This article addresses the subject of a proposed system for detecting potential malfunctions in screw conveyors using AI-powered audio analysis. The proposal’s main contribution is its use of Artificial Intelligence (AI) in the form of a convolutional neural network in conjunction with Edge Computing (EC). The paper is organised into four sections. Following an initial analysis of the problem domain, the second section describes a potential method of identifying faults through vibration analysis within the audio spectrum (100 Hz–20 kHz) using EC and AI. The concluding section describes the implementation in a real environment, including experiments and test outputs, and represents the core of the publication. The proposed system is a suitable complementary method for fault detection in a predictive machine condition monitoring system.