Search

The present study aims to utilize waste engine exhaust heat to produce hydrogen and utilize the same in the single cylinder CI engine as a closed system. A thermoelectric generator was used to convert the waste exhaust heat to hydrogen gas through PEM type fuel cell. The generator was placed in the engine exhaust and connected to the fuel cell and the output of the fuel cell was connected to the inlet manifold through a flow meter and safety devices. All the tests were conducted in a single cylinder CI engine with diesel as the base fuel and the produced hydrogen as the inducted fuel. Experiments were conducted at different load conditions with a constant speed of 1500 rpm. It is observed that the heat wasted from the exhaust increases with increase in load which improves the thermoelectric generator conversion efficiency and in turn increases the hydrogen flow rate. At maximum load, 351 ml/min of hydrogen was produced and sent to the inlet manifold of the engine. The conversion efficiency of the generator varies from 13.8% at low load to 51% at full engine load. The experimental results showed that with hydrogen induction brake thermal efficiency (BTE) was improved. At full load, BTE with hydrogen induction improves by 10% in comparison to only diesel engine operation. With hydrogen induction HC, CO and smoke emissions at full load reduced by 13.46, 31.57, and 24.7%, respectively, as compared to diesel. The decrease in emissions is attributed to decrease in diesel consumption as hydrogen replaces the diesel. However, there is a slight penalty in NOx emissions and it increases by 20% with hydrogen induction due to increase in in-cylinder temperature. • Waste engine exhaust heat was recovered in the form of electricity using TEG. • Produced electricity was used to produce hydrogen using fuel cell. • Hydrogen was inducted in the intake air along with diesel as the direct injected fuel. • Hydrogen production rate increased with load. [ABSTRACT FROM AUTHOR]

• Signal denoising in signal processing is a fundamental study which is of most essential. • The dynamic soft sensor model based on Elman neural network falls under this category. • The Ensemble Empirical Mode Decomposition (EEMD) model decomposes the actual input dataset. • The prediction results are combined thereby obtaining the final result. In industries, several key quality variables used in complex processes are immeasurable online and are not reliable because of the factors like complex environmental criteria, limited techniques for testing and high cost. Soft sensor technology has become known to solve these complexities. In industrial process, the key factors like redundancy, noise and dynamic features of data affect the accuracy of soft sensors. Thus, a predictive control approach is required which has to integrate improved methods used to detect the control signal that uses direction of structural motion. This paper proposes an innovative Ensemble Empirical Mode Decomposition Based Auto Encoder Deep Neural Network (EEMD-AEDNN) which combines the advantages of Ensemble Empirical Mode Decomposition and neural network bringing problems of mode-mixing from EEMD and false modes from neural network under control. Moreover, dynamic characteristics are captured which are distributed over time improving the modelling effects. The advantage is that noise and redundancy from actual data are removed and information loss is minimized. Furthermore, data are sequential introducing historical data for dynamic modelling. This goal is consistently achieved and thus the proposed model outperforms few standard approaches which are considered like Ensemble Empirical Mode Decomposition based Long Short-Term Memory neural network (EEMD-LSTM), Wavelet Neural Network with Random Time (WNNRT) and Ensemble Empirical Mode Decomposition-General Regression Neural Network (EEMD-GRNN). It is found that the proposed EEMD-AEDNN method achieves 94.22% of accuracy, 84.68% of RMSE, 75.34% of RAE and 54.42% of MAE in 86.5 ms. [ABSTRACT FROM AUTHOR]