LSTM-Based Anomaly Detection in Manufacturing Environmental Monitoring Data

Junjing Qiao; Enxian Zhou

doi:10.23977/autml.2023.040307

LSTM-Based Anomaly Detection in Manufacturing Environmental Monitoring Data

Download as PDF

DOI: 10.23977/autml.2023.040307 | Downloads: 9 | Views: 293

Author(s)

Junjing Qiao ¹, Enxian Zhou ¹

Affiliation(s)

¹ Shanghai Zhenhua Heavy Industries Co., Ltd., Shanghai, China

Corresponding Author

Junjing Qiao

ABSTRACT

With the proliferation of environmental monitoring data, using machine learning techniques for anomaly detection in environmental time series data has become an active research direction. This study employs Long Short-Term Memory (LSTM) neural network models to detect anomalies in manufacturing emission data. The research first preprocesses the data by handling missing values and conducting stationarity tests. The data will be divided into training and testing sets, with the model trained on normal data and tested for anomalies. Experiments show LSTM outperforms classic methods like Isolation Forest, Matrix Profile, and AutoEncoder in handling enclosed pipeline emission data. This study is primarily due to LSTM's ability to capture long-term dependencies in time series data. Establishing this model facilitates improved environmental protection and safety management, enables automated monitoring and warning, reduces manual intervention, and lowers enterprise environmental compliance risks. This study provides an effective anomaly detection model for monitoring manufacturing emissions, serving as a reliable reference for introducing machine learning into environmental monitoring domains.

KEYWORDS

Anomaly detection, Environmental monitoring, LSTM, Manufacturing emission

CITE THIS PAPER

Junjing Qiao, Enxian Zhou, LSTM-Based Anomaly Detection in Manufacturing Environmental Monitoring Data. Automation and Machine Learning (2023) Vol. 4: 55-59. DOI: http://dx.doi.org/10.23977/autml.2023.040307.

REFERENCES

[1] Housh, M., & Ostfeld, A. (2015). An integrated logit model for contamination event detection in water distribution systems. Water Research, 75, 210-223.
[2] Mukherjee, I., Sahu, N. K., & Sahana, S. K. (2021). Simulation and Modeling for Anomaly Detection in IoT Network Using Machine Learning. International Journal of Wireless Information Networks, 1-13.
[3] Lu, Q., Wang, L., & Huang, G. (2022). Abnormal detection and recovery of pollutant data considering time series characteristics. Journal of Safety and Environment.
[4] Zhong, S., Zhang, K., Bagheri, M., Burken, J. G., Gu, A., Li, B.,& Zhang, H. (2021). Machine Learning: New Ideas and Tools in Environmental Science and Engineering. Environmental Science & Technology.
[5] Du, Y., Zhang, Y., Yuan, Z., Guan, P., & Peng, Y. (2021). Accuracy analysis of air pollution prediction for LSTM network based on data preprocessing. Computer and Digital Engineering, 49(7), 1400-1425.

Subscription

E-Mail Alert

Downloads:	1652
Visits:	69406

LSTM-Based Anomaly Detection in Manufacturing Environmental Monitoring Data

Author(s)

Affiliation(s)

Corresponding Author

ABSTRACT

KEYWORDS

CITE THIS PAPER

REFERENCES

RESOURCES

JOIN US

PUBLICATION SERVICES

CONTACT US