As a new software paradigm evolved by the Internet, Internetware brings many challenges for the traditional software development methods and techniques. Though architecture-based component composition （ABC） approach...As a new software paradigm evolved by the Internet, Internetware brings many challenges for the traditional software development methods and techniques. Though architecture-based component composition （ABC） approach is originated in the traditional software paradigm, it supports the engineering of Internetware effectively due to its philosophy, rationales and mechanisms. ABC has three major contributions to the en- gineering of Internetware in detail. First, the feature oriented domain modeling method can structure the ＂disordered＂ ＂software entities＂ to ＂ordered Internetware＂ bottom-up in the problem space. Second, the architecture centric design and analysis method can support the development of self-adaptive Internetware. Third, the component operating platform is a reflective and self-adaptive middleware that not only provides Internetware with a powerful and flexible runtime infrastructure but also enables the self-adaptation of the structure and individual entities of Internetware.展开更多
Choosing the right characteristic parameter is the key to fault diagnosis in analog circuit. The feature evaluation and extraction methods based on neural network are presented. Parameter evaluation of circuit feature...Choosing the right characteristic parameter is the key to fault diagnosis in analog circuit. The feature evaluation and extraction methods based on neural network are presented. Parameter evaluation of circuit features is realized by training results from neural network; the superior nonlinear mapping capability is competent for extracting fault features which are normalized and compressed subsequently. The complex classification problem on fault pattern recognition in analog circuit is transferred into feature processing stage by feature extraction based on neural network effectively, which improves the diagnosis efficiency. A fault diagnosis illustration validated this method.展开更多
基金This work was supported by the National Basic Research Program of China （973） （Grant No. 2002CB312003） the National Natural Science Foundation of China （Grant Nos. 60233010, 90612011, 90412011, 60403030, 60303004）the Natural Science Foundation of Beijing （Grant No. 4052018）.
文摘As a new software paradigm evolved by the Internet, Internetware brings many challenges for the traditional software development methods and techniques. Though architecture-based component composition （ABC） approach is originated in the traditional software paradigm, it supports the engineering of Internetware effectively due to its philosophy, rationales and mechanisms. ABC has three major contributions to the en- gineering of Internetware in detail. First, the feature oriented domain modeling method can structure the ＂disordered＂ ＂software entities＂ to ＂ordered Internetware＂ bottom-up in the problem space. Second, the architecture centric design and analysis method can support the development of self-adaptive Internetware. Third, the component operating platform is a reflective and self-adaptive middleware that not only provides Internetware with a powerful and flexible runtime infrastructure but also enables the self-adaptation of the structure and individual entities of Internetware.
基金the National Natural Science Fundation of China (60372001 90407007)the Ph. D. Programs Foundation of Ministry of Education of China (20030614006).
文摘Choosing the right characteristic parameter is the key to fault diagnosis in analog circuit. The feature evaluation and extraction methods based on neural network are presented. Parameter evaluation of circuit features is realized by training results from neural network; the superior nonlinear mapping capability is competent for extracting fault features which are normalized and compressed subsequently. The complex classification problem on fault pattern recognition in analog circuit is transferred into feature processing stage by feature extraction based on neural network effectively, which improves the diagnosis efficiency. A fault diagnosis illustration validated this method.
