LSTM-Based Neural Network Controllers as Drop-In Replacements for PI Controllers in a Wastewater Treatment Plant
Guardat en:
| Publicat a: | Applied Sciences vol. 15, no. 22 (2025), p. 12046-12065 |
|---|---|
| Autor principal: | |
| Altres autors: | |
| Publicat: |
MDPI AG
|
| Matèries: | |
| Accés en línia: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3275502815 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2076-3417 | ||
| 024 | 7 | |a 10.3390/app152212046 |2 doi | |
| 035 | |a 3275502815 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 231338 |2 nlm | ||
| 100 | 1 | |a Muhammad, Adil | |
| 245 | 1 | |a LSTM-Based Neural Network Controllers as Drop-In Replacements for PI Controllers in a Wastewater Treatment Plant | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Wastewater Treatment Plants (WWTPs) rely on automatic control strategies to regulate pollutant concentrations and comply with environmental standards. Among them, Proportional Integral (PI) controllers are widely adopted for their simplicity and robustness, yet their effectiveness is limited by the nonlinear and time-varying dynamics of biological processes. In this work, Long Short-Term Memory (LSTM)-based Artificial Neural Network (ANN) PI controllers are proposed as data-driven replacements for conventional PIs in key WWTP feedback loops. Using the Benchmark Simulation Model No. 1 (BSM1), ANN controllers were trained to replicate the behavior of default nitrate and nitrite nitrogen (<inline-formula>SNO,2</inline-formula>) and dissolved oxygen (<inline-formula>SO,5</inline-formula>) loops, under both time-agnostic and time-aware strategies with three- and four-input configurations. The four-input time-aware model delivered the best results, reproducing PI behavior with high accuracy (coefficient of determination, <inline-formula>R2≈0.99</inline-formula>) and considerably reducing control errors. For instance, under storm influent conditions, the <inline-formula>SO,5</inline-formula> controller reduced the Integral of Squared Error (<inline-formula>ISE</inline-formula>) and Integral of Absolute Error (<inline-formula>IAE</inline-formula>) by 84.7% and 68.4%, respectively, compared with the default PI. Beyond loop-level improvements, a Transfer Learning (TL) extension was explored: the trained <inline-formula>SO,5</inline-formula> controller was directly applied to additional aerated reactors (<inline-formula>SO,3</inline-formula> and <inline-formula>SO,4</inline-formula>) without retraining, replacing fixed aeration and demonstrating adaptability while reducing design effort. Plant-wide evaluation with the <inline-formula>SNO,2</inline-formula> loop and three dissolved oxygen loops (<inline-formula>SO,3</inline-formula>–<inline-formula>SO,5</inline-formula>), all controlled by LSTM-based PI controllers, under storm influent conditions, showed further reductions in the Effluent Quality Index (<inline-formula>EQI</inline-formula>) and the Overall Cost Index (<inline-formula>OCI</inline-formula>) by 0.84% and 1.47%, respectively, highlighting simultaneous gains in effluent quality and operational economy. Additionally, the actuator and energy analyses showed that the LSTM-based controllers produced realistic and smooth control signals, maintained consistent energy use, and ensured stable overall operation, confirming the practical feasibility of the proposed approach. | |
| 653 | |a Nitrates | ||
| 653 | |a Reactors | ||
| 653 | |a Simulation | ||
| 653 | |a Design | ||
| 653 | |a Denitrification | ||
| 653 | |a Wastewater treatment | ||
| 653 | |a Robust control | ||
| 653 | |a Sludge | ||
| 653 | |a Effluents | ||
| 653 | |a Chemical oxygen demand | ||
| 653 | |a Neural networks | ||
| 653 | |a Process controls | ||
| 700 | 1 | |a Vilanova Ramon | |
| 773 | 0 | |t Applied Sciences |g vol. 15, no. 22 (2025), p. 12046-12065 | |
| 786 | 0 | |d ProQuest |t Publicly Available Content Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3275502815/abstract/embedded/Q8Z64E4HU3OH5N8U?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3275502815/fulltextwithgraphics/embedded/Q8Z64E4HU3OH5N8U?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3275502815/fulltextPDF/embedded/Q8Z64E4HU3OH5N8U?source=fedsrch |