No abstract

Abstract-Sales forecasting is one of the most crucial issues addressed in business. Control and evaluation of future sales still seem concerned both researchers and policy makers and managers of companies. this research propose an intelligent hybrid sales forecasting system Delphi-FCBPN sales forecast based on Delphi Method, fuzzy clustering and Back-propagation (BP) Neural Networks with adaptive learning rate. The proposed model is constructed to integrate expert judgments, using Delphi method, in enhancing the model of FCBPN. Winter's Exponential Smoothing method will be utilized to take the trend effect into consideration. The data for this search come from an industrial company that manufactures packaging. Analyze of results show that the proposed model outperforms other three different forecasting models in MAPE and RMSE measures.

No abstract

The implementation of the wind turbine is the major issues in the wind engineering sector. However, the presence of the wind turbines in the lower part of the atmospheric boundary layer (ABL) requires adequate study for the simulation of turbulent airflow the wind farm situated on hilly terrain. In this work, the inflow profiles with the wall treatment are examined and investigated to ascertain an equilibrium profile through the whole of the flat terrain. The purpose of this work is to present a general scalable wall-function roughness modification under a modify limitation for the CFD modeling of ABL flows by using the standard k-ε turbulence model in case of a neutral condition. In the otherwise, the application of the homogeneous conditions of the boundary layer in the presence of the complex topographic and the sensitivity studies of the inflow conditions for predicting the air velocity over hilly terrain are carried out. The methodology is implemented in the Finite Element (FE) commercial code COMSOL 5.4 by means of the User-Defined Equation (UDE). The numerical results are compared with CRIACIV boundary layer wind tunnel experimental data. We indicated that the approach used can be led to achieve a homogeneity of neutral ABL, which yields to give an accurate estimation for velocity and turbulence distribution on the presence of the hill. The obtained results are in good correlation with published experimental data in the case of the inhomogeneous surface, and it is observed that use of the scalable wall-function with roughness to solve the near wall region improves the forecast of flow.