DeepESN Neural Networks for Industrial Predictive Maintenance through Anomaly Detection from Production Energy Data

• Published in: Applied sciences 2024-10, Vol.14 (19), p.8686
• Main Authors: Bonci, Andrea, Fredianelli, Luca, Kermenov, Renat, Longarini, Lorenzo, Longhi, Sauro, Pompei, Geremia, Prist, Mariorosario, Verdini, Carlo
• Format: Article
• Language: English
• Subjects: Advertising executives; anomaly detection; artificial intelligence; Assembly lines; Business metrics; Comparative analysis; echo state network; edge computing; Energy conservation; Energy consumption; Energy efficiency; Error correction & detection; Forecasts and trends; Industrial plant emissions; Industrial production; Machine learning; Machinery; Manufacturing industry; Neural networks; Performance evaluation; predictive maintenance; Smart meters; Time series
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app14198686

Optimizing energy consumption is an important aspect of industrial competitiveness, as it directly impacts operational efficiency, cost reduction, and sustainability goals. In this context, anomaly detection (AD) becomes a valuable methodology, as it supports maintenance activities in the manufacturing sector, allowing for early intervention to prevent energy waste and maintain optimal performance. Here, an AD-based method is proposed and studied to support energy-saving predictive maintenance of production lines using time series acquired directly from the field. This paper proposes a deep echo state network (DeepESN)-based method for anomaly detection by analyzing energy consumption data sets from production lines. Compared with traditional prediction methods, such as recurrent neural networks with long short-term memory (LSTM), although both models show similar time series trends, the DeepESN-based method studied here appears to have some advantages, such as timelier error detection and higher prediction accuracy. In addition, the DeepESN-based method has been shown to be more accurate in predicting the occurrence of failure. The proposed solution has been extensively tested in a real-world pilot case consisting of an automated metal filter production line equipped with industrial smart meters to acquire energy data during production phases; the time series, composed of 88 variables associated with energy parameters, was then processed using the techniques introduced earlier. The results show that our method enables earlier error detection and achieves higher prediction accuracy when running on an edge device.