Implementing neuro-adaptive control algorithms with sliding mode learning on industrial servo drives

The demand of the industry for high performance electric motors has significantly increased nowadays. This has boosted the usage of permanent magnet brushless synchronous motors (BLSM) in many applications where the accuracy and performance requirements are high. Further improvement of the BLSM drive systems performance can be achieved by providing them with adaptive control capabilities. The relative complexity of adaptive control schemes and algorithms and the computational load that they impose have prevented until recently their practical implementation into the industrial servo systems. In this investigation, a neuro-adaptive control scheme where the rule for parameter adaptation is designed by taking into account the variable structure control (VSC) concepts and Lyapunov stability, is proposed and embedded into an inexpensive, available on the market, position control system for brushless synchronous servomotors. The experimental tests have been carried on using compact and flexible, based on open hardware and software concept, dual-axis motion controllers PMC201/PMC202 manufactured by the PicoMotion Inc. The applied software has been written using the Motion Control Framework software platform, provided together with the above controllers. The results obtained with the proposed neuro-adaptive control scheme have been compared to those obtained using the originally built into the system PI controller. The experiments have shown that the implemented advanced adaptive control approach is practically viable and can be embedded into the industrial motion control systems which will lead to their improved performance.