Applied Mechanics and Materials Vols. 20-23

Abstract: The integrated innovation satisfies new market or customer needs by combination of different technologies. The integration requires that element must be optimized, matched, and then combined into a whole technology system while not simply piling and regrouping. This paper put forward the functions as basis of technology selection. Axiomatic design is introduced to aid to decomposing the function and structure with its framework of independence axiom to minimize the dependence of functions of product. The design matrices and full design matrix indicate the interrelations between all functions and technologies. The new technology is chosen to implement the desired functions that satisfy more customer needs and then integrated into a whole system according to the interactions of functions.

Abstract: Artificial neural network(ANN) and genetic algorithm (GA) have both prevalent uses in large area. Along with the development of technology a method based on the combination of Artificial neural network (ANN) and genetic algorithm (GA) aroused. In such a case, the paper uses the combination of Artificial neural network(ANN) and genetic algorithm (GA) to solve the problems of costructing index system and comprehensive evaluation. Firstly establishing feedforward neural network model and make sure about the input and output variables. Secondly improved genetic algorithm is used to solve the problem of network weight and threshold value which is constitute by three steps real codes, random selection and Genetic Manipulation of Chromosome. Moreover as it know to all, error back propagation(BP) algorithm is effective in local searching so adding error back propagation(BP) algorithm to genetic algorithm is a good way to get the satisfying result. Thirdly the paper gets the output of index effectiveness. Thirdly according to the entropy theory that the summation of effective value which could be involved in the index system should be larger than a certain critical value, the paper screened out the final index. Fourthly it uses the fuzzy neural network method to establishing the comprehensive evaluation model. Finally take the evaluation for teaching quality for example to authenticate the feasibility of the method.

Abstract: Traffic flow forecasting has become an emphasis question for discussion in traffic engineering domain and one kernel study in Intelligent Transportation System. After ensuring the traffic flow has the characteristic of chaos, traffic flow real data have been used to reconstruct phase space. Calculate the saturation phase space embedding dimension and maximal Lyapunov exponent. By above all, a chaos neural network model is constructed, which can make high precision short-term forecast for the nonlinear big-lagged system even by imperfect and variation inputs. At last, a forecasting example provides that the traffic flow forecasting based on chaos neural network is validity and feasibility.

Abstract: AES is one of the most widely used cryptographic systems. DNA computing has the high efficiency to solve some NP-problems. Therefore many scientists try to combine DNA computing with cryptography. In this paper, an algorithm is designed to simulate a plaintext encrypted by DNA biotechnology and modern cryptography. After mapping the plaintext information as DNA chain and handling the base chain with biological genetic technology, we can get the gene codes form, then using the Rijndael algorithm to deal with the biological chain with cryptography and get the final result. It makes the DNA-based cryptography more effective and more security.

Abstract: Image encryption is one of the most important methods of image information hiding. A new image encryption method based on some techniques and knowledge of genetic engineering for image hiding is presented in this paper. This method is implemented by using modern biological techniques as tools and biological hard problems as main security basis to fully exert the special advantages. The keys are some substances of biological materials such as restriction endonuclease, polymerase and so on, the preparation flow and the experimental conditions. The analysis demonstrates that the image encryption algorithm is feasible and highly secure. Moreover, the size of the decrypted image is the same as the original image so that it can be applied for image hiding and be transmitted via the Internet.

Abstract: In this paper, we propose a novel algorithm for facial recognition based on features fusion in support vector machine (SVM). First, some local features and global features from pre-processed face images are obtained. The global features are obtained by making use of singular value decomposition (SVD). At the same time, the local features are obtained by utilizing principal component analysis (PCA) to extract the principal Gabor features. Finally, the feature vectors which are fused with global and local features are used to train SVM to realize the face expression recognition, and the computer simulation illustrates the effectivity of this method on the JAFFE database.

Abstract: Capacitive grating sensor can be used to measure the length, as its capacitance changes with the shift difference. There are several measuring systems consisting of capacitive sensor, but all their basic principles are capacitive differential sensing. The structure, principles and characteristics of capacitive sensors are introduced in this paper. Especially, we designed a high-resolution electronic length measuring system based on Capacitive Grating Sensor. And the measurement error of the system and the reason are analysed. For this system, the measuring range is from 0 to 500mm, the resolution is 1um, the indication error is 5um, the measuring speed is 1m/s. Accurate measurement on account of large displacement is achieved with the system.

Abstract: The importance of case-retrieving method selection in the CBR system is analyzed, and the defaults of traditional retrieving methods which make use of fuzzy distance to describe the distance in the similar cases are pointed out. A model for case- retrieving based on user classification is presented after the introduction of the basic principle and process of CBR. By this case-retrieving method, the retrieving fields are divided into several case bases according to user’s fondness, and it will promote the retrieving speed.

Abstract: The entropies of structure, information and the effectiveness entropy between knowledge and organization structure are main entropy sources of supply chain network. Entropy model of fractal supply chain network organization structure is established. Fractal knowledge management network outside independently organization structure is built. Finally, the entropies of structure, information and the effectiveness entropy are summed. The model shows that fractal structure has prominent effect of dropping entropy.

Abstract: Base on the characteristic of the system, a model of FMS (Flexible Manufacturing System) is carried on in this paper by combining with the merit of OOPN (Object-Oriented Petri Nets) and UML (Unified Modeling Language). The static structure of FMS is described with UML, but for the dynamic characteristics of the system we complete with object-oriented petri nets, and then the system Petri net model was transform into the UML state diagrams and sequence diagrams according to the corresponding mapping and the transformation rule, thus we obtain a integrity model of the system while improving the reliability of the model.