Locating a blind corrosion defect using optimized RAPID algorithm and artificial neural network
محل انتشار: بیست و نهمین همایش سالانه بین المللی انجمن مهندسان مکانیک ایران و هشتمین همایش صنعت نیروگاه های حرارتی
سال انتشار: 1400
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 238
فایل این مقاله در 5 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
این مقاله در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ISME29_114
تاریخ نمایه سازی: 13 تیر 1400
چکیده مقاله:
With the development of industries consisting of homogeneous plates and its use in most industries has caused in the event of damage (cracks or corrosion) in them, irreparable loss. Therefore, continuous inspection of these structures is very important. One of the methods of inspection is ultrasonic testing. Lamb waves are among the ultrasonic waves that due to their special characteristics such as the ability to inspect large areas of the structure and online monitoring, in recent decades have been considered by many researchers. The most important features of sheet wave inspection are high speed inspection of large structure, ability to detect small defects, no need to move the transducers, and ability to detect internal and external defects of the structure. One of the methods of ultrasound test is tomography. One of the most common image reconstruction algorithms in tomography method is RAPID algorithm which has been used in this project for blind defects. But in this method, the created tomogram does not give accurate information about the size and location of the defect. In this paper, a numerical model is prepared using Abaqus finite element analysis software that Lamb waves are generated using piezoelectric elements. Then, by training the neural network, these characteristics were predicted
کلیدواژه ها:
نویسندگان
Alireza Asadi
Center of Advanced Systems and Technologies (CAST), School of Mechanical Engineering, University of Tehran,Tehran, Iran
Aghil Yousefi-Koma
Center of Advanced Systems and Technologies (CAST), University of Tehran, Tehran