Graph Complexity Reduction of Exergy-Based FDI-A Tennessee Eastman Process Case Study

Article Engineering, Environmental

Exploring global attention mechanism on fault detection and diagnosis for complex engineering processes

Kun Zhou et al.

Summary: Considering the slow drift and complicated relationships caused by corrosion and fatigue in complex chemical engineering processes, a method called Industrial Process Optimization ViT (IPO-ViT) was proposed. The method makes use of the self-attention mechanism of Vision Transformer (ViT) to explore the global receptive field for fault detection and diagnosis (FDD). The results from real industrial process data and Tennessee Eastman (TE) process data showed that IPO-ViT outperforms other deep learning methods with local receptive fields, without the need for additional samples or computations. Additionally, the study identified the challenges of local attention explosion, information alignment, and expression capability in improving complex deep learning network structures for industrial applications.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2023)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Improved energy graph-based visualisation fault detection and isolation - A spectral theorem approach

Wikus Wolmarans et al.

Summary: This paper explains how the energy graph-based visualisation (EGBV) fault detection and isolation (FDI) method can be related to the spectral theorem to understand its sensitivity and robustness. The paper demonstrates that the EGBV monitoring structure can be divided into different importance components and proposes a guideline for component removal. These principles are applied to a practical heated two-tank process and show that removing less important components improves the robustness of EGBV and reduces computational requirements.

COMPUTERS & CHEMICAL ENGINEERING (2023)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

One step forward for smart chemical process fault detection and diagnosis

Xiaotian Bi et al.

Summary: Process fault detection and diagnosis is an essential tool for ensuring safe production in chemical industries. However, most current methods are not smart enough to handle the complex challenges in real industrial processes, resulting in a lack of commercialized tools. This paper provides an overview of the concept and major challenges of smart fault detection and diagnosis, evaluates recent methods, and discusses future opportunities and perspectives.

COMPUTERS & CHEMICAL ENGINEERING (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

An energy graph eigendecomposition approach to fault detection and isolation applied to a gas-to-liquids process

Sarita Greyling et al.

Summary: Fault detection and isolation (FDI) is an important part of process monitoring, and novel energy-based FDI techniques have been proposed in recent years. This study compares the applicability and performance of different energy-based methods in a gas-to-liquid process, showing varying degrees of effectiveness in fault detection and isolation.

COMPUTERS & CHEMICAL ENGINEERING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

High-speed train fault detection with unsupervised causality-based feature extraction methods

Yubo Xu et al.

Summary: With the advancement of smart sensors, there are more opportunities for efficient and effective fault detection and diagnosis in complex systems like high-speed trains. However, challenges arise due to the redundancy, uselessness, and noise of the collected data, as well as the curse of dimensionality in data-driven methods. Causality-based feature extraction methods have been shown to offer more explanatory and robust FDD modeling than traditional correlation-based methods, with experiments demonstrating their effectiveness and advantages in fault detection.

ADVANCED ENGINEERING INFORMATICS (2021)

添加到收藏夹

Article Energy & Fuels