Solar radiation prediction research is a key area of interest in the realm of solar energy utilization and has garnered significant attention in recent times. In order to realize accurate prediction of solar radiation and make solar radiation prediction better serve photovoltaic (PV) power generation, this study proposes a solar radiation prediction method based on sequence model, which integrates two kinds of neural networks, namely, temporal convolutional network (TCN) and neural basis expansion analysis (N‐BEATS). First, the dataset is preprocessed using Pearson’s correlation coefficient, outlier detection, and normalized to obtain valid and relevant data; second, the features of TCN feature extraction and N‐BEATS flexible extension are integrated to predict the solar radiation; then, the model’s hyperparameters are fine‐tuned using the grid search algorithm to ensure precise predictions; and last, the correctness of the method is verified by comparing the error metrics and the running time. Empirical findings indicate that the TCN‐N‐BEATS sequence model has high prediction accuracy and short time overhead, and it has certain application value in solar radiation prediction, and the model could offer valuable insights for predicting solar radiation.
This article relies on PHREEQC software, the hydrochemical model of the main development thermal reservoir of shallow groundwater recharge is constructed by using the dissolution kinetic rate formula. The 120-day recharge period is used to simulate the change of the hydrochemical composition of the thermal reservoir within one year.Simulation results indicate that allochthonous recharge sources have modified the hydrochemical characteristics of the geothermal reservoir within a specific range. During the recharge process, the hydrochemical field is mainly controlled by water runoff and dispersion. Taking the recharge well as the center, the hydrochemical type on the radial direction gradually changes from Na-HCO3•SO4•Cl to Na-HCO3•Cl•SO4, Na-Cl•HCO3•SO4, Na-Cl•SO4•HCO3, Na-Cl•SO4, Na-Cl•SO4•HCO3, Na-Cl•SO4 gradually changes into Na-Cl type, showing a trend of gradual transition from recharge to geothermal water in hot reservoirs.After the recharge stopped, the hydrochemical type near the recharge well changed from runoff and dispersion control to water-rock reaction and dispersion control.Continuous reinjection for 120 days induced a 0.35% reduction in reservoir porosity and permeability attenuation. Structural deterioration intensified after reinjection cessation, with porosity decline reaching 3.35% by 180 days, indicating irreversible pore structure degradation in the thermal reservoir.
In order to study the adsorption process and adsorption characteristics of shale oil at the macro scale, the isothermal adsorption experiments of illite and kerogen on heptadecane (oil phase) solution were carried out by infrared spectrophotometry and gas chromatography-mass spectrometry. The reaction mechanism of alkane solution concentration and temperature in the adsorption process was investigated. The adsorption characteristics of heptadecane on the surface and pores of illite and kerogen were elucidated by adsorption isotherm model and adsorption thermodynamic model. The results show that: The concentration of alkane solution contributes to the adsorption of illite and kerogen. As the concentration of the solution continues to increase, the adsorption rate gradually slows down. However, the temperature hardly affects the adsorption rate. At 25℃, 50℃ and 60℃, the adsorption process of illite on alkane solution is more consistent with Langmuir model and Freundlich model, respectively. The difference is that Langmuir model is suitable for describing the whole adsorption process of kerogen on alkane solution. 3) The adsorption process of illite and kerogen to heptadecane solution is an endothermic reaction. Heating helps to accelerate the migration rate of alkanes, which is conducive to the adsorption reaction. The research results clarify the adsorption characteristics of shale oil heavy components from the macro level, and fill the research gap in the application of solid-liquid isothermal adsorption physical experiments to the adsorption and occurrence of shale oil.