A novel RF-CEEMD-LSTM model for predicting water pollution.

Accurate water pollution prediction is an important basis for water environment prevention and control. The uncertainty of input variables and the nonstationary and nonlinear characteristics of water pollution series hinder the accuracy and reliability of water pollution prediction. This study proposed a novel water pollution prediction model (RF-CEEMD-LSTM) to improve the performance of water pollution prediction by combining advantages of the random forest (RF) and Long short-term memory (LSTM) models and Complementary ensemble empirical mode decomposition (CEEMD). The experimental results based on measured data show that the proposed RF-CEEMD-LSTM model can accurately predict water pollution trends, with a mean ab-solute percentage error (MAPE) of less than 8%. The RMSE of the RF-CEEMD-LSTM model is reduced by 62.6%, 39.9%, and 15.5% compared to those of the LSTM, RF-LSTM, and CEEMD-LSTM models, respectively, proving that the proposed method has good advantages in predicting non-linear and nonstationary water pollution sequences. The driving force analysis results showed that TN has the most significant impact on water pollution prediction. The research results could provide references for identifying and explaining water pollution variables and improving water pollution prediction method.

Integrated prediction of water pollution and risk assessment of water system connectivity based on dynamic model average and model selection criteria.

In recent years, with the rapid development of economy and society, river water environmental pollution incidents occur frequently, which seriously threaten the ecological health of the river and the safety of water supply. Water pollution prediction is an important basis for understanding development trends of the aquatic environment, preventing water pollution incidents and improving river water quality. However, due to the large uncertainty of hydrological, meteorological and water environment systems, it is challenging to accurately predict water environment quality using single model. In order to improve the accuracy and stability of water pollution prediction, this study proposed an integrated learning criterion that integrated dynamic model average and model selection (DMA-MS) and used this criterion to construct the integrated learning model for water pollution prediction. Finally, based on the prediction results of the integrated learning model, the connectivity risk of the connectivity project was evaluated. The results demonstrate that the integrated model based on the DMA-MS criterion effectively integrated the characteristics of a single model and could provide more accurate and stable predictions. The mean absolute percentage error (MAPE) of the integrated model was only 11.1%, which was 24.5%-45% lower than that of the single model. In addition, this study indicates that the nearest station was the most important factor affecting the performance of the prediction station, and managers should pay increased attention to the water environment of the control section that is close to their area. The results of the connectivity risk assessment indicate that although the water environment risks were not obvious, the connectivity project may still bring some risks to the crossed water system, especially in the non-flood season.

Simulation and experimental research of electric tractor drive system based on Modelica.

The electric tractor has the advantages of zero-emission, high efficiency, and low noise, which is the direction of future development and transformation of agricultural power machinery. Aim at the problem that the simulation methods commonly used in the development of electric tractor drive system are poorly generalized and cannot meet the simulation needs of complex multi-domain physical systems. This paper proposes a modeling method for an electric tractor drive system, takes the YTO-500 tractor as the research object, designs and calculates the overall scheme and parameters of its drive system, divides the drive system into modules, establishes the energy system, motor system and mechanical parts model based on Modelica, and integrates the simulation model of electric tractor drive system on this basis. The traction performance and transportation working conditions were simulated and tested. With compared and analyzed, in the traction characteristics, the simulation and test results of maximum speed, maximum traction force, and maximum traction power of each gear are consistent; within 400s transportation simulation conditions, the speed range of electric tractor is 13~28km·h-1, which is consistent with the speed range of electric tractor transportation gear. The results show that the simulation and the test results are consistent, which verifies the credibility of the simulation and the correctness of the model built, providing a basis for future research and development of agricultural machinery.

FMI-based co-simulation method and test verification for tractor power-shift transmission.

The tractor power-shift transmission (PST) research and development is a design process that incorporates many disciplines such as mechanical, control, and electronics. Modeling and simulation are typically dependent on various commercial tools for each discipline, making simulation, integration, and verification of system-level models problematic. Aiming at this, we propose a PST multi-domain co-simulation method based on the functional mock-up interface (FMI) standard, analyze the FMI-based simulation mechanism and the PST simulation system logical structure, and established the PST mechanical system model, control system model, tractor engine model, and tractor dynamic model. Based on FMI, these models are integrated into a PST co-simulation model. The starting speed, final drive half shaft speed and torque were simulated and tested. Among them, the simulation and the test starting time are 2.7s and 2.8s respectively, and the two speed curves are consistent; the simulation and the test final drive half shaft torque are approximately equal with a value of 1.5kN·m; the average Theil's inequality coefficients (TIC) value of the simulation and the test final drive half shaft speed is 0.1375, which is less than 0.25. The results show that the simulation and the test results are consistent, the PST co-simulation model is accurate, and the co-simulation method is feasible, which can improve the efficiency of tractor PST system development.