system and method with good diagnostic effect based on small wave analysis.

The invention discloses a battery fault judgment and processing method for a battery pack and belongs to the technical field of batteries. The method comprises the steps of S1, obtaining a voltage value at a charge / discharge tail end of a single battery of the power battery pack; S2, comparing the voltage value at the charge / discharge tail end of the single battery with a voltage average value when the charge / discharge is carried out; and S3, judging whether a fault exists in the single battery or not according to a comparison result and processing the fault. According to the method, the faultjudgment is carried out according to the voltage value at the charge / discharge tail end of the single battery, the reliable diagnosis of the power battery pack fault is realized, the misjudgment of the battery pack fault is reduced, an effective maintenance method is provided, the unnecessary and repeated maintenance of the battery pack is avoided, and the maintenance cost is reduced.

The invention discloses a subway fault diagnosis method based on data mining. The method comprises the steps that history fault data of a subway is disposed to form an original decision table; the original decision table is pre-processed by a rough set, redundant attributes are reduced to obtain a new attribute set, and the original decision table is transformed to a new decision table with a boolean attribute; association rules between an attribute set of the new decision table and faults are mined to store in a rule base; state data and the rules in the rule base are compared in real time to make fault diagnosis. According to the subway fault diagnosis method based on data mining, the rough set is adopted to perform data pre-processing, data mining is used in fault diagnosis, the faults occurring on the subway are judged, and not only difficulties brought by the fact that subway working personnel judges the faults according to experiences are solved, but also the speed and accuracy of fault solving are greatly improved.

An expert system for diagnosing the failure of bag-type dusting system is composed of computer, system development tool on Windows platform and using visual C++ language and Access database, and functional module system consisting of expert system introduction module, in-line failure diagnosing module, off-line failure diagnosing module, and expert direction module. Its diagnosing process includes such steps as data acquisition, signal display, in-line diagnosing and off-line diagnosing. 77 failures can be diagnosed.

The present invention relates to an industrial polypropylene production melt index detection fault diagnosis system. Said system includes field intelligent instrument connected with industrial process object, DCS system and upper-position machine. The described DCS system is composed of data interface, control station and data base; the intelligent instrument, DCS system and upper-position machine are successively connected, and the described upper-position machine includes standardization processing module, wavelet decomposition module, pivot analysis function module, wavelet reconstruction function module, support vector machine classifier function module and fault judgement module. Besides, said invention also provides a fault diagnosis method.

The invention discloses a method and a device for carrying out long light-emitting alarm diagnosis on ONUs (optical network units) on the OLT (optical line terminal) side in an EPON (Ethernet passive optical network) system, which relates to the field of EPON. The method comprises the steps that after receiving a long light-emitting alarm, an OLT closes an ONU automatic discovery window, and if online ONUs exist in an ODN network, the OLT records the LLID (logical link identification) index numbers of all the online ONUs, at the moment, all the online ONUs are suspected ONUs; and the OLT broadcasts to the ONUs under the ODN (optical distribution network), sends a light module light-emitting turn-off instruction, and closes the light module light-emitting of the illegal ONUs. The method and device disclosed by the invention can carry out rapid and reliable diagnosis on long light-emitting errors of abnormal light-emitting ONUs in the EPON system, and for the controllable abnormal light-emitting ONUs, the light-emitting function of a light module is closed, or a power supply of the light module is turned off, thereby reducing the influence of the abnormal light-emitting ONUs on network services; and a positioning message is outputted to uncontrollable abnormal light-emitting ONUs, thereby facilitating the maintenance of an ODN network.

A facility fault diagnosing method uses a vibration characteristic. A vibration generated according to a fault of a facility is divided into a plurality of vibration characteristics. Vibration code items are configured by subdividing the vibration characteristics. The detailed vibration code items are associated and databased for each fault type to store the detailed vibration code items. An input of a detailed vibration code item selection signal is received for the each vibration characteristic from a user. A fault type of a facility is determined on the basis of the each input detailed vibration code item and association information between the fault type and the detailed vibration code items. The vibration fault is diagnosed through a combination of a plurality of detailed vibration components by breaking a scheme of diagnosing the vibration fault using only one vibration component so that a more reliable facility fault diagnosis can be performed.

The invention discloses a locomotive air conditioning controlling system. The locomotive air conditioning controlling system comprises a locomotive air conditioning main control board, a power supply,a condensing fan, a ventilator, a compressor, an electric heater, a fresh air valve, a communication network, a temperature detector, a temperature adjusting switch, a mode controlling switch and a pressure protecting switch connected to the locomotive air conditioning main control board, the power supply is connected with the locomotive air conditioning main control board through a power supplycontrolling port, the condensing fan is connected with the locomotive air conditioning main control board through the input and output controlling ports of the condensing fan, the ventilator is connected with the locomotive air conditioning main control board through the input and output controlling ports of the ventilator, and the compressor is connected with the locomotive air conditioning maincontrol board through the input and output controlling ports of the compressor. The locomotive air conditioning controlling system has the controlling functions such as ventilation, cooling, heating,over-current, temperature detection and fresh air volume adjustment, automatic controlling is achieved through an environment temperature and return air temperature sensor, the manual function is set,and the locomotive air conditioning controlling system can provide the comfortable indoor environment for a locomotive driver cab accordingly.

The invention discloses an open-circuit fault diagnosis method for a neutral-point clamped single-phase three-level inverter. The method comprises the following steps of: obtaining neutral-point clamping bus current information by changing a detection mode of a current sensor, and obtaining a corresponding relationship among a switching state of two bridge arms under a normal condition, a phase current and a theoretical current value detected by the current sensor through off-line calculation; establishing a corresponding relation between a current sensor detection current actual value and different power tube open-circuit fault conditions when the phase current has different polarities, and setting a fault diagnosis rule according to the change of the current sensor detection value in thecorresponding relation; and carrying out the open-circuit fault diagnosis of the single-phase three-level inverter by comparing the change relationship between the theoretical current value detectedby the current sensor and the actual value acquired on line and combining a fault diagnosis rule. The method provided by the invention is independent of an adopted control strategy, is simple to implement, does not need a complex online calculation process, is accurate in open-circuit fault diagnosis, and has a good engineering application value.

A method for detecting a short circuit to ground or to the operating voltage of a signal line (11, 12) of a resolver (16) has the following steps:—measuring the potential of the signal lines (13a, 13b; 14a, 14b) of the receiver coil (18) with respect to ground at two sampling times (R and F) provided symmetrically at the middle of the excitation period;—calculating an offset value for a signal line pair (13a, 13b; 14a, 14b) by calculating the average value of the four measured values (UHR, ULR, UHF and ULF) for the associated receiver coil (17, 18); and—identifying a short circuit and the potential to which the short-circuited line is connected in that the offset value is compared to threshold values.

The invention discloses a fault diagnosis method and system of an integrated processing platform of angular acceleration signals. Compared with the prior art, the method has the advantages that faultdetection is not only performed on a sensor, the fault detection is also performed on an integrated control platform to remove the interference of a hardware system, so that the fault diagnosis of thesensor is more reliable; angular acceleration sensor data are processed by adopting wavelet decomposition, an original signal can be decomposed into components of different frequency bands, so that fault features can be better characterized more detailed in the frequency domain, and the fault diagnosis accuracy can be improved; the adopted Bayesian regularization algorithm is a modification of the Levenberg-Marquardt algorithm, which can well improve the generalization ability of a neural network and optimize the structure of the neural network, thus improving the performance of the neural network.

The present invention relates to a facility fault diagnosing method using a vibration characteristic, which comprises the steps of: dividing a vibration generated according to a fault of a facility into a plurality of vibration characteristics, configuring detailed vibration code items by subdividing the vibration characteristics, and associating and databasing the detailed vibration code items for each fault type to store the detailed vibration code items; receiving an input of a detailed vibration code item selection signal for the each vibration characteristic from a user; and determining a fault type of a facility on the basis of the each input detailed vibration code item and association information between the fault type and the detailed vibration code items. According to the present invention, a vibration fault is diagnosed through a combination of a plurality of detailed vibration components by breaking a scheme of diagnosing the vibration fault using only one vibration component so that a more reliable facility fault diagnosis can be performed.

The invention discloses a terminal sensing system for constructing a digital twin of a three-phase asynchronous motor. The terminal sensing system comprises a current transformer and a voltage converter which are used for sensing various electrical parameters of the three-phase asynchronous motor; a vibration sensor, a sound sensor and a rotating speed sensor which are used for measuring mechanical motion characteristics of the three-phase asynchronous motor; an infrared thermal camera and a 3D camera which are used for sensing related physical characteristics of the three-phase asynchronous motor; an ARM processor and a Raspberry Pi module which are used for data processing; and a 5G communication module which is used for real-time data transmission. Various operating parameters of the three-phase asynchronous motor are comprehensively obtained, and powerful data support is provided for constructing a digital twin of the three-phase asynchronous motor in a virtual space, mapping and fusing the digital twin and a physical entity in real time and performing remote, accurate and reliable fault diagnosis on the entity of the three-phase asynchronous motor.

The invention discloses an intelligent protection system for a flexible DC distribution network based on a neural network. Power grid data acquired by each sensor distributed at a distributed power generation side, a user side and a line of the DC distribution network are transmitted to a signal acquisition module, the data are converted to corresponding digital signals, the digital signals are transmitted to a central processing unit for analysis and processing, data classification is then carried out, signal feature extraction is carried out, and information reflecting the operation state of the power grid in real time can be obtained. If a fault signal is detected, a real-time database is entered, an expert database is called to the real-time database, after a fault type is diagnosed, a corresponding measure is taken, and a tripping / closing action of the system is controlled and executed. An artificial intelligence technology applicable to a complicated system and a computer technology are combined, the neural network is introduced, the expert database is updated continuously through the algorithm, fault diagnosis on the DC distribution line is more efficient, accurate and reliable, intelligent protection for the DC distribution line is realized, and the DC distribution system is ensured to operate safely and stably.

The invention relates to a diagnosis method for a diode open-circuit fault of a metro rectifier unit based on waveform characteristics, which mainly comprises the steps of A, respectively performing real-time acquisition on output voltage of the rectifier unit and A-phase input current of four rectifier bridges; B, performing normalization processing to obtain normalized output voltage; C, solvinga minimum value set of the normalized voltage signal within a period between a sampling moment t to a sampling moment (t-T+1); D, determining that a fault occurs when the absolute value of the difference between two adjacent minimum values in the minimum value set is greater than 0.1; E, comparing the A-phase input current with set positive and negative thresholds to determine the rectifier bridge where the failure diode is located; and F, determining the specific position of the failure diode according to the A-phase input current waveforms corresponding to diodes at different positions whenbeing conducted. The diagnosis method realizes recognition and positioning for the diode open-circuit fault quickly and effectively, reduces the diagnosis cost, facilitates timely maintenance and more effectively avoids the expansion of losses and the occurrence of accidents.

The invention provides a fault diagnosis method and device for a ternary catalytic converter. The fault diagnosis method comprises the following steps: 1) obtaining a control signal and gas inlet flowgenerated by a front oxygen sensor; 2) based on the control signal and the gas inlet flow, performing analog computation to obtain an analog oxygen sensor voltage signal; 3) computing to obtain analog oxygen sensor amplitude according to the analog oxygen sensor voltage signal; 4) obtaining a voltage signal generated by a rear oxygen sensor; 5) computing measured rear oxygen sensor amplitude according to the voltage signal of the rear oxygen sensor; and 6) based on the analog oxygen sensor amplitude and the measured rear oxygen sensor amplitude, diagnosing whether the catalytic converter hasfaults or not.

Disclosed in the invention is a remote fault analysis and feedback system of an urban rail transit vehicle. The system comprises a vehicle-mounted device system and a ground device system. The vehicle-mounted device system includes a data acquisition module, a data transmitting-receiving module, and an intelligent display terminal; and the ground device system contains a data transmitting-receiving module, a fault analysis module, and a fault knowledge base. According to the invention, the vehicle-mounted device system collects vehicle data and the ground device system receive the data to carry out analyses continuously; diagnosis is carried out based on a fault tree and fault diagnosis steps; and a diagnosis result can be fed back to a vehicle intelligent terminal in real time. Therefore, accuracy and reliability of the fault diagnosis can be improved.

The invention discloses a multi-information fusion fire hazard detection method, comprising the following steps: preprocessing is carried out on a fire hazard detection signal sequence obtained by site period sampling, and unreasonable data generated by normal environmental change is removed; a gray model GM (1, 1) is built according to the preprocessed original fire hazard detection signal sequence, and fire hazard detection signal data at follow-up time points is predicted, so as to obtain an equal dimensionality new information gray prediction model; the original hazard detection signal sequence is utilized to carry out posterior check on the fire hazard detection signal data obtained by prediction, so as to check whether the fire hazard detection signal data generated by prediction ongray prediction model is qualified or not; and a diagnosis neural network is utilized to diagnose the qualified fire hazard detection signal time sequence data, so as to obtain a fire hazard detection result. By means of the invention, reliable fault diagnosis can be provided and the false alarm rate of fire detection result can be reduced.

An industrial production process diagnostic system based on small wave analysis comprises industrial process object connected on site intelligent meter, DCS system and its upper position control machine with the DCS system made of data interface, control station, data base, the intelligent meter, DCS system and the upper position control machine connected sequentially, with the said upper position control machine composed of standardized handling module, small wave dissolving module, pivot element analysis function module, small wave restructuring module, support vector machine classifier module and diagnostic judging module. It also puts forward a failure diagnostic method. It provides an industrial production process failure diagnostic system and method with good diagnostic effect based on small wave analysis.

An oil drilling drill string online monitoring system and a fault diagnosis method belong to the oil drilling monitoring technology. Including PCB board, upper computer, torque sensor and acceleration sensor connected to the drill string respectively, the torque sensor and acceleration sensor are respectively connected to the PCB board, and the collected torque signal and vibration signal are sent to the PCB board, and the PCB board will pre- The processed data communicates with the host computer through the Bluetooth module. The patent of the invention has good portability, can monitor the drilling state of the drill string in real time, and can accurately and reliably diagnose abnormal conditions, so that drilling workers can take remedial measures in time and effectively prevent dangerous accidents.

The fault diagnosis system includes on site intelligent instrument connected to objects of industrial process, DCS system, and upper device. The DCS system is composed of data interface, control station, and database. The intelligent instrument is connected to DCS system, and upper device. The upper device includes the standardization process module, functional module of pivot element analysis, functional module for supporting classifier of vector machine, failure predication module, signal acquisition module, module for determining data to be diagnosed, and fault diagnosis module. The invention also discloses a fault diagnosis method. The invention discloses fault diagnosis system and method capable of well treating measured non-linear data obtained from small sample with high capability of generalizing model, as well as capable of obtaining good diagnosis result under condition of small sample in industrial process.

The invention proposes a power grid fault diagnosis system and its method based on relay protection auxiliary decision-making system, based on the wave recording master station, by establishing a limited information interaction mechanism, and integrating the reliable advantages of the trustworthy master station in judging line faults, it maximizes the The wave recording master station has the advantage of quick response to line faults, and at the same time makes up for the shortcomings of the lack of protection action component information in the wave recording fault analysis report, and finally realizes a high degree of automation for relay protection agencies, reliable line fault judgment, and complete analysis reports. The line fault decision-making information has the ability to replace the auxiliary decision-making process of relay protection agency personnel, and directly face the direct decision-making ability of the control agency; with the assistance of the Baoxin master station, the wave recording master station has completed the confirmation and correction of the wave recording fault analysis report, supplemented The information of the protective action components is obtained, the possibility of misjudgment and missed judgment of line faults is eliminated, and the ability of reliable analysis of line faults and automatic output of decision-making to the regulatory agency is provided.

The invention discloses a method and a device for carrying out long light-emitting alarm diagnosis on ONUs (optical network units) on the OLT (optical line terminal) side in an EPON (Ethernet passive optical network) system, which relates to the field of EPON. The method comprises the steps that after receiving a long light-emitting alarm, an OLT closes an ONU automatic discovery window, and if online ONUs exist in an ODN network, the OLT records the LLID (logical link identification) index numbers of all the online ONUs, at the moment, all the online ONUs are suspected ONUs; and the OLT broadcasts to the ONUs under the ODN (optical distribution network), sends a light module light-emitting turn-off instruction, and closes the light module light-emitting of the illegal ONUs. The method and device disclosed by the invention can carry out rapid and reliable diagnosis on long light-emitting errors of abnormal light-emitting ONUs in the EPON system, and for the controllable abnormal light-emitting ONUs, the light-emitting function of a light module is closed, or a power supply of the light module is turned off, thereby reducing the influence of the abnormal light-emitting ONUs on network services; and a positioning message is outputted to uncontrollable abnormal light-emitting ONUs, thereby facilitating the maintenance of an ODN network.