A composite model of field reliability based on a generalized Arrhenius model and a support vector machine model for spindle systems

Xiaoxu Li,Zhaojun Yang,Yang Li,Hongxun Zhao,Xiaotao Li,Dong Zhu,Chuanhai Chen

doi:10.1177/1687814018801258

Abstract

A spindle system is one of the key subsystems of machine tools, whose reliability affects machining precision and production cycle directly. In the field, spindle systems expose to operating environmental conditions and complex working conditions that are referred to as stresses in this article collectively, which can accelerate or decelerate the process of failure. In order to analyze field reliability of spindle systems, the main structure, failure modes of spindle systems are analyzed, and main stresses involved with reliability are determined preliminarily. Then, based on the failure mode and the characteristics of stresses, a linear relationship of stresses and field reliability is built based on generalized Arrhenius models assuming that stresses are independent of each other. The non-linear, coupling relationship of stresses is described by a support vector machine model, whose parameters are selected by cross-validation. Then, two models are integrated to a composite model for minimum assessment error using optimal combined forecasting method. Finally, the proposed model is validated by a real case study, and the assessment errors conform to the production requirement.

Highlights

A spindle system is one of the key subsystems of machine tools, which rotates the tools or workpiece precisely in space and transmits the required energy to the cutting zone for metal removal.[1]
According to the assessment results, the applications of three models are as follows: the linear model can provide a good description of stress effects and screen significant stresses by the field data; the support vector machine15 (SVM) model is good at dealing with non-linear relationship and possible interactions among stresses, which is recommended with higher assessment accuracy and computing power; a composite model of the SVM model and the linear model is more practical in engineering for its highest assessment accuracy and a clear explanation of failure mechanism
When the assessment accuracy and failure mechanism are taken into account, a composite model of the SVM model and linear model is more practical

Summary

Introduction

A spindle system is one of the key subsystems of machine tools, which rotates the tools or workpiece precisely in space and transmits the required energy to the cutting zone for metal removal.[1]. According to the assessment results, the applications of three models are as follows: the linear model can provide a good description of stress effects and screen significant stresses by the field data; the SVM model is good at dealing with non-linear relationship and possible interactions among stresses, which is recommended with higher assessment accuracy and computing power; a composite model of the SVM model and the linear model is more practical in engineering for its highest assessment accuracy and a clear explanation of failure mechanism

Declaration of conflicting interests

Findings

Conclusion