Batch process online fault detection method of dynamic multi-direction local outlier factor algorithm

Abstract

The invention provides a batch process online fault detection method of a dynamic multi-direction local outlier factor algorithm, relating to a batch process fault detection method. Firstly, three-dimensional data is expanded into two-dimensional in the sliding window of a training sample, and the standard processing is carried out. Then k neighbors of a training set (i) are found in each window, and a local outlier factor algorithm is used to calculate a reachability distance and a local reachability density to obtain an LOF statistical amount. The control limit of the LOF statistical amount at that time is calculated through nuclear density estimation. K neighbors of new time data are founded in the training set, and the LOF statistical amount at that time is calculated by using a local outlier factor algorithm. If the statistical amount exceeds a control limit, the data sample at that time is failed, otherwise, the data sample is normal. If a test indicates that a system is failed, the staff needs to identify a situation timely and eliminate danger. According to the method, the process monitoring can be carried out effectively, and a fault detection effect is improved.

Description

technical field [0001] The invention relates to a fault detection method for intermittent processes, in particular to an online fault detection method for intermittent processes using Dynamic Multiway Local Outlier Factor (DMLOF). Background technique [0002] In recent years, due to the continuous progress and development of science and technology, the batch process has been widely used in the production of high-quality, high value-added products. Therefore, the detection and fault diagnosis of batch processes have always attracted much attention. However, the signals collected in the intermittent process often have non-Gaussian, nonlinear, and multi-modal characteristics, which put forward high requirements on the performance of fault detection. Compared with the traditional batch process, the multi-mode batch process is more complicated, and has the characteristics of severe nonlinearity, time-varying and multi-working conditions, which makes the fault diagnosis of the m...

AI Technical Summary

Problems solved by technology

These methods assume that the data obeys a single distribution, and reduce the data from high-dimensional space to low-dimensional space by retaining the principal components, changing the data distribution and losing local information, while the actual data is often a mixture of Gaussian and non-Gaussian distributions, so these methods Poor monitoring effect on chemical process with complex data distribution

How to solve the problem of multimodal distribution characteristics of data, while using local neighborhood information, there is currently no method for fault detection of multimodal intermittent processes

Images