Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

34 results about "Failure index" patented technology

Power distribution network fault power failure influence factor sensitivity analysis method based on BP neural network

InactiveCN109858663AEffectively identify weak pointsForecastingResourcesSensitivity analysesDistribution networks
The invention relates to a power distribution network fault power failure influence factor sensitivity analysis method based on a BP neural network algorithm, and the method comprises the steps: 1, sorting a power distribution network fault power failure influence factor set related to investment, and forming association relationship of investment-influence factor-household average fault power failure indexes; 2, taking each influence factor as the input of a BP neural network algorithm, taking the household average fault power failure index as the output of the BP neural network algorithm, and establishing a fault power failure prediction model; 3, analyzing each influence factor influencing the power failure index of the household average fault by adopting a sensitivity analysis method;4, sorting the absolute values of the sensitivity of the influence factors according to the size; a plurality of influence factors having the maximum influence on the household average fault power failure index are obtained, and the higher the absolute value sequence of the sensitivity of the influence factors is, the weaker the influence factors are, so that the direction guidance can be providedfor the investment of the power distribution network.
Owner:CHINA AGRI UNIV +1

A mechanical equipment fault automatic identification method based on acoustic image monitoring

The invention provides a mechanical equipment fault automatic identification method based on acoustic image monitoring. According to the method, a line spectrum identification library and a fault acoustic image identification library are respectively established under the condition of continuous, normal and stable operation of mechanical equipment; the line spectrum of noise signals of the mechanical equipment acquired by a sound imaging instrument in real time is identified in the line spectrum identification library; if the identification is successful, a line spectrum failure index is outputted; otherwise, the line spectrum is determined to be an abnormal line spectrum; and an acoustic image of the abnormal line spectrum is calculated and identified in the fault acoustic image identification library; if the identification is successful, an acoustic image composite fault index and an equipment fault plan are output; otherwise, the equipment fault plan corresponding to the abnormal line spectrum is diagnosed; the abnormal line spectrum, the acoustic image of abnormal line spectrum and its corresponding mechanical equipment fault plan are added to the fault acoustic image identification library. After adoption of the method of the present invention, an acoustic imaging fault detection system can be used in any complex sound field, and can continuously realize automatic alarm and fault prompting functions.
Owner:NAVAL UNIV OF ENG PLA

Failure prediction system and failure prediction method

ActiveCN111542846AImprove symptom detection accuracyForecastingNon-redundant fault processingPrediction systemData mining
The present invention performs machine learning wherein: the period between a reference time point, which corresponds to a failure prediction time point, and an earlier time point, which is a predetermined first length of time earlier than the reference time point, is set as a warning sign detection period; if no failure occurred during the period between the reference time point and a later timepoint, which is a predetermined second length of time later than the reference time point, then that period is set as a prediction period, and otherwise if a failure occurred during the period betweenthe reference time point and the later time point, then the period between the reference time point and the time point at which the failure occurred is set as the prediction period; the reference time point is then sequentially shifted; a feature quantity based on operation log information obtained during the warning sign detection period is set as an explanatory variable; and a failure index value is set as a response variable, the failure index value being based on whether or not occurrence of a specific event is indicated by operation log information associated with failure occurrence indicated by failure record information obtained during the prediction period, and also based on the length of time between the reference time point and the time point at which the failure occurred.
Owner:HITACHI LTD

A device-based vibration signal alarm recognition method and computing device

The invention discloses a device-based vibration signal alarm identification method and a computing device. The method is suitable for being executed in the computing device. The method includes the following steps that: the vibration signals of a device at a current time point are collected, and a root mean square index amplitude corresponding to the vibration signals is calculated; whether the root mean square index amplitude exceeds a preset first real-time threshold is judged; if the root mean square index amplitude exceeds the preset first real-time threshold, a rotation speed, a gear failure index, a bearing failure index and a power frequency failure index corresponding to the vibration signals are obtained; whether the rotation speed, the gear failure index, the bearing failure index and the power frequency failure index all meet their respective invalid alarm states is judged; if the rotation speed, the gear failure index, the bearing failure index and the power frequency failure index all meet their respective invalid alarm states, it is determined that the state of the device is normal, and no alarm signals are issued, otherwise, it is determined that the state of the device is abnormal, and alarm signals are issued.
Owner:日照广亚机电设备有限公司

A Prediction Method of Tensile Strength of Composite π-shaped Bonded Connection Structure Based on Average Failure Index

The invention relates to a composite material Pi-shaped gluing connection structure tensile strength prediction method based on an average invalidation index. The method includes the following steps: (1) a Pi connector geometrical model is built according to geometrical parameters of a composite material Pi-shaped gluing connection structure; (2) determining tensile load and boundary condition of the composite material Pi-shaped connector geometrical model according to the stress condition of the integrated composite material structure; (3) acquiring an accurate Pi connector three-dimensional finite element model through grid encryption based on the Pi connector geometrical model, meanwhile ensuring that grids on key connection faces L, U and B are even and calculating stress distribution of the three-dimensional finite element model under tensile load; (4) extracting positive axis stress component value of nodes on the Pi connector key connection faces L, U and B and calculating the invalidation index Rij on the key connection face; (5) respectively calculating the average invalidation indexes based on the key connection faces L, U and B of the Pi connector; (6) conducting calculation according to the tensile load P0 and the maximum value of the average invalidation indexes to obtain the invalidation strength value P of the obtained connector. The method is applicable to engineering application, can remarkably shorten the developing period of the Pi connector and reduces test cost.
Owner:BEIHANG UNIV

Optimization Method of Key Structural Parameters for Reliable Motion of Engine Exhaust Nozzle

The invention discloses a method for optimizing the motion flexibility and reliability of an engine composite tail nozzle, comprising steps: the first step, analyzing important parameters affecting the motion flexibility and reliability of the tail nozzle, and determining the optimization object; the second step 1. Confirm the numerical range of each optimization object parameter, and carry out follow-up optimization for this range; the third step is to formulate the engine exhaust nozzle motion performance evaluation index and stress damage failure index; the fourth step is to establish the impact of composite material exhaust nozzle Dynamics simulation, optimize the simulation calculation of each parameter; the fifth step, by analyzing the influence trend of each parameter on the movement flexibility and reliability of the tail nozzle, put forward the composite material tail nozzle pin hole matching unilateral clearance, surface friction Suggested indicators for parameter selection for coefficients and driving air pressure. The invention solves the problems of low movement flexibility and easy failure of the tail nozzle, and realizes the improvement from sensory experience to theoretical method, from qualitative exploration to quantitative optimization.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY

Fault diagnosis method and system combining multi-point statistics and health trend prediction

The invention provides a fault diagnosis method and system combining multi-point statistics and health trend prediction, and the method comprises the steps: determining a fault detection method according to the fault features of a to-be-detected device; according to the fault detection method, determining a time delay post-judgment interval length; initializing the preset parameters; acquiring sensor output data of the to-be-detected device, wherein the sensor output data comprises measurement data of the to-be-detected device at a target moment; determining a corresponding device health change trend prediction method according to the self characteristics of the to-be-detected device and the measurement data, and predicting a health change trend according to the device health change trend prediction method to obtain a failure index sigma of the to-be-detected unit; performing single-point fault detection on the to-be-detected unit at the current moment; updating the preset parameters, and judging whether the later judgment interval is ended or not; and if so, analyzing and diagnosing the fault of the to-be-detected device to obtain a fault diagnosis result. Therefore, the accuracy of fault diagnosis can be improved.
Owner:SHANGHAI SPACEFLIGHT INST OF TT&C & TELECOMM

Assurance effectiveness-based method for evaluating survivability of optical transport network

The invention discloses an assurance effectiveness-based method for evaluating the survivability of an optical transport network. The method comprises two integrated measuring indicators: an assurance failure index and an assurance influence index, wherein the assurance failure index is an indicator for measuring the assurance effectiveness of the optical transport network from the perspective of business loss, evaluation of the influence degree of the network assurance effectiveness after business interruption is evaluation of a specific value of the sum of bandwidths of network loss business after a node or link failure in the network to the sum of the bandwidths of the business transmitted in the whole network, and the assurance effectiveness of the network is measured through evaluating the loss of the volume of the business transmitted in the network; the assurance influence index is used for evaluating the influence degree of the business on the equivalent assurance capacity for average information provided after network configuration business, the assurance effectiveness of the network is measured mainly through evaluating the potential influence degree of the failure on the network and the equivalent assurance capacity for the information between two points in the network is firstly defined. The evaluation is comprehensive and accurate and the evaluation result is more specific in meaning.
Owner:AIR FORCE ENG UNIV OF PLA AIRCRAFT MAINTENACE MANAGEMENT SERGEANT SCHOOL

Method of Orthogonal Analysis for Formulating Ice-melting Strategy of Tower-Line System

ActiveCN107368650BPrevent Tower Falling AccidentsOptimal Icing StrategiesDesign optimisation/simulationSpecial data processing applicationsElement modelStress ratio
The invention discloses a method for making a de-icing policy of a tower line system through orthogonal analysis. The method comprises the steps of 1, building a three-dimensional finite element model of the tower line system; 2, determining a multi-factor two-level orthogonal table, compiling a multi-factor two-level orthogonal test scheme, and defining mechanics failure indexes of towers; 3, according to the multi-factor two-level orthogonal test scheme, applying designed wind load and ice load to a hanging position of each wire insulator and a hanging position of each ground wire respectively by adopting a finite element method, simulating stress conditions of each tower under different loads, and obtaining a maximum axial stress ratio and a dangerous unit number of an angle steel unit of each tower; and 4, for each index, calculating an index average value of each factor and each level, and obtaining a most serious icing condition according to the index average value, thereby obtaining an optimal de-icing sequence. According to the method, the most serious icing condition can be assessed under the condition of giving parameters of icing, a wind speed, a span and the like, and the optimal de-icing sequence of the tower line system is given.
Owner:WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products