Abstract. For the problem of parametric identification of control objects proposed a method based on the use of artificial neural network feedforward type a perceptron. This method allows us to estimate the parameters of the mathematical model of the system with a maximum error of 2.8% and significantly reduce the time of the identification procedure.

Purpose of research.. Increasing the ore productivity of the grinding mill under the influence of external disturbances, preventing overloading of the mill in operating conditions close to overloading.Methods. To achieve this goal, it is proposed a new automatic control system (ACS) for ore volumetric filling of grate-discharge ball mill in a closed grinding cycle using model predictive control and active disturbance observer (MPC-DOB). And in addition, virtual analyzer (VA) of the ore weight in the mill based on the developed model of the grinding process is proposed for mill overload control. The ACS was tested on a laboratory installation with the mill PC-model in Simulink and the PLC based implementation of control algorithms. Results. MPC-DOB was compared with other ACS based on PID, MPC controllers for various test scenarios and show high performance under the influence of sinusoidal and step disturbances by reducing relative standard deviation (RSD) by 4-7 %. The combined using of MPC-DOB and VA made it possible to increase the grinding process ore productivity by 1 % and improve the quality of mill vibration stabilization in the mode of functional instability.  Conclusion. The developed ACS can be used in the process control system for grinding in a ball mill with a grate to increase the productivity and stability of the technological process and reduce the energy consumption of the mill drive.

This study is aimed at getting simplified model of mill filling technological process of fine crushing in a closed-circuit grinding with screen separation. Optimal and simple model structure are supposed to be used in adaptive predictive control loop. The minor factors that directly affect the mill load indicator are not taken into account, since some of them cannot be directly measured, and other ones affect the process only in the long term. In this paper the athors considered mill filling process identification in the center-discharge ball mill by the method of neural networks (NN). The method includes the identification of the nonlinear process using nonlinear autoregressive with external input (NARX) neural network. The most accurate model was found by varying the structural parameters of the network. The best models were tested in the course of the actual grinding process. The best estimation of the NN model to the real object is obtained with 72.1% match.

No abstract

No abstract