A novel approach for the detection of anomalous energy consumption patterns in industrial cyber‐physical systems

Abstract

Most scenarios emerging from the Industry 4.0 paradigm rely on the concept of cyber‐physical production systems (CPPS), which allow them to synergistically connect physical to digital setups so as to integrate them over all stages of product development. Unfortunately, endowing CPPS with AI‐based functionalities poses its own challenges: although advances in the performance of AI models keep blossoming in the community, their penetration in real‐world industrial solutions has not so far developed at the same pace. Currently, 90% of AI‐based models never reach production due to a manifold of assorted reasons not only related to complexity and performance: decisions issued by AI‐based systems must be explained, understood and trusted by their end users. This study elaborates on a novel tool designed to characterize, in a non‐supervised, human‐understandable fashion, the nominal performance of a factory in terms of production and energy consumption. The traceability and analysis of energy consumption data traces and the monitoring of the factory's production permit to detect anomalies and inefficiencies in the working regime of the overall factory. By virtue of the transparency of the detection process, the proposed approach elicits understandable information about the root cause from the perspective of the production line, process and/or machine that generates the identified inefficiency. This methodology allows for the identification of the machines and/or processes that cause energy inefficiencies in the manufacturing system, and enables significant energy consumption savings by acting on these elements. We assess the performance of our designed method over a real‐world case study from the automotive sector, comparing it to an extensive benchmark comprising state‐of‐the‐art unsupervised and semi‐supervised anomaly detection algorithms, from classical algorithms to modern generative neural counterparts. The superior quantitative results attained by our proposal complements its better interpretability with respect to the rest of algorithms in the comparison, which emphasizes the utmost relevance of considering the available domain knowledge and the target audience when design AI‐based industrial solutions of practical value. Finally, the work described in this paper has been successfully deployed on a large scale in several industrial factories with significant international projection.

Explainable AI for Cyber-Physical Systems: Issues and Challenges

“…Industry 4.0 integrates cyber-physical systems, robotics, additive manufacturing, big data, augmented reality, IoT, system integration, and cloud computing. Many applications of Industry 4.0 involve cyber-physical production systems, integrating physical and digital systems so they are synergistically involved in all stages of product development [40].…”

“…According to Mendia et al [40], 90% of AI models never reach production in real-world industrial solutions. This is due in part to complexity and performance, but more importantly, it is due to explainability concerns [40].…”

“…According to Mendia et al [40], 90% of AI models never reach production in real-world industrial solutions. This is due in part to complexity and performance, but more importantly, it is due to explainability concerns [40]. The AI-derived recommendations need to be explained by the system as well as understood and trusted by the users.…”

“…Mendia et al [40] contributed an XAI model called NAIA, "a novel tool designed to characterize, in a non-supervised, human-understandable fashion, the nominal performance of a factory in terms of production and energy consumption." This tool can be integrated with cyber-physical production systems to trace and analyze energy consumption, facilitating anomaly detection and inefficiency detection and providing human-understandable information about the root cause of the problem.…”

Recent trends and advances in machine learning challenges and applications for industry 4.0

“…Principal component analysis extracts features, and Kruskal-Wallis and Tukey statistical tests compare classifier performance. Mendia et al (2022) present NAIA, a hybrid solution that combines domain knowledge and machine learning techniques to characterize and monitor the nominal performance of a factory in terms of production and energy consumption. The authors claim that NAIA can identify anomalies and inefficiencies in the factory operation and provide understandable information about the root cause of the problem.…”