Comparison between Physics-Based Approaches and Neural Networks for the Energy Consumption Optimization of an Automotive Production Industrial Process
The automotive production sector plays a significant role in the energy consumption of all the industrial sphere, which currently represents approximately 38% of the total global energy use. Especially in production sites with several manufacturing lines working in parallel, the occurrence of failur...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/19/6916 |
| _version_ | 1797575924723482624 |
|---|---|
| author | Francesco Pelella Luca Viscito Federico Magnea Alessandro Zanella Stanislao Patalano Alfonso William Mauro Nicola Bianco |
| author_facet | Francesco Pelella Luca Viscito Federico Magnea Alessandro Zanella Stanislao Patalano Alfonso William Mauro Nicola Bianco |
| author_sort | Francesco Pelella |
| collection | DOAJ |
| description | The automotive production sector plays a significant role in the energy consumption of all the industrial sphere, which currently represents approximately 38% of the total global energy use. Especially in production sites with several manufacturing lines working in parallel, the occurrence of failures and anomalies or sudden changes in the production volume may require a re-scheduling of the entire production process. In this regard, a digital twin of each phase of the process would give several indications about the new re-scheduled manufacture in terms of energy consumption and the control strategy to adopt. Therefore, the main goal of this paper is to propose different modeling approaches to a degreasing tank process, which is a preliminary phase at automotive production sites before the application of paint to car bodies. In detail, two different approaches have been developed: the first is a physics-based thermodynamic approach, which relies on the mass and energy balances of the system analyzed, and the second is machine learning-based, with the calibration of several artificial neural networks (ANNs). All the investigated approaches were assessed and compared, and it was determined that, for this application and with the data at our disposal, the thermodynamic approach has better prediction accuracy, with an overall mean absolute error (MAE) of 1.30 °C. Moreover, the model can be used to optimize the heat source policy of the tank, for which it has demonstrated, with historical data, an energy saving potentiality of up to 30%, and to simulate future scenarios in which, due to company constraints, a re-scheduling of the production of more work shifts is required. |
| first_indexed | 2024-03-10T21:46:11Z |
| format | Article |
| id | doaj.art-e7e7917eea074a7dba9f3d9dd15c9829 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T21:46:11Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-e7e7917eea074a7dba9f3d9dd15c98292023-11-19T14:20:39ZengMDPI AGEnergies1996-10732023-09-011619691610.3390/en16196916Comparison between Physics-Based Approaches and Neural Networks for the Energy Consumption Optimization of an Automotive Production Industrial ProcessFrancesco Pelella0Luca Viscito1Federico Magnea2Alessandro Zanella3Stanislao Patalano4Alfonso William Mauro5Nicola Bianco6Department of Industrial Engineering, Università degli Studi di Napoli Federico II, P.le Tecchio 80, 80125 Naples, ItalyDepartment of Industrial Engineering, Università degli Studi di Napoli Federico II, P.le Tecchio 80, 80125 Naples, ItalyCentro Ricerche Fiat, Str. Torino 50, 10043 Orbassano, ItalyCentro Ricerche Fiat, Str. Torino 50, 10043 Orbassano, ItalyDepartment of Industrial Engineering, Università degli Studi di Napoli Federico II, P.le Tecchio 80, 80125 Naples, ItalyDepartment of Industrial Engineering, Università degli Studi di Napoli Federico II, P.le Tecchio 80, 80125 Naples, ItalyDepartment of Industrial Engineering, Università degli Studi di Napoli Federico II, P.le Tecchio 80, 80125 Naples, ItalyThe automotive production sector plays a significant role in the energy consumption of all the industrial sphere, which currently represents approximately 38% of the total global energy use. Especially in production sites with several manufacturing lines working in parallel, the occurrence of failures and anomalies or sudden changes in the production volume may require a re-scheduling of the entire production process. In this regard, a digital twin of each phase of the process would give several indications about the new re-scheduled manufacture in terms of energy consumption and the control strategy to adopt. Therefore, the main goal of this paper is to propose different modeling approaches to a degreasing tank process, which is a preliminary phase at automotive production sites before the application of paint to car bodies. In detail, two different approaches have been developed: the first is a physics-based thermodynamic approach, which relies on the mass and energy balances of the system analyzed, and the second is machine learning-based, with the calibration of several artificial neural networks (ANNs). All the investigated approaches were assessed and compared, and it was determined that, for this application and with the data at our disposal, the thermodynamic approach has better prediction accuracy, with an overall mean absolute error (MAE) of 1.30 °C. Moreover, the model can be used to optimize the heat source policy of the tank, for which it has demonstrated, with historical data, an energy saving potentiality of up to 30%, and to simulate future scenarios in which, due to company constraints, a re-scheduling of the production of more work shifts is required.https://www.mdpi.com/1996-1073/16/19/6916automotive production processpaint shopdigital twinmodel predictive controlartificial neural networkphysics-based model |
| spellingShingle | Francesco Pelella Luca Viscito Federico Magnea Alessandro Zanella Stanislao Patalano Alfonso William Mauro Nicola Bianco Comparison between Physics-Based Approaches and Neural Networks for the Energy Consumption Optimization of an Automotive Production Industrial Process Energies automotive production process paint shop digital twin model predictive control artificial neural network physics-based model |
| title | Comparison between Physics-Based Approaches and Neural Networks for the Energy Consumption Optimization of an Automotive Production Industrial Process |
| title_full | Comparison between Physics-Based Approaches and Neural Networks for the Energy Consumption Optimization of an Automotive Production Industrial Process |
| title_fullStr | Comparison between Physics-Based Approaches and Neural Networks for the Energy Consumption Optimization of an Automotive Production Industrial Process |
| title_full_unstemmed | Comparison between Physics-Based Approaches and Neural Networks for the Energy Consumption Optimization of an Automotive Production Industrial Process |
| title_short | Comparison between Physics-Based Approaches and Neural Networks for the Energy Consumption Optimization of an Automotive Production Industrial Process |
| title_sort | comparison between physics based approaches and neural networks for the energy consumption optimization of an automotive production industrial process |
| topic | automotive production process paint shop digital twin model predictive control artificial neural network physics-based model |
| url | https://www.mdpi.com/1996-1073/16/19/6916 |
| work_keys_str_mv | AT francescopelella comparisonbetweenphysicsbasedapproachesandneuralnetworksfortheenergyconsumptionoptimizationofanautomotiveproductionindustrialprocess AT lucaviscito comparisonbetweenphysicsbasedapproachesandneuralnetworksfortheenergyconsumptionoptimizationofanautomotiveproductionindustrialprocess AT federicomagnea comparisonbetweenphysicsbasedapproachesandneuralnetworksfortheenergyconsumptionoptimizationofanautomotiveproductionindustrialprocess AT alessandrozanella comparisonbetweenphysicsbasedapproachesandneuralnetworksfortheenergyconsumptionoptimizationofanautomotiveproductionindustrialprocess AT stanislaopatalano comparisonbetweenphysicsbasedapproachesandneuralnetworksfortheenergyconsumptionoptimizationofanautomotiveproductionindustrialprocess AT alfonsowilliammauro comparisonbetweenphysicsbasedapproachesandneuralnetworksfortheenergyconsumptionoptimizationofanautomotiveproductionindustrialprocess AT nicolabianco comparisonbetweenphysicsbasedapproachesandneuralnetworksfortheenergyconsumptionoptimizationofanautomotiveproductionindustrialprocess |