<tr> <td> <pre><br />Pressure vessel of acoustic emission signals of artificial neural network pattern recognition research<br /></Pre> </td> </tr><br /><tr> <td> <pre><br />E13CarfiveauGaryWtAustinRussel1. Nondestructiveevaluationofcorrosionthroughinsu] atiorIEA]. RevieWofProgressinQu ~ tntitativeNondestructiveEwduation (NewYork: 1996.174I a 1746. [2] WalterMatulewic2, etaLThedetectionofcormsionunderimuladonbyreal-timeradiography [A]. ASNT'sInternationalChemicalandPetroleumIndus-tryImpecfionTechnology ? TopicConference [c],abercrombie madrid. NewYork :1995.71 - 74. [83GuptaNandK, PhDBruce, GIsaacson. Real-timeinservice # peinspectionthroughinsulatlon [A] ASNTSpringConferenceand5AnnualResearchSymposiumq. I ~ nbul :1996.15-18. E43HeFeugqLProgressreportondevelopmentofCOITOsiona nddepositradiographictesting [A]. 2RCMofCRKc]. ? Hsc1999. (Continued from page 146) 3 Conclusions (1) pressure vessel with a real live acoustic emission signals generated by a large sample of data sources and training to get the BP neural network can be on-site metal pressure vessel acoustic emission source nature of the success of pattern recognition This result exceeded the previous use of acoustic emission signal parameters of acoustic emission source can not be effective pattern recognition results, but also that of BP network for acoustic emission parameters of the artificial neural network pattern recognition. (2) made of metal with artificial neural network acoustic emission source mechanisms for pressure vessels for quantitative analysis of the concept,ed hardy, found a source of acoustic emission to quantify the severity of the method,mulberry københavn. Through the use of artificial neural network designed for eight field collected acoustic emission source pressure vessel pattern recognition analysis of the results obtained reveal the mechanism of acoustic emission sources. (3) neural network design and training data selection for neural network pattern recognition results are very important. Also try to obtain a single mode source of acoustic emission signals to the neural network training, you can get better recognition effect References: [13 Shen Gong Tian, ??Wan flare, Liu wind. And so on. New manufacturing tank pressure test port of acoustic emission detection]. Non-destructive testing. 1992,14 (3) :65 - 68. [2] Shen Gong-tian, Duan Qing Confucianism, Li Bangxian,mulberry outlet. 800 ammonia washing tower of acoustic emission testing and evaluation of the mouth]. Non-destructive testing, 1994,mulberry,16 (11) 3o5-310. [3] FowlerTJ. Chemicalindustryapplieafiomofacoustk ~ ssinnD]. MaterialsEvaluation, 1992,50 (7) :875-882 .4] Shen Gong-tian, Zhou Yufeng Duan Qing Confucianism,abercrombie düsseldorf, and so on. On-site inspection of pressure vessels, Acoustic Emission Source D],hollister. Non-destructive testing,hollister milano, 1999,21 (7) :321-325. : 5] GrabecI, Sachse arsenic Applicationofanintelligentalgnatprocessingsystemto AEawiysi ~ rj],abercrombie münchen. journalofAcousticalSodewofAmerica,ed hardy nederland, 1989.85 (3) :1226-1235. : 6] SchseW, GrabecIgor. IntelligentprocessingofaCOUS-ticemissionsignals [J]. MaterialsEvaluation. 1992.50 (71:826-854. · L49.<br /></Pre> </td> </tr>
Related articles?
<ul>
<li>????????????????????</li>
<li>indicating that the hydrothermal lead and zinc</li>
<li>too monoclinic probe Jian K value measurement</li>
</ul>
[13 Shen Gong Tian
