Multi-model approach can significantly improve the prediction performance of soft sensors in the process with multiple operational conditions.However,traditional clustering algorithms may result in overlapping phenome...Multi-model approach can significantly improve the prediction performance of soft sensors in the process with multiple operational conditions.However,traditional clustering algorithms may result in overlapping phenomenon in subclasses,so that edge classes and outliers cannot be effectively dealt with and the modeling result is not satisfactory.In order to solve these problems,a new feature extraction method based on weighted kernel Fisher criterion is presented to improve the clustering accuracy,in which feature mapping is adopted to bring the edge classes and outliers closer to other normal subclasses.Furthermore,the classified data are used to develop a multiple model based on support vector machine.The proposed method is applied to a bisphenol A production process for prediction of the quality index.The simulation results demonstrate its ability in improving the data classification and the prediction performance of the soft sensor.展开更多
Non-executive directors are now very well established in Chinese business. The uniform and final criterion of weighting the independence of non-executive directors is not available. It will be valuable to draw an anal...Non-executive directors are now very well established in Chinese business. The uniform and final criterion of weighting the independence of non-executive directors is not available. It will be valuable to draw an analogy with the criterion of weighting the independence of non-executive directors in the UK, where over a dozen different criterions are applied.展开更多
Wellbore instability is reported frequently as one of the most significant incidents during drilling operations.Analysis of wellbore instability includes estimation of formation mechanical properties and the state of ...Wellbore instability is reported frequently as one of the most significant incidents during drilling operations.Analysis of wellbore instability includes estimation of formation mechanical properties and the state of in situ stresses.In this analysis,the only controllable parameter during drilling operation is the mud weight.If the mud weight is larger than anticipated,the mud will invade into the formation,causing tensile failure of the formation.On the other hand,a lower mud weight can result in shear failures of rock,which is known as borehole breakouts.To predict the potential for failures around the wellbore during drilling,one should use a failure criterion to compare the rock strength against induced tangential stresses around the wellbore at a given mud pressure.The Mohr–Coulomb failure criterion is one of the commonly accepted criteria for estimation of rock strength at a given state of stress.However,the use of other criteria has been debated in the literature.In this paper,Mohr–Coulomb,Hoek–Brown and Mogi–Coulomb failure criteria were used to estimate the potential rock failure around a wellbore located in an onshorefield of Iran.The log based analysis was used to estimate rock mechanical properties of formations and state of stresses.The results indicated that amongst different failure criteria,the Mohr–Coulomb criterion underestimates the highest mud pressure required to avoid breakouts around the wellbore.It also predicts a lower fracture gradient pressure.In addition,it was found that the results obtained from Mogi–Coulomb criterion yield a better comparison with breakouts observed from the caliper logs than that of Hoek–Brown criterion.It was concluded that the Mogi–Coulomb criterion is a better failure criterion as it considers the effect of the intermediate principal stress component in the failure analysis.展开更多
基金Supported by the National Natural Science Foundation of China(61273070)the Foundation of Priority Academic Program Development of Jiangsu Higher Education Institutions
文摘Multi-model approach can significantly improve the prediction performance of soft sensors in the process with multiple operational conditions.However,traditional clustering algorithms may result in overlapping phenomenon in subclasses,so that edge classes and outliers cannot be effectively dealt with and the modeling result is not satisfactory.In order to solve these problems,a new feature extraction method based on weighted kernel Fisher criterion is presented to improve the clustering accuracy,in which feature mapping is adopted to bring the edge classes and outliers closer to other normal subclasses.Furthermore,the classified data are used to develop a multiple model based on support vector machine.The proposed method is applied to a bisphenol A production process for prediction of the quality index.The simulation results demonstrate its ability in improving the data classification and the prediction performance of the soft sensor.
文摘Non-executive directors are now very well established in Chinese business. The uniform and final criterion of weighting the independence of non-executive directors is not available. It will be valuable to draw an analogy with the criterion of weighting the independence of non-executive directors in the UK, where over a dozen different criterions are applied.
文摘Wellbore instability is reported frequently as one of the most significant incidents during drilling operations.Analysis of wellbore instability includes estimation of formation mechanical properties and the state of in situ stresses.In this analysis,the only controllable parameter during drilling operation is the mud weight.If the mud weight is larger than anticipated,the mud will invade into the formation,causing tensile failure of the formation.On the other hand,a lower mud weight can result in shear failures of rock,which is known as borehole breakouts.To predict the potential for failures around the wellbore during drilling,one should use a failure criterion to compare the rock strength against induced tangential stresses around the wellbore at a given mud pressure.The Mohr–Coulomb failure criterion is one of the commonly accepted criteria for estimation of rock strength at a given state of stress.However,the use of other criteria has been debated in the literature.In this paper,Mohr–Coulomb,Hoek–Brown and Mogi–Coulomb failure criteria were used to estimate the potential rock failure around a wellbore located in an onshorefield of Iran.The log based analysis was used to estimate rock mechanical properties of formations and state of stresses.The results indicated that amongst different failure criteria,the Mohr–Coulomb criterion underestimates the highest mud pressure required to avoid breakouts around the wellbore.It also predicts a lower fracture gradient pressure.In addition,it was found that the results obtained from Mogi–Coulomb criterion yield a better comparison with breakouts observed from the caliper logs than that of Hoek–Brown criterion.It was concluded that the Mogi–Coulomb criterion is a better failure criterion as it considers the effect of the intermediate principal stress component in the failure analysis.
