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

Abstract

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.

MF-TCPV: A Machine Learning and Fuzzy Comprehensive Evaluation-Based Framework for Traffic Congestion Prediction and Visualization

“…The method of predicting traffic speed is the same as the method of predicting traffic flow. Parameter optimization Single kernel functions have poor capability when the samples are unevenly distributed in the high-dimensional space [42]. So, we combine single kernel functions linearly to a construct combined kernel function as shown in (1).…”

Prediction of energy consumption in grinding using artificial neural networks to improve the distribution of fragmentation size [Predicción del consumo de energía en la molienda utilizando redes neuronales artificiales para mejorar la distribución del tamaño de la fragmentación]

“…Saldaña, et al (2023), in their research divided the historical data into two groups, that is, the training set (70%) and the validation set (30%), while the fitted model was used to estimate the production after the application of the M2M strategy and simulate production, at different values of the mill rotation speed and lining age factors. Like Azizi, et al (2020), in their study to investigate the application of three powerful Kernel-based supervised learning algorithms to develop a global model of the wear rate of grinding media based on input factors such as pH, percentage of solids, the loading weight of the balls and the rotation speed of the mill and the grinding time, the models were trained using 40 randomly selected data (representing 80% of the total data) and the remaining 10 data (which represent 20%) were applied for testing purposes. In this investigation, the 126 data were also divided into 101 (representing 80%) for training and 25 (representing 20%) for testing.…”

“…of energy optimizing grinding conditions. Azizi, et al (2020), in their study compared single-core and RNA-based techniques. They determined that the use of multi-core support vector machines benefits from a higher degree of correctness and generalizability in predicting the wear rate of grinding media.…”

Digitalization Solutions in the Mineral Processing Industry: The Case of GTK Mintec, Finland

“…Such models not only can be integrated into the digital twins to better simulate the processes but also can provide new insights into the behavior and operation of different components and potential improvements. Apart from these, ML, especially unsupervised and semisupervised techniques, can be leveraged for condition monitoring and fault detection in the processing plant, thereby improving reliability and safety [23,[52][53][54].…”