Development of an intelligent management system: integration of machine learning and knowledge engineering techniques

Abstract

In modern industrial environments, ensuring high-quality and uninterrupted production is a major daily challenge. With the goal of preserving the accumulated knowledge of experts, which forms the "corporate memory"—the company’s true capital—this work proposes an intelligent system that combines processes for reusing past experience, predicting future needs, and capitalizing on domain knowledge to support effective corrective and preventive maintenance. The system leverages previous interventions to suggest appropriate solutions for current failures. Additionally, the developed software intelligently adjusts the optimal stock levels of spare parts and adapts their logistics based on observed usage, and finally facilitates task assignment to technicians according to the current context of interventions. This IT solution is a modular and scalable platform developed from real-world industrial maintenance scenarios, ensuring the progressive integration of new experiences from resolved failures, to gradually enhance decision-making support capabilities.