On geometric constraint solving based on the immune neural network

The geometric constraint solving is a popular problem in the current constraint design research. A constraint can describe a relation to be satisfied. Once the user defines a series of relations, the system will select a proper state to satisfy the constraints after the parameters are modified. Firstly we transform the constraint problem into an optimization problem. And then we propose a novel network framework combining the immune mechanism with the neural information - immune neural network to solve the geometric constraint problems. The users can make use of the characteristic information of the problem to be solved by the network and the network can be simplified by infusing the transcendental knowledge to adjust the the inspiriting function of the concealed layer unit so that the work efficiency and accuracy can be improved. The experiment can indicate that the immune neural network is not only feasible but also effective. It can simplify the framework applied in the concrete problem of the original model and it has a good work capability.