Deep Compression of Neural Networks for Fault Detection on Tennessee Eastman Chemical Processes
This work addresses storage and deployment challenges for real-time fault detection in chemical processes, but it is incremental as it combines existing compression methods.
The paper tackles the problem of high memory requirements for neural networks in fault detection on the Tennessee Eastman process by applying deep compression techniques, achieving a 91.5% reduction in model size while maintaining over 94% accuracy.
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.