Fischer-Tropsch diesel fuel synthesized from coal (CFT) is an alternative fuel that gives excellent emission performance in compression ignition (CI) engines. In order to study the vibration characteristics, which are important for determining the applicability of the fuel, CFT-diesel blends were tested on a CI engine to acquire vibration signals from the engine head and block. Based on the FFT and continuous wavelet transformation (CWT) analysis, the influence of CFT on the vibration was studied. The results showed that the root mean square (RMS) values of the vibration signal decrease as the proportion of CFT in the blends increases. The CWT results indicated that the vibration energy areas motivated by the pressure shock of transient combustion were weak with increasing CFT proportion for the different frequency bands. The blend of 90% pure petro-diesel and 10% CFT registered the largest RMS value for piston side thrust response, and the RMS of high-frequency pressure oscillation response is greater than that of the main response of combustion, for FT30. Therefore, CFT has the potential to reduce the combustion vibration of the engine at all frequency bands, and there is a possibility that the proportion of blended fuel can be modified to satisfy the vibration characteristics requirements in different frequency bands.

Cycle-to-cycle variations during the combustion phase should be comprehensively investigated because these variations are among the most serious causes of higher emissions and lower efficiency. The main objective of this study was to evaluate the relationship between cyclic variations and combustion parameters. The combustion and cyclic variation characteristics were investigated using a diesel engine operating on Fischer–Tropsch (F–T) fuel synthesized from coal. Experiments were conducted under full load conditions at three engine speeds of 1200, 2000, and 2800 rpm. The results revealed that cyclic variations of F–T diesel were lower than those of 0# diesel, acquired the minimum value at the speed of 2000 rpm, and reached the maximum at the speed of 2800 rpm. The mean fluctuation intensity of F–T diesel was 0.185, 0.189, and 0.205 at speeds of 1200, 2000, and 2800 rpm, respectively, smaller than that of 0# diesel under the corresponding conditions. The relationships between cyclic variations and combustion parameters were analyzed by correlation methods. Maximum in-cylinder pressure (P_max) increased linearly with increased ignition delay, while it decreased linearly with increased combustion duration. The Pearson’s correlations between P_max and ignition delay were 0.75, 0.78, and 0.73; however, the corresponding values between P_max and combustion duration were 0.61, 067, and 0.65 when fueled with F–T diesel at speeds of 1200, 2000, and 2800 rpm, respectively. Moreover, the Pearson’s correlations of 0# diesel were higher than those of F–T diesel at the same operating loads. Compared with combustion duration, the ignition delay had more important effects on cyclic variations with a higher Pearson’s correlation. Furthermore, the ignition delay significantly influenced cyclic variation under a high speed load, while the combustion duration had a marked effect under low speed conditions. Overall, the results revealed the importance of combustion parameters on cyclic variation, which has great significance for controlled cyclic variation in diesel engines.

In this paper, an electronically controlled diesel engine fueled with Fischer-Tropsch fuel was selected to optimize soot and NO_x emissions. First, the effects of injection parameters on exhaust performance and combustion properties were studied on an engine test bench and then a prediction model based on a support vector machine (SVM) was established according to the test results. On this basis, a decision analysis of soot and NO_x solutions assigned with different weights was performed based on the TOPSIS analysis method. It turned out that the "trade-off" relation between soot and NO_x emission was improved effectively. As a matter of fact, the Pareto front selected by this method showed a significant decline compared with the original operating points, in which soot declined by 3.7-7.1% and NO_x declined by 1.2-2.6%. Finally, the experiments were used to confirm the validity of the results, which indicated that the Pareto front corresponded well with the test value. The maximum relative error between the soot Pareto front and the measured value is 8% while it is 5% for NO_x emission, and the R² values of soot and NO_x under various conditions are more than 0.9. This instance proved that research on diesel engine emission optimization based on the SVM and NSGA-II is feasible and valid.

Alternative fuels have attracted wide attention owing to the increasing energy consumption and environmental pollution problems, which are caused by the extensive application of diesel engines for various occasions. The Fischer–Tropsch (F–T) diesel synthesized from coal is considered as one kind of ideal alternative fuel for diesel engines; however, its combustion and exhaust emission characteristics are different from those of national diesel owing to its special fuel properties. Therefore, the combustion and emission characteristics of F–T diesel and 0# diesel, which meet the China stage VI were compared in a common rail direct injection (CRDI) diesel engine. Moreover, energy-saving and pollution-reduction potential were analyzed in one CRDI diesel engine fueled with F–T diesel. The results showed that F–T diesel had an earlier ignition point, shorter ignition delay, lower cylinder pressure, and heat release rate compared with those of 0# diesel at the same operating conditions. Meanwhile, the amplitude, oscillation level, and energy of cylinder pressure were decreased to some extent, with the maximum drops of 0.98 bar, 16.4 dB, and 1.01 × 10¹² Pa, respectively. Additionally, under external characteristic conditions, maximum break thermal efficiency (BTE) and break-specific fuel consumption (BSFC) of F–T diesel were reduced by 1.1 and 2.1% on average compared with those of 0# diesel. In addition, CO, HC, NOx, and SOOT emissions of F–T diesel were found to be lower than those of 0# diesel, which were decreased by an average of 8, 3.7, 2.1, and 1.3%, respectively.

Artificial Neural Network (ANN) and Support Vector Machine (SVM) have been widely used to solve non-linear problems. In the current study, based on 112 groups of experimental data, ANN and SVM models were established and compared to improve the trade-off relationship between SOOT and NOx emissions of a Common Rail Diesel Injection (CRDI) engine fueled with Fischer-Tropsch (F-T) diesel under different operating conditions and injection parameters. The model parameters for the different predictive targets were selected by evaluating the mean square error (MSE) and determination coefficient. Compared to the number of network iterations, the number of implied nodes had a greater effect on the MSE of the ANN model. Compared to the penalty parameter, the width coefficient had a weaker impact on the SVM performance. A comparative analysis showed that the SVM had better predictive accuracy and generalization ability than the ANN, with a maximum error not exceeding five percent and a determination coefficient of over 0.9. Subsequently, the optimal SVM model was combined with the NSGA-II algorithm to determine the optimal injection parameters for the CRDI engine, resulting in solutions to simultaneously decrease the SOOT and NOx emissions. The optimized injection parameters resulted in a 3.7–7.1% reduction in SOOT emission and a 1.2–2.6% reduction in NOx emissions compared to the original engine operating conditions. Based on limited experimental samples, SVM is inferred to be a useful tool for predicting the exhaust emissions of engines fueled with F-T diesel and can provide support for optimizing injection parameters.