Tests of Inflatable Structure Shape Control Using Genetic Algorithm and Neural Network

Inflatable space structures need to maintain in a desired shape in space in order to achieve satisfactory performance. The active shape control technique has shown its advantages in solving this problem. Due to strong non-linear properties of the inflatable structures, it is a challenging task to model the inflatable structure properties and to find optimal control output. In this paper, a scheme is proposed based on genetic algorithm and neural network, which is then verified on the shape control of a small size membrane structure. The membrane to be controlled is a 200mm × 300mm rectangular Kapton membrane, pulled by two tensions along each edge. Different combinations of the tensions produce various wrinkles on the membrane. A neural network model is developed to map boundary stretching tensions and space environment to membrane flatness, and then is used to estimate the membrane flatness. The genetic algorithm is utilized to search the best tension combinations from the neural network model to minimize the membrane wrinkle amplitude. An active control system is developed and tests are performed. The results show that genetic algorithm works very well in optimizing the tensions and neural network is effective to estimate the flatness of the membrane.