Prediction of System-Level Energy Harvesting Characteristics of a Thermoelectric Generator Operating in a Diesel Engine Using Artificial Neural Networks

Abstract

This study evaluated the potential of artificial neural networks (ANNs) to predict the system-level performance of a thermoelectric generator (TEG), whose performance depends on various variables including engine load, engine rotation speed, and external load resistance. Therefore, a Python code was developed to determine an optimal ANN structure by tracking the training/prediction errors of the ANN as a function of the number of hidden layers and nodes of hidden layers. The optimal ANN was trained using 484 output current (I)–load resistance (R) datasets obtained under three different engine rotation speeds and five different engine loads. The prediction accuracy of the ANN was validated by comparing 88 I–R datasets reproduced by the ANN using experimental data that were not used for training. In the validation procedure, differences of only 3.49% and 2.59% were observed in the experimental and ANN-predicted output power obtained for the 1000 rpm–0.8 MPa brake mean effective pressure (BMEP) and 1500 rpm–0.4 MPa BMEP scenarios, respectively. The exhaust gas flow characteristics were used for training and validation to predict the pumping loss caused by the installation of the TEG in the middle of the exhaust tailpipe with high accuracy. The results demonstrated that the ANN effectively reproduced datasets to fill the gaps between the discretized experimental results for all the experimental scenarios without any noticeable overfitting and underfitting. The net power gain obtained by the ANN exhibited a clear peak point for the engine rotation speed of 2000 rpm, which is difficult to obtain using experimental data.

Using Machine Learning Techniques to Discover Novel Thermoelectric Materials

“…Last but not least, the use of the best-segmented ratio design in a thermoelectric generator system showed improved performance and boosted output power by 6.8%. Kim et al estimated the performance of a TEG running on a diesel engine using ANNs implemented using Python code [100]. Validation studies found a 3.49% difference between the output power of the experimental and predicted TEG.…”

Evaluation of Thermoelectric Generators under Mismatching Conditions

“…where 𝜌 𝐽 ⃗ is the Joule heating, 𝛼𝐽 ⃗ ∇𝑇 is the work done against the Seebeck field, and 𝑞 = [ℎ𝑃(𝑇 − 𝑇 )]/𝐴 is the heat loss on the side of the TEG's legs due to convection, where the term ℎ [W/m K] is the heat transfer coefficient, 𝑇 the ambient temperature, 𝑃 and 𝐴 are the perimeter and area of the TEG's leg cross-section, respectively [28]. The divergence of Equation (3) using the product rule yields (7).…”

“…A single thermoelectric generator (TEG) is a device composed of semiconductor materials (N and P-type) connected electrically in series and thermally in parallel (More than two modules can be electrically connected either in series or parallel) that produces electric power from a temperature difference (Seebeck effect), or cooling from an electric potential source (Peltier effect) [1]. These devices are used in a wide range of applications i.e., bio-integrated wearable devices [2], pipe heat energy waste [3], automobile exhaust heat [4,5], heat exchangers [6], combustion engines [7,8], photovoltaic systems [9][10][11], and space exploration [12][13][14].…”

Multiobjective Optimization and Machine Learning Algorithms for Forecasting the 3E Performance of a Concentrated Photovoltaic-Thermoelectric System

“…The field of ML has gained increased interest in recent years, especially with the advent of neural networks that seek to transition the world from artificial narrow intelligence to artificial general intelligence [40]. The merits of ML over the conventional modelling tools used to analyze the performance of energy conversion devices like standalone PVs [41][42][43] and TEMs [44][45][46] have been comprehensively discussed in literature. Issues like modelling complexity, computational time consumption, massive energy requirements, and even deployment ease have been reportedly solved using ML [47][48][49].…”