<![CDATA[This research aims to identify work patterns for heavy equipment, namely dozers, dump trucks and excavators, using the K-Prototype Clustering algorithm. This algorithm was chosen because of its ability to handle data that has a combination of numeric and categorical attributes, which are often found in heavy equipment operational data. By applying K-Prototype Clustering, we can group heavy equipment usage data into several representative clusters. The results show that heavy equipment usage patterns can be grouped effectively, allowing the identification of clusters with similar operational characteristics. This cluster helps in optimizing heavy equipment allocation, planning preventive maintenance, and improving overall operational efficiency. Implementation of clustering results in operational practice shows the potential for reducing idle time and increasing machine productivity. This research concludes that the use of the K-Prototype Clustering algorithm is an effective method for identifying heavy equipment work patterns. Strategic recommendations resulting from clustering can be applied to improve operational efficiency and effectiveness in the construction and mining industries.]]>
Copyrights © 2025
