Experimental analysis
Brake thermal efficiency (BTE)
Figure 6 exemplifies the variation of BTE with BP for CR 16:1, CR 17:1 and CR 18:1. The effective burning of test fuels inside the combustion chamber and conversion of useful BP output is named the BTE (Dhinesh et al., 2016). The figure shows that the increase in engine load (L) and CR increases the BTE gradually for all test fuels. However, the neat TCB and its blends follow the decrease in trend for all loading conditions. The TCB blends with lower heating value and higher kinematic viscosity and density promote inferior atomization and vaporization, leading to lesser BTE (Ashok et al. 2018). Among the different TCB blends, the TCB30 blend shows improved BTE for all CR and engine load variations because the lower viscosity and density of the TCB30 mixture makes the fuel combustion as efficient (Baranitharan et al. 2019). At top load condition, the CR 18:1 shows that the maximum BTE for TCB30 blend (33.52%) is highest among other TCB blends and is 1.25% less than that of neat diesel fuel. Generally, the TCB blends are combusted at higher CR 18:1, resulting in increased compression pressure and the temperature to shorten the ignition delay period (ID) and enhance the test fuel volatility promoting higher BTE (Wamankar et al. 2015). But, the CR 16:1 and 17:1 result in lower BTE for all test fuels.
Brake specific fuel consumption (BSFC)
BSFC measures test fuel efficiency and the ratio of total fuel consumption (TFC) to engine BP output (Nanthagopal et al., 2019). An interaction between TCB blend, CR and BP on the BSFC is shown in Fig. 7. It indicates the variation of CR from 16:1 to 18:1 decreases the BSFC for an increase in BP. But, the rise in TCB blend ratio on neat diesel fuel shows more BSFC for full power outputs due to the decreasing trend of green diesel heating value resulted in higher BSFC (Venugopal et al. 2018). Furthermore, the CR varied from 16:1 to 18:1 decreases the ignition delay (ID) period for all operated test fuels makes the highest decrement in BSFC (Hosamani et al. 2018). For higher CR 18:1 shows that the minimum BSFC was observed as 0.264 kg/kWh for diesel, 0.27 kg/kWh for TCB30, 0.287 kg/kWh for TCB50, 0.311 kg/kWh for TCB70 and 0.326 kg/kWh for TCB100 operated at peak power outputs. The high mean effective pressure developed inside the combustion chamber promotes the combustion as complete for all test fuels resulting in the efficient power output at minimum BSFC (Lahane and Subramanian 2014). But these BSFC values are maximum at lower CR of 16:1 and 17:1. Because inadequate mixing and atomization of test blends caused incomplete combustion, leading to higher BSFC (Vellaiyan 2020).
Exhaust gas temperature (EGT)
Figure 8 shows the variation of EGT with brake power operated at CR 16:1, CR 17:1 and CR 18:1. It was observed that the increase in BP shows an increasing trend of EGT for all the test fuels. Similarly, the higher CR 18:1 generates more EGT since the engine operating temperature is high (Shivakumar et al., 2011). EGT for green diesel is more when correlated with neat diesel fuel, and it increases as the proportion of TCB is increased. It may be credited due to higher physical ID period, increased viscosity and poor volatility of TCB blend (Senthil Kumar et al. 2019). At top load engine operation, the value of EGT for TCB100 is 382.48 oC, 394.23 oC and 411.23 oC operated at the CR 16:1, CR 17:1 and CR 18:1, respectively. This may occur because more oxygen content (O2) in the TCB100 promotes higher EGT (Dhinesh et al., 2016). The engine operated at higher CR 18:1 compress the air is entered into the cylinder increases the temperature. It helps to better fuel mixing, and atomization leads to complete combustion that lowers the EGT for neat diesel fuel (Wamankar et al., 2015).
Hydrocarbon emission (HC)
Figure 9 portrays the variation of HC emission with the influence of different compression ratios (CR 16:1, CR 17:1 and CR 18:1) operated at low load and full load conditions. Generally, the unburned HC emission is formed during rich mixture combustion, penetration of fuel spray across the combustion chamber wall, and leakages in the fuel injector system (Annamalai et al., 2016). At low load engine operation, more HC formation was observed for all test fuels operated at different compression ratios of CR 16:1, CR 17:1 and CR 18:1. More accumulation of fuel molecules in the combustion chamber reduces engine combustive products reaction temperature is a credible reason for higher HC emission (Prasada Rao et al. 2017). An increase in BP and CR makes a significant reduction in HC formation. Likely, the rise in green diesel percentage on neat diesel fuel reduces the formation of unburned HC emissions. The reason is higher cetane number, availability of oxygen molecules in the green diesel enhances the air-fuel mixture rate and vaporization (Balasubramanian et al. 2018). At peak power outputs, HC formation is decreased by 39.13% for diesel, 43.07% for TCB30, 46.04% for TCB50, 42.59% for TCB70 and 37.5% for TCB100 when compared to low load condition operated at the CR 18:1. Higher CR 18:1 increases the cylinder pressure and temperature inside the combustion chamber, shorter the ID period, leading to better fuel combustion resulted in lower HC formation (Dhingra et al. 2014).
Carbon monoxide emission (CO)
The variation of CO emission with CR 16:1, CR 17:1 and CR 18:1 running at low load and full load conditions are plotted in Fig. 10. It shows that more CO formation in the neat diesel fuel operation equated with green diesel blends. The deficiency of O2 content in the neat diesel fuel forms higher CO operated at low and peak power outputs (Musthafa et al., 2018). However, the presence of oxygen content in the green diesel promotes complete oxidation of carbon monoxide (CO) into carbon-di-oxide (CO2) reduces the formation of CO emission at different modes of CR operations (Dhinesh et al. 2016). At low-load conditions, all the test fuels (Diesel, TCB30, TCB50, TCB70 and TCB100) have resulted in higher CO emission operated at the compression ratios of 16:1, 17:1 and 18:1. The important reasons are lower operating temperature, and the A/F mixture in the combustion chamber exhibited higher CO formation (Hawi et al., 2019). Notably, the CO emissions are diminished by 43.06% for diesel fuel, 44.78% for TCB30, 48.39% for TCB50, 51.67% for TCB70 and 0.011% for TCB100 operated at CR 18:1 when correlated with top load state. But, the CO levels are higher for other compression ratios of 16:1 and 17:1. It is mainly due to the increase in CR increases the in-cylinder air temperature reduces the ignition delay period (ID) causes complete burning of the test fuels (Shameer and Ramesh 2017).
Oxides of nitrogen emission (NOx)
The NOx formation in the CI engines depends on the air-fuel mixture rate, in-cylinder combustion temperature, and O2 content in the intake air and test fuel (Manimaran et al., 2019). Figure 11 shows the variation of NOx emission with the influence of different input variables (BP, CR and TCB blend) under low load and high load operations. The graph observed that the increase in compression ratio increases the NOx formation for all test fuels. The engine at high load operation produces higher in-cylinder temperature lead to NOx formation. Similarly, an increase in the green diesel ratio on neat diesel increases the formation of NOx. This is due to the proportional increment of O2 molecules, density of the green diesel leading to peak in-cylinder gas temperature, and most negligible radiative heat losses develops higher NOx (Rashed et al.2016). The test engine operated at the CR 18:1 generates a higher temperature inside the combustion chamber during the compression stroke results in more NOx (Koten 2018). However, the engine operated at lower CR 16:1 produce lesser NOx emission due to a reduction in flame formation temperature, and localized in-cylinder gas temperature leads to NOx as small during low load engine operations (Sathiyamoorthi and Sankaranarayanan 2016). Among other TCB blends, the TCB30 shows lesser NOx emission, and it was reduced by 7.82% than TCB30, 10.89% than TCB50 and 14.62% than TCB100, respectively.
Smoke opacity emission (%)
In general, the smoke opacity was formed due to the disproportion of the A/F ratio and unavailability of O2 in the fuel-rich pockets (Ramesh et al., 2019). Figure 12 illustrated the variation of smoke opacity for different compression ratios and fuel blends, namely TCB30, TCB50, TCB70 and TCB100 at low load and full load conditions. An increase in brake power gradually increases the test fuel admission into the engine cylinder to maintain the engine speed at the constant value of 1500 rpm, which leads to a higher smoke level (Anand et al., 2010). But, the increase in green diesel percentage on neat diesel resulted in minimal smoke opacity except for TCB100. The absence of aromatic compounds and lower carbon (C) to hydrogen (H) ratio in the green diesel blends leads to better fuel atomization, and efficient combustion lowers smoke opacity formation (Ashok et al. 2018). The higher viscosity and the larger fuel droplet size of TCB100 promote higher smoke emission (Ganesan et al., 2020). At peak load condition, the CR 18:1 resulted in lower smoke levels, and it was diminished by 14.43% for TCB30, 24.87% for TCB50, 36.04% for TCB70 and 12.52% for TCB100 when compared to neat diesel. The high combustion pressure and temperature generated at the CR 18:1 operation improve combustion efficiency resulting in lesser smoke. But, the lower CR of 16:1 and 17:1 results in more smoke emission than CR 18:1. It may be credited to longer ID makes slow-burning, and lower in-cylinder gas temperature causes fuel combustion as incomplete is the reason for more smoke formation (Gnanamoorthi and Devaradjane 2015).
Carbon dioxide emission (CO2)
Figure 13 depicts the variation of CO2 emission against different CR and TCB blend operated at the minimum and maximum loading conditions. The graph observed that the varying CR from 16:1 to 18:1 gradually increases the CO2 emission levels for all test fuels. This is due to the complete combustion of test fuels ultimately converts the formation of CO into CO2 reduces CO2 emission (Ramalingam et al. 2020). Correspondingly, the percentage increase in green diesel on diesel fuel causes more CO2 emission due to increasing the percentage of O2 content in the TCB blend oxidize the shape of CO into CO2 produces a higher percentage of CO2 emission in the green diesel combustive products (Parida et al. 2019). At maximum power output, the value of CO2 emission is lower for diesel fuel (7.81%), and the remaining test blends of TCB30 (9.21%), TCB50 (9.52%), TCB70 (10.27%), and TCB100 (10.42%) shows higher CO2 emissions powered at CR 18:1. But, the CR 16:1 and 17:1 shows lower CO2 formation. Notably, the CO2 emissions are increased by 17.93%, 21.89%, 31.25% and 33.41% for TCB30, TCB50, TCB70, and TCB100, respectively, when compared to neat diesel fuel. The main reason is the development of combustion temperature around 1500 oC; the more availability of O2 content in the green diesel improves the combustion rate, leading to more CO2 formation functioning at the higher CR 18:1 (Pradhan et al. 2017).
Artificial Neural Networks (ANN)
ANN has an intersect collection of neurons to develop the critical regression model to resolve the forecasting and decision-making problems (Venugopal et al., 2018). The prediction of engine process parameters using the ANN technique is unique compared to simulation software and mathematical models. However, selecting an appropriate network is vital for ANN model precision (Uslu and Celik 2020). ANN model consists of three layers: the input layer, hidden layer, and output layer. The input layer is linked with the output layer through the hidden layer. The bias and weights are updated in the hidden layer with the calculation of error between the experimental and predicted values until the error as small.
For all input parameters, a trained ANN model was simulated to achieve the corresponding outputs. The regression correlation coefficient (R2), MAPE, and RMSE were calculated using the ANN model's targets and outputs in the following Eqs. (2) - (4)
(2)
(3)
(4)
Where, x - actual value, y - predicted value, n - number of marks in the data group
The proposed ANN model workflow chart is displayed in Fig. 14. In part 1, the input factors are biodiesel blend (B), engine load (L) and compression ratio (CR) was introduced for network creation. Randomly 53 data (70%) chosen from the experimental results were used for the training set, 11 data (15%) selected for the validation set and the remaining 11 data (15%) was used in the testing set. Secondly, it has been trained with this input information to obtain the best ANN model to evaluate the training, validation and test cycles. The last part is applied for ANN accuracy control and collection of data.
ANN modeling
The neural network tool in MATLAB has been selected for this research work to predict diesel engine performance and emission characteristics. The ANN model is developed based on the FFBP (feed-forward back propagation algorithm), the most commonly used algorithm. It is used for the training of experimental test data. Levenberg-Marquardt (TRAINLM) has applied to predict the MSE (mean square error) directed neural network loss function. The Hyperbolic tangent sigmoid (TANSIG) transfer function produces better results, making the ANN model more significant. Figure 15 shows that the selected topology for the prediction of engine output variables is 3-12-8. Initially, the 3 neurons of biodiesel blend (B), engine load (L) and compression ratio (CR) located in the input layer, and the output layer consist of 8 neurons are performance (BTE, BSFC and EGT) and emission (HC, CO, CO2, NOx and smoke) parameters. The generation of unique code optimizes the hidden layer and is observed by the variation of RMSE with respect to the number of neurons, as shown in Fig. 16. It indicates the maximum error trained with a minimum number of neurons known as the underfitting zone. As the number of neurons is maximum, the training error decreases. But, the gap between training, validation and testing error increases, represented as the overfitting zone. From the above observations, the error and gap between all data sets are minimum at the optimal neuron of 12. It has been selected as the optimal neuron in the hidden layer of the neural network.
Based on input and output variables, the multiple regression model was generated using ANN. Figure 17 indicates the overall regression fit for training, validation and test sets. It shows that the correlation coefficient (R) values of training, validation, test, and overall are 0.99798, 0.99619, 0.99092 and 0.99673, respectively. These obtained R2 values are about 1, which indicates the high precision of the ANN model output responses.
Sensitivity analysis of ANN model
Sensitivity analysis evaluates the effect of specific input factors to grade their importance equivalent to the output responses. According to the importance of input factors, efficient and inefficient variables are evaluated. The inefficient variables are eliminated from the ANN model. It will simplify the numerical model and reducing training time (Ibrahim et al. 2019). The backward stepwise was found from the literature reviews as the simple method for ANN model sensitivity analysis. The engine load, biodiesel blend, and compression ratio were used to conduct the ANN model's sensitivity analysis. From Table 5, the ANN model 1 trained with all the input factors gives R2 and RMSE values of 0.99445 and 7.5126. Removal of the compression ratio from the training data set moderately increases the RSME value. It shows that the effect of compression ratio is inefficient for the numerical model. Next, the biodiesel blend was omitted, and their R2 and RMSE data are 0.97712 and 21.0544, which implies the lesser contribution in the ANN model. Finally, model 4 resulted in the R2 of 0.44173 and RMSE of 140.7514, presents the importance of engine load. The R2 value is drastically decreased, with error increases (RMSE). Therefore, it was concluded that the engine load is the most efficient variable on the ANN model.
Table 5
Sensitivity analysis of the ANN model
ANN model
|
Engine load
|
Biodiesel blend
|
Compression ratio
|
R2
|
RMSE
|
1
|
Yes
|
Yes
|
Yes
|
0.99445
|
7.5126
|
2
|
Yes
|
Yes
|
No
|
0.99378
|
8.7584
|
3
|
Yes
|
No
|
Yes
|
0.97712
|
21.0544
|
4
|
No
|
Yes
|
Yes
|
0.44173
|
140.7514
|
Performance of ANN model
Figure 18. indicates the evaluation of experimental values with ANN predicted values for engine performance parameters. Notably, the R2 values of BTE, BSFC and EGT are 0.9988, 0.9996 and 0.9983, respectively. Similarly, the RSME values are minimum for all performance outputs. The correlation coefficient (R2) values are closer to 1 indicates the high accuracy of the proposed ANN model. It shows that using the proposed ANN model is ample to predict the engine performance parameters of BTE, BSFC and EGT.
The engine emission parameters are evaluated by interpretation of experimental and predicted values are shown in Fig. 19. The correlation coefficient (R2) values were found as 0.9968, 0.9994, 0.9996, 0.9636 and 0.9994 concerning emission variables of HC, CO, NOx, smoke opacity and CO2. The error and correlation output responses are obtained from the proposed ANN model is minimum. It indicates that the proposed ANN model is enough to forecast exhaust emissions.