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
An integrated framework is presented to represent and classify process data for on-line identifying abnormal operating conditions. It is based on pattern recognition principles and consists of a feature extraction ste...An integrated framework is presented to represent and classify process data for on-line identifying abnormal operating conditions. It is based on pattern recognition principles and consists of a feature extraction step, by which wavelet transform and principal component analysis are used to capture the inherent characteristics from process measurements, followed by a similarity assessment step using hidden Markov model (HMM) for pattern comparison. In most previous cases, a fixed-length moving window was employed to track dynamic data, and often failed to capture enough information for each fault and sometimes even deteriorated the diagnostic performance. A variable moving window, the length of which is modified with time, is introduced in this paper and case studies on the Tennessee Eastman process illustrate the potential of the proposed method.展开更多
CFG pile has been widely applied as one of the common ground treatment techniques. As a concealed work, the construction quality of pile foundation not only relates to the success of the project, but also concerns the...CFG pile has been widely applied as one of the common ground treatment techniques. As a concealed work, the construction quality of pile foundation not only relates to the success of the project, but also concerns the benefits of thousands of hot, seholds. Only strengthening the supervision and management during the construction and strictly designing and specifying CFG pile can ensure the construction quality of CFG pile. But most researches focus on operating mechanism and theoretical analysis, and there are fewer researches about the construction of CFG pile. The real construction of CFG pile has no specified operation and lacks of the construction guidance, which not only causes great problems and has great influence on the intensity of CFG pile, but also makes the real pile body have great difference from the design requirements. Therefore, the study on construction of CFG pile in the paper has great significance.展开更多
This paper discusses the issue of the hidden curriculum in the setting of a language classroom. The author first talks about the definition of the hidden curriculum from a theoretical perspective and proposes her own ...This paper discusses the issue of the hidden curriculum in the setting of a language classroom. The author first talks about the definition of the hidden curriculum from a theoretical perspective and proposes her own working definition. She then elaborates on the reasons and main manifestations of the hidden curriculum from the teachers＇ and learners＇ angles respectively with examples taken from language classrooms. Based on some profound reflections, some feasible suggestions on how to minimize the negative impacts of the hidden curriculum are suggested. On the basis of the previous discussion, the author reaches a conclusion： Language teachers should not avoid or ignore the hidden curriculum existing in the language teaching processes; rather, they are expected to face it positively and try their very best to solve the problems it brings. A sound attitude towards the hidden curriculum can help language teachers better understand and implement the formal or official curriculum made by the school or the state.展开更多
Banking institutions all over the world face significant challenge due to the cumulative loss due to defaults of borrowers of different types of loans. The cumulative default loss built up over a period of time could ...Banking institutions all over the world face significant challenge due to the cumulative loss due to defaults of borrowers of different types of loans. The cumulative default loss built up over a period of time could wipe out the capital cushion of the banks. The aim of this paper is to help the banks to forecast the cumulative loss and its volatility. Defaulting amounts are random and defaults occur at random instants of time. A non Markovian time dependent random point process is used to model the cumulative loss. The expected loss and volatility are evaluated analytically. They are functions of probability of default, probability of loss amount, recovery rate and time. Probability of default being the important contributor is evaluated using Hidden Markov modeling. Numerical results obtained validate the model.展开更多
The causal states of computational mechanics define the minimal sufficient memory for a given discrete stationary stochastic process. Their entropy is an important complexity measure called statistical complexity （or...The causal states of computational mechanics define the minimal sufficient memory for a given discrete stationary stochastic process. Their entropy is an important complexity measure called statistical complexity （or true measure complexity）. They induce the s-machine, which is a hidden Markov model （HMM） generating the process. But it is not the minimal one, although generative HMMs also have a natural predictive interpretation. This paper gives a mathematical proof of the idea that the s-machine is the minimal HMM with an additional （partial） determinism condition. Minimal internal state entropy of a generative HMM is in analogy to statistical complexity called generative complexity. This paper also shows that generative complexity depends on the process in a nice way. It is, as a function of the process, lower semi-continuous （w.r.t. weak-, topology）, concave, and behaves nice under ergodic decomposition of the process.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.
基金Supported by National High-Tech Program of China (No. 2001AA413110).
文摘An integrated framework is presented to represent and classify process data for on-line identifying abnormal operating conditions. It is based on pattern recognition principles and consists of a feature extraction step, by which wavelet transform and principal component analysis are used to capture the inherent characteristics from process measurements, followed by a similarity assessment step using hidden Markov model (HMM) for pattern comparison. In most previous cases, a fixed-length moving window was employed to track dynamic data, and often failed to capture enough information for each fault and sometimes even deteriorated the diagnostic performance. A variable moving window, the length of which is modified with time, is introduced in this paper and case studies on the Tennessee Eastman process illustrate the potential of the proposed method.
文摘CFG pile has been widely applied as one of the common ground treatment techniques. As a concealed work, the construction quality of pile foundation not only relates to the success of the project, but also concerns the benefits of thousands of hot, seholds. Only strengthening the supervision and management during the construction and strictly designing and specifying CFG pile can ensure the construction quality of CFG pile. But most researches focus on operating mechanism and theoretical analysis, and there are fewer researches about the construction of CFG pile. The real construction of CFG pile has no specified operation and lacks of the construction guidance, which not only causes great problems and has great influence on the intensity of CFG pile, but also makes the real pile body have great difference from the design requirements. Therefore, the study on construction of CFG pile in the paper has great significance.
文摘This paper discusses the issue of the hidden curriculum in the setting of a language classroom. The author first talks about the definition of the hidden curriculum from a theoretical perspective and proposes her own working definition. She then elaborates on the reasons and main manifestations of the hidden curriculum from the teachers＇ and learners＇ angles respectively with examples taken from language classrooms. Based on some profound reflections, some feasible suggestions on how to minimize the negative impacts of the hidden curriculum are suggested. On the basis of the previous discussion, the author reaches a conclusion： Language teachers should not avoid or ignore the hidden curriculum existing in the language teaching processes; rather, they are expected to face it positively and try their very best to solve the problems it brings. A sound attitude towards the hidden curriculum can help language teachers better understand and implement the formal or official curriculum made by the school or the state.
文摘Banking institutions all over the world face significant challenge due to the cumulative loss due to defaults of borrowers of different types of loans. The cumulative default loss built up over a period of time could wipe out the capital cushion of the banks. The aim of this paper is to help the banks to forecast the cumulative loss and its volatility. Defaulting amounts are random and defaults occur at random instants of time. A non Markovian time dependent random point process is used to model the cumulative loss. The expected loss and volatility are evaluated analytically. They are functions of probability of default, probability of loss amount, recovery rate and time. Probability of default being the important contributor is evaluated using Hidden Markov modeling. Numerical results obtained validate the model.
文摘The causal states of computational mechanics define the minimal sufficient memory for a given discrete stationary stochastic process. Their entropy is an important complexity measure called statistical complexity （or true measure complexity）. They induce the s-machine, which is a hidden Markov model （HMM） generating the process. But it is not the minimal one, although generative HMMs also have a natural predictive interpretation. This paper gives a mathematical proof of the idea that the s-machine is the minimal HMM with an additional （partial） determinism condition. Minimal internal state entropy of a generative HMM is in analogy to statistical complexity called generative complexity. This paper also shows that generative complexity depends on the process in a nice way. It is, as a function of the process, lower semi-continuous （w.r.t. weak-, topology）, concave, and behaves nice under ergodic decomposition of the process.
