Periodic prediction neural network based industrial data fault prediction method

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: ...

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

Images