Process Monitoring Using Canonical Correlation Analysis
Journal: Journal of Independent Studies and Research - Computing (Vol.17, No. 1)Publication Date: 2019-01-01
Authors : Shakir Muhammad SHAIKH Yin SHEN Shahid KARIM VISHAL KUMAR;
Page : 0-0
Keywords : :Canonical correlation Analysis; Process Monitoring; Kernel Density Estimation; Tennessee Eastman Process;
Abstract
Principal component analysis (PCA) and partial least square (PLS) used for fault diagnosis and process monitoring for systems. It is expected that the information to be examined isn't self-connected. However, the most largescale chemical industrial plants are nonlinear in nature so these techniques do not cope with them, invalid in nature. To fulfil the gap, there is need to develop an algorithm which can manage these nonlinearities of the process. The demands of industrial products are increasing rapidly so different adaptable techniques are being proposed. Canonical Correlation Analysis (CCA) is multivariate data-driven methodology which takes input-output both process data into consideration. Most industrial systems assumed that the data to be analyzed is Gaussian in nature. However, it is not due to the nonlinearity's real systems in nature. In this work, an algorithm is developed that can monitor the system process using CCA with control limit that is achieved from the kernel density estimation by estimating probability density function (pdf).
Other Latest Articles
- DISCOURSE BASED OPINION MINING ON ROMAN URDU DATA
- Designing Dispersion Flattened Photonic Crystal Fiber for Wideband Applications
- PERFORMANCE ANALYSIS OF MPLS AND TRADITIONAL IP IN NODE SCALABLE NETWORKS
- Comprehensive Performance Evaluation Of Network Intrusion System Using Machine Learning Approach
- Design And Implementation Of Interim Payment Certificate And Synchronization Of Production Extension In Microsoft AX Dynamics
Last modified: 2021-05-18 16:03:48