State-of-health (SOH) estimation is crucial for ensuring efficient, reliable and safe operation of power battery in electric vehicle (EV) application. However, due to the complicated physicochemical reactions happened in battery cells, it is extremely difficult to accurately estimate SOH, especially in real-world EV application scenarios. Traditional SOH estimation methods, including both model-based and data-driven ones, are deterministic, which cannot capture the stochastic property of battery aging process aroused from the inherent inconsistency during battery production. In this paper, Bayesian network (BN), which is a probabilistic graphical modeling method for indeterministic process, is used to battery degradation modeling. Its structure is derived from existing knowledge about battery aging mechanism. Two-year operational data and capacity calibration results of 16 electric taxies are collected for model training and validation. Specifically, a systematic data filling procedure is proposed to predict the missing values of variables necessary for SOH estimation. Markov Chain Monte Carlo method is adopted to generate the samples from parameterized BN for SOH estimation. Results show that the estimation result is very close to the calibrated SOH with mean absolute error below 4%. The proposed method is promising to be applied online for SOH estimation in real-world EV application.INDEX TERMS Electric vehicle, battery aging, state-of-health estimation, real-world data.

No abstract

In this study, a spatially stratified proportional fertilizer application device was designed, which was mainly composed of a fertilizer equalization and stirring structure, fertilizer guide plate, and fertilizer plate. This was aimed at solving challenges presented by current fertilizer devices that include a poor layering effect due to untimely return of soil, excess nutrients in the early stages of plant growth, and insufficient quantities in the later stages. The “seed fertilizer + chasing fertilizer” is time-consuming and laborious; seed and fertilizer (without layering) are applied to the soil at once, which tends to cause too much nutrients for plants in the early stage and not enough nutrients in the later stage; and the layered fertilizer machines currently on the market have a poor layering effect due to untimely soil return. Through theoretical analysis and calculation, the structural parameters of the device were determined, and the main influencing factors of the movement law of fertilizer in the device were analyzed. Through simulating soil tank tests, the main factors affecting the effect of fertilizer spatial stratification were designed by quadratic regression orthogonal rotation combination designs. The optimal parameters including the length of the first fertilizer plate was 100 mm, the installation angle of the fertilizer plate was 80°, the spacing of the fertilizer port was 30 mm, and the uniform stirring speed was 650 r/min. The results of the bench test showed that the fertilizer granules could be uniformly stirred at the optimized stirring speed, with average values of 74.56, 76.56, and 105.19 g, which met the agronomic fertilizer application requirements, and the coefficient of variation of fertilizer application amount in each layer was less than 1%. The field test results showed that the stratified proportional fertilizer application device could achieve the stratified proportional application of fertilizer in the soil in ranges of 80.2–95.4, 150.3–180.2, and 230.3–250.4 mm for the upper, middle, and lower layers, respectively, with an error within 10 mm from the designed theoretical application depth. Compared with the conventional fertilizer application method, this fertilizer application method had a more obvious promotion effect on the 100-grain weight and yield of corn.

No abstract

In this paper, an online energy management strategy (EMS) for hybrid electric tracked vehicle (HETV) is developed based on deep deterministic policy gradient (DDPG) with time-varying weighting factor to further improve economic performance of HETV and reduce computational burden. The DDPG is applied to model the EMS problem for the target HETV. Especially, a time-varying weighting factor is introduced here to update old network parameters with experience learned from most recent cycle segment. Afterwards, simulation is conducted to verify the effectiveness and adaptability of the proposed method. Results show that DDPG-based EMS with online updating mechanism can achieve nearly 90% fuel economy performance as that of dynamic programming while computational time is greatly reduced. Finally, hardware-in-loop experiment is carried out to evaluate the real-world performance of the proposed method.