A Failure Rate Prediction Method Combining bp Neural Network and Two-parameter Weibull Distribution

A BP neural network and Weibull distribution technology, applied in electrical testing/monitoring, testing/monitoring control systems, instruments, etc., can solve problems such as discrete failure rates and inability to predict future failure situations, and achieve the effect of solving large randomness

Active Publication Date: 2019-01-25
NANJING UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the calculation methods for the failure rate are still based on the traditional calculation of the ratio of the outage time to the planned use time, but this method has a large error when calculating the equipment that has just been put into production and has poor failure data , and the failure rate calculated by this method is discrete and has great randomness, so it cannot accurately predict future failure conditions

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Failure Rate Prediction Method Combining bp Neural Network and Two-parameter Weibull Distribution
  • A Failure Rate Prediction Method Combining bp Neural Network and Two-parameter Weibull Distribution
  • A Failure Rate Prediction Method Combining bp Neural Network and Two-parameter Weibull Distribution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The following is attached figure 1 , 2 The failure rate prediction method combined with BP neural network and two-parameter Weibull distribution of the present invention is described in detail. The embodiments and examples of the present invention are preferred solutions for the purpose of explanation, and are not intended to limit the scope of the present invention.

[0015] Refer to attached figure 1 , 2 , the failure rate prediction method combined with BP neural network and two-parameter Weibull distribution is as follows:

[0016] First, use the BP neural network to establish a data prediction model and a fault state prediction model, and expand the data set at the time of the fault; including the following steps: (1) Determine the input and output vectors according to the specified equipment; (2) Construct BP based on the input and output vectors Neural network forecasting model; (3) Network training for BP neural network; (4) Input test set samples into the fo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a failure rate prediction method through combination of a BP neural network and two-parameter weibull distribution, relates to the field of engineering practical application process equipment reliability, and more particularly relates to equipment failure rate prediction through the method of combination of the BP neural network and two-parameter weibull distribution. The technical scheme is listed as follows: the failure rate prediction method through combination of the BP neural network and two-parameter weibull distribution is listed as follows: firstly, a data prediction model and a failure state prediction model are established by using the BP neural network, and a failure time data set is extended; secondly, the failure data set is extended according to the failure data obtained through the BP neural network prediction models, and the equipment failure rate is predicted by using two-parameter weibull distribution; and finally constructive suggestions can be put forward for actual production and the guidance can be made for equipment repair and maintenance plans according to the corresponding failure rate of the time point in the future or the average failure rate of the time period in the future predicted by the method.

Description

technical field [0001] The failure rate prediction method combined with BP neural network and two-parameter Weibull distribution of the present invention relates to the field of equipment reliability in the actual engineering application process, and more specifically relates to the method of combining BP neural network and two-parameter Weibull distribution to predict the failure rate of equipment. Make predictions. Background technique [0002] The reliability of equipment plays a particularly important role in the normal operation of the enterprise, especially some major equipment plays a pivotal role in the entire production process of the enterprise. At present, most of the calculations of equipment failure rates are still based on traditional methods, which are highly random and rely on a large amount of historical data. Most of the calculation methods for the failure rate are still based on the traditional calculation of the ratio of the outage time to the planned us...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G05B23/02
CPCG05B23/0229G05B23/0283
Inventor 王静虹李晨阳蒋军成
Owner NANJING UNIV OF TECH
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