Monitoring of Mineral Processing Operations based on Multivariate Similarity Indices
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 proxim...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
Elsevier
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/35838 |
| _version_ | 1848754605127630848 |
|---|---|
| author | Auret, L. Aldrich, Chris |
| author2 | L Auret |
| author_facet | L Auret Auret, L. Aldrich, Chris |
| author_sort | Auret, L. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | 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. |
| first_indexed | 2025-11-14T08:43:04Z |
| format | Conference Paper |
| id | curtin-20.500.11937-35838 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:43:04Z |
| publishDate | 2011 |
| publisher | Elsevier |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-358382023-01-27T05:52:10Z Monitoring of Mineral Processing Operations based on Multivariate Similarity Indices Auret, L. Aldrich, Chris L Auret C Aldrich random forests machine learning mineral processing Fault detection 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. 2011 Conference Paper http://hdl.handle.net/20.500.11937/35838 Elsevier restricted |
| spellingShingle | random forests machine learning mineral processing Fault detection Auret, L. Aldrich, Chris Monitoring of Mineral Processing Operations based on Multivariate Similarity Indices |
| title | Monitoring of Mineral Processing Operations based on Multivariate Similarity Indices |
| title_full | Monitoring of Mineral Processing Operations based on Multivariate Similarity Indices |
| title_fullStr | Monitoring of Mineral Processing Operations based on Multivariate Similarity Indices |
| title_full_unstemmed | Monitoring of Mineral Processing Operations based on Multivariate Similarity Indices |
| title_short | Monitoring of Mineral Processing Operations based on Multivariate Similarity Indices |
| title_sort | monitoring of mineral processing operations based on multivariate similarity indices |
| topic | random forests machine learning mineral processing Fault detection |
| url | http://hdl.handle.net/20.500.11937/35838 |