Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Periodic prediction neural network based industrial data fault prediction method

A predictive neural network and fault prediction technology, applied in electrical testing/monitoring, testing/monitoring control systems, instruments, etc., can solve problems such as incomplete data, difficult fault analysis and prediction, and scarce fault data, so as to improve training speed , improve the quality of forecasting, and improve the effect of forecasting accuracy

Inactive Publication Date: 2019-04-19
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The difficulty of fault diagnosis and prediction lies in: in the large-scale time series data collected in actual scenarios, fault data is usually very scarce, and future faults may be faults that have not occurred before, making it difficult to achieve effective fault analysis and prediction
The incompleteness of data brought about by various scene restrictions is a common problem in current big data processing research.
If only analyzing from actual data, it is impossible to theoretically verify all possible scenarios of actual system failures, so it is also difficult to discover all the modes of failures and effectively predict failures

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
  • Periodic prediction neural network based industrial data fault prediction method
  • Periodic prediction neural network based industrial data fault prediction method
  • Periodic prediction neural network based industrial data fault prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0017] Such as figure 1 As shown, the specific design of the model in a periodic prediction neural network-based industrial data fault prediction method is detailed:

[0018] The periodic prediction neural network model is mainly based on GRU, namely Gated Recurrent Unit. According to the characteristics of periodic data, redesign the periodic prediction neural network model, focusing on the design of neuron connection mode and loss function.

[0019] The ne...

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 periodic prediction neural network based industrial data fault prediction method. The method includes steps: (1) designing mode exploration branch rings, and establishing an equipment operating state mode for storage and representation of various operating states and time-series relationships of equipment; (2) designing a periodic prediction neural network for predicting anext state and fault probability according to time series of a current period in a cloud environment; (3) in the cloud environment, performing dynamic node selection and data duality in an operatingprocess to iteratively explore new faults which are not occurred, and establishing a data experiment mechanism to realize fault prediction in a real-time cloud environment. The periodic neural networkprediction based industrial data fault prediction method has the advantage that by combination of industrial data fault prediction and the neural network and design of a periodic prediction neural network model, algorithm prediction precision is improved while the algorithm execution rate is increased.

Description

technical field [0001] The invention relates to a neural network, fault prediction, and big data cloud computing environment, in particular to an industrial data fault prediction method based on a periodic prediction neural network. Background technique [0002] With the widespread application of cloud computing technology, industrial equipment operation management adopts on-site data collection and then transmits it to the cloud for data analysis and processing, which has become a common mode. An urgent problem is how to organically integrate the effective mining of a large amount of historical data and the real-time processing of dynamic operating data, so as to realize data intelligence and solve problems in equipment operation. Obviously, this requires an industrial data fault prediction method based on periodic prediction neural network to support intelligent processing of large-scale time series data. [0003] The difficulty of fault diagnosis and prediction lies in: ...

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 Applications(China)
IPC IPC(8): G05B23/02
CPCG05B23/0243G05B2219/24065
Inventor 耿祖琨张卫山任鹏程
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products