The article delves into the development of a fuzzy clustering-based process-monitoring strategy for a multistage manufacturing facility. The monitoring strategy for a multistage manufacturing facility normally employs the multiblock variant of principal component analysis, i.e. MBPCA. However, in case of MBPCA, the clustering of process variables in blocks is facilitated by the prior process knowledge. However, in several cases, the complete process knowledge may not be available. In the current article, a methodology has been proposed to classify the process variables into blocks using the fuzzy clustering technique. The blocks are further used to develop a process representation or model using the consensus principal component analysis based methodology. The model, hence, devised facilitates the detection of upset condition or fault in the process. The diagnosis of the faults has been carried out to estimate the relative contribution of the blocks and the relative contribution of the process and feedstock characteristics within the block. A case study pertaining to an integrated steel plant engaged in the production of wire rods has been used to validate the proposed monitoring strategy.
CITATION STYLE
Suman, S., & Das, A. (2020). Fuzzy Clustering-Based Process-Monitoring Strategy for a Multistage Manufacturing Facility. In Advances in Intelligent Systems and Computing (Vol. 1053, pp. 459–469). Springer. https://doi.org/10.1007/978-981-15-0751-9_43
Mendeley helps you to discover research relevant for your work.