Generative adversarial wavelet neural operator: Application to fault detection and isolation of multivariate time series data

TL;DR

This paper introduces GAWNO, a novel unsupervised deep learning framework combining wavelet neural operators and GANs for effective fault detection and isolation in multivariate time series data, validated on industrial datasets.

Contribution

The paper presents GAWNO, a new method integrating wavelet neural operators with GANs for improved fault detection and isolation in complex multivariate systems.

Findings

GAWNO outperforms baseline methods in fault detection accuracy.

Effective in capturing temporal and spatial dependencies.

Validated on multiple industrial datasets.

Abstract

Fault detection and isolation in complex systems are critical to ensure reliable and efficient operation. However, traditional fault detection methods often struggle with issues such as nonlinearity and multivariate characteristics of the time series variables. This article proposes a generative adversarial wavelet neural operator (GAWNO) as a novel unsupervised deep learning approach for fault detection and isolation of multivariate time series processes.The GAWNO combines the strengths of wavelet neural operators and generative adversarial networks (GANs) to effectively capture both the temporal distributions and the spatial dependencies among different variables of an underlying system. The approach of fault detection and isolation using GAWNO consists of two main stages. In the first stage, the GAWNO is trained on a dataset of normal operating conditions to learn the underlying data distribution. In the second stage, a reconstruction error-based threshold approach using the trained GAWNO is employed to detect and isolate faults based on the discrepancy values. We validate the proposed approach using the Tennessee Eastman Process (TEP) dataset and Avedore wastewater treatment plant (WWTP) and N2O emissions named as WWTPN2O datasets. Overall, we showcase that the idea of harnessing the power of wavelet analysis, neural operators, and generative models in a single framework to detect and isolate faults has shown promising results compared to various well-established baselines in the literature.