Predictive neural network controller for hydrostatic transmission control

Predictive control is often used in industry and a large number of implementation algorithms has been presented in literature. Most of these control algorithms use process model to predict the future behavior of a plant and because of this, the model predictive control (MPC) is often used. The most important advantage of the MPC technology comes from the process model itself which allows the controller to deal with an exact copy of the real process dynamics, implying a much better control quality. The constraints with respect to input and output signals are directly considered in the control calculation, resulting in very rare or even no constraint violation. Another important characteristic, which contributes to the success of theMPC technology, is that theMPC algorithms consider plant behavior over a future horizon in time (Fig. 1). Thus, the disturbances can be predicted and eliminated. This permits the controller to drive the output more closely to the reference trajectory. Although most processes usually contain complex nonlinearities, most of the MPC algorithms are based on a linear model of the process. The aim for most of the applications is to maintain the system at a desired steady state, rather than moving rapidly between different operating points, so a precisely identified linear model is sufficiently accurate in the neighborhood of a single operating point. Often, the output of the controller is obtained using software optimization techniques and the control algorithm cannot always be used in manufacturing applications. As linear models are reliable from this point of view, they will provide most of the benefits with MPC technology. If the process is highly nonlinear and subject to disturbances of a high frequency a nonlinear model is necessary to describe the behavior of the process. Also in servo control problems where the operating point changes frequently, a nonlinear model of the plant is indispensable.