It is difficult to develop the corresponding fault diagnosis system and the software reusability is bad because the engineering equipment types are so many and their performance is diverse. This paper discussed the so...It is difficult to develop the corresponding fault diagnosis system and the software reusability is bad because the engineering equipment types are so many and their performance is diverse. This paper discussed the solution to engineering equipment integrated fault diagnosis system based on component technology, put forward the sys- tem model and gave the system frame design process and working principle. The software was designed based on the three-layer hierarchy. It is easy to rease and maintain, and the operation of the software is simple. A kind of new theory and method to develop the engineering equipment fault diagnosis system for the future was provided.展开更多
Attribute reduction is necessary in decision making system. Selecting right attribute reduction method is more important. This paper studies the reduction effects of principal components analysis (PCA) and system reco...Attribute reduction is necessary in decision making system. Selecting right attribute reduction method is more important. This paper studies the reduction effects of principal components analysis (PCA) and system reconstruction analysis (SRA) on coronary heart disease data. The data set contains 1723 records, and 71 attributes in each record. PCA and SRA are used to reduce attributes number (less than 71 ) in the data set. And then decision tree algorithms, C4.5, classification and regression tree ( CART), and chi-square automatic interaction detector ( CHAID), are adopted to analyze the raw data and attribute reduced data. The parameters of decision tree algorithms, including internal node number, maximum tree depth, leaves number, and correction rate are analyzed. The result indicates that, PCA and SRA data can complete attribute reduction work,and the decision-making rate on the reduced data is quicker than that on the raw data; the reduction effect of PCA is better than that of SRA, while the attribute assertion of SRA is better than that of PCA. PCA and SRA methods exhibit goodperformance in selecting and reducing attributes.展开更多
For the EOF decomposition continuation phase space, the least square method is applied under the condition of orthogonal basis to find coefficients of all quadratic nonlinear terms of a state evo- lution equation such...For the EOF decomposition continuation phase space, the least square method is applied under the condition of orthogonal basis to find coefficients of all quadratic nonlinear terms of a state evo- lution equation such that a dynamic system that indicates the evolution features of a weather/cli- mate system in a limited area can be formulated. The scheme is compared with that for phase space continuation by time series drift. Results show that the dynamic system established in terms of the present method is likely to give more precise and realistic description of evolution of the weather/ climate system.展开更多
文摘It is difficult to develop the corresponding fault diagnosis system and the software reusability is bad because the engineering equipment types are so many and their performance is diverse. This paper discussed the solution to engineering equipment integrated fault diagnosis system based on component technology, put forward the sys- tem model and gave the system frame design process and working principle. The software was designed based on the three-layer hierarchy. It is easy to rease and maintain, and the operation of the software is simple. A kind of new theory and method to develop the engineering equipment fault diagnosis system for the future was provided.
基金Supported by Ministry of Education of China ( No. 02038) , Asian Research Center of Nankai University ( No. AS0405) , and Tianjin Higher Education Science Development Fund( No. 20030621 ).
文摘Attribute reduction is necessary in decision making system. Selecting right attribute reduction method is more important. This paper studies the reduction effects of principal components analysis (PCA) and system reconstruction analysis (SRA) on coronary heart disease data. The data set contains 1723 records, and 71 attributes in each record. PCA and SRA are used to reduce attributes number (less than 71 ) in the data set. And then decision tree algorithms, C4.5, classification and regression tree ( CART), and chi-square automatic interaction detector ( CHAID), are adopted to analyze the raw data and attribute reduced data. The parameters of decision tree algorithms, including internal node number, maximum tree depth, leaves number, and correction rate are analyzed. The result indicates that, PCA and SRA data can complete attribute reduction work,and the decision-making rate on the reduced data is quicker than that on the raw data; the reduction effect of PCA is better than that of SRA, while the attribute assertion of SRA is better than that of PCA. PCA and SRA methods exhibit goodperformance in selecting and reducing attributes.
基金This work is sponsored by the National Natural Science Foundation of Chinathe Natural Science Foundation of Jiangsu Province
文摘For the EOF decomposition continuation phase space, the least square method is applied under the condition of orthogonal basis to find coefficients of all quadratic nonlinear terms of a state evo- lution equation such that a dynamic system that indicates the evolution features of a weather/cli- mate system in a limited area can be formulated. The scheme is compared with that for phase space continuation by time series drift. Results show that the dynamic system established in terms of the present method is likely to give more precise and realistic description of evolution of the weather/ climate system.
