An approach for batch processes monitoring and fault detection based on multiway kernel partial least squares(MKPLS) was presented.It is known that conventional batch process monitoring methods,such as multiway partia...An approach for batch processes monitoring and fault detection based on multiway kernel partial least squares(MKPLS) was presented.It is known that conventional batch process monitoring methods,such as multiway partial least squares(MPLS),are not suitable due to their intrinsic linearity when the variations are nonlinear.To address this issue,kernel partial least squares(KPLS) was used to capture the nonlinear relationship between the latent structures and predictive variables.In addition,KPLS requires only linear algebra and does not involve any nonlinear optimization.In this paper,the application of KPLS was extended to on-line monitoring of batch processes.The proposed batch monitoring method was applied to a simulation benchmark of fed-batch penicillin fermentation process.And the results demonstrate the superior monitoring performance of MKPLS in comparison to MPLS monitoring.展开更多
In this article, a nonlinear dynamic multiway partial least squares (MPLS) based on support vector machines (SVM) is developed for on-line fault detection in batch processes. The approach, referred to as SVM-based DMP...In this article, a nonlinear dynamic multiway partial least squares (MPLS) based on support vector machines (SVM) is developed for on-line fault detection in batch processes. The approach, referred to as SVM-based DMPLS, integrates the SVM with the MPLS model. Process data from normal historical batches are used to develop the MPLS model, and a series of single-input-single-output SVM networks are adopted to approximate nonlinear inner relationship between input and output variables. In addition, the application of a time-lagged window technique not only makes the complementarities of unmeasured data of the monitored batch unnecessary, but also significantly reduces the computation and storage requirements in comparison with the traditional MPLS. The proposed approach is validated by a simulation study of on-line fault detection for a fed-batch penicillin production.展开更多
In this article, a nonlinear dynamic multiway partial least squares (MPLS) based on support vector ma- chines (SVM) is developed for on-line fault detection in batch processes. The approach, referred to as SVM-based D...In this article, a nonlinear dynamic multiway partial least squares (MPLS) based on support vector ma- chines (SVM) is developed for on-line fault detection in batch processes. The approach, referred to as SVM-based DMPLS, integrates the SVM with the MPLS model. Process data from normal historical batches are used to de- velop the MPLS model, and a series of single-input-single-output SVM networks are adopted to approximate nonlinear inner relationship between input and output variables. In addition, the application of a time-lagged win- dow technique not only makes the complementarities of unmeasured data of the monitored batch unnecessary, but also significantly reduces the computation and storage requirements in comparison with the traditional MPLS. The proposed approach is validated by a simulation study of on-line fault detection for a fed-batch penicillin production.展开更多
发酵过程具有时变性、动态性和多阶段性的特点,对其进行故障监测主要采用离线建模方式,但这种方法并不能很好地反映当前生产过程的数据特征。近年来有学者使用即时学习（Just in Time Learning,JITL）在线建模策略来建立精确的在线模型...发酵过程具有时变性、动态性和多阶段性的特点,对其进行故障监测主要采用离线建模方式,但这种方法并不能很好地反映当前生产过程的数据特征。近年来有学者使用即时学习（Just in Time Learning,JITL）在线建模策略来建立精确的在线模型并进行故障监测,但是即时学习在线建模策略存在着模型更新频繁、计算量大的问题？本文提出一种带有模型更新机制的即时学习多向偏最小二乘（JITL-MPLS）的故障监测方法：依据马氏距离相似度,选择相似历史样本建立多向偏最小二乘监测模型;而后通过对比上一时刻的质量测量值和当前时刻的质量预测值的差值是否超限来判断模型是否需要更新,当其差值没有超限,即上一时刻监测模型能够表征当前时刻的数据特征,不更新模型,而是继续沿用,否则更新模型。最后将此方法应用于青霉素发酵仿真系统的在线监测,验证了该方法的有效性。展开更多
The quality prediction of tube hollow model based on the variance staged multiway partial least square (MPLS) method was proposed.The key aspects of staged decomposition of the productive data,calculation of the varia...The quality prediction of tube hollow model based on the variance staged multiway partial least square (MPLS) method was proposed.The key aspects of staged decomposition of the productive data,calculation of the variance value,modeling,and on-lined prediction in the variance-staged MPLS method were introduced.Based on the model,iterative optimal control method was used for quality control of tube hollow.The experimental results show that the obvious benefits of this method are low maintenance cost,good real time function,high reliability precision,and practical application to on-line prediction and optimization on the quality of tube hollow.展开更多
A supersaturated design （SSD）, whose run size is not enough for estimating all the main effects, is commonly used in screening experiments. It offers a potential useful tool to investigate a large number of factors ...A supersaturated design （SSD）, whose run size is not enough for estimating all the main effects, is commonly used in screening experiments. It offers a potential useful tool to investigate a large number of factors with only a few experimental runs. The associated analysis methods have been proposed by many authors to identify active effects in situations where only one response is considered. However, there are often situations where two or more responses are observed simultaneously in one screening experiment, and the analysis of SSDs with multiple responses is thus needed. In this paper, we propose a two-stage variable selection strategy, called the multivariate partial least squares-stepwise regression （MPLS-SR） method, which uses the multivariate partial least squares regression in conjunction with the stepwise regression procedure to select true active effects in SSDs with multiple responses. Simulation studies show that the MPLS-SR method performs pretty good and is easy to understand and implement.展开更多
Energy consumption is an important quality index in the production of seamless tubes. The complex factors affecting energy consumption make it difficult to build its mechanism model, and optimization is also very diff...Energy consumption is an important quality index in the production of seamless tubes. The complex factors affecting energy consumption make it difficult to build its mechanism model, and optimization is also very difficult, if not impossible. The piercing process was divided into three parts based on the production process, and an energy consumption prediction model was proposed based on the step mean value staged multiway partial least square meth- od. On the basis of the batch process prediction model, a genetic algorithm was adopted to calculate the optimum mean value of each process parameter and the minimum piercing energy consumption. Simulation proves that the op- timization method based on the energy consumption prediction model can obtain the optimum process parameters effectively and also provide reliable evidences for practical production.展开更多
基金National Natural Science Foundation of China (No. 61074079)Shanghai Leading Academic Discipline Project,China (No.B504)
文摘An approach for batch processes monitoring and fault detection based on multiway kernel partial least squares(MKPLS) was presented.It is known that conventional batch process monitoring methods,such as multiway partial least squares(MPLS),are not suitable due to their intrinsic linearity when the variations are nonlinear.To address this issue,kernel partial least squares(KPLS) was used to capture the nonlinear relationship between the latent structures and predictive variables.In addition,KPLS requires only linear algebra and does not involve any nonlinear optimization.In this paper,the application of KPLS was extended to on-line monitoring of batch processes.The proposed batch monitoring method was applied to a simulation benchmark of fed-batch penicillin fermentation process.And the results demonstrate the superior monitoring performance of MKPLS in comparison to MPLS monitoring.
基金Supported by the National Natural Science Foundation of China (No.60574038) and the Open Project Program of the State Key Laboratory of Bioreactor Engineering/ECUST.
文摘In this article, a nonlinear dynamic multiway partial least squares (MPLS) based on support vector machines (SVM) is developed for on-line fault detection in batch processes. The approach, referred to as SVM-based DMPLS, integrates the SVM with the MPLS model. Process data from normal historical batches are used to develop the MPLS model, and a series of single-input-single-output SVM networks are adopted to approximate nonlinear inner relationship between input and output variables. In addition, the application of a time-lagged window technique not only makes the complementarities of unmeasured data of the monitored batch unnecessary, but also significantly reduces the computation and storage requirements in comparison with the traditional MPLS. The proposed approach is validated by a simulation study of on-line fault detection for a fed-batch penicillin production.
基金the National Natural Science Foundation of China (No.60574038) the Open Project Program of the State KeyLaboratory of Bioreactor Engineering/ECUST.
文摘In this article, a nonlinear dynamic multiway partial least squares (MPLS) based on support vector ma- chines (SVM) is developed for on-line fault detection in batch processes. The approach, referred to as SVM-based DMPLS, integrates the SVM with the MPLS model. Process data from normal historical batches are used to de- velop the MPLS model, and a series of single-input-single-output SVM networks are adopted to approximate nonlinear inner relationship between input and output variables. In addition, the application of a time-lagged win- dow technique not only makes the complementarities of unmeasured data of the monitored batch unnecessary, but also significantly reduces the computation and storage requirements in comparison with the traditional MPLS. The proposed approach is validated by a simulation study of on-line fault detection for a fed-batch penicillin production.
文摘发酵过程具有时变性、动态性和多阶段性的特点,对其进行故障监测主要采用离线建模方式,但这种方法并不能很好地反映当前生产过程的数据特征。近年来有学者使用即时学习（Just in Time Learning,JITL）在线建模策略来建立精确的在线模型并进行故障监测,但是即时学习在线建模策略存在着模型更新频繁、计算量大的问题？本文提出一种带有模型更新机制的即时学习多向偏最小二乘（JITL-MPLS）的故障监测方法：依据马氏距离相似度,选择相似历史样本建立多向偏最小二乘监测模型;而后通过对比上一时刻的质量测量值和当前时刻的质量预测值的差值是否超限来判断模型是否需要更新,当其差值没有超限,即上一时刻监测模型能够表征当前时刻的数据特征,不更新模型,而是继续沿用,否则更新模型。最后将此方法应用于青霉素发酵仿真系统的在线监测,验证了该方法的有效性。
基金Project(60674063) supported by the National Natural Science Foundation of China
文摘The quality prediction of tube hollow model based on the variance staged multiway partial least square (MPLS) method was proposed.The key aspects of staged decomposition of the productive data,calculation of the variance value,modeling,and on-lined prediction in the variance-staged MPLS method were introduced.Based on the model,iterative optimal control method was used for quality control of tube hollow.The experimental results show that the obvious benefits of this method are low maintenance cost,good real time function,high reliability precision,and practical application to on-line prediction and optimization on the quality of tube hollow.
基金supported by the National Natural Science Foundation of China （Grant Nos. 10971107, 11271205）, the ＂131＂ Talents Program of Tianjin, and the Fundamental Research Funds for the Central Universities （Grant Nos. 65030011, 65011481）.
文摘A supersaturated design （SSD）, whose run size is not enough for estimating all the main effects, is commonly used in screening experiments. It offers a potential useful tool to investigate a large number of factors with only a few experimental runs. The associated analysis methods have been proposed by many authors to identify active effects in situations where only one response is considered. However, there are often situations where two or more responses are observed simultaneously in one screening experiment, and the analysis of SSDs with multiple responses is thus needed. In this paper, we propose a two-stage variable selection strategy, called the multivariate partial least squares-stepwise regression （MPLS-SR） method, which uses the multivariate partial least squares regression in conjunction with the stepwise regression procedure to select true active effects in SSDs with multiple responses. Simulation studies show that the MPLS-SR method performs pretty good and is easy to understand and implement.
基金Item Sponsored by National Natural Science Foundation of China (60674063)
文摘Energy consumption is an important quality index in the production of seamless tubes. The complex factors affecting energy consumption make it difficult to build its mechanism model, and optimization is also very difficult, if not impossible. The piercing process was divided into three parts based on the production process, and an energy consumption prediction model was proposed based on the step mean value staged multiway partial least square meth- od. On the basis of the batch process prediction model, a genetic algorithm was adopted to calculate the optimum mean value of each process parameter and the minimum piercing energy consumption. Simulation proves that the op- timization method based on the energy consumption prediction model can obtain the optimum process parameters effectively and also provide reliable evidences for practical production.
