Improving convolutional neural networks for fault diagnosis in chemical processes by incorporating global correlations.

Fault diagnosis (FD) has received attention because of its importance in maintaining safe operations of industrial processes. Recently, modern data-driven FD approaches such as deep learning have shown encouraging performance. Particularly, convolutional neural networks (CNNs) offer an alluring capacity to deal with multivariate time-series data converted into images. Nonetheless, existing CNN techniques focus on capturing local correlations. However, global spatiotemporal correlations often prevail in multivariate time-series data from industrial processes. Hence, extracting global correlations using CNNs from such data requires deep architectures that incur many trainable parameters. This paper proposes a novel local–global scale CNN (LGS-CNN) that directly accounts for local and global correlations. Specifically, the proposed network incorporates local correlations through traditional square kernels and global correlations are collected utilizing spatially separated one-dimensional kernels in a unique arrangement. FD performance on the benchmark Tennessee Eastman process dataset validates the proposed LGS-CNN against CNNs, and other state-of-the-art data-driven FD approaches. • A novel convolutional neural network is proposed for complex fault diagnosis tasks. • The proposed model can handle both local and global spatiotemporal correlations. • The ability to capture global spatiotemporal dependencies is mathematically analyzed. • A closer look at the local receptive fields of the proposed model is provided. • An evaluation against a group of data-driven fault diagnosis techniques is included. [ABSTRACT FROM AUTHOR]