http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Xinqun Zhu (검색결과 4 건)
- 무료
- 기관 내 무료
- 유료
-
Damage localization and quantification of a truss bridge using PCA and convolutional neural network
Xinqun Zhu,Jiajia Hao,Yang Yu,Chunwei Zhang,Jianchun Li 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.30 No.6
Deep learning algorithms for Structural Health Monitoring (SHM) have been extracting the interest of researchers and engineers. These algorithms commonly used loss functions and evaluation indices like the mean square error (MSE) which were not originally designed for SHM problems. An updated loss function which was specifically constructed for deep-learningbased structural damage detection problems has been proposed in this study. By tuning the coefficients of the loss function, the weights for damage localization and quantification can be adapted to the real situation and the deep learning network can avoid unnecessary iterations on damage localization and focus on the damage severity identification. To prove efficiency of the proposed method, structural damage detection using convolutional neural networks (CNNs) was conducted on a truss bridge model. Results showed that the validation curve with the updated loss function converged faster than the traditional MSE. Data augmentation was conducted to improve the anti-noise ability of the proposed method. For reducing the training time, the normalized modal strain energy change (NMSEC) was extracted, and the principal component analysis (PCA) was adopted for dimension reduction. The results showed that the training time was reduced by 90% and the damage identification accuracy could also have a slight increase. Furthermore, the effect of different modes and elements on the training dataset was also analyzed. The proposed method could greatly improve the performance for structural damage detection on both the training time and detection accuracy.
-
Jayawardhana, Madhuka,Zhu, Xinqun,Liyanapathirana, Ranjith,Gunawardana, Upul Techno-Press 2015 Structural monitoring and maintenance Vol.2 No.3
This paper addresses the issue of reliability and performance in wireless sensor networks (WSN) based structural health monitoring (SHM), particularly with decentralized damage identification techniques. Two decentralized damage identification algorithms, namely, the autoregressive (AR) model based damage index and the Wiener filter method are developed for structural damage detection. The ambient and impact testing have been carried out on the steel beam structure in the laboratory. Seven wireless sensors are installed evenly along the steel beam and seven wired sensor are also installed on the beam to monitor the dynamic responses as comparison. The results showed that wireless measurements performed very much similar to wired measurements in detecting and localizing damages in the steel beam. Therefore, apart from the usual advantages of cost effectiveness, manageability, modularity etc., wireless sensors can be considered a possible substitute for wired sensors in SHM systems.
-
Huidong Zhang,Xinqun Zhu,Yuan-feng Wang,Shu Yao 국제구조공학회 2021 Steel and Composite Structures, An International J Vol.40 No.4
The major sources of damping in steel structures are within the joints and the structural material. For welded large-scale single-layer lattice domes subjected to earthquake ground motions, the stick-slip phenomenon at the bearings is an important source of the energy dissipation. However, it has not been extensively investigated. In this study, the equivalent friction damping ratio (EFDR) at the bearings of a welded large-scale single-layer lattice dome subjected to earthquake ground motions is quantified using an approximate method based on the energy balance concept. The complex friction behavior and energy dissipation between contact surfaces are investigated by employing an equivalent modeling method. The proposed method uses the stick-slip-hook components with a pair of circular isotropic friction surfaces having a variable friction coefficient to model the energy loss at the bearings, and the effect of the normal force on the friction force is also considered. The results show that the EFDR is amplitude-dependent and is related to the intensity of the ground motions; it exhibits complex characteristics that cannot be described by the conventional models for damping ratios. A parametric analysis is performed to investigate in detail the effects of important factors on the EFDR. Finally, the friction damping mechanism at bearings is discussed. This study enables researchers and engineers to have a better understanding of the essential characteristics of friction damping under earthquake ground motions.
-
Guihan Peng,Shozo Nakamura,Xinqun Zhu,Qingxiong Wu,Hailiang Wang 사단법인 한국계산역학회 2017 Computers and Concrete, An International Journal Vol.20 No.5
Concrete filled steel tubular (CFST) composite girder is a new type of structures for bridge constructions. The existing design codes cannot be used to predict the thermal stress in the CFST truss girder structures under solar radiation. This study is to develop the temperature gradient curves for predicting thermal stress of the structure based on field and laboratory monitoring data. An in-field testing had been carried out on Ganhaizi Bridge for over two months. Thermal couples were installed at the cross section of the CFST truss girder and the continuous data was collected every 30 minutes. A typical temperature gradient mode was then extracted by comparing temperature distributions at different times. To further verify the temperature gradient mode and investigate the evolution of temperature fields, an outdoor experiment was conducted on a 1:8 scale bridge model, which was installed with both thermal couples and strain gauges. The main factors including solar radiation and ambient temperature on the different positions were studied. Laboratory results were consistent with that from the in-field data and temperature gradient curves were obtained from the in-field and laboratory data. The relationship between the strain difference at top and bottom surfaces of the concrete deck and its corresponding temperature change was also obtained and a method based on curve fitting was proposed to predict the thermal strain under elevated temperature. The thermal stress model for CFST composite girder was derived. By the proposed model, the thermal stress was obtained from the temperature gradient curves. The results using the proposed model were agreed well with that by finite element modelling.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
