摘要
目的应用高压水射流进行混凝土构件表面处理前确定机械的初始参数,实现对处理深度全面合理的控制.方法用AJP-E25135型高压泵,RG-2002HNDF型、口径为0.25 mm七喷嘴旋转喷枪,对36组不同的初始参数、同批制作的砾石混凝土试块进行了高压水射流表面处理试验,并运用人工神经网络技术,对试验数据进行理论分析.结果建立了压力、靶距、口径、S/A(砂率)与处理深度关系的预测模型并把模型的预测结果与实验结果进行了比较,平均相对误差为0.000 5.结论模型能够满足工程实际需要,可用于混凝土构件表面处理深度的估计与分析,以及特定处理深度条件下初始参数的预测.并可广泛应用于高压水表面处理深度模型的参数优化选择,智能化控制等领域.
A parametric model of high-pressured water-let cutting depth with water pressure, standoff-distance, caliber, S/A was established, using neural network analysis of experimental results. Using AJP- E25135 high-pressure pump, and RG-2002HNDF with 0.25 mm caliber rotating spraying gun carrying out the experiment of high-pressured water-jet in surface preparation. The experiment is to sprinkle water on 36 gravel concretes which are made at the same time. Then the article analyses the data by using the technology of artificial neural network, The article sets up the relationship among pressure, target distance, caliber, S/A and cutting depth, then compares the forecasting result with the experimental result, with the average error 0.000 5. The model meets the practical demand of project. It can be used to evaluate and analyze surface cutting depth of concrete, it can also be used to forecast initial parameter of a given cutting depth. So this model can be widely used in the fields of parametric model of high-pressured water-jet in surface preparation and intellectual control, etc.
出处
《沈阳建筑大学学报（自然科学版）》
EI
CAS
2006年第6期1047-1051,共5页
Journal of Shenyang Jianzhu University：Natural Science
基金
建设部科技攻关项目(05-k4-16)
辽宁省教育厅科技基金(2004D252)
关键词
高压水射流
神经网络
处理深度
靶距
high-pressured water-jet
neural network
cutting depth
target distance
