The prediction of remaining useful life (RUL) of lithium–ion batteries is key to the reliability assessment of batteries and affects safe application of batteries. This article introduces a CEEMDAN-RF-MHA-ED-LSTM method. Using CEEMDAN, the battery capacity data were decomposed to obtain intrinsic mode functions (IMFs), and the weight of each IMF was obtained via the random forest (RF) algorithm. The LSTM neural network was used, the encoder–decoder (ED) structure was introduced, the multi-head attention (MHA) mechanism was used to construct a network model, and the particle swarm optimization (PSO) algorithm was used to optimize the model parameters. Each IMF was input into the model, and the obtained forecast results were weighted and reconstructed to obtain the final forecast data. This method was validated on the battery dataset released by NASA. Compared with that of the single LSTM model, the mean absolute error of the proposed method decreases by 74%, 62%, 71%, and 55% on the No. 05, 06, 07, and 18th battery datasets, respectively. The root mean square error decreased by 72%, 59%, 70%, and 54%, and the mean absolute percent error decreased by 75%, 65%, 71%, and 58%, respectively. This method can accurately predict battery RUL.

Mobile machinery means a power-driven vehicle that is specifically designed and constructed to perform work on or off the road. To reduce the nitrogen oxide (NO_x) emissions that come from mobile machinery, a combination of a physical model and closed-loop control is applied to the selective catalytic reduction (SCR) system. Based on the design of the variable cross-section extended exhaust structure, the differential pressure measurement was achieved, and the physical model of the exhaust flow based on the differential pressure was established. Based on the analysis of the heat and mass transfer process of the SCR catalyst, a prediction model for the internal temperature field of the catalyst was established by combining the upstream and downstream exhaust temperature sensors. Using the SCR downstream nitrogen oxides signal and the proportional–integral–derivative (PID) closed-loop control algorithm, segmented PID closed-loop control under the large hysteresis response of the SCR system was realized. The above algorithms were used to form the control code through MATLAB/Simulink and downloaded to the embedded microprocessor. The test results show that the established model can realize the real-time calculation of the exhaust gas flow rate and the internal temperature of the catalyst. Under steady-state conditions, the calculation error of the exhaust flow rate is less than ±3%, and the calculation error of the catalyst temperature is less than ±5%. Under transient conditions, the calculation error of the exhaust flow rate is less than ±9%, and the calculation error of the catalyst temperature is less than ±8%. The nitrogen–oxygen signal-based PID closed-loop algorithm can improve the nitrogen–oxygen conversion efficiency and control accuracy of the model.

This paper aims to investigate the characteristics of selective catalytic reduction(SCR) in a V₂O₅-WO₃/TiO₂ catalyst by studying the key parameter, and obtain the control method of NH₃ injection under sample test bench. Four parameters are defined and adopted to represent the NO-NH₃ reaction characteristics. The effect of NH₃/NO ratio(NSR), catalyst temperature and NH₃ injection period on NO conversion efficiency and NH₃ slip was investigated. The correlation between NH₃ slip and ammonia saturation storage level was studied. The experimental results show that the ammonia saturation storage level has great effects on NO reduction and NH₃ slip. The NO conversion efficiency and NH₃ slip strongly depends on the ammonia saturation storage level. Under such condition, the NO conversion efficiency is best when the ammonia saturation storage level is 68.2%~73%, until the value reach to 75% before the NH₃ slip. Pulse injection can improve the NO conversion efficiency and NH₃ slip. The period of pulse injection has few influence on the mean value of NO at the outlet, however, it affects the peak value of NO and NH₃ slip. Using varied period pulse injection can further improve NO conversion efficiency and restrain NH₃ slip. The outlet NO is able to be reduced by adopting suitable NH₃ pulse injection interval.