MOLA: Enhancing Industrial Process Monitoring Using Multi-Block Orthogonal Long Short-Term Memory Autoencoder

TL;DR

MOLA introduces a novel multi-block orthogonal LSTM autoencoder framework for improved fault detection in industrial processes, leveraging orthogonal feature extraction, expert knowledge-based variable grouping, and adaptive fusion for enhanced monitoring accuracy.

Contribution

The paper presents a new multi-block orthogonal LSTM autoencoder architecture with an adaptive Bayesian fusion method, advancing fault detection accuracy and efficiency in large-scale industrial process monitoring.

Findings

Significantly improves fault detection performance over single-model approaches.

Effective in handling large-scale, heterogeneous process data.

Demonstrated superior results on the Tennessee Eastman Process benchmark.

Abstract

In this work, we introduce MOLA: a Multi-block Orthogonal Long short-term memory Autoencoder paradigm, to conduct accurate, reliable fault detection of industrial processes. To achieve this, MOLA effectively extracts dynamic orthogonal features by introducing an orthogonality-based loss function to constrain the latent space output. This helps eliminate the redundancy in the features identified, thereby improving the overall monitoring performance. On top of this, a multi-block monitoring structure is proposed, which categorizes the process variables into multiple blocks by leveraging expert process knowledge about their associations with the overall process. Each block is associated with its specific Orthogonal Long short-term memory Autoencoder model, whose extracted dynamic orthogonal features are monitored by distance-based Hotelling's $T^2$ statistics and quantile-based cumulative sum (CUSUM) designed for multivariate data streams that are nonparametric, heterogeneous in nature. Compared to having a single model accounting for all process variables, such a multi-block structure improves the overall process monitoring performance significantly, especially for large-scale industrial processes. Finally, we propose an adaptive weight-based Bayesian fusion (W-BF) framework to aggregate all block-wise monitoring statistics into a global statistic that we monitor for faults, with the goal of improving fault detection speed by assigning weights to blocks based on the sequential order where alarms are raised. We demonstrate the efficiency and effectiveness of our MOLA framework by applying it to the Tennessee Eastman Process and comparing the performance with various benchmark methods.