No abstract

Rough set theory is a mathematics tool specifying imperfection and uncertainty. Based on the knowledge theory of the rough set, the numerical values of some features or attributes are not required. Through data reduction, this article analyzes the investment decision of hydraulic engineering and obtains the following by reduction: i. when the construction expense of the hydraulic engineering is low, but the financial income is high, the investment in the construction project can be selected; ii. when the expense of the hydraulic construction project is low and the external influence is common or the financial expense is common, if the external influence is low or the financial income is high, the investment can be delayed; iii. when the construction strategic benefit of the hydraulic engineering is low, the decision rule of no investment can be selected. The novel findings discovered by this article have provided scientific information regarding investment decisions of hydraulic engineering.

The fluctuation of groundwater causes a change in the groundwater environment and then affects the migration and transformation of pollutants. To study the influence of water level fluctuations on nitrogen migration and transformation, physical experiments on the nitrogen migration and transformation process in the groundwater level fluctuation zone were carried out. A numerical model of nitrogen migration in the Vadose zone and the saturated zone was constructed by using the software HydrUS-1D. The correlation coefficient and the root mean square error of the model show that the model fits well. The numerical model is used to predict nitrogen migration and transformation in different water level fluctuation scenarios. The results show that, compared with the fluctuating physical experiment scenario, when the fluctuation range of the water level increases by 5 cm, the fluctuation range of the nitrogen concentration in the coarse sand, medium sand and fine sand media increases by 37.52%, 31.40% and 21.14%, respectively. Additionally, when the fluctuation range of the water level decreases by 5 cm, the fluctuation range of the nitrogen concentration in the coarse sand, medium sand and fine sand media decreases by 36.74%, 14.70% and 9.39%, respectively. The fluctuation of nitrogen concentration varies most significantly with the amplitude of water level fluctuations in coarse sand; the change in water level has the most significant impact on the flux of nitrate nitrogen and has little effect on the change in nitrite nitrogen and ammonium nitrogen, and the difference in fine sand is the most obvious, followed by medium sand, and the difference in coarse sand is not great.

The identification of the critical source of nonpoint source pollution (NPS) plays an important role in formulation of Best Management Practices (BMPs). SWAT (Soil and Water Assessment Tool) was adopted for NPS nitrogen pollution modeling for Qinhuangdao City. The model was calibrated and validated by Sequential Uncertainty Fitting Version 2 algorithm of SWAT-CUP (SWAT Calibration and Uncertainty Programs) software. The model was used to quantify contributions of different nitrogen sources to rivers total nitrogen (TN) load, and address the spatial-temporal distribution of NPS TN to river. The results show that Changli county, Funing county and Lulong county have the most quantity of TN-to-river. The main sources of TN pollution are livestock, nitrogen fertilizing and atmospheric deposition, which account for 49.47%, 26.14% and 15.31% of river TN load, respectively. Rural residential land has the largest TN load (63.418kg/ha). The quantity of nitrogen from soil and atmosphere is mostly affected by precipitation, and that from livestock, nitrogen fertilizing and rural life is affected by both precipitation and sewage time. So to solve the nonpoint source nitrogen pollution issue, the plan development must take the factors of time, region and type into account.

The evaluation of groundwater quality plays an important part in the evaluation of groundwater resources. It analyses the temporal and spatial distributions and utilisation of underground water according to the main components and corresponding water quality standards for underground water. Thereby, it can provide a scientific basis for the development, utilisation, planning, and management of groundwater resources. Set pair analysis (SPA), based on the improved five-element connectivity degree, was used in this research to establish a comprehensive evaluation model of water quality, so as to evaluate the groundwater quality in XuChang, Henan Province, China. Meanwhile, fuzzy evaluation was also used to measure groundwater quality. As demonstrated in the research results, SPA is proven to be convenient and useful with objective and stable results, it therefore is an effective approach with which to evaluate groundwater quality. In addition, the results obtained using SPA matched those from fuzzy comprehensive evaluation; it was concluded, based on the analysis, that the groundwater in XuChang was severely polluted. The groundwater quality at the observation points located in the lower reaches is poorer than that of the upper reaches; hazardous substances permeate underground to pollute shallow groundwater through decomposition and loss due to weathering and rainfall.

Input variable selection plays a key role in data-driven streamflow forecasting models. In this study, we propose a two-stage wrapper model to drive one-month-ahead streamflow forecasting in the context of high-dimensional candidate input variables. Initially, the Boruta algorithm, a feature selection method, was applied to select all the relevant input variables for the streamflow series. Then, a novel binary grey wolf optimizer (BGWO)regularized extreme learning machine (RELM) wrapper was derived. We carried out experiments on two US catchments with 132 candidate input variables, including local meteorological information, global climatic indices, and lags of the streamflow series. Furthermore, the sensitivities of the proposed model in terms of the optimal objective function were compared. The results indicate two important findings. First, the proposed model outperformed commonly used models in terms of four error evaluation criteria. Second, for the proposed model, the root mean square error is a more suitable criterion than the Akaike information criterion (AIC) and the Bayesian information criterion (BIC) for the optimal objective function. These findings are of great reference value for developing ELM models for streamflow forecasting.

Because of the nitrogen pollution problem in groundwater, the migration conversion mechanism of nitrogen in groundwater level fluctuations was analyzed. Technology and methods through indoor experiments and theoretical analysis were used to study coarse sand, medium sand, and fine sand groundwater level fluctuation in the aeration zone and saturated zone under the situation of nitrogen distribution characteristics, revealing groundwater level fluctuation with the nitrogen migration mechanism. The experimental results showed that the variation range of the nitrate-nitrogen (NO3−−N) concentration with the water level is medium sand > fine sand > coarse sand. The ammonium nitrogen (NH4+−N) concentration showed a downward trend after water level fluctuations, and there were more apparent fluctuations in coarse sand and medium sand. The nitrite nitrogen (NO2−−N) in coarse sand and medium sand first increased the water level and then gradually reached a balance. The sampling points below the water level in fine sand showed a downward trend with fluctuation of the water level, and then gradually reached equilibrium. The results provide a scientific basis for the remediation and treatment of soil and groundwater pollution.

In the maintenance system of wind power units, shaft centerline orbit is an important feature to diagnosis the status of the unit. This paper presents the diagnosis of the orbit as follows: acquire characters of orbit by the affine invariant moments, take this as the characteristic parameters of neural networks to construct the identification model, utilize Simulated Annealing (SA) Algorithm to optimize the weights matrix of Hopfield neural network, and then some typical faults were selected as examples to identify. Experiment's results show that SA-Hopfield identification model performed better than the previous methods.