• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2068-2082
• /
• 2023

With the rapid development of deep learning, Depth Map Super-Resolution (DMSR) method has achieved more advanced performances. However, when the upsampling rate is very large, it is difficult to capture the structural consistency between color features and depth features by these DMSR methods. Therefore, we propose a color-image guided DMSR method based on iterative depth feature enhancement. Considering the feature difference between high-quality color features and low-quality depth features, we propose to decompose the depth features into High-Frequency (HF) and Low-Frequency (LF) components. Due to structural homogeneity of depth HF components and HF color features, only HF color features are used to enhance the depth HF features without using the LF color features. Before the HF and LF depth feature decomposition, the LF component of the previous depth decomposition and the updated HF component are combined together. After decomposing and reorganizing recursively-updated features, we combine all the depth LF features with the final updated depth HF features to obtain the enhanced-depth features. Next, the enhanced-depth features are input into the multistage depth map fusion reconstruction block, in which the cross enhancement module is introduced into the reconstruction block to fully mine the spatial correlation of depth map by interleaving various features between different convolution groups. Experimental results can show that the two objective assessments of root mean square error and mean absolute deviation of the proposed method are superior to those of many latest DMSR methods.

• Smart Structures and Systems
• /
• v.15 no.4
• /
• pp.1121-1137
• /
• 2015

This study presents probabilistic-based damage identification technique for highlighting damage in metallic structures. This technique utilizes distributed piezoelectric transducers to generate and monitor the ultrasonic Lamb wave with narrowband frequency. Diagnostic signals were used to define the scatter signals of different paths. The energy of scatter signals till different times were calculated by taking root mean square of the scatter signals. For each pair of parallel paths an error function based on the energy of scatter signals is introduced. The resultant error function then is used to estimate the probability of the presence of damage in the monitoring area. The presented method with an autofocusing feature is applied to aluminum plates for method verification. The results identified using both simulation and experimental Lamb wave signals at different central frequencies agreed well with the actual situations, demonstrating the potential of the presented algorithm for identification of damage in metallic structures. An obvious merit of the presented technique is that in addition to damages located inside the region between transducers; those who are outside this region can also be monitored without any interpretation of signals. This novelty qualifies this method for online structural health monitoring.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.1469-1474
• /
• 2007

In recent years, research to machine large-surface micro-features has become important because of the light guide panel of a large-scale liquid crystal display and the bipolar plate of a high-capacity proton exchange membrane fuel cell. In this study, in order to realize the systematic design technology and performance improvements of an ultra-precision machine for machining the large-surface micro-features, a structural characteristic analysis was performed using its virtual prototype. The prototype consisted of gantry-type frame, hydrostatic feed mechanisms, linear motors, brushless DC servo motor, counterbalance mechanism, and so on. The loop stiffness was estimated from the relative displacement between the tool post and C-axis table, which was caused by a cutting force. Especially, the causes of structural stiffness deterioration were identified through the structural deformation analysis of sub-models.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.04a
• /
• pp.907-910
• /
• 2012

Since the inner barrel assembly of the Advanced Power Reactor 1400 reactor vessel is a new design feature introduced instead of CEA(control element assembly) shroud assembly, the inner barrel assembly can be a significant object of structural integrity assessment. This paper covers the structural responses of top plate, which is a component of the inner barrel assembly, against the deterministic hydraulic load induced by pump pulsation and the random hydraulic load induced by turbulence of coolant. The top plate responds to the deterministic hydraulic load more than to the random hydraulic load and shows enough structural integrity. The results of this paper will be important basis for the selection of instruments and measurement location.

• Proceeding of EDISON Challenge
• /
• 2015.03a
• /
• pp.274-278
• /
• 2015

There are different kinds of aircrafts, such as conventional airplane, rotorcraft, fighter, and unmanned aerial vehicle. Their shape and feature are dependent upon their assigned mission. One of the fundamental analyses during the design of the aircraft is the structural analysis. The structural analysis becomes more complicated and needs more computations because of the on-going complex aircrafts' structure. In order for efficiency in the structural analysis, a simplified approach, such as equivalent beam or plate model, is preferred. However, it is not clear which analysis will be appropriate to analyze the realistic configuration, i.e., an equivalent beam or plate analysis for an aircraft wing. It is necessary to assess the boundary between the one-dimensional beam analysis and the two-dimensional plate theory for an accurate structural analysis. Thus, in this paper, the static structural analysis results obtained by EDISON solvers were compared with the three-dimesional results obtained from MSC NASTRAN. Before that, EDISON program was verified by comparing the results with those from MSC NASTRAN program and analytic solution.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1993.10a
• /
• pp.181-185
• /
• 1993

A useful finite element method to determine the stiffness of assembled member by stud bolt was introduced in this paper. Since threads on clamped members and stud bolts may produce different stress distribution, brief theories and equations based on bolt and nut may produce less conservative results or, this case. A finite element model using non-linear gap element was indtroduced to find out the basic feature of stress distribution caused by threads on both stud and member.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.06a
• /
• pp.1-18
• /
• 2000

This paper describes firstly a prediction for desirable features of the machine tool in the year 2015 and beyond, and then delineates something definite in relation to some representative machine tools, which could be realised in very near future. The paper depicts furthermore another aspect of future machine tools, I. e., innovative structural designs. In addition, author asserts the importance of grass root-like knowledge, when predicting the desirable feature of machine tools future together with showing some evidences.

• Journal of Digital Convergence
• /
• v.15 no.1
• /
• pp.239-245
• /
• 2017

For privacy protection, we propose a vehicle license plate region detection method in road view image served from portal site. Because vehicle license plate regions in road view images have different feature depending on distance, long distance vehicle license plate regions are not detected by feature of low resolution. Therefore, we suggest a method to detect short distance vehicle license plate regions by edge feature and long distance vehicle license plate regions using MSER feature. And then, we select candidate region of vehicle license plate region from detected region of each method, because the number of the vehicle license plate has a structural feature, we used it to detect the final vehicle license plate region. As the experiment result, we got a recall rate of 93%, precision rate of 75%, and F-Score rate of 80% in various road view images.

• Journal of Information Technology Services
• /
• v.18 no.2
• /
• pp.143-159
• /
• 2019

Machine learning (ML) is a method of fitting given data to a mathematical model to derive insights or to predict. In the age of big data, where the amount of available data increases exponentially due to the development of information technology and smart devices, ML shows high prediction performance due to pattern detection without bias. The feature engineering that generates the features that can explain the problem to be solved in the ML process has a great influence on the performance and its importance is continuously emphasized. Despite this importance, however, it is still considered a difficult task as it requires a thorough understanding of the domain characteristics as well as an understanding of source data and the iterative procedure. Therefore, we propose methods to apply deep learning for solving the complexity and difficulty of feature extraction and improving the performance of ML model. Unlike other techniques, the most common reason for the superior performance of deep learning techniques in complex unstructured data processing is that it is possible to extract features from the source data itself. In order to apply these advantages to the business problems, we propose deep learning based methods that can automatically extract features from transaction data or directly predict and classify target variables. In particular, we applied techniques that show high performance in existing text processing based on the structural similarity between transaction data and text data. And we also verified the suitability of each method according to the characteristics of transaction data. Through our study, it is possible not only to search for the possibility of automated feature extraction but also to obtain a benchmark model that shows a certain level of performance before performing the feature extraction task by a human. In addition, it is expected that it will be able to provide guidelines for choosing a suitable deep learning model based on the business problem and the data characteristics.