2025· Neural Information Processing Systems· pp. 116022-116050· 2 citations· 43 references
Computer Science
TL;DR
NoBOOM is presented, the first collection of datasets for anomaly detection in real-world chemical process data, including labeled data from a running process at BASF SE, one of the world’s leading chemical companies.
Abstract
Monitoring chemical processes is essential to prevent catastrophic failures, optimize costs and profits, and ensure the safety of employees and the environment. A key component of modern monitoring systems is the automated detection of anomalies in sensor data over time, called time series, enabling partial automation of plant operation and adding additional layers of supervision to crucial components. The development of anomaly detection methods in this domain is challenging, since real chemical process data is usually proprietary, and simulated data is generally not a sufficient replacement. In this paper, we present NoBOOM, the first collection of datasets for anomaly detection in real-world chemical process data, including labeled data from a running process at our industry partner BASF SE — one of the world’s leading chemical companies —
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
Due to significant developments in technology, manufacturing processes are being equipped with sensors that provide continuous monitoring of the input and output process parameters. Signals observed through such sensors provide crucial details about the quality of the manufactured items. While significant amount of work has been found in the literature that aims at monitoring products quality through acquired process signals, these studies assume enough frequency of defective products implying balanced models training data. In the case of data imbalance, such methods provide biased and misleading prediction results. This work presents an anomaly detection‐based framework for monitoring profile generating processes in the case of infrequent process defectives. The framework integrates three unsupervised anomaly detection algorithms: Isolation Forest (IF), Local Outlier Factor (LOF) and Density Based Scan (DBSCAN). The proposed framework is illustrated through two industrial case studies, a thread tapping process and a 3D printing process. For the tapping process, the DBSCAN model provided the best performance with AUC = 0.838, accuracy = 71.32%, and sensitivity = 92.0%. For the 3D printing process, IF algorithm achieved the best performance, with AUC = 0.862, accuracy = 75.19%, and sensitivity = 86.67%. Furthermore, an anomaly‐based control chart is introduced to enable continuous monitoring of profile generating processes and facilitate early detection of abnormal process behaviour. The results demonstrate the effectiveness of anomaly detection approaches for handling imbalanced process data and highlight their promising potential for intelligent quality control in modern manufacturing processes.
H. Alshraideh, Nour Al‐Huda Al‐Abed Al‐Rahim, Mahmoud Awad· Quality and Reliability Engi...· 0 citations
A structured methodology for ML-based PdM frameworks, covering data-driven, physics-based, and hybrid approaches, including supervised, unsupervised, and deep learning models is proposed, offering valuable insights for developing efficient and scalable PdM solutions.
Sithik Shah· International Journal of App...· 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
Abstract. The introduction of a data-based fault detection and diagnosis (FDD) has radically changed the concept of automated manufacturing systems as it provides the capability to monitor real-time in an intelligent manner, diagnose faults beforehand, and predictive maintenance schedules. Data-driven methods, in contrast to traditional reactive ones, make use of continuous sensor data streams to anticipate anomalies before they can result in critical failures using advanced analytics. This proactive feature has a great impact in minimizing unplanned downtime, increasing the safety of operations, and enhancing the overall efficiency of equipment. The FDD systems have been made effective with the help of the artificial intelligence (AI) and the Industrial Internet of Things (IoT). Sensors that have the ability to collect data through IoT can easily get data on various changes of the manufacturing facilities and the AI algorithms can help extract meaningful information data and support in making automated decisions. The other technologies such as cloud platform and edge computing, enable real-time processing of data and scalable analytics, thereby improving responsiveness and efficiency in the system. This implies that manufacturing systems are turning to be more adaptable, independent and robust.
V. K. Nassa· Materials Research Proceedin...· 0 citations
Hydrogen refueling station (HRS) requires continuous safety monitoring, yet conventional management relies largely on periodic inspection and manual oversight, limiting proactive risk mitigation. This study presents a data-driven intelligent analysis platform for real-time monitoring and anomaly detection of HRS safety data, including pressure, temperature, and flow-rate measurements from compressors, storage tanks, and dispensers. The platform integrates data collection adapters, a time-series database, and machine learning-based diagnostic modules (regression, clustering, and classification) into a unified reference software framework. For anomaly detection, an unsupervised LSTM-Variational Autoencoder trained on normal operating data is combined with DBSCAN-based clustering and a Mann–Kendall trend test to jointly identify point anomalies and pattern-level drifts, addressing the scarcity of labeled abnormal data in HRS environments. A continual learning mechanism further adapts detection thresholds to gradual and abrupt pattern changes without full retraining. The system was deployed and validated at BAM’s demonstration hydrogen refueling station in Germany, integrated with a remote safety-monitoring system and confirmed through performance testing, demonstrating reliable, proactive hydrogen safety management.
Minsu Kim, Seongseop Kim, Seungwoo Lee et al.· Applied Sciences· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
