Learn More
The production of polyacrylonitrile carbon fiber (PANCF) includes a set of industrial processes with high complexity. One key process is the coagulation process for PAN as-spun fiber in the coagulation bath. This process has a lot of variables coupling with each other, which increases the difficulty of acquiring satisfactory control performance. In this(More)
A bidirectional optimizing approach for the melting spinning process based on an immune-enhanced neural network is proposed. The proposed bidirectional model can not only reveal the internal nonlinear relationship between the process configuration and the quality indices of the fibers as final product, but also provide a tool for engineers to develop new(More)
Sigmoid surface controller has been proved to be effective in motion control of autonomous underwater vehicles, but it is hard to adjust its control parameters. Improved particle swarm optimization of sigmoid surface controller was proposed in this paper, which solves the problems that particle swarm optimization may be trapped in local optimum and fails to(More)
Co-evolutionary algorithm behaves in a complicated and counterintuitive way for some complex problems. The introduction of interactive immune concept can increase its convergence rate and effectiveness. This paper represents an optimization process of polyester filament in melt spinning with the interactive immune co-evolutionary design approach and also(More)
The existing design approaches of variable structure control for a class of affine systems with uncertainties are discussed and three modified sigmoid variable rate reaching laws are proposed based on sigmoid function and normal distribution function. Variable structure control system designed by appling this types of reaching laws, better than the(More)