Reinforcement adaptive learning neural-net-based friction compensation control for high speed and precision

There is an increasing number of applications in high-precision motion control systems in manufacturing, i.e., ultra-precision machining, assembly of small components and micro devices. It is very difficult to assure such accuracy due to many factors affecting the precision of motion, such as frictions and disturbances in the drive system. The standard proportional-integral-derivative (PID) type servo control algorithms are not capable of delivering the desired precision under the influence of frictions and disturbances. In this paper, the frictions are identified by a neural net, which has a critic element to measure the system performance. Then, the weight adaptation rule, defined as reinforcement adaptive learning, is derived from the Lyapunov stability theory. Therefore the proposed scheme can be applicable to a wide class of mechanical systems. The simulation results on a 1-degree-of-freedom mechanical system verify the effectiveness of the proposed algorithm.