Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Journal of Theoretical and Applied Mechanics

2 2019

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Structural damage detection in moving load problem using JRNNs based method

Jena Shakti P., Parhi Dayal R.

Journal of Theoretical and Applied Mechanics

2019

Vol. 57 nr 3

665--676

Damage detection in a structure using the vibration signature is a quiet smart method for condition monitoring of the structure. In this problem, the Recurrent Neural Networks (RNNs) based method has been implemented for damage detection in the moving load problem as an inverse method. A multi-cracked simply supported beam under a traversing load has been considered for the present problem. The localization and severities of the supervised cracks on the structure are determined using the adapted Jordan’s Recurrent Neural Networks (JRNNs) approach. The mechanism of Levenberg-Marquardt’s back propagation algorithm has been implemented to train the networks. To check the adoptability of the proposed JRNNs method, numerical analyses along with laboratory test verifications have been conducted and found to be well emerged.

Analysis of hybrid CSA-DEA method for fault detection of cracked structures

Sahu Sasmita, Kumar Priyadarshi Biplab, Parhi Dayal R.

Journal of Theoretical and Applied Mechanics

2019

Vol. 57 nr 2

369--382

Formation of damage in a structural element often causes failures which is not desirable at all by a maintenance team. Identification of location and severity of damage can aid in taking necessary steps to reduce catastrophic failures of structures. As a result, non-destructive methods of damage detection have gained popularity over the last few years. In this paper, a method of damage detection is proposed to identify the location and severity of damage by hybridising a clonal selection algorithm with a differential evolution algorithm. The inputs to the hybrid system are the relative values of the first three natural frequencies of the damaged structure, and the outputs are relative crack locations and relative crack depths. For training the hybrid system, the natural frequencies are found out using finite element analysis and experimental analysis for different crack locations and crack depths. The test results from the proposed hybrid method are compared with finite element analysis and experimental analysis for validation, and satisfactory outcomes have been observed.