A NMF-based extraction of physically meaningful components from sensory data of metal casting processes. (January 2020)

• Record Type: Journal Article
• Authors: Weiderer, Peter; Tomé, Ana Maria; Lang, Elmar W.
• Is Part Of: Journal of manufacturing systems. Volume 54(2020)
• Page Start: 62
• Page End: 73
• Publication Date: 2020-01
• Subjects: Blind source separation -- Nonnegative matrix factorization -- Temperature time series -- Metal casting -- Mold casting; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2019.09.013
• Languages: English
• ISSNs: 0278-6125

Abstract

Highlights: Simple temperature signals can be decomposed into physical meaningful components with unsupervised learning by using a physics-motivated initialization. Via Blind Source Separation variations during a thermal manufacturing process can be modeled in an interpretable way and monitored during running production. An non-interruptive measurement method for the release agent layer in metal casting, which solely relies on the use of temperature sensors, is shown. Abstract: The paper introduces a novel approach for the extraction of physically meaningful thermal component time series during the manufacturing of casting parts. We treat their extraction as Blind Source Separation (BSS) problem by exploiting process-related prior knowledge. Our proposed method arranges temperature time series into a data matrix, which is then decomposed by Non-negative Matrix Factorization (NMF). The latter is guided by a knowledge-based strategy, which initializes the NMF component matrix with time curves designed according to basic physical processes. The temperature time series encompass exclusively non-negative data. Hence NMF lends itself a natural choice as it does not impose mathematical constraints that lack any immediate physical interpretation. We show how to extract components linked to physical phenomena that typically occur during production and cannot be monitored directly. We apply our method to real world data, collected in a foundry during the series production of casting parts for the automobile industry and demonstrate its efficiency.