給出一種神經(jīng)網(wǎng)絡(luò)方法在鋼橋結(jié)構(gòu)損傷檢測(cè)中的應(yīng)用。著重討論了網(wǎng)絡(luò)設(shè)計(jì)和學(xué)習(xí)算
法問題。網(wǎng)絡(luò)結(jié)構(gòu)模擬桁架橋，訓(xùn)練樣本從多個(gè)損傷區(qū)域產(chǎn)生。仿真表明，本算法只需少量的結(jié)構(gòu)參數(shù)就可得到較滿意的辨識(shí)結(jié)果，且適用于現(xiàn)場(chǎng)測(cè)量數(shù)據(jù)不精確或不能完全已知的情況，具有較好的工程實(shí)用性。
關(guān)鍵詞人工神經(jīng)網(wǎng)絡(luò)損傷識(shí)別 桁架橋
Abstract The paper presents an application of ANN on the damage detection of steel bridge
structures. The issues relating to the design of network and learning algorithm are addressed and network architectures have been developed with reference to trussed bridge structures. The training patterns are generated for multiple damaged zones in a structure. The results of simulation show that the algorithm is suitable for structural identification of bridges where the measured data are expected to be imprecise and often incomplete. The engineering importance of the method is demonstrated from the fact that measured input at only a few locations in the structure is needed in the identification process using the ANN.
Key words ANN; Damage detection; Bridge truss structure