Estimation and monitoring of key performance indicators of manufacturing systems using the multi-output Gaussian process

Abstract

Recently, the estimation and monitoring of manufacturing key performance indicators (KPIs) have drawn significant attention. In this article, a KPI estimation and monitoring method using a multi-output Gaussian process (MGP) is proposed. The Gaussian process (GP) is an effective non-parametric flexible tool for data-driven statistical modelling for various systems. The unique features of the proposed method is that the MGP enjoys the high flexibility and desirable analytical properties of the GP while also capturing the correlation between different KPIs, thus providing better estimation accuracy and error quantification. The advantageous features of the proposed method are demonstrated through a numerical study as well as a case study with real world data in the estimation and monitoring of throughput for a multiclass production operation.

Keywords:

• performance measures
• statistical methods
• manufacturing systems engineering
• multi-output Gaussian process
• convolution process