A new algorithm for adjusting PI controller coefficients in shearer operation control

The article considers the control system of shearers designed for breaking and loading rocks onto a scraper conveyor. When cutting a coal seam by a shearer, the external disturbances (coal resistance to cutting), solid inclusions and change in the width of a shearer drum, which vary indefinitely, lead to the deterioration in the quality of transients. A typical cutting process controller in the form of a PI controller with the parameters configured for a specific mode of operation of the shearer is incapable to ensure the optimal functioning of the control system in all modes due to the non-linearity of the controlled object and owing to the random changes in the coal resistance to cutting. To improve the control quality indicators, it is necessary to select the parameters of the PI controller so as to minimize the amplitudes of the current steps of the cutting motor, and thereby to reduce the amplitudes of the torque in the transmission of the cutting drive and to minimize the system settling time. In this paper, we present an adjustment algorithm based on obtaining the values of the controller parameters for each of the possible operating modes of the shearer, identifying the type of a disturbing effect by the response curves of the system available to observation. Furthermore, it is proposed to use of an artificial feed-forward neural network as an operational tool of recognizing a multidimensional response curve in the control loop. The correctness of the obtained results is confirmed by the results of computer modeling.