Modeling and prediction of wear rate of grinding media in mineral processing industry using multiple kernel support vect
- PDF / 1,101,010 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 74 Downloads / 159 Views
Modeling and prediction of wear rate of grinding media in mineral processing industry using multiple kernel support vector machine Asghar Azizi1 · Reza Rooki2 · Nader Mollayi3 Received: 14 May 2020 / Accepted: 15 July 2020 © Springer Nature Switzerland AG 2020
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 R2 are achieved 0.99417 and 0.993 for training and testing datasets, respectively. Keywords Wear rate · Grinding media · Mineral processing · Multiple kernel · Support vector machine
1 Introduction The grinding media wear plays an important role in the economics of grinding processes in mineral processing plants. Wear is defined as a progressive loss of material from a solid body owing to its contact and relative movement against a surface [1]. It has been accepted that wear is resulted in a lower the operational efficiency of machinery and its components, and also it is a major source of costs in the various industries [2]. Meanwhile, it is known that the mining and metallurgy industries significantly depend on the comminution operations to increase mineral liberation. Comminution is one of the most important operational units in the mineral processing industry and it
is well known that the direct operating costs in comminution circuits (including crushing and milling) are mainly the energy consuming and the metal lost through wear in the mineral industry [3, 4]. Radziszewski reported that typical operational costs may be divided into extraction (30–70%), separation (5–20%), and comminution (30–50%) [5]. Moema et al. stated that consumption of grinding media forms an important part of the operational costs and grinding medium wear can constitute up to 40–45% of the total operation cost in comminution process [6]. In addition, King et al. expressed that wear rate is one of the most significant parameters for appraising the overall performance of grinding medium [7]. Thus, grinding media should be produced to provide the highest performance
Electronic supplementary material The online version of this article (https://doi.org/10.1007/s42452-020-03212-0)
Data Loading...
