High noise levels in industrial workplaces pose significant challenges to occupational safety, particularly with hearing protection and effective communication. Traditional hearing protection devices, while effectively attenuating harmful noise, often compromise situational awareness by excessively isolating workers from the acoustic environment and preventing the perception of critical auditory cues (e.g., emergency alarms), thereby introducing additional safety risks. This paper presents a smart industrial safety system that integrates Internet of Things (IoT) and artificial intelligence (AI) and is based on intelligent hearing protection devices to (a) selectively attenuate hazardous industrial noise while (b) preserving human speech and (c) reproduce targeted audio notifications to workers near malfunctioning or hazardous machinery. A real-time voice activity detection (VAD) model is employed to distinguish vocal components from background noise to adaptively control digital signal processing filters. Furthermore, indoor localization enables the delivery of targeted audio messages to workers in proximity to relevant events. Experimental evaluations on embedded hardware demonstrate that the selected VAD model operates well within real-time constraints and effectively supports dynamic noise filtering. Objective evaluation of the filtering stage using Mean Opinion Score (MOS), signal-to-noise ratio (SNR), and Harmonics-to-Noise Ratio (HNR) shows consistent quality improvements across all tested conditions, with MOS gains up to +118%, SNR increases between +10.4 and +29.0 dB, and HNR improvements up to +6.22 dB, indicating enhanced speech intelligibility and preservation of voice harmonic structure even under high-noise scenarios. Robustness validation of the VAD module across varying acoustic conditions confirms reliable speech detection performance, achieving perfect classification at +10 dB SNR, very high accuracy at 0 dB (98.3%, ROC AUC 0.998), and stable operation even at $-7$ dB SNR (79.8% accuracy, ROC AUC 0.878). The proposed architecture achieves a balanced trade-off between hearing protection and speech intelligibility while enhancing the effectiveness of safety communications in noisy industrial environments.

Continuous verification of Personal Protective Equipment (PPE) compliance in CNC machining environments is a measurement problem: compliance state must be inferred from noisy, intermittent RFID readings, time-stamped with finite sampling resolution and network latency. Manual inspection offers no quantifiable measurement uncertainty and cannot serve as auditable evidence for quantitative risk assessment. This paper reports a distributed multi-agent measurement architecture, comprising an RFID-based Smart Gate and a dual Digital Twin feedback layer for a CNC Z32 lathe, together with a full measurement-uncertainty budget for the two indicators characterising the detection chain: the Positive Detection Ratio (PDR) and the Authorisation Latency (AL). Following the Guide to the Expression of Uncertainty in Measurement (GUM), five uncertainty sources are identified and classified as Type A or Type B (sampling quantisation, debounce-window variability, network time-synchronisation offset, RFID detection stochasticity, HTTP/TCP transmission jitter), allocated to each measurand's budget, combined with a stated coverage factor, and complemented by a rule-of-three upper confidence bound for the observed zero False Authorisation Rate (FAR). Experimental validation gives FAR = 0, PDR in the range 50.7-82.7 % across PPE categories, authorisation latency below 1 s at 10 Hz, and unit sensitivity/specificity in detecting spindle-guard tampering, with zero packet loss in the machine-feedback layer. Expressing these indicators with a stated coverage interval, rather than as bare point estimates, turns them into metrologically traceable quantities usable in a quantitative risk-assessment matrix under EN ISO 12100:2010, and illustrates a general method for attaching a defensible uncertainty budget to distributed, RFID-based access-control instrumentation.