Design And Implementation Of Information System For Underground Pipe Network Of Small Grain Storage Based On GIS

The current depot underground pipeline information management means, very short,underground pipeline data loss and deviation of pipe network distribution condition unknown.Once the extend of grain depot, blind construction, underground pipeline damage occurs,caused water, electricity, gas stop, even the interruption of communication, which is notconducive to food security. Focusing on the management problems in underground pipenetwork of traditional grain storage，such as low-leveled standard, the authors introducedGIS-tech,designed the basic framework of the information management system forunderground pipe network of grain storage and researched the critical techniques that canbring the system into exist，thus realizing the scientification, automation and standardizationof the management，improving the efficiency and curtailing the cost.Our country is a major grain producer as well as a major grain consumer. The State andgovernment pays special attention to the food storage. The equipments of multi-function ofaeration, fumigation and handling have been achieved mechanization and electrificationbasically. As an industry engaged in grain purchasing and storage, the operation in grain depothas its timeliness and periodicity. So the study on the regular pattern of electric power aboutgrain depot and electric load prediction has important economic and social significance onmaking the grain storage safely and green. Moreover, the forecasting of the grain warehouse’selectric power guarantees the safety of our state’s grain, which is macro-controlled by thestate itself. We should discover that whether the operation of our grain depot has someabnormalities by comparing the actual electricity consumption to the forecasting, and thenreport this situation to the management. According to the fact that the use of electricity ingrain depot is nonlinear time series, the article introduces the prediction model of electricitybased on Radial Basis Function Neural Network, and conducts the modeling and predictionby adopting the historical electricity consumption of a typical grain depot. As the result ofsimulation shows, the model obtains better forecasting results in grain depot electricity.