- 摘 要
-
車 軼1， 尤 杰2， 徐東坡3， 仲偉秋1
（1 大連理工大學(xué)建設(shè)工程學(xué)部，大連116024；2 中興通訊股份有限公司CAF規(guī)劃系統(tǒng)部，深圳518055；3 中國人民解放軍73670部隊(duì)，南京210009）[摘要] 在分析5種具有不同輸入變量的神經(jīng)網(wǎng)絡(luò)模型的基礎(chǔ)上，建立了鋼筋混凝土無腹筋梁抗剪強(qiáng)度的優(yōu)化人工神經(jīng)網(wǎng)絡(luò)模型。該模型具有4個(gè)輸入變量（混凝土抗拉強(qiáng)度、剪跨比、縱筋配筋率和截面有效高度）和一個(gè)輸出變量（抗剪強(qiáng)度）。通過對數(shù)據(jù)的放縮處理，提高了網(wǎng)絡(luò)訓(xùn)練效率。此外還對我國GB50010-2002規(guī)范、ACI318 -08規(guī)范、Eurocode2、日本JSCE規(guī)范和加拿大CSA A23. 3-04規(guī)范的無腹筋梁抗剪計(jì)算公式進(jìn)行了對比研究。研究表明，神經(jīng)網(wǎng)絡(luò)模型具有較高計(jì)算精度，能夠很好地預(yù)測無腹筋梁的抗剪強(qiáng)度。在各國規(guī)范公式中，CSA A23. 3-04．規(guī)范的計(jì)算結(jié)果與試驗(yàn)結(jié)果吻合很好，我國GB50010-2002規(guī)范、ACI318-08規(guī)范和Eurocode2公式計(jì)算結(jié)果的離散性較大。
[關(guān)鍵詞] 人工神經(jīng)網(wǎng)絡(luò)；抗剪強(qiáng)度；混凝土無腹筋梁
中圖分類號：TU375.1 文獻(xiàn)櫟識碼：A 文章編號：1002-848X(2011) S2-0223-06Artificial neural network model for sheer strength of reinforced concrete beams without web reinforcement
Che Yi1, You Jie2, Xu Dongpo3, Zhong Weiqiu1
(1 Faculty of Infrastructure Engineering, Dalian Uruversity of Technology, Dalian 116024, China; 2 ZTE Corporation CAF Planning & System Department, Shenzhen 518055, China; 3 People's Liberation Army 73670 Troops, Nanjing 210009, China)Abstract: An optinuzed artificial neural network( ANN) model for predicting shear strength of reinforced concrete beams without web reinforcement was presented on the basis of study on 5 ANN models with different input variables. The artificial neural network model has four input variables,i.e.concrete tensile strength, shear-to-span ratio, longitudinal reinforcement and effective depth, and an output variable, i.e. shear strength. By scaling the data processing, the efficiency of network training was improved. Predictions of shear design equations in GB50010-2002 code, ACI318-08 code, Eurocode2, JSCE code and CSA A23.3-04 code were also compared with test data. It is found that the proposed artificial neural network model predicts shear strength of beams without web reinforcement with a very good accuracy. Among the code equations, CSA A23. 3-04method fits tests data well, wlule equations in GB50010-2002 code, ACB18-08 code and Eurocode2 present large scatters of results.
Keywords: artificial neural network; shear strength; concrete beams without web reinforcement
- 下載地址
-
