The conventional single model strategy may be ill- suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis （GLDA） based Gaussian process regression （GPR...The conventional single model strategy may be ill- suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis （GLDA） based Gaussian process regression （GPR） approach is developed for the quality prediction of nonlinear and multiphase batch processes. After the collected data is preprocessed through batchwise unfolding, the hidden Markov model （HMM） is applied to identify different operation phases. A GLDA algorithm is also presented to extract the appropriate process variables highly correlated with the quality variables, decreasing the complexity of modeling. Besides, the multiple local GPR models are built in the reduced- dimensional space for all the identified operation phases. Furthermore, the HMM-based state estimation is used to classify each measurement sample of a test batch into a corresponding phase with the maximal likelihood estimation. Therefore, the local GPR model with respect to specific phase is selected for online prediction. The effectiveness of the proposed prediction approach is demonstrated through the multiphase penicillin fermentation process. The comparison results show that the proposed GLDA-GPR approach is superior to the regular GPR model and the GPR based on HMM （HMM-GPR） model.展开更多
Underground water （Borehole） has been the main alternative source of drinking water for most communities in my country. Previous studies have revealed high levels of contamination. The origin of which can be attribu...Underground water （Borehole） has been the main alternative source of drinking water for most communities in my country. Previous studies have revealed high levels of contamination. The origin of which can be attributed to geochemical processes, combustion of fossil fuels, mining and anthropogenic activities. Most borehole water and well water in local communities of Nigeria are not safe for drinking due to heavy industrial and environmental pollution. This study was undertaken to assess the quality in some selected boreholes in the Port Harcourt metropolis for a period of two years. Borehole water samples were randomly collected from thirteen boreholes in a local community in plastic bottles （100 mL） in the months of September for the years of study （2010 ＆ 2011）. Four out of the seven heavy metals analyzed were found to be present in the first year of study. These were Fe, Cu, Mn and Zn. In the second year of study, Pb, Cr, Fe and Co were not detected in all of the samples except Cu and Fe which were present in only two samples. Mn and Zn were found to be present in all of the samples for both years of study.展开更多
基金The Fundamental Research Funds for the Central Universities(No.JUDCF12027,JUSRP51323B)the Scientific Innovation Research of College Graduates in Jiangsu Province(No.CXLX12_0734)
文摘The conventional single model strategy may be ill- suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis （GLDA） based Gaussian process regression （GPR） approach is developed for the quality prediction of nonlinear and multiphase batch processes. After the collected data is preprocessed through batchwise unfolding, the hidden Markov model （HMM） is applied to identify different operation phases. A GLDA algorithm is also presented to extract the appropriate process variables highly correlated with the quality variables, decreasing the complexity of modeling. Besides, the multiple local GPR models are built in the reduced- dimensional space for all the identified operation phases. Furthermore, the HMM-based state estimation is used to classify each measurement sample of a test batch into a corresponding phase with the maximal likelihood estimation. Therefore, the local GPR model with respect to specific phase is selected for online prediction. The effectiveness of the proposed prediction approach is demonstrated through the multiphase penicillin fermentation process. The comparison results show that the proposed GLDA-GPR approach is superior to the regular GPR model and the GPR based on HMM （HMM-GPR） model.
文摘Underground water （Borehole） has been the main alternative source of drinking water for most communities in my country. Previous studies have revealed high levels of contamination. The origin of which can be attributed to geochemical processes, combustion of fossil fuels, mining and anthropogenic activities. Most borehole water and well water in local communities of Nigeria are not safe for drinking due to heavy industrial and environmental pollution. This study was undertaken to assess the quality in some selected boreholes in the Port Harcourt metropolis for a period of two years. Borehole water samples were randomly collected from thirteen boreholes in a local community in plastic bottles （100 mL） in the months of September for the years of study （2010 ＆ 2011）. Four out of the seven heavy metals analyzed were found to be present in the first year of study. These were Fe, Cu, Mn and Zn. In the second year of study, Pb, Cr, Fe and Co were not detected in all of the samples except Cu and Fe which were present in only two samples. Mn and Zn were found to be present in all of the samples for both years of study.
