Evaluation and analysis of neural network on the utilization efficiency of bulk ore terminal machinery in port

Abstract

Ore transportation is the main content of the terminal business, but its layout is scattered and the weight is diverse, which requires the joint cooperation of different machinery to complete. However, there are differences in the function and structure of machinery such as transmission belts and hoisting, and it is impossible to optimize them using uniform standards. Therefore, how to effectively adjust the working hours and methods of machinery is the focus of current research. Based on this, this paper proposes a neural network-based method to evaluate the bulk ore in the port and construct an efficient transportation index system. Then, with the help of the normalization and normalization function, the ore was mapped, and the order and priority of different transportation points were adjusted in the form of iterative calculation, and the transportation effect was calculated. Finally, the effectiveness of the neural network method is verified by comparison in other ways. The results show that the normalization treatment can reduce the difference between ore and machinery, and improve its uniformity to 85.6%. The neural network can improve the mechanical efficiency, reduce the transportation time by 20%, and increase the fit with the ore to 92.6%; Neural network can save the rental cost of machinery, saving 15~20%. It can be shown that the neural network has an obvious optimization effect on the transportation of bulk ore in the port, which can improve its transportation efficiency.