•  
  •  
 

Abstract

This scientific article investigates the problem of analyzing technological process parameters in the fields of chemistry, energy, and metallurgy based on sensor data and applying intelligent signal processing methods. The main objective is to evaluate the effectiveness of artificial intelligence and deep learning models for intelligent analysis, forecasting, and anomaly detection of data obtained from sensors. Time-series data collected from industrial sensors were analyzed using LSTM (Long Short-Term Memory) and Autoencoder neural networks, as well as the Kalman filter. At the first stage of the study, sensor signals were denoised and their true state was estimated using the Kalman filter. According to the results, the filter achieved a high level of accuracy (RMSE = 0.001), allowing precise reconstruction of the overall signal trend. In the next stage, time-series forecasting was performed using the LSTM network. The LSTM model effectively learned long-term dependencies and was able to predict dynamic variations in industrial sensor signals. The obtained results (MAE = 8.079, RMSE = 10.626, MAPE = 9.194%) demonstrate that the model achieved a high level of accuracy. The Autoencoder architecture was applied for unsupervised anomaly detection. The model achieved a Precision of 0.934 and a PR-AUC value of 0.929, indicating high accuracy in identifying anomalous conditions. However, due to a relatively low Recall (0.249), some abnormal cases were not detected. Therefore, it is recommended to improve the Recall–Precision balance in future studies through threshold calibration and ensemble-based approaches.

First Page

33

Last Page

44

References

  1. Cao, Z., Li, J., & Zhang, T. (2025). A long-tailed distribution time-series dataset in boiler equipment. Figshare. https://doi.org/10.6084/m9.figshare.28868849
  2. Zhou, Y., Zhang, L., & Wang, J. (2020). Deep learning-based combustion modeling for industrial boilers: A review. Energy Reports, 6, 1234–1247. https://doi.org/10.1016/j.egyr.2020.09.034
  3. Li, H., Sun, W., & Chen, Q. (2021). Application of deep neural networks in boiler operation optimization. Applied Thermal Engineering, 182, 116060. https://doi.org/10.1016/j.applthermaleng.2020.116060
  4. Wang, Y., Li, Z., & Zhang, N. (2024). A hybrid soft sensor model for measuring the oxygen content in boiler flue gas. Sensors, 24(7), 2340. https://doi.org/10.3390/s24072340
  5. Lyu, T., Gan, Y., Zhang, R., Wang, S., & Zhuo, Y. (2024). Development of a real-time NOx prediction soft sensor algorithm for power plants based on a hybrid boost integration model. Energies, 17(19), 4926. https://doi.org/10.3390/en17194926
  6. He, M.-Q., Zhang, C., & Liu, X. (2023). Dynamic soft sensor modeling of matte grade in copper flash smelting process. Measurement, 229, 113364. https://doi.org/10.1016/j.measurement.2023.113364
  7. Wei, B., Huang, D., & Zhang, K. (2024). A hybrid soft sensor for key product yield of FCC unit based on deep learning framework driven by data and process mechanism. Chemical Engineering Research and Design, 203, 119–131. https://doi.org/10.1016/j.cherd.2024.02.008
  8. Recio-Colmenares, R., Martínez, E., & Rodríguez, J. (2023). Design of a soft sensor based on long short-term memory for WWTP monitoring. Sensors, 23(22), 9236. https://doi.org/10.3390/s23229236
  9. Ji, S., Li, W., & Zhang, B. (2024). A soft sensor model for predicting the flow of a hydraulic pump based on GCN–LSTM. Actuators, 13(1), 38. https://doi.org/10.3390/act13010038
  10. Wibbeke, J., Alves, D., & Rohjans, S. (2023). Estimating time-delayed variables using transformer-based soft sensors. Energy Informatics, 6, 16. https://doi.org/10.1186/s42162-023-00274-3
  11. Song, Y., Liu, G., & Zhao, C. (2024). Unsupervised anomaly detection in shearers via CNN–ConvLSTM autoencoder. International Journal of Coal Science & Technology. https://doi.org/10.1007/s40789-024-00730-9
  12. Winter, M., Fink, C., & Müller, T. (2024). Soft sensor for viable cell counting by dynamic oxygen uptake rate. New Biotechnology, 83, 16–25. https://doi.org/10.1016/j.nbt.2024.06.001
  13. Zeng, H., Xu, P., & Luo, Y. (2024). Dual-attention LSTM–autoencoder for chemical process fault detection. Knowledge-Based Systems, 293, 111514. https://doi.org/10.1016/j.knosys.2024.111514
  14. Kaggle. (n.d.). Time series of industrial boiler operations [Data set]. Retrieved October 17, 2025, from https://www.kaggle.com/datasets/nikitamanaenkov/time-series-of-industrial-boiler-operations/data
  15. Liu, Z.-X., Wang, Z.-Y., Wang, Y., et al. (2022). Optimal zonotopic Kalman filter-based state estimation and fault-diagnosis algorithm for linear discrete-time systems with time delay. International Journal of Control, Automation and Systems, 20, 1757–1771. https://doi.org/10.1007/s12555-021-0267-x
  16. Afridi, Y. S., Hasan, L., Ullah, R., Ahmad, Z., & Kim, J.-M. (2023). LSTM-based condition monitoring and fault prognostics of rolling element bearings using raw vibrational data. Machines, 11(5), 531. https://doi.org/10.3390/machines11050531
  17. Yun, H., Kim, H., Jeong, Y. H., & Jun, M. B. G. (2023). Autoencoder-based anomaly detection of industrial robot arm using stethoscope-based internal sound sensor. Journal of Intelligent Manufacturing, 34(3). https://doi.org/10.1007/s10845-021-01862-4

Download

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.