Modeling of diesel particulate filter temperature dynamics during exotherm using neural networks
Diesel Particulate Filter (DPF) in the diesel engine exhaust stream needs frequent regeneration (exotherm) to remove captured particulate matter (PM, or soot) without damaging to the porous DPF structure by controlling the peak temperatures and temperature gradients across the DPF. In this study, te...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-10-01
|
| Series: | Frontiers in Thermal Engineering |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fther.2023.1265490/full |
| _version_ | 1797657114471038976 |
|---|---|
| author | Adithya Legala Adithya Legala Venkata LakkiReddy Phillip Weber Xianguo Li |
| author_facet | Adithya Legala Adithya Legala Venkata LakkiReddy Phillip Weber Xianguo Li |
| author_sort | Adithya Legala |
| collection | DOAJ |
| description | Diesel Particulate Filter (DPF) in the diesel engine exhaust stream needs frequent regeneration (exotherm) to remove captured particulate matter (PM, or soot) without damaging to the porous DPF structure by controlling the peak temperatures and temperature gradients across the DPF. In this study, temperature distribution in a DPF is measured at 42 strategic locations in the test DPF under various regeneration conditions of exhaust flow rates, regeneration temperatures and soot loads. Then a data-based model with feed-forward neural network architecture is designed to model the thermal gradients and temperature dynamics of the DPF during the regeneration process. The neural network feature vector selection, network architecture, hyperparameter calibration process, measured data preprocessing, and experimental data acquisition procedure are evaluated. Over 7,400 experimental data points at various regeneration temperatures, flow rates and soot loads are used in training and validating the neural network model. It is found that the neural network model can accurately predict the 42 DPF bed temperatures simultaneously at different locations, and the time series analysis of both model-predicted and experimentally measured temperatures shows a good correlation. This indicates that the currently developed neural network model can provide spatial distribution of temperature in the DPF, and comprehend the nonlinearity of the temperature dynamics due to DPF soot load at exothermic conditions. These results demonstrate that the data-based model has capability in predicting thermal gradients within a DPF, aiding in determining a safer DPF regeneration strategy, onboard diagnostics and DPF development. |
| first_indexed | 2024-03-11T17:39:42Z |
| format | Article |
| id | doaj.art-49d2a8240feb4ff1ab8ff2111d61c561 |
| institution | Directory Open Access Journal |
| issn | 2813-0456 |
| language | English |
| last_indexed | 2024-03-11T17:39:42Z |
| publishDate | 2023-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Thermal Engineering |
| spelling | doaj.art-49d2a8240feb4ff1ab8ff2111d61c5612023-10-18T12:28:05ZengFrontiers Media S.A.Frontiers in Thermal Engineering2813-04562023-10-01310.3389/fther.2023.12654901265490Modeling of diesel particulate filter temperature dynamics during exotherm using neural networksAdithya Legala0Adithya Legala1Venkata LakkiReddy2Phillip Weber3Xianguo Li4Southwest Research Institute, San Antonio, TX, United StatesDepartment of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON, CanadaSouthwest Research Institute, San Antonio, TX, United StatesSouthwest Research Institute, San Antonio, TX, United StatesDepartment of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON, CanadaDiesel Particulate Filter (DPF) in the diesel engine exhaust stream needs frequent regeneration (exotherm) to remove captured particulate matter (PM, or soot) without damaging to the porous DPF structure by controlling the peak temperatures and temperature gradients across the DPF. In this study, temperature distribution in a DPF is measured at 42 strategic locations in the test DPF under various regeneration conditions of exhaust flow rates, regeneration temperatures and soot loads. Then a data-based model with feed-forward neural network architecture is designed to model the thermal gradients and temperature dynamics of the DPF during the regeneration process. The neural network feature vector selection, network architecture, hyperparameter calibration process, measured data preprocessing, and experimental data acquisition procedure are evaluated. Over 7,400 experimental data points at various regeneration temperatures, flow rates and soot loads are used in training and validating the neural network model. It is found that the neural network model can accurately predict the 42 DPF bed temperatures simultaneously at different locations, and the time series analysis of both model-predicted and experimentally measured temperatures shows a good correlation. This indicates that the currently developed neural network model can provide spatial distribution of temperature in the DPF, and comprehend the nonlinearity of the temperature dynamics due to DPF soot load at exothermic conditions. These results demonstrate that the data-based model has capability in predicting thermal gradients within a DPF, aiding in determining a safer DPF regeneration strategy, onboard diagnostics and DPF development.https://www.frontiersin.org/articles/10.3389/fther.2023.1265490/fullartificial neural network (ANN)diesel particulate filter (DPF)particulate matter (PM)active regenerationexotherm reactiontemperature gradient modeling |
| spellingShingle | Adithya Legala Adithya Legala Venkata LakkiReddy Phillip Weber Xianguo Li Modeling of diesel particulate filter temperature dynamics during exotherm using neural networks Frontiers in Thermal Engineering artificial neural network (ANN) diesel particulate filter (DPF) particulate matter (PM) active regeneration exotherm reaction temperature gradient modeling |
| title | Modeling of diesel particulate filter temperature dynamics during exotherm using neural networks |
| title_full | Modeling of diesel particulate filter temperature dynamics during exotherm using neural networks |
| title_fullStr | Modeling of diesel particulate filter temperature dynamics during exotherm using neural networks |
| title_full_unstemmed | Modeling of diesel particulate filter temperature dynamics during exotherm using neural networks |
| title_short | Modeling of diesel particulate filter temperature dynamics during exotherm using neural networks |
| title_sort | modeling of diesel particulate filter temperature dynamics during exotherm using neural networks |
| topic | artificial neural network (ANN) diesel particulate filter (DPF) particulate matter (PM) active regeneration exotherm reaction temperature gradient modeling |
| url | https://www.frontiersin.org/articles/10.3389/fther.2023.1265490/full |
| work_keys_str_mv | AT adithyalegala modelingofdieselparticulatefiltertemperaturedynamicsduringexothermusingneuralnetworks AT adithyalegala modelingofdieselparticulatefiltertemperaturedynamicsduringexothermusingneuralnetworks AT venkatalakkireddy modelingofdieselparticulatefiltertemperaturedynamicsduringexothermusingneuralnetworks AT phillipweber modelingofdieselparticulatefiltertemperaturedynamicsduringexothermusingneuralnetworks AT xianguoli modelingofdieselparticulatefiltertemperaturedynamicsduringexothermusingneuralnetworks |