[论文解读] Generative adversarial wavelet neural operator: Application to fault detection and isolation of multivariate time series data

Jyoti Rani, Tapas Tripura+2 more|arXiv (Cornell University)|Jan 8, 2024

Fault Detection and Control Systems被引用 5

一句话总结

这篇论文提出 GAWNO，一种将小波神经算子与 GAN 结合的生成对抗框架，用于检测和隔离多变量时间序列中的故障，并在工业数据集上得到验证。

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.

研究动机与目标

• 面向来自工业过程的高维、非线性的多变量时间序列的故障检测与隔离。
• 开发一个在正常运行下学习底层数据分布的框架，以实现异常检测。
• 结合小波分析与神经算子以捕捉时空依赖并提升泛化能力。

提出的方法

• 构建 Generative Adversarial Wavelet Neural Operator (GAWNO)，在 GAN 架构中集成 Wavelet Neural Operators (WNO) 。
• 使用受 U-Net 启发的生成器和判别器，二者都是 WNO，带有提升和降提升的小波积分块。
• 通过离散小波变换在小波空间对核进行参数化，以实现多尺度学习。
• 在正常运行数据上训练 GAN 以学习分布，然后通过重建/与阈值的差异来检测故障。
• 在判别器中使用积分泛函最后一层，将函数值输出映射到标量概率。

实验结果

研究问题

• RQ1 GAWNO 框架是否能够学习正常时间序列数据的精确多变量概率分布？
• RQ2 相较于已有基线，GAWNO 在多变量时间序列中检测和隔离故障的效果如何？
• RQ3 基于小波的算子学习和 GAN 对抗训练在非线性多变量动力学下是否提升故障判别？

主要发现

• GAWNO 使用与 GAN 融合的小波神经算子在正常运行下学习底层分布。
• 故障检测与隔离通过与从正常数据学得的阈值相比的重建/差异来执行。
• 在 Tennessee Eastman Process (TEP) 与 WWTP N2O 数据集上的验证显示，相对于基线有希望的故障检测/隔离性能。
• 该框架利用小波局部化来同时捕捉多变量数据的时-频与空间依赖。
• 该架构采用深度、内存高效的 U-Net 风格生成器/判别器，具备跳跃连接和多分辨率小波块。
• 与文献基线相比，GAWNO 在所测试数据集上显示出有希望的有效性。