 |
advertisement |
|
|
|
|
|
|
Industrial Automatic Control Systems and Controllers Annotation << Back
Using Neural Networks with Deep Learning to Predict and Assess the Ultimate Resource Structures of Buildings |
V.V. Kotelnikov, A.N. Rykov, S.O. Kozelskaya
The problem of predicting the ultimate resource structures of reinforced concrete structures based on neural networks. Residual life prediction problem is considered as a problem of regression. The level of damage and deformation of complex structures has a poor degree of formalization. Driving formalization forecasting problem is presented by the example of farms carrying the body of a timber shop. The neural network is selected as a convolutional neural network. Convolutional layers allocate space features, allowing critical to fi nd the right cause of the defect. A trained neural network convolution. To check the results of the convolutional neural network and the expert opinions of rank correlation was used. The analysis of the results of applying the convolution neural network to predict and assess the resource limit.
Keywords: the ultimate resource; the evaluation designs; deep learning; convolutional neural networks; Kendall correlation.
Contacts: E-mail: Каа2606@rambler.ru
Pp. 39-45. |
|
|
|
Last news:
Выставки по автоматизации и электронике «ПТА-Урал 2018» и «Электроника-Урал 2018» состоятся в Екатеринбурге Открыта электронная регистрация на выставку Дефектоскопия / NDT St. Petersburg Открыта регистрация на 9-ю Международную научно-практическую конференцию «Строительство и ремонт скважин — 2018» ExpoElectronica и ElectronTechExpo 2018: рост площади экспозиции на 19% и новые формы контент-программы Тематика и состав экспозиции РЭП на выставке "ChipEXPO - 2018" |