Many applications of principal component analysis (PCA) can be found in dimensionality reduction. But linear PCA method is not well suitable for nonlinear chemical processes. A new PCA method based on im-proved input ...Many applications of principal component analysis (PCA) can be found in dimensionality reduction. But linear PCA method is not well suitable for nonlinear chemical processes. A new PCA method based on im-proved input training neural network (IT-NN) is proposed for the nonlinear system modelling in this paper. Mo-mentum factor and adaptive learning rate are introduced into learning algorithm to improve the training speed of IT-NN. Contrasting to the auto-associative neural network (ANN), IT-NN has less hidden layers and higher training speed. The effectiveness is illustrated through a comparison of IT-NN with linear PCA and ANN with experiments. Moreover, the IT-NN is combined with RBF neural network (RBF-NN) to model the yields of ethylene and propyl-ene in the naphtha pyrolysis system. From the illustrative example and practical application, IT-NN combined with RBF-NN is an effective method of nonlinear chemical process modelling.展开更多
Abnormal conditions are hazardous in complex process systems, and the aim of condition recognition is to detect abnormal conditions and thus avoid severe accidents. The relationship of linkage fluctuation between moni...Abnormal conditions are hazardous in complex process systems, and the aim of condition recognition is to detect abnormal conditions and thus avoid severe accidents. The relationship of linkage fluctuation between monitoring variables can characterize the operation state of the system. In this study,we present a straightforward and fast computational method, the multivariable linkage coarse graining(MLCG) algorithm, which converts the linkage fluctuation relationship of multivariate time series into a directed and weighted complex network. The directed and weighted complex network thus constructed inherits several properties of the series in its structure. Thereby, periodic series convert into regular networks, and random series convert into random networks. Moreover, chaotic time series convert into scale-free networks. It demonstrates that the MLCG algorithm permits us to distinguish, identify, and describe in detail various time series. Finally, we apply the MLCG algorithm to practical observations series, the monitoring time series from a compressor unit, and identify its dynamic characteristics. Empirical results demonstrate that the MLCG algorithm is suitable for analyzing the multivariable linkage fluctuation relationship in complex electromechanical system. This method can be used to detect specific or abnormal operation condition, which is relevant to condition identification and information quality control of complex electromechanical system in the process industry.展开更多
The article explains the role and future trend of IT industry,and states that information technology represented by the Internet and computers has brought about the third industrial revolution in history.An important ...The article explains the role and future trend of IT industry,and states that information technology represented by the Internet and computers has brought about the third industrial revolution in history.An important impetus for economic growth in modern times,the IT industry has greatly promoted sustainable development and is profoundly changing mankind's way of life and production.In discussing the development trend of world IT industry,the article suggests that with potential new breakthroughs in information technology,the trend of agglomeration and integration of industries has become increasingly obvious,competition of intellectual properties and standards is intensifying and ubiquitous network is taking shape.It points out that China should bring into better play the role of IT industry as an'amplifier'in economic growth,a'transformer'in development mode and a'propeller'in industrial upgrading.It is important to follow a policy that emphasizes independent innovation,market-driven approach,open and compatible technologies,integrated and comprehensive applications, and serving both military and civil purposes,so that a quantum leap of IT industry will be achieved.China should advance industrialization with information technologies and promote the IT industry in the course of industrialization in an effort to build an IT industry with Chinese characteristics.Greater efforts should be made to develop such core sectors as microelectronics,computer,software,key components and materials,as well as sectors with international competitiveness,including broadband mobile communication,next-generation network and information services.Continued improvement should be made in policies guiding the development of IT industry with a view to making China a country with a strong IT industry by 2020.展开更多
基金Supported by Beijing Municipal Education Commission (No.xk100100435) and the Key Research Project of Science andTechnology from Sinopec (No.E03007).
文摘Many applications of principal component analysis (PCA) can be found in dimensionality reduction. But linear PCA method is not well suitable for nonlinear chemical processes. A new PCA method based on im-proved input training neural network (IT-NN) is proposed for the nonlinear system modelling in this paper. Mo-mentum factor and adaptive learning rate are introduced into learning algorithm to improve the training speed of IT-NN. Contrasting to the auto-associative neural network (ANN), IT-NN has less hidden layers and higher training speed. The effectiveness is illustrated through a comparison of IT-NN with linear PCA and ANN with experiments. Moreover, the IT-NN is combined with RBF neural network (RBF-NN) to model the yields of ethylene and propyl-ene in the naphtha pyrolysis system. From the illustrative example and practical application, IT-NN combined with RBF-NN is an effective method of nonlinear chemical process modelling.
基金supported by the National Natural Science Foundation of China(Grant No.51375375)
文摘Abnormal conditions are hazardous in complex process systems, and the aim of condition recognition is to detect abnormal conditions and thus avoid severe accidents. The relationship of linkage fluctuation between monitoring variables can characterize the operation state of the system. In this study,we present a straightforward and fast computational method, the multivariable linkage coarse graining(MLCG) algorithm, which converts the linkage fluctuation relationship of multivariate time series into a directed and weighted complex network. The directed and weighted complex network thus constructed inherits several properties of the series in its structure. Thereby, periodic series convert into regular networks, and random series convert into random networks. Moreover, chaotic time series convert into scale-free networks. It demonstrates that the MLCG algorithm permits us to distinguish, identify, and describe in detail various time series. Finally, we apply the MLCG algorithm to practical observations series, the monitoring time series from a compressor unit, and identify its dynamic characteristics. Empirical results demonstrate that the MLCG algorithm is suitable for analyzing the multivariable linkage fluctuation relationship in complex electromechanical system. This method can be used to detect specific or abnormal operation condition, which is relevant to condition identification and information quality control of complex electromechanical system in the process industry.
文摘The article explains the role and future trend of IT industry,and states that information technology represented by the Internet and computers has brought about the third industrial revolution in history.An important impetus for economic growth in modern times,the IT industry has greatly promoted sustainable development and is profoundly changing mankind's way of life and production.In discussing the development trend of world IT industry,the article suggests that with potential new breakthroughs in information technology,the trend of agglomeration and integration of industries has become increasingly obvious,competition of intellectual properties and standards is intensifying and ubiquitous network is taking shape.It points out that China should bring into better play the role of IT industry as an'amplifier'in economic growth,a'transformer'in development mode and a'propeller'in industrial upgrading.It is important to follow a policy that emphasizes independent innovation,market-driven approach,open and compatible technologies,integrated and comprehensive applications, and serving both military and civil purposes,so that a quantum leap of IT industry will be achieved.China should advance industrialization with information technologies and promote the IT industry in the course of industrialization in an effort to build an IT industry with Chinese characteristics.Greater efforts should be made to develop such core sectors as microelectronics,computer,software,key components and materials,as well as sectors with international competitiveness,including broadband mobile communication,next-generation network and information services.Continued improvement should be made in policies guiding the development of IT industry with a view to making China a country with a strong IT industry by 2020.
