GA−BP Prediction Model for Automobile Exhaust Waste Heat Recovery Using Thermoelectric Generator
Open Access
Abstract
Thermoelectric generator (TEG) has important applications in automotive exhaust waste heat recovery. The Back propagation neural network (BP) can predict the electrical generating performance of TEG efficiently and accurately due to its advantage of being good at handing nonlinear data. However, BP algorithm is easy to fall into local optimum, and its training data usually have deviation since the data are obtained through the simulation software. Both of the problems will reduce the prediction accuracy. In order to further improve the prediction accuracy of BP algorithm, we use the genetic algorithm (GA) to optimize BP neural network by selection, crossover, and mutation operation. Meanwhile, we create a TEG for the heat waste recovery of automotive exhaust and test 84 groups of experimental data set to train the GA−BP prediction model to avoid the deviation caused by the simulation software. The results show that the prediction accuracy of the GA−BP model is better than that of the BP model. For the predicted values of output power and output voltage, the mean absolute percentage error (MAPE) increased to 2.83% and 2.28%, respectively, and the mean square error (MSE) is much smaller than the value before optimization, and the correlation coefficient (R2) of the network model is greater than 0.99.Keywords
Funding Information
- National Natural Science Foundation of China (U21A2079, 52002382, 2021C01026, LR21E020002, 2019298, 2020R52032, 2022Z187)
- Zhejiang Provincial Key R&D Program (U21A2079, 52002382, 2021C01026, LR21E020002, 2019298, 2020R52032, 2022Z187)
- Zhejiang Provincial Natural Science Foundation of China (U21A2079, 52002382, 2021C01026, LR21E020002, 2019298, 2020R52032, 2022Z187)
- Youth Innovation Promotion Association of the Chinese Academy of Sciences (U21A2079, 52002382, 2021C01026, LR21E020002, 2019298, 2020R52032, 2022Z187)
- Zhejiang Provincial High-level Talent Special Support Plan (U21A2079, 52002382, 2021C01026, LR21E020002, 2019298, 2020R52032, 2022Z187)
- Ningbo Key Research and Development Plan (U21A2079, 52002382, 2021C01026, LR21E020002, 2019298, 2020R52032, 2022Z187)
This publication has 32 references indexed in Scilit:
- Energy Efficient Thermoelectric Generator-Powered Localized Air-Conditioning System Applied in a Heavy-Duty VehicleJournal of Energy Resources Technology, 2018
- Optimal design of a segmented thermoelectric generator based on three-dimensional numerical simulation and multi-objective genetic algorithmEnergy, 2018
- Artificial Neural Network Based Prediction of Energy Generation from Thermoelectric Generator with Environmental ParametersJournal of Clean Energy Technologies, 2017
- Effects of heat enhancement for exhaust heat exchanger on the performance of thermoelectric generatorApplied Thermal Engineering, 2015
- Effect of vehicle driving conditions on the performance of thermoelectric generatorEnergy Conversion and Management, 2015
- Artificial neural network development by means of a novel combination of grammatical evolution and genetic algorithmEngineering Applications of Artificial Intelligence, 2015
- Investigation and design optimization of exhaust-based thermoelectric generator system for internal combustion engineEnergy Conversion and Management, 2014
- TEG On-Vehicle Performance and Model Validation and What It Means for Further TEG DevelopmentJournal of Electronic Materials, 2012
- A Novel Optimization Method for the Electric Topology of Thermoelectric Modules Used in an Automobile Exhaust Thermoelectric GeneratorJournal of Electronic Materials, 2012
- Determination of Output Parameters of a Thermoelectric Module using Artificial Neural NetworksElektronika ir Elektrotechnika, 2011