Anomaly detection in predictive maintenance: A new evaluation framework for temporal unsupervised anomaly detection algorithms

Carrasco, Jacinto; López, David Martín; Aguilera-Martos, Ignacio; García-Gil, Diego; Markova, Irina; García-Bárzana, Marta; Arias-Rodil, Manuel; Luengo, Julián; Herrera, Francisco

doi:10.1016/j.neucom.2021.07.095

Cited by 38 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Contributions such as [2,10,34] extend the support beyond the use of the basic performance measures in the evaluation phase. The work [2] generalizes the metrics provided by AD benchmarks by introducing the concept of Preceding Window ROC, which extends the popular ROC diagram to the case of time series. Also, the evaluation process is adapted to better fit the needs of AD algorithm assessment, e.g., by rewarding early anomaly detection.…”

Section: Related Workmentioning

confidence: 99%

ODIN AD: A Framework Supporting the Life-Cycle of Time Series Anomaly Detection Applications

Niccolò

Fraternali

Torres

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Anomaly detection (AD) in numerical temporal data series is a prominent task in many domains, including the analysis of industrial equipment operation, the processing of IoT data streams, and the monitoring of appliance energy consumption. The life-cycle of an AD application with a Machine Learning (ML) approach requires data collection and preparation, algorithm design and selection, training, and evaluation. All these activities contain repetitive tasks which could be supported by tools. This paper describes ODIN AD, a framework assisting the life-cycle of AD applications in the phases of data preparation, prediction performance evaluation, and error diagnosis.

show abstract

Section: Related Workmentioning

confidence: 99%

ODIN AD: A Framework Supporting the Life-Cycle of Time Series Anomaly Detection Applications

Niccolò

Fraternali

Torres

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Among many applications of PdM in the industry, it is worth focusing on anomaly detection approaches. In the paper [ 23 ], several methods of anomaly detection [ 24 , 25 , 26 ] were used for welding process data analysis. The other work [ 27 ] presents the artificial neural networks application for anomaly detection in photovoltaic systems.…”

Section: Related Workmentioning

confidence: 99%

Sensor-Based Predictive Maintenance with Reduction of False Alarms—A Case Study in Heavy Industry

Hermansa

Kozielski

Michalak

et al. 2021

Sensors

View full text Add to dashboard Cite

In this paper, the problem of the identification of undesirable events is discussed. Such events can be poorly represented in the historical data, and it is predominantly impossible to learn from past examples. The discussed issue is considered in the work in the context of two use cases in which vibration and temperature measurements collected by wireless sensors are analysed. These use cases include crushers at a coal-fired power plant and gantries in a steelworks converter. The awareness, resulting from the cooperation with industry, of the need for a system that works in cold start conditions and does not flood the machine operator with alarms was the motivation for proposing a new predictive maintenance method. The proposed solution is based on the methods of outlier identification. These methods are applied to the collected data that was transformed into a multidimensional feature vector. The novelty of the proposed solution stems from the creation of a methodology for the reduction of false positive alarms, which was applied to a system identifying undesirable events. This methodology is based on the adaptation of the system to the analysed data, the interaction with the dispatcher, and the use of the XAI (eXplainable Artificial Intelligence) method. The experiments performed on several data sets showed that the proposed method reduced false alarms by 90.25% on average in relation to the performance of the stand-alone outlier detection method. The obtained results allowed for the implementation of the developed method to a system operating in a real industrial facility. The conducted research may be valuable for systems with a cold start problem where frequent alarms can lead to discouragement and disregard for the system by the user.

show abstract

“…Relying on traditional image processing technology to solve the problem of visual inspection of industrial defects has a long research history, which can be divided into two types of research methods ( Carrasco et al, 2021 ). On the one hand, the specific feature extractors are manually designed to extract pixel-wise and structure-wise image features, which then are fed into the traditional classifier (KNN, SVM, BP etc .)…”

Section: Introductionmentioning

confidence: 99%

Adaptive visual detection of industrial product defects

Zhang

Wang

Chen

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

Visual inspection of the appearance defects on industrial products has always been a research hotspot pursued by industry and academia. Due to the lack of samples in the industrial defect dataset and the serious class imbalance, deep learning technology cannot be directly applied to industrial defect visual inspection to meet the real application needs. Transfer learning is a good choice to deal with insufficient samples. However, cross-dataset bias is unavoidable during simple knowledge transfer. We noticed that the appearance defects of industrial products are similar, and most defects can be classified as stains or texture jumps, which provides a research basis for building a universal and adaptive industrial defect detection model. In this article, based on the idea of model-agnostic meta-learning (MAML), we propose an adaptive industrial defect detection model through learning from multiple known industrial defect datasets and then transfer it to the novel anomaly detection tasks. In addition, the Siamese network is used to extract differential features to minimize the influence of defect types on model generalization, and can also highlight defect features and improve model detection performance. At the same time, we add a coordinate attention mechanism to the model, which realizes the feature enhancement of the region of interest in terms of two coordinate dimensions. In the simulation experiments, we construct and publish a visual defect dataset of injection molded bottle cups, termed BC defects, which can complement existing industrial defect visual data benchmarks. Simulation results based on BC defects dataset and other public datasets have demonstrated the effectiveness of the proposed general visual detection model for industrial defects. The dataset and code are available at https://github.com/zhg-SZPT/MeDetection.

show abstract

Anomaly detection in predictive maintenance: A new evaluation framework for temporal unsupervised anomaly detection algorithms

Cited by 38 publications

References 18 publications

ODIN AD: A Framework Supporting the Life-Cycle of Time Series Anomaly Detection Applications

ODIN AD: A Framework Supporting the Life-Cycle of Time Series Anomaly Detection Applications

Sensor-Based Predictive Maintenance with Reduction of False Alarms—A Case Study in Heavy Industry

Adaptive visual detection of industrial product defects

Contact Info

Product

Resources

About