Deep Compression of Neural Networks for Fault Detection on Tennessee Eastman Chemical Processes

TL;DR

This paper demonstrates that combining pruning, clustering, and quantization techniques can significantly compress neural networks for fault detection in chemical processes while maintaining high accuracy, enabling efficient real-time deployment.

Contribution

It introduces a comprehensive application and evaluation of deep compression methods on neural networks for fault detection in chemical processes, achieving over 91% model size reduction.

Findings

Model sizes reduced by up to 91.5%

Fault detection accuracy maintained above 94%

All combined techniques outperform individual methods

Abstract

Artificial neural network has achieved the state-of-art performance in fault detection on the Tennessee Eastman process, but it often requires enormous memory to fund its massive parameters. In order to implement online real-time fault detection, three deep compression techniques (pruning, clustering, and quantization) are applied to reduce the computational burden. We have extensively studied 7 different combinations of compression techniques, all methods achieve high model compression rates over 64% while maintain high fault detection accuracy. The best result is applying all three techniques, which reduces the model sizes by 91.5% and remains a high accuracy over 94%. This result leads to a smaller storage requirement in production environments, and makes the deployment smoother in real world.