A novel self-supervised strategy for effective single-machine training based on classifying the distance between the monitored machine and each microphone sensor of a multi-channel recording system is introduced, providing a cost-efficient and privacy-preserving alternative while delivering competitive detection performance.
Abstract
The rise of low-power, affordable sensing technologies and machine learning algorithms has sparked a growing interest in using data-driven approaches to monitor industrial assets. In particular, applying machine learning to analyze the sounds produced by manufacturing tools is becoming an effective method for quickly detecting deviations from standard operating conditions. However, the implementation of these systems encounters a major challenge due to the difficulty in obtaining suitable training data. Self-supervised learning offers a promising solution to this issue. It enables the training of anomaly detection models exclusively with signals representing normal conditions, which are more accessible than anomalous signals. Despite its potential, achieving robust and consistent performance across machines of varying models and types remains critical. Existing methods generally follow one of two approaches. The first, single-machine training, involves training a dedicated model using local data from each machine. Although straightforward, this approach often yields suboptimal performance. The second, multi-machine training, aims to enhance detection capability by aggregating data from multiple machines to train a shared model. This strategy requires transmitting data from geographically dispersed manufacturing sites—often belonging to different clients—to centralized facilities, raising concerns about data transmission costs and risks of exposing sensitive production information. We address these issues by introducing a novel self-supervised strategy for effective single-machine training based on classifying the distance between the monitored machine (i.e., the sound source) and each microphone sensor of a multi-channel recording system. Our method bypasses the need for data aggregation, providing a cost-efficient and privacy-preserving alternative while delivering competitive detection performance. Experiments on the MIMII dataset highlight the effectiveness of our approach, with performance improvements up to 14.53% over conventional single-machine training strategies and 18.58% over multi-machine training strategies.
Modern power systems are often equipped with advanced monitoring infrastructure that can collect vast and diverse data streams. Data-driven approaches, such as anomaly detection (AD), can be applied to these data, complementing existing monitoring practices, and supporting adaptive and intelligent decision-making. Industrial anomaly detection is challenging due to the predominance of normal operational data, rare anomalous events, and limited labeled samples. The success of unsupervised AD approaches are often dependent on the proper thresholds, which determine whether or not a sample is anomalous. The often manual process of setting the thresholds can be challenging in ensuring the accuracy, reliability, and robustness of AD in a wide range of operational scenarios. To address this challenge, we propose a self-supervised, meta-learning-based anomaly detection framework that reduces reliance on explicit threshold tuning. The method combines multiple models to exploit complementary strengths and uses reconstruction errors of an ensemble of autoencoders as meta-features to improve detection of subtle anomalies. By generating labels from meta-features, the approach supports learning in label-scarce scenarios. Experiments on different public and industrial datasets show that integrating meta-features and generated pseudo-labels achieves performance comparable to supervised learning based on the ground truth labels. The results demonstrate the proposed approach as a promising threshold independent solution for real-world, label-scarce industrial applications.
S. M. Naidu, Pawel M. Stano, J. Ottewill et al.· IEEE Access· 0 citations
Motors are crucial elements in the industry, where unexpected failures can interrupt production cycles, reduce profits, and raise safety concerns; and therefore an early anomaly detection in motor behavior is highly appreciated. As an extension of the known internet of things (IoT), industrial IoT or IIoT allows connection of motors and their drive units through distributed sensing platforms capable of acquiring operational data related to power, temperature, vibration, and rotational speed. Once these data are transferred through the available IIoT infrastructure and stored appropriately for later off-line processing, the limited availability of labeled fault data remains a major obstacle in practical industrial applications. As a remedy, this study proposes a semi-supervised anomaly detection framework that relies exclusively on non-intrusive three-phase electrical telemetry. Focusing on a commercial offset printing press, high-frequency power measurements were collected from failure-sensitive dryer motors. Time-domain statistical features, including mean, clearance factor, and shape factor extracted from active power, power factor, and current signals, were employed to train an unsupervised One-Class Support Vector Machine (OC-SVM). Experimental results obtained from 84 hours of real industrial telemetry demonstrated the effectiveness of the proposed approach in modeling normal operating behavior, achieving a Recall of 93.79%, a False Positive Rate of 5.12%, and an F1-Score of 94.59%. The developed framework enables early anomaly detection, lowers maintenance expenses, reduces operational downtime, and enhances overall system reliability, supporting the advancement of smart Industry 4.0 environments.
M. Zeidan, S. Aldalahmeh, Z. Haymoor et al.· IEEE Jordan Conference on Ap...· 0 citations
Supervisory Control and Data Acquisition (SCADA) systems play a crucial role in monitoring the operational health of modern wind turbines by continuously collecting large volumes of sensor data. Efficient analysis of this data is essential for early fault detection, predictive maintenance, and reliable turbine operation. However, anomaly detection in SCADA environments remains challenging due to data imbalance, noise, nonlinear relationships, and dynamic operating conditions. Traditional machine learning approaches often suffer from limited generalization capability and may fail to achieve a balanced trade-off between precision and recall. To address these challenges, this paper proposes a Hybrid Machine Learning Framework for SCADA-based anomaly detection in wind turbine systems using ensemble learning. The proposed framework integrates Isolation Forest, One-Class Support Vector Machine (OCSVM), and Deep Autoencoder models to capture complementary anomaly characteristics from operational data. The outputs of these base models are further combined using an AdaBoost-based stacking architecture to improve classification robustness and anomaly detection performance. Experiments were conducted on a publicly available wind turbine SCADA dataset containing more than 50,000 operational samples and multiple turbine health parameters. The proposed hybrid framework was evaluated using Precision, Recall, F1-score, Area Under Curve (AUC), and confusion matrix analysis. Experimental results demonstrate that the proposed model significantly outperforms standalone approaches, achieving a Recall of 0.8702, F1-score of 0.7118, and AUC of 0.9678. Furthermore, the framework substantially reduces false negative predictions, making it highly suitable for predictive maintenance applications. The findings indicate that integrating machine learning, deep learning, and ensemble learning techniques provides a robust and effective solution for intelligent anomaly detection in industrial SCADA systems.
Keywords: machine learning; deep learning; Anomaly detection; AutoEncoder; Ensemble Learning; One-Class SVM; SCADA; Wind Turbine Monitoring; Isolation Forest; Predictive Maintenance
Zakir Ahmed Ansari, Dr. Tariq Siddiqui· International Journal of Tec...· 0 citations
This study develops and evaluates an AI-based analytical system for detecting anomalies in industrial processes. The work reviews major sources of risk in industrial control systems, distinguishes point, contextual, and collective anomalies, and summarizes the principal machine-learning approaches used for industrial anomaly detection. A synthetic dataset modeled on the Secure Water Treatment (SWaT) testbed was created with 10 sensor and actuator variables and 10,000 one-second observations, including 1,000 anomalous samples. After missing-value interpolation, duplicate removal, low-variance filtering, and standardization for consistent analysis and visualization, an Isolation Forest with 200 trees was trained in a novelty-detection configuration using normal operating data. On the held-out test set, the model achieved 88.63% accuracy, 45.86% precision, 75.67% recall, and an F1-score of 57.11%. The results show that Isolation Forest can detect most simulated anomalies, although the relatively low precision indicates a substantial false-alarm burden. Future work should validate the approach on authorized real SWaT or PLC-SCADA data, investigate hybrid temporal models, and incorporate explainable-AI methods to support operator decision-making.
Mehdiyeva Almaz, Ahmedov Elmar, Uzakov Gulom et al.· 2026 International Conferenc...· 0 citations
This research establishes a statistically robust and deployable foundation for next-generation intelligent transportation systems by coupling Bayesian learning theory with edge computing design.
Seyed Mohammad Hosseini, V. Kiani, Hadi Sadoghi-Yazdi· Computing· 0 citations
A thorough analysis of unsupervised learning techniques used in the health monitoring of industrial robots explores significant trends and key algorithms, such as clustering, autoencoders, and generative models, assessing their effectiveness in identifying faults and performance degradation.
Muhammad Umar Elahi, Rana Talal Ahmad Khan, Muhammad Haris Yazdani et al.· Mathematics· 0 citations
