Adaptive controller design-based neural networks for output constraint continuous stirred tank reactor

For a class of continuous stirred tank reactor with output constraint and uncertainties, an adaptive control approach is proposed based on the approximation property of the neural networks. The considered systems can be viewed as a class of pure-feedback systems. At present, the control approach for the systems with output constraint is restricted to strict-feedback systems. No effective control approach is obtained for a general class of pure-feedback systems. In order to control this class of systems, the systems are decomposed by using the mean value theory, the unknown functions are approximated by using the neural networks, and Barrier Lyapunov function is introduced. Finally, it is proven that all the signals in the closed-loop system are bounded and the system output is not violated by using Lyapunov stability analysis method. A simulation example is given to verify the effectiveness of the proposed approach.