Advanced Materials Research Vol. 411

Abstract: To efficiently mining the classification model, an artificial immune inspired hybrid classification algorithm was put forward by means of combining antibody clonal selection, fuzzy C means clustering (FCM) and information entropy principle. In this algorithm, fuzzy C means clustering algorithm was employed to generate initial antibody population for making use of the prior knowledge of the training data. From the viewpoint of information entropy, for evolving memory cells the information entropy of antibodies population was employed to provide stop criteria of training. Finally classification was performed in a nearest neighbor approach. Experimental results on the fault detection of DAMADICS demonstrate the effectiveness of the algorithm. Compared with CLONALG artificial immune classifiers, the hybrid classifier has a superior performance in terms of recognition rate, computation time, number of memory cells and condense rate.

Abstract: Printing press manufacturers need to detect assembled machine whether the printing is qualified. This wastes a lot of paper, ink and human, and is not conducive to business efficiency. In this paper, through analysis of web press, the instrument is developed that takes the paper to detect the offset with non-printing ink on the printing press, through high-precision optical sensors, it can get the offset of conveyor belt material in the course of the amount of deviation. The amount of assembly precision machine is detected based on deviation; Then design a circuit tester hardware and software; Finally, the detector was tested, the results show that the detector is designed to achieve the design requirements.

Abstract: In order to analyze that widespread usage of electric vehicles is feasible and practical from environmental and economic aspects, we should take the following steps: firstly we divide the world into three areas and set up a differential equation model to predict the quantity of various types of future automobiles and development of the automobiles. Then it is necessary to establish an optimization model about the type and the number of power station. We also develop the model that the widespread usage of electric saves oil by the way of generating of clean energy instead of traditional energy. Finally, the global wide usage of electric vehicles can save 1.73ⅹ106L liter oil.