In the expansion of Industry 4.0, many automation processes are being enhanced as a means of accomplishing higher productivity goals. With the prospect of new achievable objectives, the demand for faster and more reliable resource processing methods has also increased. Similarly, machining processes have also been improved with the development of IoT devices by streamlining operations, enabling predictive maintenance, and providing real-time data for better decision-making and collaborating with such productivity levels. For instance, in metal milling, IoT-based sensor techniques are being developed and proven efficient in increasing speed and reliability while reducing system invasiveness and complexity, which grants more profitability. The present paper proposes a real-time metal roughness average (Ra) analysis method based on Acoustic Emission (AE), which indirectly estimates roughness through signal processing and feature extraction of the AE signal through Power Spectral Density (PSD) evaluation. The experimental setting consists of a steel workpiece in which straight lines were milled with four distinct roughness levels (6 μm, 12 μm, 18 μm, and 24 μm, produced by defined milling parameters), and the method was able to estimate the Ra with an error under 7%. This work aims to contribute to the real-time monitoring of surface roughness in alignment with Industry 4.0 requirements by demonstrating the effectiveness of IoT-based solutions and the potential of Acoustic Emission in machinery sensing and process automation.

The heterogeneous and anisotropic nature of Carbon Fiber Reinforced Polymers (CFRP) introduces challenges in characterizing failure mechanisms, particularly delamination, in advanced composite engineering structures used across multiple industrial sectors. Although deep learning models, especially Convolutional Neural Networks (CNNs), have demonstrated high diagnostic performance in Structural Health Monitoring (SHM), their inherent blackbox nature limits interpretability and trust, thereby restricting deployment in real-world engineering applications. To address these limitations, this work proposes a methodology that integrates deep learning with Explainable Artificial Intelligence (XAI) to enable transparent and reliable delamination detection in CFRP structures. The main contribution in Artificial Intelligence lies in the integration of convolutional neural networks with time–frequency representations of guided-wave signals and model-agnostic explainability techniques for intelligent fault detection in composite materials. From an engineering perspective, the proposed approach is applied to SHM and delamination diagnosis of CFRP specimens subjected to fatigue loading in engineering systems using Lamb waves acquired by piezoelectric transducers. The recorded Lamb wave signals were transformed into time–frequency representations and used as inputs to multiple CNN architectures, all of which achieved accuracy, precision, and sensitivity values exceeding 95%. Model transparency was ensured through the use of Local Interpretable Model-Agnostic Explanations (LIME), which enabled interpretation of the classifiers’ decision-making process. The explainability analysis highlighted physically meaningful indicators of delamination, such as amplitude attenuation and frequency shifts, demonstrating the potential of the proposed framework as an intelligent decision-support tool for fault detection and monitoring in engineering applications involving composite structures.

This study investigates the machining challenges of fiber-reinforced composite materials (FRCMs), focusing on carbon fiber-reinforced polymer (CFRP) plates, which exhibit high abrasiveness, delamination tendency, and accelerated tool wear. Two solid carbide helical end mills, designed for composite machining, were evaluated through helical interpolation drilling. Acoustic emission signals were continuously acquired via a piezoelectric sensor during standardized cycles, and tool wear was assessed using confocal microscopy and a digital altimeter. Signal processing played a central role, combining energy-based metrics and damage indices to identify the onset of wear and early delamination, enhancing the understanding of tool degradation and improving machining reliability.

Industry 4.0 has allowed an increase in process quality through Tool Condition Monitoring (TCM) techniques, as they enable the identification of anomalous behaviors caused by tool wear, for instance, by analyzing extracted features from real-time signals collected during machining processes. Thus, increasing understanding of the tool wear process is relevant to maintaining process quality and reducing machining downtime and catastrophic failure occurrences. This work analyzes the tool wear of five different hard metal tools through different feature extraction techniques, along with other signal metrics like the Root Mean Squared Deviation (RMSD), the Correlation Coefficient Deviation Metric (CCDM), the Rank-based Entropy (RBE), the Fractal Geometry Indicator (FGI), and the Chaos Quantifier (CQ). The features were extracted from Acoustic Emission (AE) signals collected during an experimental drilling process of a Carbon Fiber Reinforced Polymer (CFRP) plate. Although some works have already employed quantitative approaches based on these techniques to gain insight into tool wear characteristics, this research innovates by combining and comparing techniques from time, frequency, and time–frequency domains, and other feature metrics to obtain a fuller comprehension of the signal attributes that help to differentiate tool wear states. It also presents results from features that have only been recently employed in AE feature extraction, such as RBE, FGI, and CQ. Results indicate that the extracted characteristics, when analyzed together, allow for a clearer visual differentiation of tool wear states.

Fused Filament Fabrication (FFF) stands out due to its simple operating principle, low production cost, and wide range of available materials. However, the inherent anisotropy of thermoplastics frequently leads to interlinear void formation during deposition, compromising the mechanical properties of printed parts. Currently, the lack of effective in situ monitoring methods for the spatial localization of defects restricts the widespread adoption of FFF in industrial applications. As an alternative, vibration-assisted inspection has gained recognition as a developing non-invasive technique for process data acquisition. To improve knowledge to this topic, this study proposes extracting dynamic characteristic curves from objects constructed via FFF. The proposed methodology involves introducing two identical electrodynamic transducers in a pitch–catch configuration, where one transducer acts as an emitter and the other as a receiver, both integrated into the printer’s heated bed. The energy propagating through the bed reflects the vibration signals of the part under construction, which are collected by the receiver transducer. The results present a novel methodology to locate structural damage indicators during object fabrication by characterizing the medium, the heated bed and, consequently, the printed part itself. Thus, it was possible to identify the highest-magnitude bands and, based on them, generate acoustic maps that detect potential anomalies during the process.