Papers by Keyword: Forecast Model

Abstract: Parking is difficult in today's social problems faced by big cities. To solve this problem, a new parking facility planning and design was required and the parking demand forecast is a very important step in this process. The paper first discusses the necessity of parking demand forecast and the development process of parking demand forecast model, then a few parking demand forecasting model were compared and analyzed, final the motor vehicle OD method was selected to forecast parking demand according to the characteristics of the parking demand forecast and urban transport planning simultaneously. The results show that the precision of prediction results is acceptable.

Abstract: In order to meet the requirements of the market economy, the power company needs to make power market analysis and forecast, it is the basic work of guarantee of the investment returns and improves operational efficiency, and it also is the basic work of network operations, planning, marketing, and the financial budget for the foundation. The accuracy of electricity demand forecast will not only affect the safe and reliable of power network, but also to network operators on the production and operational decision making and operational efficiency. To meet the power network’s commercial operation, and for the requirements of network’s modernization and scientific management; In order to predict the market’s electricity demand accurately, reduce the load forecast engineers’ frequently and complicated data processing work, also to ensure that the derive of historical data and ensure information sharing. Development of the electricity market-oriented environment for the network's power market analysis and forecast system is very necessary.

Abstract: Back Propagation network, Widely used in automatic control, image recognition, hydrological forecasting and water quality evaluation, etc., as one of the Artificial Neural Networks, has stronger property of mapping, classification, functional fitting. This article takes the water flow of Lanzhou section of Yellow river as example by use of BP model to predict the water flow. It is well proved that BP network model can reach the purposes of early warning and forecasting.

Abstract: This paper introduces the experimental results of long-term carbonization of concrete with machine-made sand (MSC), which is part of the studies on durability of this new concrete. Three strength grades of concrete C30, C40 and C50, and the contents of stone powder in machine-made sand of 5%, 9% and 13% in mass were considered in the mix proportion of concrete with machine-made sand. The ordinary concrete with natural river sand in the same strength grade was tested at the same time for comparison. The test was conducted for 360 days, and the results showed that the carbonization of MSC was similar with that of ordinary concrete, the carbonized depth increased with the increasing carbonization time. The carbonization was rapid at initial before 28 days, and became slowly with the time going by. The content of stone powder in machine-made sand affected the carbonization of MSC in some extent, which should be limited in a reasonable range. Based on the test data, the formulas for forecasting the carbonized depth of MSC are suggested.

Abstract: As part of the studies on the durability of concrete with machine-made sand, this paper introduces the test results and the forecast model of time-dependent chloride penetration of this kind of concrete. Three strength grades of concrete C30, C40 and C50, and the contents of stone powder in machine-made sand of 5%, 9% and 13% in mass were considered in the mix proportion of concrete with machine-made sand. The ordinary concrete with natural river sand in the same strength grade was tested at the same time for comparison. The test was conducted for 360 days, the results showed that the effect of the content of stone powder on the chloride penetration of concrete was obvious at early curing time of 7 days, and tended to be lower with the increase of curing time. When the curing time was longer than 90 days, this effect could be neglected, and the resistance to chloride penetration of concrete with machine-made sand was almost equal to or larger than that of ordinary concrete. The decrement of chloride diffusion coefficient varied from sharp to gentle with the curing time, the resistance of concrete to chloride penetration increased with the increase of concrete strength. Meanwhile, to facilitate the calculation in practice, the forecast model of chloride diffusion coefficient of concrete is proposed.

Abstract: After analyzing and reviewing the short-term forecasting methods research of pork price at home and abroad, a chaotic neural network model based on genetic algorithm (CNN-GA) was put forward according to the nonlinear characteristics of pork price,which established on the base of the chaotic theory and the neural network technology. Chosen the daily retail price data of the pork (streaky pork) from January 1, 2008 to June 11, 2012,we designed the basic structure of CNN-GA, and thentrainedit in order to attain the trained CNN-GA model. Finally, the trained CNN-GA model was used to predict the 20 days’ (from June 12, 2012 to July 1, 2012) retail price of pork (streaky pork) and then compared the predicted price with the real price to test the model’s forecast accuracy and application ability.The result shows that the model has high prediction precision, good fitting effect and hasan important reference and practical significance for the short-term price forecasting of the pork market.

Abstract: This paper reviews the state-of-art of researches on the carbonization of concrete. The influencing factors are concluded as two aspects as the internal concrete and the external environment and service conditions. The main internal factors include the cement and admixtures, the water to cement ratio, the concrete strength and others such as the type, grading and size of aggregate and the additives. The main external factors include the concentration and pressure of carbon dioxide, the temperature and relative humidity of environment, the curing and service conditions and the loading states. The typical forecast models of carbonized depth of concrete based on the fundamental reaction engineering principles, the lab experimental results and the practical engineering investigations are summarized for the reference of further study.

Abstract: The time limit for a project forecast question is the project progress risk main content, the fit and unfit quality of Forecasts technical and the result quality directly Influence the entire project construction progress. This article applies the technology of The function approaches which based on the impact of the project on the comprehensive analysis of various factors，has constructed the progress risk BP network forecast model, and according to the example computation, has carried on the confirmation to this model.

Abstract: It is clear that urban river eco-security model may provide an alternative choice of urban river Engineering Construction decision and correspond to the direction of sustainable city. Our goal is to provide a framework to conceptualize the impacts of various urban river eco-security development strategies over a time scale of several decades, while taking into account interactions and feedback loops between various criteria to the fullest extent allowed by available data and theory. Flooding is serious natural disaster, but there is a lack of integrated strategy on urban river ecosystem management in Taiwan. This study aims to construct a integrated index formwork by function and goal of eco-security of urban river. The other purposes of this research are apply the System Dynamics to understand the trend on forecast modeling. Formulate a system dynamics model to simulate the trend of Tamsui River Eco-Security. This research , construction of five subsystems, “discharge security” ,” purification security”, “water security”, “habitat security” and “biosecurity”. The error value between simulation and real situation are few to prove the model is effective .The study results indicate that the eco-security for Danshui River is going to biomass raising, drainage raising, habitat increasing and pollution reducing. The cogitation has integrated by system dynamic model which coming together to form precaution, water use, conservation and ecological restoration to keep the sustainability of urban nature resources by the research.

Abstract: It is very important to forecast the gas well productivity of gas reservoir accurately. On the basis of analyzing the parameter performance of support vector machine (SVM) for regression estimation, the paper proposes gas well productivity prediction model based on particle swarm optimization (PSO) and SVM. The parameter of SVM was optimized by PSO. This method took advantage of the minimum structure risk of SVM and the quickly globally optimizing ability of PSO. Compared with BP neural network model, the proposed GA-SVM model for gas well productivity in practical engineering has higher accuracy and speed, and the maximum error is 2.8% . Thus, it provided a new approach to predict the gas well productivity.