Authors
Clint Saidy, Kaishu Xia, Anil Kircaliali, Ramy Harik, Abdel Bayoumi
Conference
(pp. 1051-1061). Springer, Cham.
Abstract
Statistical Process Control (SPC) is a technique of gauging and monitoring quality by closely observing a given manufacturing process. Appropriate quality data is collected in the form of product measurements or readings from various machines. This data is used in evaluating, monitoring and controlling the variability of the considered manufacturing process. This paper proposes the expansion of SPC methods to predictive maintenance. Applications of SPC techniques in various fields outside of basic production systems have been increasing in popularity. This paper investigates the practicality and viability of using Control Charts in predictive maintenance and health monitoring. Moreover, this study discusses numerous enabling technologies, such as Industrial Internet of Things (IIOT), that help to advance real-time monitoring of industrial processes. This study also expands on the use of Naïve-Bayes and other Machine Learning methods to identify strong (naïve) dependencies between specific faults and special patterns in monitored measurements. Despite its idealistic independence assumption, the naïve Bayes classifier is effective in practice since its classification decision may often be correct even if its probability estimates are inaccurate. Optimal conditions of naïve Bayes will be also identified, and a deeper understanding of data characteristics that affect the performance of naïve Bayes is analyzed.
Keywords
predictive maintenance, statistical process control, industry 4.0, health monitoring, machine learning, data analytics
Citation
Clint Saidy, Kaishu Xia, Anil Kircaliali, Ramy Harik, & Abdel Bayoumi. (August 2020). The Application of Statistical Quality Control Methods in Predictive Maintenance 4.0: An Unconventional Use of Statistical Process Control (SPC) Charts in Health Monitoring and Predictive Analytics. (pp. 1051-1061). Springer, Cham. doi:https://doi.org/10.1007/978-3-030-57745-2_87
Link: https://link.springer.com/chapter/10.1007/978-3-030-57745-2_87