Editorial: Recent advances of AI and machine learning methods in integrated R&D, manufacturing, and supply chain

Abstract

In the Industry 4.0 era, chemical process industry is embracing the broad adoption of Artificial Intelligence (AI) and Machine Learning (ML) methods and algorithms. This Research Topic aims to highlight state-of-the-art research in the fields of R&D, Manufacturing, and Supply Chain management. The papers demonstrate how AI/ML developments are contributing to speed up the product development cycle and how the industry is operating towards breakthrough performances in safety, reliability, and sustainability. The Research Topic is composed by four papers, covering different corners of the spectra of methodologies, processes and problems, as can be appreciated by the following short descriptions of each contribution. Webb et al., addressed the problem of exploring process databases to make robust diagnosis of the relevant modes, which can either be different operational conditions or faults. The authors explore dimensionality reduction (PCA, UMAP) and clustering methods (K-means, DBSCAN, and HDBSCAN). The article is therefore aligned with the current interest in exploiting data for improving process operations. In a similar application domain, Ma et al., demonstrated how nonlinear methods (such as LSTM neural networks) can integrate with linear methods (such as PCA) to optimize the decoking frequency in an industrial cracking furnace. The article is a testimony of successful AI and ML applications in manufacturing. In the scope of industrial process monitoring, Ji et al., designed and demonstrated a multiscale method based on time-frequency analysis (wavelet packet decomposition) and feature fusion (support vector data description). This work goes beyond the use of single scale features, OPEN ACCESS