No abstract

The significance in constructing a driving style identification model for open-pit mine truck drivers is to reduce diesel consumption and improve training. First, we developed a driving behavior and mining truck condition monitoring system for an open-pit mine. Under heavy-load and no-load conditions of a mining truck, based on the same experimental truck and haulage road, the data of driving behavior and truck status of different drivers were collected. The driving style characteristic parameters of mining trucks under heavy-load and no-load conditions were constructed through Pearson correlation analysis. Using a k-means clustering algorithm, driving style can be divided into three types: normal type, soft type, and aggressive type, and we verified the validity of this driving style classification with a box plot. On this basis, the parameters of random forest, k-nearest neighbor, support vector machine, and neural network models were optimized and the accuracy was compared through a cross-validation grid search, and then a driving style identification model based on the random forest method was finally proposed. Driving style parameter weight values were obtained based on the Gini coefficient. Last, the fuel consumption characteristics of different driving styles were calculated. The results show that the driving style identification models based on random forest can effectively identify different driving styles when the mining truck is operating under heavy load and no load, and the overall accuracy of the model is 95.39% and 90.74% respectively. The fuel consumption of the aggressive driving style was the largest and was 10% higher than the average fuel consumption. The research results provide data support and new ideas for operation training and fuel-saving driving of mining trucks in open-pit mines.

In the process of open-pit mining, the system parameters determine the economic benefit and production efficiency of the mine. Conventional optimization involves building a system model for the process parameters. However, complex large-scale systems such as open-pit mining are difficult to model, resulting in a failure to obtain effective solutions. This paper describes a system simulation method for the process parameters involved in open-pit mining. The nature and interaction of each component of the system are analyzed in detail, and the logical flow of each layer of the system is determined. Taking the basic operational linkages of the equipment as the system drivers, we obtained the operational flow of dragline information. The barycentric circular projection method is used to simplify the control logic of the system, and a system storage state model is constructed to identify dynamic changes in the system and obtain the operation parameters of the dragline. A discrete event system is used for quantitative modeling, and the event step method is employed to advance the simulation process and obtain decision information. Finally, simulations are performed using various system parameters. The simulation results show that the maximum efficiency is achieved when the dragline height is ∼13 m, giving a capacity of 4276.52 m3/h. Error analysis indicates that the modeling error is minimized using a simulation correction coefficient of α = 0.94.

Cast blasting–dragline stripping technology is the most advanced mining technology used in open-pit mines. For a long time, however, its precision has been hindered. In this paper, we aim to improve the precision of cast blasting–dragline stripping technology and promote its intelligent design. We present a method to determine cast blasting stockpile forms. First, the 3D point cloud data for the Heidaigou open-pit mine from recent years were collected and counted, and a 3D mathematical model of overcasting stripping steps was constructed. Then, data classification and multivariate statistical analysis were used to establish a cast blasting stockpile characteristic parameter database. Next, locally weighted linear regression was used as the fitting method to achieve shape fitting under different cast blasting step heights. Finally, interval estimation was used as the fitting result test method to verify the morphology of the acquired cast blasting stockpile form. The research results show that the cast blasting stockpile form obtained by fitting can truly reflect the cast blasting effect of the Heidaigou open-pit mine and ensure the reliability and accuracy of the subsequent design of cast blasting–dragline stripping technology.