DETECTA 2.0: Research into non-intrusive methodologies supported by Industry 4.0 enabling technologies for predictive and cyber-secure maintenance in SMEs

TL;DR

The paper addresses the challenge of delivering predictive maintenance and cybersecurity for SMEs in Industry 4.0. It presents DETECTA 2.0, a non-intrusive, modular system that fuses real-time anomaly detection, digital twin visualization, semi-supervised learning, and a time-series predictor (N-HiTS) to forecast machine utilization. The approach is validated through a milling-machine case study in Industrias Maxi, achieving improvements such as reduced false positives (from 40% in Phase I to 10% in Phase II) and a 25-minute-ahead forecasting MAE of 1.07. The work offers a scalable, cost-effective solution for SMEs to enhance predictive maintenance and cybersecurity, leveraging on-premise deployment and interoperable components within Industry 4.0 ecosystems.

Abstract

The integration of predictive maintenance and cybersecurity represents a transformative advancement for small and medium-sized enterprises (SMEs) operating within the Industry 4.0 paradigm. Despite their economic importance, SMEs often face significant challenges in adopting advanced technologies due to resource constraints and knowledge gaps. The DETECTA 2.0 project addresses these hurdles by developing an innovative system that harmonizes real-time anomaly detection, sophisticated analytics, and predictive forecasting capabilities. The system employs a semi-supervised methodology, combining unsupervised anomaly detection with supervised learning techniques. This approach enables more agile and cost-effective development of AI detection systems, significantly reducing the time required for manual case review. At the core lies a Digital Twin interface, providing intuitive real-time visualizations of machine states and detected anomalies. Leveraging cutting-edge AI engines, the system intelligently categorizes anomalies based on observed patterns, differentiating between technical errors and potential cybersecurity incidents. This discernment is fortified by detailed analytics, including certainty levels that enhance alert reliability and minimize false positives. The predictive engine uses advanced time series algorithms like N-HiTS to forecast future machine utilization trends. This proactive approach optimizes maintenance planning, enhances cybersecurity measures, and minimizes unplanned downtimes despite variable production processes. With its modular architecture enabling seamless integration across industrial setups and low implementation costs, DETECTA 2.0 presents an attractive solution for SMEs to strengthen their predictive maintenance and cybersecurity strategies.

Figures (7)

• Figure 1: Visualization of system architecture for PdM and cybersecure SMEs in Industry 4.0
• Figure 2: Digital Twin graphical interface created using the open-source software Grafana.
• Figure 3: General Schema of the Decision Support and Alert System
• Figure 4: Visual analysis of the Decision Tree model using confusion matrix and SHAP values
• Figure 5: Consumption Forecasting of NHiTS model