Modeling and prediction of wear rate of grinding media in mineral processing industry using multiple kernel support vector machine

In this study, we investigates the application of three powerful kernel-based supervised learning algorithms to develop a global model of the wear rate of grinding media based on the input factors such as pH, solid percentage, throughout, charge weight of balls, rotation speed of mill and grinding time. It is found that there is a trade-off between the training and testing error when a single kernel function is used and therefore these methods cannot provide the generalization capability. However, this problem is solved utilizing the multiple kernel learning frameworks for support vector machine in which the kernel function was expressed as a combination of basis kernel functions. It is distinguished that compared to the single kernel and ANN-based techniques, the use of multiple kernel support vector machines benefit from a higher degree of correctness and generalization ability for prediction of wear rate of grinding media. Meanwhile, the findings indicate that in this state, the values of R 2 are achieved 0.99417 and 0.993 for training and testing datasets, respectively.