Predictive model using machine learning to determine fuel consumption in CAT-777F mining equipment
by Marco Cotrina; Jairo Marquina; Jose Mamani; Solio Arango; Joe Gonzalez; Johnny Ccatamayo; Eduardo Noriega
International Journal of Mining and Mineral Engineering (IJMME), Vol. 15, No. 2, 2024

Abstract: The main objective of the research was to determine fuel consumption in CAT-777F equipment considering parameters such as speed, resistance and payload of the equipment, using a machine learning neural network algorithm. The methodology used was exploratory level, quantitative approach, applied type and non-experimental cross-sectional design. The results obtained when performing the EDA showed a high relationship of 84% between the 'payload' of the equipment and the fuel consumption, indicating that keeping the payload of the truck constant, the fuel consumption will be lower. When validating the model, the result of the ANN metric indicates that the coefficient of determination (R²) obtained a value greater than or equal to 68%. Likewise, using the random forest regressor algorithm to determine the percentage of incidence in each of the parameters, it was obtained that the payload has a percentage of incidence of 87%. Finally, it is concluded that the use of neural networks can predict fuel consumption in CAT-777F equipment.

Online publication date: Fri, 19-Jul-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Mining and Mineral Engineering (IJMME):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com