Abstract
The reconstruction algorithm for the probabilistic inspection of damage (RAPID) is aimed at localizing structural damage via the signal difference coefficient (SDC) between the signals of the present and reference conditions. However, tomography is only capable of presenting the approximate location and not the length and angle of defects. Therefore, a new quantitative evaluation method called the multiple back propagation neural network (Multi-BPNN) is proposed in this work. The Multi-BPNN employs SDC values as input variables and outputs the predicted length and angle, with each output node depending on an individual hidden layer. The cracks of different lengths and angles at the center weld seam of offshore platforms are simulated numerically. The SDC values of the simulations and experiments were normalized for each sample to eliminate external interference in the experiments. Then, the normalized simulation data were employed to train the proposed neural network. The results of the simulations and experimental verification indicated that the Multi-BPNN can effectively predict crack length and angle, and has better stability and generalization capacity than the multi-input to multi-output back propagation neural network.
Highlights
IInn rreecceennttyyeeaarsr,s,effeoffrotsrthsahvaevbeeebneeinncrienacsrienagsliyngfolycufsoecduosendthoensttrhuectsutrraulchtuearaltlhhmeaolnthitomrinogni(tSoHrinMg)hoorfeopfflsahtfoorrempslfaotfrotrhme spuforrpothsee opfusrtpruocsteuoraflsstarufecttyu, raanldsacrfeatcyk, daentdecctiroanckatdtehteeccteionnteratwtehled cseenamters wofepldlatsfeoarmmss oisf opnlaetofofrtmhes hisotosnpeootsf. tIhnefluhoent csepdotbsy
Lamb wave tomography originates from computed tomography in clinical applications, and it has been widely investigated in recent decades
Aimed toward the quantitative evaluation of defects, this study proposes the Multi-BPNN, which takes the signal difference coefficient (SDC) as the input variable and predicts the lengths and angles of crack instances
Summary
AIdrticelentification of Crack Length and Angle at the CIdeenntteirfiWcaetilodnSoefaCmraocfkOLfefsnhgothreaPnldatAfonrgmles aUtstihneg a NCeenutrearl WNeeltdwoSrekamApopf rOoaffcshhore Platforms Using a Neural Network Approach Qingxi Yang 1, Gongbo Li 2, Weilei Mu 2,*, Guijie Liu 2 and Hailiang Sun 3. The signal difference coefficient (SDC) based on the probabilistic reconstruction algorithm has been widely used, mainly because it can detect small defects with a sparse sensor network [6,7]. Hay [8] proposed the well-known reconstruction algorithm for the probabilistic inspection of damage (RAPID), which detects defects by calculating the differences in the Lamb wave signals between intact and faulty conditions. Mu proposed a localisation approach for marine platform damage based on particle swarm optimisation (PSO) This method reduces the positioning time obviously and ensures the high positioning accuracy [19]. In the above formula, μI,σμFσan=d σI∑σF re(pIre−seμnt)the ∑expec(Fted−vaμlu)es and standard deviation(s3)of the inIntatchteaanbdofvaeufltoyrmsigunlaa,lμs, ,rμespaenctdivσelyσ. represent the expected values and standard deviations of taaathhcrceetetsstitnhaawIInsstenaoaatRcRwttwAwrAaaoPeePnnitiIIdgsrgDDdahhf,nu,tatefsfecuoodddelrrtrumyamacloaesssacptriptgrarelientoixcicxacoiiifafilnniisnctcs,ia.otratrerlnaialsnsinnpn.esseeammcartlriiiytlvttytwdeeerldreiy––jce(.rrrcxeeer,ccaeyeesa)iiisvvn=ieegnrrgepplβelaail−piilrritpβRi((cFtF−iaijiic(glg1axpuul,arrypeet)ta2e2tr)t),en, trthwhneehwssephpreaeatrttiiehaaellthddtweiisstottwrrifiboobucufittoioiocofinntohoofeffttehthhleleeipeddlsleeeifpfeae(scr4ceet)t y
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
