Focusing on the issue that conflict is hard to detect accurately and comprehensively in collaborative design, a conflict detection model based on constraint was proposed. Considering the hierarchical constraints and constraint satisfaction, the detection model divided constraints into two sets: one set is with known constraints and the other set is with unknown constraints. The constraints of two sets were detected respectively. The set with known constraints was detected by interval propagation algorithm. Meanwhile, Back Propagation (BP) neural network was used to detect the set with unknown constraints. Immune Algorithm (IA) was utilized to optimize the weights and thresholds of BP neural network, and the steps of optimization process were put forward. In the comparison experiments with BP neural network optimized by Genetic Algorithm (GA), the convergent speed was increased by 69.96%, which indicated that BP neural network optimized by IA has better performance in convergent speed and global searching ability. The constraints were described by eXtensible Markup Language (XML), so that computers could automatically recognize and establish the constraint network. The implementation of conflict detection system based on constraint satisfaction was designed. Taking co-design of wind planetary gear train as an example, a conflict detection system in collaborative design was developed on Matlab with C#. The conflict detection model is proved to be feasible and effective, and provides a solution of conflict detection for collaborative design.

A Bayesian blind deblurring algorithm was proposed for solving the contradiction of image details restoration and blocking effect amplification. Based on Bayesian framework, prior models were established for origin image, observed image, point spread function and model parameters. Gauss-Markov random field model that can effectively describe local statistical features of image was introduced as prior model of origin image. Then the iterative formulas of origin image and the point spread function were deduced by using Bayesian formula. The experimental results show that image restorted by the proposed algorithm has fewer blocking effect and better visual effect than the restored image by Total Variation (TV) prior model. Whether the size of point spread function is known or not, compared with TV prior model, the proposed algorithm can increase the Improved Signal to Noise Ratio (ISNR) of the restored image about 1dB.

With high computing complexity, traditional 2-D maximum entropy method is a defective method in image segmentation, although many algorithms have been proposed to bear on this problem. Considering GQAs (Genetic Quantum Algorithm) ability to retain the diversity of population and to converge rapidly, a 2-D maximum entropy method based on GQA was put forward. Compared with 2-D maximum entropy method based on classical genetic algorithm in experiments, this method was proved to perform better.