Dynamic Quality Prediction of Manufacturing Process Based on Extreme Learning Machine

Abstract

In many manufacturing processes, the abnormal changes of some key process parameters could result in various categories of faulty products. In this paper, a machine learning approach is developed for dynamic quality prediction of the manufacturing processes. In the proposed model, an extreme learning machine is developed for monitoring the manufacturing process and recognizing faulty quality categories of the products being produced. The proposed model is successfully applied to a japanning-line, which improves the product quality and saves manufacturing cost.

Batch production prediction for the mechanical cutting industry based on process capability analysis: Experimental and modelling

“…Li et al used grey models to establish reliability models and used the latest data to achieve accurate predictions 2 . Guo et al proposed a dynamic quality prediction method for manufacturing processes based on machine learning 3 . In addition, to predict product quality in multi-variety and small-batch production, Xiao et al developed a prediction framework consisting of data-driven and mechanism-based methods 4 .…”