Monitoring of Mineral Processing Operations based on Multivariate Similarity Indices
MetadataShow full item record
Multivariate process monitoring through covariance control charts considers changes in the relationships among process variables, but is limited by linearity assumptions. In this paper two nonlinear indicators of multivariate structure are considered, viz. mutual information and random forest proximity measures. Similarity matrices are constructed from data encapsulated by sliding windows of different sizes across the time series data associated with process operations. Diagnostic metrics reflect the differences between stationary base windows representative of normal operating conditions and test windows containing new process data. A case study in mineral processing shows that better results can be obtained with these nonlinear methods.
Showing items related by title, author, creator and subject.
Kirby, Nigel Matthew (2003)The widespread use of high temperature superconductors through improved understanding of their underlying physics is in part dependent on the synthesis of large, high quality single crystals for physical research. Crucible ...
A grounded theory study of the clinical use of the nursing process within selected hospital settings.O'Connell, Beverly O. (1997)The nursing process is the espoused problem solving framework that forms the basis of the way in which patient care is determined, delivered, and communicated in a multiplicity of health care settings. Although its use ...
de V. Groenewald, J.; Coetzer, L.; Aldrich, Chris (2006)With the increasing availability of large amounts of real-time process data and a better fundamental understanding of the operation of mineral processing units, statistical monitoring of mineral processing plants is ...