Developing deep neural network for damage detection of beam-like structures using dynamic response based on FE model and real healthy state. (November 2020)

• Record Type: Journal Article
• Authors: Mousavi, Zohreh; Ettefagh, Mir Mohammad; Sadeghi, Morteza H.; Razavi, Seyed Naser
• Is Part Of: Applied acoustics. Volume 168(2020)
• Publication Date: 2020-11
• Subjects: Structural Health Monitoring -- Deep Convolutional Neural Network -- Feature Learning -- Dynamic Response -- Model Updating -- Beam-Like Structures; Acoustical engineering -- Periodicals; Periodicals; 620.2
• DOI: 10.1016/j.apacoust.2020.107402
• Languages: English
• ISSNs: 0003-682X

Abstract

Highlights: A novel method is proposed for damage detection of real mechanical systems in presence of the varying uncertainties such as modeling errors, measurement errors, and varying loading conditions based on FE model and real healthy state. A deep convolutional neural network (DCNN) with training interference and customized architectureis designed to learn features from frequency data. The proposed DCNN is trained using frequency data of the FE model and real healthy state, then is tested using frequency data of the real system. Abstract: Fundamentally, Structural Health Monitoring (SHM) of mechanical systems is essential to avoid their catastrophic failure. The first key contribution of this paper is presenting a new method for damage detection of mechanical systems in presence of the uncertainties such as modeling errors, measurement errors, varying loading conditions and environmental noises based on Finite Element (FE) model and real healthy state. On the other hand, deep learning has been widely used in image and signal analyses with great success. According to this enhancement, the second key contribution of this paper is designing a developed Deep Convolutional Neural Network (DCNN) with training interference and customized architecture to learn the features. In industrial environments, most structures are exposed to varying environmental conditions and it is difficult to collect data containing real damages, and generally, only the data of a real healthy system is available; therefore, it is necessary to have an effective method for damage detection of real systems based on the artificial damages and real healthy data. From this standpoint, the third key contribution of this paper is training process of the proposed DCNN using raw frequency data of the FE model and real healthy state, which is then tested using the raw frequency data of the real system. The proposed DCNN can directly learn the features from raw frequency data of the FE model and real healthy state and discover the damage-sensitive features in order to damage detection of a real system. In this method, only dynamic responses of real healthy system are used to updating the FE model and minimizing the errors. The efficacy of the proposed method is validated using the experimental beam structure. Time data and several manual features from time and frequency data as well as two intelligent methods are used as comparisons. The results show that the proposed method can learn the features from raw frequency data and achieve higher accuracy than other comparative methods.