Explainable anomaly detection framework for predictive maintenance in manufacturing systems

Choi, Heejeong; Kim, Donghwa; Kim, Jounghee; Kim, Jina; Kang, Pilsung

doi:10.1016/j.asoc.2022.109147

Cited by 26 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are exploring the incorporation of a multi-class classification scheme that differentiates between 'normal', 'warning', and 'abnormal' states within the manufacturing process. By employing this expanded taxonomy, we can shed light on the potential causes of anomalous conditions and enhance the interpretability of our anomaly detection system [5,32]. This labeling approach will offer a more meaningful understanding of the underlying causes behind the predicted failures.…”

Section: A Discussionmentioning

confidence: 99%

“…First, our LSTM-autoencoder model is a DL algorithm composed of many parameters and layers. However, there still exists the black box issue: it is difficult to understand the prediction results of anomalies using DL technologies [5]. Explanations are required for the results predicted as anomalies [5,32].…”

Section: B Limitations and Future Researchmentioning

confidence: 99%

“…However, there still exists the black box issue: it is difficult to understand the prediction results of anomalies using DL technologies [5]. Explanations are required for the results predicted as anomalies [5,32]. We propose future research directions that involve incorporating explanatory artificial intelligence (XAI) methodologies, such as surrogate models, local interpretable model-judgment explanation (LIME), and Shapley Additive exPlanations (SHAP).…”

Section: B Limitations and Future Researchmentioning

confidence: 99%

“…In smart factories, manufacturing equipment data collected from connected Internet of Things devices or sensors are monitored and controlled in real-time using sophisticated software systems [1,2]. As a result, manufacturers can expect increased productivity, decreased downtime and maintenance costs, and improved product quality [3][4][5]. Despite data-driven efforts, however, smart factories have not effectively addressed the issue of delays caused by downtime during manufacturing processes [1,6].…”

Section: Introductionmentioning

confidence: 99%

“…Various efforts exist to prevent process downtime in smart factories using equipment data [5][6][7]. These efforts aim to build a supervisory control and data acquisition (SCADA) based smart factory system that can preemptively handle downtime using various time-series data, such as equipment status, temperature, and humidity, originating from process sensors [2,8].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Enhanced Anomaly Detection in Manufacturing Processes Through Hybrid Deep Learning Techniques

Lee,

Kim,

Kim

2023

IEEE Access

View full text Add to dashboard Cite

Smart factory systems have been introduced to prevent the decline in overall equipment effectiveness caused by the presence of defects within factory manufacturing equipment. In this context, it is crucial to predict process downtime using manufacturing equipment data and take preemptive actions. However, anomaly detection models for preemptive actions have limitations in labeling anomaly alarms. Moreover, from real-time data collection to model deployment, it needs to consider the model-based service implementation for stakeholders. Our research develops a hybrid deep learning-based anomaly detection model that does not require data labeling. The advantage of this model stems from its ability to identify anomalous patterns via the reconstruction of the sequential progression inherent in the data. According to our experimental findings, the proposed hybrid model demonstrated superior efficacy compared to alternative anomaly detection algorithms. By preemptively predicting downtime within the manufacturing process, it contributes to enhanced production efficiency. Furthermore, we develop an anomaly detection system based on a real-time service framework from the data collection step to improve the activation of smart factories. This research contributes to the literature on the monitoring and management of anomaly detection in smart factories. It also has practical implications for the manufacturing industry by recommending efficiency measures for smart factories to reduce downtime in manufacturing processes and improve product quality.

show abstract

Section: A Discussionmentioning

confidence: 99%