Condition Monitoring of Manufacturing Processes under Low Sampling Rate

Abstract

Manufacturing processes can be monitored for anomalies and failures just like machines, in condition monitoring and prognostic and health management. This research takes inspiration from condition monitoring and prognostic and health management techniques to develop a method for part production process monitoring. The contribution brought by this paper is an automated technique for process monitoring that works with low sampling rates of 1/3Hz, a limitation that comes from using data provided by an industrial partner and acquired from industrial manufacturing processes. The technique uses kernel density estimation functions on machine tools spindle load historical time signals for distribution estimation. It then uses this estimation to monitor the manufacturing processes for anomalies in real time. A modified version was tested by our industrial partner on a titanium part manufacturing line.

Time Latency-Centric Signal Processing: A Perspective of Smart Manufacturing

“…Bayma et al [29] proposed a Non-linear Output Frequency Response Functions (NOFRFs)-based approach for analyzing non-linear systems from the contexts of condition monitoring, fault diagnosis, and non-linear modal analysis. Bernard et al [13] articulated that in the machine/process-condition monitoring research area, the methods used or introduced highly depend on high data acquisition rates. They emphasized the need for alternative methods that can perform with low data acquisition rates to meet some challenges of intelligent manufacturing, such as fast computation and low data storage.…”

“…These algorithms become the core of an intelligent monitoring system. However, the conventional signal processing methods (time, frequency, and timefrequency domain-based processing) require high data acquisition rates [13] and cannot mimic the dynamics underlying the signals [11]. Now, complex communication networks underlying smart manufacturing entail a phenomenon called time latency (also known as time delay) [14,15], which results in a low data acquisition rate.…”

“…Section 2 presents a literature review on sensor signal processing methods for machine-and process-condition monitoring. Section 3 presents the significances of the delay domain-based signal processing since the delay domain directly incorporates time latency associated However, the conventional signal processing methods (time, frequency, and timefrequency domain-based processing) require high data acquisition rates [13] and cannot mimic the dynamics underlying the signals [11]. Now, complex communication networks underlying smart manufacturing entail a phenomenon called time latency (also known as time delay) [14,15], which results in a low data acquisition rate.…”

Innovative Smart Drilling with Critical Event Detection and Material Classification

“…The seamless connection in CPS allows for collecting data from the real environment, then, suitable decisions are selected and enacted in real-time [16,18,19]. CPS features advanced actuation and sensing [1], in-process measurement [20], real-time health monitoring [21], life assessment [1,11,20], self-adaptation [22], and collaboration with artificial intelligence (AI) [1,23,24]. The aim of this project is to develop a novel drilling machine that incorporates technologies discovered in the fourth industrial revolution such that it can revolutionize the drilling process.…”