Shih-lin Hung

Followers

Following

Co-authors

Public Views

Interests

Uploads

Papers by Shih-lin Hung

Detection of structural damage via free vibration responses generated by approximating artificial neural networks

This work presented a novel neural network-based approach for detecting structural damage. The pr... more This work presented a novel neural network-based approach for detecting structural damage. The proposed approach involves two steps. The first step, system identification, uses neural system identification networks (NSINs) to identify the undamaged and damaged states of a structural system. The second step, structural damage detection, uses the aforementioned trained NSINs to generate free vibration responses with the same initial condition or impulsive force. Comparing the periods and amplitudes of the free vibration responses of the damaged and undamaged states allows the extent of changes to be assessed. Furthermore, numerical and experimental examples demonstrate the feasibility of applying the proposed method for detecting structural damage.

Download

Fuzzy Neural Network Learning Model for Image Recognition

Integrated Computer-Aided Engineering

Developing an energy-efficient and low-delay wake-up wireless sensor network-based structural health monitoring system using on-site earthquake early warning system and wake-on radio

Journal of Civil Structural Health Monitoring

Object-oriented backpropagation and its application to structural design

Neurocomputing

... The generalized delta rule with backpropagation learn-ing strategy associated with a multilay... more

Parallel backpropagation learning algorithms on CRAY Y-MP8/864 supercomputer

Neurocomputing

ABSTRACT Parallel backpropagation neural networks learning algorithms have been developed employi... more ABSTRACT Parallel backpropagation neural networks learning algorithms have been developed employing the vectorization and microtasking capabilities of vector MIMD machines. They have been implemented in C on CRAY Y-MP/864 supercomputer under UNICOS operating system. The algorithms have been applied to two different domains: engineering design and image recognition, and their performance has been investigated. A maximum speedup of about 6.7 is achieved using eight processors for a large network with 5950 links due to microtasking only. When vectorization is combined with microtasking, a maximum speedup of about 33 is realized using eight processors.

Machine learning in engineering design-an unsupervised fuzzy neural network case-based learning model

Proceedings Intelligent Information Systems. IIS'97, 1997

ABSTRACT Engineering design is a creative and experience oriented process. Facing a new design ca... more ABSTRACT Engineering design is a creative and experience oriented process. Facing a new design case, an experienced designer will recall the similar cases in a case base which have been solved before. Then, the designer will attempt to find the solution from these similar cases in a way of adaptation or synthesis. An unsupervised fuzzy neural network (UFN) case-based learning model has been developed to perform the aforementioned design process and implemented in two steps. The UFN learning model has been applied to the domain of engineering design. The learning results show that the learning performance of the new learning model is superior to that of a supervised learning model only in complicated or discrete domains. Also, the unsupervised fuzzy neural network learning model can learn complicated design problems within a reasonable CPU time

Locating damage using integrated global-local approach with wireless sensing system and single-chip impedance measurement device

TheScientificWorldJournal, 2014

This study developed an integrated global-local approach for locating damage on building structur... more This study developed an integrated global-local approach for locating damage on building structures. A damage detection approach with a novel embedded frequency response function damage index (NEFDI) was proposed and embedded in the Imote2.NET-based wireless structural health monitoring (SHM) system to locate global damage. Local damage is then identified using an electromechanical impedance- (EMI-) based damage detection method. The electromechanical impedance was measured using a single-chip impedance measurement device which has the advantages of small size, low cost, and portability. The feasibility of the proposed damage detection scheme was studied with reference to a numerical example of a six-storey shear plane frame structure and a small-scale experimental steel frame. Numerical and experimental analysis using the integrated global-local SHM approach reveals that, after NEFDI indicates the approximate location of a damaged area, the EMI-based damage detection approach can t...

Download

Pilot Study of Wireless Sensor Platform for Existing Tunnel Environment Monitoring

Computing in Civil Engineering (2007), 2007

Wireless Sensor Networks for Monitoring Indoor Environment: An Application to Hospital Buildings

Integrating flahive triangle pattern with sub-pixel analysis for non-contact measurement of structural dynamic response by using a novel image processing technique

variabless of the nodes connected to it by the incoming links. This function is

Unsupervised fuzzy neural networks for damage detection of structures

Structural Control and Health Monitoring, 2007

ABSTRACT This work presents an artificial neural network (ANN) approach for detecting structural ... more ABSTRACT This work presents an artificial neural network (ANN) approach for detecting structural damage. In place of the commonly used supervised neural network, this work adopts an unsupervised neural network which incorporates the fuzzy concept (named the unsupervised fuzzy neural network, UFN) to detect localized damage. The structural damage is assumed to take the form of reduced elemental stiffness. The damage site is demonstrated to correlate with the changes in the modal parameters of the structure. Therefore, a feature representing the damage location, termed the damage localization feature (DLF) is presented. When the structure experiences damage or change in the structural member, the measured DLF is obtained by analyzing the recorded dynamic responses of the structure. The location of the structural damage then can be identified using the UFN according to the measured DLF information. This study verifies the proposed model using an example involving a five-storey frame building. Both single- and multiple-damaged sites are considered. The effects of measured noise and the use of incomplete modal data are introduced to inspect the capability of the proposed detection approach. Additionally, the simulation results of well-known back-propagation network (BPN) and UFN are compared. The analysis results indicated that the use of fuzzy relationship in UFN made the detection of structural damage more robust and flexible than the BPN. Copyright © 2005 John Wiley &amp; Sons, Ltd.

Towards Development of Wireless Sensor System for Monitoring Anesthetic Agents

Sensor Letters, 2010

Abstract: In this paper, the design and development of sensing system for volatile anesthetic age... more Abstract: In this paper, the design and development of sensing system for volatile anesthetic agent based on wireless sensor network is proposed. The proposed system include smart sensor chip fabricated by dip coating conducting polymer for sensing sevoflurane, the most commonly used inhalational anesthetic agent. This paper also discusses the total sensor system design including hardware design, software design and sensor integration. Present sensor system consists of both wireless sensing unit and a wireless receiving unit. The ...

A model of perceptron learning with a hidden layer for engineering design

Neurocomputing, 1991

ABSTRACT A model of machine learning in engineering design, called PERHID, is presented based on ... more ABSTRACT A model of machine learning in engineering design, called PERHID, is presented based on the concept of perceptron learning algorithm with a two-layer neural network. PERHID has been constructed by combining the perceptron with a single-layer AND neural net. The problem of structural design is cast in a form that can be described by a two-layer neural network. Some results from PERHID learning model are presented in tabular form. The paper is concluded by a comparison of the learning by the previously developed single-layer perceptron and PERHID.

Active Pulse Structural Control Using Artificial Neural Networks

Journal of Engineering Mechanics, 2000

Increasing interest has focused on applying active control systems to civil engineering structure... more Increasing interest has focused on applying active control systems to civil engineering structures subjected to dynamic loading. This study presents an active pulse control algorithm, termed the adaptive neural structural active pulse (ANSAP) controller, to control civil engineering structures under dynamic loading. The ANSAP controller minimizes structural cumulative responses during earthquakes by applying active pulse control forces. The effect of pulses is assumed to be delayed until just before the next sampling time so that the control force can be calculated in time and applied; the newly developed control strategy circumvents the effect of time delay due to the computation time. The ANSAP controller also circumvents the difficulty of obtaining system parameters of a real structure for the algorithm for active structural control. Illustrative examples reveal significant reductions in cumulative structural responses, which demonstrates the feasibility of using the adaptive artificial network for controlling civil engineering structures under dynamic loading.

Download

Neural Network Forecast Model in Deep Excavation

Journal of Computing in Civil Engineering, 2002

Diaphragm wall deflection is an important field measurement in deep excavation. The monitoring da... more Diaphragm wall deflection is an important field measurement in deep excavation. The monitoring data are applied to evaluate the construction performance to avoid a supporting system failure or damages incurred to adjacent structures. Despite the numerous case histories of construction projects and several forecasting methods, no method accurately forecasts the performance of construction due to the complicated geotechnical and construction factors affecting the behavior of the diaphragm wall. This work predicts the diaphragm wall deflection by using the adaptive limited memory-Broyden-Fletcher-Goldfarb-Shanno supervised neural network. Eighteen case histories of deep excavations with four to seven excavation stages are selected for training and verification. In addition, the knowledge representation adopts measured wall deflections of previous excavation stages as inputs to the network. Doing so substantially reduces the importance of soil parameters, which are often extremely fluctuating and difficult to assess. Simulation results indicate that the artificial neural network can reasonably predict the magnitude, as well as the location, of maximum deflection of the diaphragm wall.

Download

MS_CMAC Neural Network Learning Model in Structural Engineering

Journal of Computing in Civil Engineering, 1999

ABSTRACT The present American Institute of Steel Construction specifications use the alignment ch... more ABSTRACT The present American Institute of Steel Construction specifications use the alignment charts and approximate formulas conveniently to determine some coefficients in design, such as moment gradient coefficient C(b) for beams of I-shaped section and effective length factor K of columns. In these methods, the coefficients are unconservative when the boundary conditions are different from the development of specifications. The governing equations, numerical approaches, on the K and C(b) coefficients provide more accurate results. The approaches, however, are not readily available for structural engineers to use in design. Applying neural network computing toward structural engineering problems has received increasing interest, with particular emphasis placed on supervised neural networks. The cerebellar model articulation controller (CMAC), one of the supervised neural network learning models, is mostly used in the domain of control. In this work, we use a newly developed Macro Structure CMAC (MS(-)CMAC) neural network learning model to aid steel structure design. The topology of the novel learning model is constructed by a number of time inversion CMACs as a tree structure. The learning performance of the MS(-)CMAC is first compared with a stand-alone time inversion CMAC using one structural engineering example. That comparison indicates not only superior prediction-but also fast learning propriety for the MS-CMAC neural network learning model. In addition, the MS-CMAC neural network learning model is applied to two steel design problems. It is shown that the MS-CMAC not only can learn structural design problems within a reasonable central processing unit time but also can estimate more accurate coefficients than that estimated through alignment charts and approximate formulas in American Institute of Steel Construction specifications.

Augmented IFN Learning Model

Journal of Computing in Civil Engineering, 2000

Solving engineering problems is a creative, experiential process. An experienced engineer general... more Solving engineering problems is a creative, experiential process. An experienced engineer generally solves a new problem by recalling and reusing some similar instances examined before. According to such a method, the integrated fuzzy neural network (IFN) learning model was developed and implemented as a computational model for problem solving. This model has been applied to design problems involving a complicated steel structure. Computational results indicate that, because of its simplicity, the IFN model can learn the complicated problems within a reasonable computational time. The learning performance of IFN, however, relies heavily on the values of some working parameters, selected on a trial-and-error basis. In this work, we present an augmented IFN learning model by integrating a conventional IFN learning model with two novel approaches-a correlation analysis in statistics and a self-adjustment in mathematical optimization. This is done to facilitate the search for appropriate working parameters in the conventional IFN. The augmented IFN is compared with the conventional IFN using two steel structure design examples. This comparison reveals a superior learning performance for the augmented IFN learning model. Also, the problem of arbitrary trial-anderror selection of the working parameters is avoided in the augmented IFN learning model.

Download

Detection of Damage Location Using a Novel Substructure-Based Frequency Response Function Approach with a Wireless Sensing System

International Journal of Structural Stability and Dynamics, 2012

This paper intends to detect the damage locations for building structures under an earthquake exc... more This paper intends to detect the damage locations for building structures under an earthquake excitation using a novel substructure-based FRF approach with a damage location index (SubFRFDI). An Imote2.NET-based wireless structural health monitoring system was developed and employed in the experimental studies for the sake of deployment flexibility, low maintenance cost, low power consumption, self-organization capability, and wireless communication capability. The feasibility of the proposed approach for damage detection was examined using the numerical response of a six-storey shear plane frame structure subjected to a base excitation. The results demonstrate that the SubFRFDI can be successfully used to identify the damage of different levels at a single site or multiple sites. The SubFRFDI is independent of the responses to various input earthquake excitations. Even with the addition of noises, the SubFRFDI still functions well. The feasibility and robustness of the proposed Imo...

Download

A Concurrent Adaptive Conjugate Gradient Learning Algorithm On Mimd Shared-Memory Machines

International Journal of High Performance Computing Applications, 1993

A concurrent adaptive conjugate gradient learning al gorithm has been developed for training of m... more A concurrent adaptive conjugate gradient learning al gorithm has been developed for training of multilayer feed-forward neural networks and implemented in C on a MIMD shared-memory machine (CRAY Y-MP/8- 864 supercomputer). The learning algorithm has been applied to the domain of image recognition. The per formance of the algorithm has been evaluated by ap plying it to two large-scale training examples with 2,304 training instances. The concurrent adaptive neural networks algorithm has superior convergence property compared with the concurrent momentum back-propagation algorithm. A maximum speedup of about 7.9 is achieved using eight processors for a large network with 4,160 links as a result of microtask ing only. When vectorization is combined with micro tasking, a maximum speedup of about 44 is realized using eight processors.

Shih-lin Hung

Uploads

Papers by Shih-lin Hung

Log In