pit or underground mining environments, where structures are subject to extreme loading, corrosion, and seismic conditions, the initial design is only the starting point. Having an AIM system in place from the early stages allows for a transition from a reactive to a proactive approach. Figure 1 – Asset Lifecycle and Asset Integrity Management 2. STATE OF THE ART Conventional inspection practices in mining rely heavily on the inspector's subjective experience and physical methods that involve high logistical costs (scaffolding, aerial work platforms). These practices suffer from human biases and consistency errors that can lead to an underestimation or overestimation of structural risk (Rachman & Ratnayake, 2019). The use of Machine Learning (ML) and Computer Vision in Risk-Based Inspection eliminates this variability. According to Rachman (2019), ML allows for the simultaneous processing of complex variables and degradation patterns, prioritizing assets based on the actual probability of failure. Integrating drones with high-resolution sensors enables data capture in hardto-reach areas (transfer chutes, milling structures, port terminals), drastically reducing workplace safety risks and allowing for informed decision-making based on a data density impossible to obtain manually. 3. FOUNDATIONS OF THE AIM MODEL: THE THREE DIMENSIONS OF INTEGRITY To build a management model that guarantees operational sustainability, it is necessary to delve deeper into the technical hierarchy of integrity. Following the principles of El-Reedy (2022) and the CCPS (2016), the AIM model is based on three interconnected dimensions: 3.1. Design Integrity This dimension constitutes the asset's baseline. It focuses on ensuring that the infrastructure possesses the necessary mechanical and structural capacity to fulfill its purpose under the anticipated conditions throughout its useful life.
RkJQdWJsaXNoZXIy MTM0Mzk2