Development and Modeling of Ensemble Machine Learning Algorithms in Colored Petri Nets for Execution Failure Diagnosis in Robotic Manipulators

Abstract

The growing adoption of Artificial Intelligence (AI) in industry has automated tasks and interconnected processes, enabling autonomous operational diagnostics. However, due to their often non-transparent nature, machine learning algorithms used in AI (particularly ensemble models) have limited comprehensibility, especially when it comes to combining them for complex applications. This limitation can compromise process reliability and hinder the recognition of failure patterns. To mitigate this limitation, this work investigates the modeling of algorithm combinations in hierarchical colored Petri nets. The feature importance by the permutation technique is also modeled and employed to quantify the contribution of each attribute in the classification process, aiming to provide a clear and dynamic visualization for predicting execution failures in robotic manipulators. This methodology provides a precise identification of the steps executed by the model to make decisions, addressing visualization gaps in robotic manipulator failure applications. The validation was conducted through two experiments: the first explored non-failure-centric scenarios for the developed model, and the second utilized a database already tailored to the problem of interest. In this context, the proposed model achieved results similar to those reported in the literature, demonstrating its applicability. The results of this work aim to improve transparency and trust in automated industrial systems.