Ensemble modelling technique for a micro-drilling process based on a two-stage bootstrap

ABSTRACT

Quality improvement in micro-manufacturing processes relies on empirical models. However, if an estimated model varies from the true model because of random errors in experiments, the resulting operating conditions may be located far from the true optimal operating conditions. Using the Pareto chart, which highlights the most important among a set of factors, this article develops a novel ensemble modelling technique which considers the model selection via bootstrap methods. In addition, an integrative optimization strategy is proposed based on interval-data theory, in which the squared bias and the reliability of operating conditions are incorporated into a single framework of a strategy. The proposed method is illustrated with a micro-drilling process, which clearly shows how useful and effective the proposed method is. Through comparative studies, it is also shown that the proposed method has a good robustness property and it provides a reliable scheme for optimizing the machining parameters.

KEYWORDS:

• Ensemble modelling
• model selection
• bootstrap method
• Pareto chart
• micro-manufacturing process

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by National Natural Science Foundation of China [grant numbers 71702072, 71471088 and 71771121]; the Postdoctoral Science Foundation of Jiangsu Province [grant number 1701142B]; the China Postdoctoral Science Foundation [grant number 2017M611808]; the Fundamental Research Fund for the Central Universities [grant number NR2017004]; and the Natural Science Foundation for Jiangsu Institutions [grant number BK20170810].