Variation source identification for deep hole boring process of cutting-hard workpiece based on multi-source information fusion using evidence theory

详细信息    查看全文

• 作者：Xueliang Zhou ; Pingyu Jiang
• 关键词：Variation source identification ; Evidence theory ; Run chart ; Fuzzy support vector machine (FSVM)
• 刊名：Journal of Intelligent Manufacturing
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：28
• 期：2
• 页码：255-270
• 全文大小：
• 刊物类别：Business and Economics
• 刊物主题：Production; Manufacturing, Machines, Tools; Control, Robotics, Mechatronics;
• 出版者：Springer US
• ISSN：1572-8145
• 卷排序：28

文摘

Variation source identification for machining process is a key issue in closed-loop quality control, and critical for quality and productivity improvement. Meanwhile, it is a challenging engineering problem, especially for deep hole boring process of cutting-hard workpiece due to its complexity and instability. In this paper, a systematic method of variation source identification for deep hole boring process based on multi-source information fusion using Dempster–Shafter (D–S) evidence theory is proposed. A logic framework for variation source identification is presented to address how this issue can be formulated in the frame of evidence theory, in terms of evidence acquisition, variation source frame of discernment, mass functions and the rules for evidence combination and decision-making. First, run charts are applied to detect the non-random variation of quality measurements of one workpiece, which are acquired at equidistant positions along the axis direction of the hole. And the unnatural run chart patterns are detected by using fuzzy support vector machine and regarded as information cues for variation source identification. Then, the frame of discernment which consists of potential variation source in case of every specific unnatural pattern is constructed. The mass functions that represent the degree of belief supported by the unnatural patterns regarding the possible causes are determined by using judgment matrixes, and treated as pieces of evidences of variation source identification. Afterwards, all of the evidences are combined by using D–S fusion rules. The rules for making reliable diagnostic decisions are also addressed. Finally, a case study is put forward to demonstrate the feasibility and effectiveness of the proposed methodology. The results indicate that the proposed method can resolve the conflicts among the evidences and improve the accuracy of variation source identification for deep hole boring process.