Condition-based maintenance (CBM) has gained significant attention in the field of heavy equipment maintenance due to its potential to optimize maintenance activities, reduce downtime, and improve equipment reliability. Integrating artificial intelligence (AI) techniques into CBM can further enhance its effectiveness by enabling intelligent decision-making based on real-time equipment condition data. This paper presents an ambitious first attempt to develop an intelligent CBM system for enhancing heavy equipment maintenance using AI. The study focuses on data acquisition, feature extraction, and maintenance decision-making using single layer perceptron (SLP) as a prototype. The initial input data of the proposed SLP with random number of X 1 (1,83) X 2 (3,92) and a random weight of 2,50 and 1,40 resulting in decreasing error within 10 iterations of the program. The findings highlight the feasibility and potential benefits of creating an intelligent CBM system, paving the way for more proactive and efficient heavy equipment maintenance practices.