AI-Enhanced design of excavator engine room cooling system using computational fluid dynamics and artificial neural networks

• Published in: Case studies in thermal engineering 2024-02, Vol.54, p.103959, Article 103959
• Main Authors: Kwon, Tae Woo, Kim, Hui Geun, Lee, Jae Seok, Jeong, Chan Hyeok, Choi, You Chul, Ha, Man Yeong
• Format: Article
• Language: English
• Subjects: AI learning; Artificial neural network; Computational fluid dynamics; Cooling system; Excavator; Optimization
• ISSN: 2214-157X; 2214-157X
• DOI: 10.1016/j.csite.2023.103959

Excavators mainly perform high-load operations in fixed positions, so the stability of their performance depends solely on their cooling system. In this study, computational fluid dynamics (CFD) analysis was conducted using Fluent 2022 R22 software to analyze the cooling system in the engine room of an excavator. A comprehensive parametric study was performed, considering different cooling fan layouts and operating rates, to establish a database of cooling performance data for the excavator. Artificial neural network (ANN) models were trained on the constructed database and were then applied to design the cooling system and predict the performance. Further, optimal designs that maximized the cooling performance and energy efficiency were selected. This study demonstrates the feasibility of using ANN models to quickly and accurately predict and design the cooling system of an excavator in a cost-effective manner.