A Multi-objective Optimization Approach for Feature Selection in Gentelligent Systems

TL;DR

This paper presents a hybrid multi-objective evolutionary algorithm for feature selection in Gentelligent systems, improving fault detection and manufacturing efficiency by optimizing multiple conflicting objectives simultaneously.

Contribution

It introduces a novel hybrid framework combining multi-objective evolutionary algorithms with feature selection tailored for Gentelligent systems, validated on real-world industrial datasets.

Findings

Effective optimization of feature selection and classification performance.

Demonstrated generalizability across different industrial datasets.

Improved fault detection and manufacturing process monitoring.

Abstract

The integration of advanced technologies, such as Artificial Intelligence (AI), into manufacturing processes is attracting significant attention, paving the way for the development of intelligent systems that enhance efficiency and automation. This paper uses the term "Gentelligent system" to refer to systems that incorporate inherent component information (akin to genes in bioinformatics-where manufacturing operations are likened to chromosomes in this study) and automated mechanisms. By implementing reliable fault detection methods, manufacturers can achieve several benefits, including improved product quality, increased yield, and reduced production costs. To support these objectives, we propose a hybrid framework with a dominance-based multi-objective evolutionary algorithm. This mechanism enables simultaneous optimization of feature selection and classification performance by exploring Pareto-optimal solutions in a single run. This solution helps monitor various manufacturing operations, addressing a range of conflicting objectives that need to be minimized together. Manufacturers can leverage such predictive methods and better adapt to emerging trends. To strengthen the validation of our model, we incorporate two real-world datasets from different industrial domains. The results on both datasets demonstrate the generalizability and effectiveness of our approach.