Abstract

Support vector data description (SVDD) has been widely applied to batch process fault detection. However, it often performs poorly, especially when incipient faults occur, because it only considers the shallow data feature and omits the probabilistic information of features. In order to provide better monitoring performance on incipient faults in batch processes, an improved SVDD method, called deep probabilistic SVDD (DPSVDD), is proposed in this work by integrating the convolutional autoencoder and the probability-related monitoring indices. For mining the hidden data features effectively, a deep convolutional features extraction network is designed by a convolutional autoencoder, where the encoder outputs and the reconstruction errors are used as the monitor features. Furthermore, the probability distribution changes of these features are evaluated by the Kullback-Leibler (KL) divergence so that the probability-related monitoring indices are developed for indicating the process status. The applications to the benchmark penicillin fermentation process demonstrate that the proposed method has a better monitoring performance on the incipient faults in comparison to the traditional SVDD methods.

Highlights

  • Due to the huge market demand for small-batch and high-added-value products, the batch process has been important means of production in modern industrial systems

  • As the advanced computer control systems bring a large amount of process data, data-driven fault detection methods have become a topic of major interest [3,4]

  • In order to achieve this goal, a deep convolutional feature-based probabilistic Support vector data description (SVDD) method is proposed for monitoring incipient faults in batch processes

Read more

Summary

Introduction

Due to the huge market demand for small-batch and high-added-value products, the batch process has been important means of production in modern industrial systems. In order to prompt the incipient fault detection capability of SVDD, PCA-SVDD has been put forward by Li et al [22], where PCA is used to perform the data subspace decomposition and SVDD is applied to build the monitoring statistics. TS-PCA for process dynamic feature extraction, and Wang et al [24] constructed a MICPCA-SVDD method and validated it on the polyethylene industrial process These studies demonstrate that PCA-SVDD can achieve better detection of incipient faults. In order to achieve this goal, a deep convolutional feature-based probabilistic SVDD method is proposed for monitoring incipient faults in batch processes. We use a penicillin fermentation process to validate the proposed method

Batch Process Data Preprocessing
Overview of SVDD Principle
PCA-SVDD Method
Method Framework
Deep Convolutional Feature Extraction
Probabilistic Monitoring Index Construction
Batch Process Monitoring Procedure
Case Study
Findings
Method SVDD
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call