Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models
We benchmark performance of long-short term memory (LSTM) network machine learning model and autoregressive integrated moving average (ARIMA) statistical model in temporal forecasting of distributed temperature sensing (DTS). Data in this study consists of fluid temperature transient measured with t...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10838524/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087998147067904 |
|---|---|
| author | Stella Pantopoulou Matthew Weathered Darius Lisowski Lefteri H. Tsoukalas Alexander Heifetz |
| author_facet | Stella Pantopoulou Matthew Weathered Darius Lisowski Lefteri H. Tsoukalas Alexander Heifetz |
| author_sort | Stella Pantopoulou |
| collection | DOAJ |
| description | We benchmark performance of long-short term memory (LSTM) network machine learning model and autoregressive integrated moving average (ARIMA) statistical model in temporal forecasting of distributed temperature sensing (DTS). Data in this study consists of fluid temperature transient measured with two co-located Rayleigh scattering fiber optic sensors (FOS) in a forced convection mixing zone of a thermal tee. We treat each gauge of a FOS as an independent temperature sensor. We first study prediction of DTS time series using Vanilla LSTM and ARIMA models trained on prior history of the same FOS that is used for testing. The results yield maximum absolute percentage error (MaxAPE) and root mean squared percentage error (RMSPE) of 1.58% and 0.06% for ARIMA, and 3.14% and 0.44% for LSTM, respectively. Next, we investigate zero-shot forecasting (ZSF) with LSTM and ARIMA trained on history of the co-located FOS only, which is advantageous when limited training data is available. The ZSF MaxAPE and RMSPE values for ARIMA are comparable to those of the Vanilla use case, while the error values for LSTM increase. We show that in ZSF, performance of LSTM network can be improved by training on most correlated gauges between the two FOS, which are identified by calculating the Pearson correlation coefficient. The improved ZSF MaxAPE and RMSPE for LSTM are 4.4% and 0.33%, respectively. Performance of ZSF LSTM can be further enhanced through transfer learning (TL), where LSTM is re-trained on a subset of the FOS that is the target of forecasting. We show that LSTM pre-trained on correlated dataset and re-trained on 30% of testing target dataset achieves MaxAPE and RMSPE values of 2.32% and 0.28%, respectively. |
| format | Article |
| id | doaj-art-6c8e84d7853e465689153f0a7b9c9f4e |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6c8e84d7853e465689153f0a7b9c9f4e2025-02-06T00:00:50ZengIEEEIEEE Access2169-35362025-01-0113102521026410.1109/ACCESS.2025.352643810838524Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical ModelsStella Pantopoulou0https://orcid.org/0000-0003-0361-633XMatthew Weathered1https://orcid.org/0000-0003-4134-9789Darius Lisowski2https://orcid.org/0000-0001-8214-2114Lefteri H. Tsoukalas3Alexander Heifetz4https://orcid.org/0000-0002-8891-9323Nuclear Science and Engineering Division, Argonne National Laboratory, Lemont, IL, USANuclear Science and Engineering Division, Argonne National Laboratory, Lemont, IL, USANuclear Science and Engineering Division, Argonne National Laboratory, Lemont, IL, USASchool of Nuclear Engineering, Purdue University, West Lafayette, IL, USANuclear Science and Engineering Division, Argonne National Laboratory, Lemont, IL, USAWe benchmark performance of long-short term memory (LSTM) network machine learning model and autoregressive integrated moving average (ARIMA) statistical model in temporal forecasting of distributed temperature sensing (DTS). Data in this study consists of fluid temperature transient measured with two co-located Rayleigh scattering fiber optic sensors (FOS) in a forced convection mixing zone of a thermal tee. We treat each gauge of a FOS as an independent temperature sensor. We first study prediction of DTS time series using Vanilla LSTM and ARIMA models trained on prior history of the same FOS that is used for testing. The results yield maximum absolute percentage error (MaxAPE) and root mean squared percentage error (RMSPE) of 1.58% and 0.06% for ARIMA, and 3.14% and 0.44% for LSTM, respectively. Next, we investigate zero-shot forecasting (ZSF) with LSTM and ARIMA trained on history of the co-located FOS only, which is advantageous when limited training data is available. The ZSF MaxAPE and RMSPE values for ARIMA are comparable to those of the Vanilla use case, while the error values for LSTM increase. We show that in ZSF, performance of LSTM network can be improved by training on most correlated gauges between the two FOS, which are identified by calculating the Pearson correlation coefficient. The improved ZSF MaxAPE and RMSPE for LSTM are 4.4% and 0.33%, respectively. Performance of ZSF LSTM can be further enhanced through transfer learning (TL), where LSTM is re-trained on a subset of the FOS that is the target of forecasting. We show that LSTM pre-trained on correlated dataset and re-trained on 30% of testing target dataset achieves MaxAPE and RMSPE values of 2.32% and 0.28%, respectively.https://ieeexplore.ieee.org/document/10838524/Distributed temperature sensingRayleigh scattering fiber optic sensorsthermal hydraulic temperature sensingmachine learningstatistical methodsARIMA |
| spellingShingle | Stella Pantopoulou Matthew Weathered Darius Lisowski Lefteri H. Tsoukalas Alexander Heifetz Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models IEEE Access Distributed temperature sensing Rayleigh scattering fiber optic sensors thermal hydraulic temperature sensing machine learning statistical methods ARIMA |
| title | Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models |
| title_full | Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models |
| title_fullStr | Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models |
| title_full_unstemmed | Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models |
| title_short | Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models |
| title_sort | temporal forecasting of distributed temperature sensing in a thermal hydraulic system with machine learning and statistical models |
| topic | Distributed temperature sensing Rayleigh scattering fiber optic sensors thermal hydraulic temperature sensing machine learning statistical methods ARIMA |
| url | https://ieeexplore.ieee.org/document/10838524/ |
| work_keys_str_mv | AT stellapantopoulou temporalforecastingofdistributedtemperaturesensinginathermalhydraulicsystemwithmachinelearningandstatisticalmodels AT matthewweathered temporalforecastingofdistributedtemperaturesensinginathermalhydraulicsystemwithmachinelearningandstatisticalmodels AT dariuslisowski temporalforecastingofdistributedtemperaturesensinginathermalhydraulicsystemwithmachinelearningandstatisticalmodels AT lefterihtsoukalas temporalforecastingofdistributedtemperaturesensinginathermalhydraulicsystemwithmachinelearningandstatisticalmodels AT alexanderheifetz temporalforecastingofdistributedtemperaturesensinginathermalhydraulicsystemwithmachinelearningandstatisticalmodels |