• Geomechanics and Engineering
• /
• 제31권2호
• /
• pp.129-147
• /
• 2022

The properties of soil are naturally highly variable and thus, to ensure proper safety and reliability, we need to test a large number of samples across the length and depth. In pile foundations, conducting field tests are highly expensive and the traditional empirical relations too have been proven to be poor in performance. The study proposes a state-of-art Particle Swarm Optimization (PSO) hybridized Artificial Neural Network (ANN), Extreme Learning Machine (ELM) and Adaptive Neuro Fuzzy Inference System (ANFIS); and comparative analysis of metaheuristic models (ANN-PSO, ELM-PSO, ANFIS-PSO) for prediction of bearing capacity of pile foundation trained and tested on dataset of nearly 300 dynamic pile tests from the literature. A novel ensemble model of three hybrid models is constructed to combine and enhance the predictions of the individual models effectively. The authenticity of the dataset is confirmed using descriptive statistics, correlation matrix and sensitivity analysis. Ram weight and diameter of pile are found to be most influential input parameter. The comparative analysis reveals that ANFIS-PSO is the best performing model in testing phase (R² = 0.85, RMSE = 0.01) while ELM-PSO performs best in training phase (R² = 0.88, RMSE = 0.08); while the ensemble provided overall best performance based on the rank score. The performance of ANN-PSO is least satisfactory compared to the other two models. The findings were confirmed using Taylor diagram, error matrix and uncertainty analysis. Based on the results ELM-PSO and ANFIS-PSO is proposed to be used for the prediction of bearing capacity of piles and ensemble learning method of joining the outputs of individual models should be encouraged. The study possesses the potential to assist geotechnical engineers in the design phase of civil engineering projects.

• Smart Structures and Systems
• /
• 제19권2호
• /
• pp.127-136
• /
• 2017

Fiber reinforced polymer (FRP) has received widespread attention in the field of civil engineering because of its superior durability and corrosion resistance. This article presents the damage mechanisms of a novelty composite called carbon nanofiber modified flax fiber polymer (CNF-modified FFRP). The ability of acoustic emission (AE) to detect damage evolution for different configurations of specimens under uniaxial tension was examined, and some useful AE characteristic parameters were obtained. Test results shows that the mechanical properties of modified composites are associated with the CNF content and the evenness of CNF dispersed in the epoxy matrix. Various damage mechanisms was established by means of scanning electron microscope images. The fuzzy c-means clustering were proposed to classify AE events into groups representing different generation mechanisms. The classifiers are constructed using the traditional AE features -- six parameters from each burst. Amplitude and peak-frequency were selected as the best cluster-definition features from these AE parameters. After comprehensive comparison, a correlation between these AE events classes and the damage mechanisms observed was proposed.

• Smart Structures and Systems
• /
• 제16권2호
• /
• pp.329-345
• /
• 2015

As commonly known, sensor errors and faulty signals may potentially lead structures in vibration to catastrophic failures. This paper presents a new approach to deal with sensor errors/faults in vibration control of structures by using the Fault detection and isolation (FDI) technique. To demonstrate the effectiveness of the approach, a space truss structure with semi-active devices such as Magneto-Rheological (MR) damper is used as an example. To address the problem, a Linear Matrix Inequality (LMI) based fixed-order $H_{\infty}$ FDI filter is introduced and designed. Modeling errors are treated as uncertainties in the FDI filter design to verify the robustness of the proposed FDI filter. Furthermore, an innovative Fuzzy Fault Tolerant Controller (FFTC) has been developed for this space truss structure model to preserve the pre-specified performance in the presence of sensor errors or faults. Simulation results have demonstrated that the proposed FDI filter is capable of detecting and isolating sensor errors/faults and actuator faults e.g., accelerometers and MR dampers, and the proposed FFTC can maintain the structural vibration suppression in faulty conditions.

• 한국지능시스템학회논문지
• /
• 제22권1호
• /
• pp.94-99
• /
• 2012

본 논문은 대규모 비선형 시스템의 분산 샘플치 제어 문제를 논한다. 대상 시스템은 타카기-수게노 퍼지모델로 표현된다. 중복분해 기법을 이용하여 아날로그 분산 제어기를 설계하고 이것은 지능형 디지털 재설계 기법에 의하여 샘플치 제어기로 변환된다. 설계조건은 선형행렬부등식으로 표현된다. 모의실험 결과에 의하여 제안된 기법의 효용성을 입증한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.5-8
• /
• 2003

This paper presents a methodology to be able to select an appropriate RP system that suits the end use of a part. Evaluation factors used in process selection include major attributes such as accuracy, roughness, strength, elongation, part cost and build time that greatly affect the performance of RP systems. Crisp values such as accuracy and surface roughness are obtained with a new test part developed. The test part is designed with conjoint analysis to reflect users' preference. The part cost and build time that have approximate ranges due to cost and many variable parameters are presented by linguistic values that can be described with triangular fuzzy numbers. Based on the evaluation values obtained, an appropriate RP process for a specific part application is selected by using the modified TOPSIS(Technique of Order Preference by Similarity to Ideal Solution) method. It uses crisp data as well as linguistic variables, and each weight on the alternatives is assigned by using pair-wise comparison matrix. The ranking order helps the decision making of the selection of RP systems.

• Asian-Australasian Journal of Animal Sciences
• /
• 제20권12호
• /
• pp.1783-1790
• /
• 2007

The genetic diversity of domestic quail and two wild quail species, Japanese （Coturnix coturnix）and Common quail (Coturnix japonica), found in China was studied using microsatellite DNA markers. According to a comparison of the corresponding genetic indices in the three quail populations, such as Polymorphism Information Content (PIC), Mean Heterozygosity ($\bar{H}$) and Fixation Index, wild Common quail possessed rich genetic diversity with 4.67 alleles per site. Its values for PIC and $\bar{H}$ were the highest, 0.5732 and 0.6621, respectively. Domestic quail had the lowest values, 0.5467 and 0.5933, respectively. Wild Japanese quail had little difference in genetic diversity from domestic quail. In addition, from analyses of the fuzzy cluster based on standard genetic distance, the similarity relationship matrix coefficient between wild Japanese quail and domestic quail was 0.937, and that between wild Common quail and domestic quail was 0.783. All of these results showed that the wild Japanese quail were closer to the domestic quail for phylogenetic relationship than wild Common quail. These results at the molecular level provide useful data about quail's genetic background and further supported the hypothesis that the domestic quail originated from the wild Japanese quail.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제7권1호
• /
• pp.1-6
• /
• 2007

The SVDD (support vector data description) is one of the most well-known one-class support vector learning methods, in which one tries the strategy of utilizing balls defined on the feature space in order to distinguish a set of normal data from all other possible abnormal objects. Recently, with the objective of generalizing the SVDD which treats all training data with equal importance, the so-called D-SVDD (density-induced support vector data description) was proposed incorporating the idea that the data in a higher density region are more significant than those in a lower density region. In this paper, we consider the problem of further improving the D-SVDD toward the use of a partial reference set for testing, and propose an LMI (linear matrix inequality)-based optimization approach to solve the improved version of the D-SVDD problems. Our approach utilizes a new class of density-induced distance measures based on the RSDE (reduced set density estimator) along with the LMI-based mathematical formulation in the form of the SDP (semi-definite programming) problems, which can be efficiently solved by interior point methods. The validity of the proposed approach is illustrated via numerical experiments using real data sets.

• 한국지능시스템학회논문지
• /
• 제18권1호
• /
• pp.60-65
• /
• 2008

본 논문에서는 강인 디지털 제어기를 통한 스마트 스페이스의 안정도에 대해 논의하고자 한다. 제안된 제어기 설계 방법은 지능형 디지털 재 설계 기법을 적용하는 것이다. 좀 더 구체적으로, 불확실성 및 비선형성이 포함된 아날로그 시스템을 Takagi-Sugeno 퍼지 모델을 사용하여 나타낸다. 그리고 전역적 지능형 디지털 재 설계를 위하여 해당 문제를 볼록 최적화 관점으로 변환 한 후, 에러가 가질 수 있는 놈의 영역을 최소화하여 상태 정합을 이루고자 하였다. 전역적 접근을 통해 정리된 식은 선형 행렬 부등식으로 나타나게 된다. 마지막으로, 설계된 제어기를 HVAC (Heating, ventilating, and air conditioning) 시스템에 적용함으로써 효율성을 입증하고자 한다.

• 한국정보처리학회논문지
• /
• 제6권7호
• /
• pp.1970-1979
• /
• 1999

본 논문에서는 수동 AVI 기술을 이용하여 차량 번호 판과 운전자 얼굴을 동시에 인식하는 시스템에 대해 제안하고자 한다. 이를 위해 우선적으로 환경에 불편인 전처리과정 알고리즘의 제시와 목표영역이 되는 차량 번호판 영역과 운전자 얼굴 영역을 추출하는 방법에 대해 다루고자 한다. 이후 목표영역에서 문자 영역분리와 인식 파라미터 추출을 행하고 차량 번호판의 경우 원형 정합으로, 운전자 얼굴 영역의 경우 퍼지 관계 행렬을 생성하여 최종적인 인식을 수행하고자 한다. 본 논문에서 제안하는 시스템은 환경에 불변인 전처리과정의 수행과 기존의 AVI 시스템에서 차량 번호 판만을 인식했던 것을 운전자 얼굴 인식까지 행함으로써 기존 AVI 시스템의 적용성 확대를 기할 수 있었다.

• Smart Structures and Systems
• /
• 제18권3호
• /
• pp.525-540
• /
• 2016

The CFRP-confined circular concrete-filled steel tubular column is composed of concrete, steel, and CFRP. Its failure mechanics are complex. The most important difficulties are lack of an available method to establish a relationship between a specific damage mechanism and its acoustic emission (AE) characteristic parameter. In this study, AE technique was used to monitor the evolution of damage in CFRP-confined circular concrete-filled steel tubular columns. A fuzzy c-means method was developed to determine the relationship between the AE signal and failure mechanisms. Cluster analysis results indicate that the main AE sources include five types: matrix cracking, debonding, fiber fracture, steel buckling, and concrete crushing. This technology can not only totally separate five types of damage sources, but also make it easier to judge the damage evolution process. Furthermore, typical damage waveforms were analyzed through wavelet analysis based on the cluster results, and the damage modes were determined according to the frequency distribution of AE signals.