Statistical process monitoring using control charts is a well-established quality tool for understanding and improving the performance of manufacturing processes over the time. In view of Industry 4.0, industries are looking forward for innovative, automated solutions to process monitoring and control over the traditional approaches. This chapter presents an innovative approach for monitoring the machining process using integration of three well-established techniques to provide a machine vision based multivariate statistical process monitoring technique (MSPM) with dimensionality reduction using principal component analysis (PCA). The approach is demonstrated using a case study of industrial components manufactured on conventional lathe machines. It involves extraction of critical dimensions and surface characteristics using image processing techniques, data dimensionality reduction using PCA, followed by process monitoring using Hotelling T2 multivariate statistical control chart based on principal component scores. The approach has a potential to provide an industry-ready solution to automated, economic and 100% process monitoring.
CITATION STYLE
Joshi, K. N., Patil, B. T., & Vaishnav, H. B. (2020). Principal Components Based Multivariate Statistical Process Monitoring of Machining Process Using Machine Vision Approach. In Studies in Big Data (Vol. 64, pp. 145–160). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-25778-1_7
Mendeley helps you to discover research relevant for your work.