Earticle

사람은 독서나 필기 중 중요 문구를 형광펜으로 칠하는 것에서 착안하여, 본 논문에서는 복잡한 배경 질감을 가진 영상에서의 불량유형을 효과적으로 분류하기 위해 불량 픽셀 영역을 하이라이팅 하여 신경망을 훈련하는 방법을 제안한다. 제안 방법의 가능성을 검증하기 위하여 불량유형 구분이 매우 어려운 타이어 밴드 직물의 불량유형 분류에 제안 방법을 적용한다. 또한, 타이어 밴드 직물 영상에 특화된 백라이트 하이라이팅 방법을 제안한다. 백라이트 하이라이트 영상은 GradCAM 기법과 간단한 영상처리를 이용하여 획득할 수 있다. 실험에서 우리는 제안하는 하이라이팅 기법이 분류 정확도뿐만 아니라 훈련속도 면에서 기존 방법보다 우수함을 보였다. 인식률 면에서는 제안 방법이 기존 방법 대비 최대 13.4%의 향상을 달성하였다. 타이어 밴드 직물 영상에 특화된 백라이트 하이라이팅 기법이 윤곽 하이라이팅 기법보다 정확도 측면에서 우수함을 보였다.

Motivated by people highlighting important phrases while reading or taking notes we propose a neural network training method by highlighting defective pixel areas to classify effectively defect types of images with complex background textures. To verify our proposed method we apply it to the problem of classifying the defect types of tire band fabric images that are too difficult to classify. In addition we propose a backlight highlighting technique which is tailored to the tire band fabric images. Backlight highlighting images can be generated by using both the GradCAM and simple image processing. In our experiment we demonstrated that the proposed highlighting method outperforms the traditional method in the view points of both classification accuracy and training speed. It achieved up to 13.4% accuracy improvement compared to the conventional method. We also showed that the backlight highlighting technique tailored for highlighting tire band fabric images is superior to a contour highlighting technique in terms of accuracy.

The importance of soundness and safety evaluation in weld zone using by the ultrasonic wave has been recently increased rapidly because of the collapses of huge structures and safety accidents. Especially, the ultrasonic method that has been often used for a major non-destructive testing(NDT) technique in many engineering fields plays an important role as a volume test method. Hence, the defecting any defects of weld Bone in austenitic stainless steel type 304 using by ultrasonic wave and neural network is explored in this paper. In order to detect defects, a distance amplitude curve on standard scan sensitivity and preliminary scan sensitivity represented of the relation between ultrasonic probe, instrument, and materials was drawn based on a quantitative standard. Also, a total of 93％ of defect types by testing 30 defect patterns after organizing neural network system, which is learned with an accuracy of 99％, based on ultrasonic evaluation is distinguished in order to classify defects such as holes or notches in experimental results. Thus, the proposed ultrasonic wave and neural network is useful for defect detection and Ultrasonic Non-Destructive Evaluation(UNDE) of weld zone in austenitic stainless steel 304.

This paper proposes a new steel strip surface inspection system. The system acquires bright and dark field images of defects by using a stroboscopic IR LED illuminator and area camera system and the defect images are preprocessed and segmented in real time for feature extraction. 4113 defect samples of hot rolled steel strip are used to develop KNN (k- Nearest Neighbor) classifier which classifies the defects into 8 different types. The developed KNN classifier demonstrates about 85% classifying performance which is considered very plausible result.

본 논문에서는 항공기 복합재료 내부의 결함을 자동으로 검출하고 분류하는 초음파 검사 방식을 제안한다. 결함 검출을 위해서 초음파의 국부 최대값을 이용해 피크(peak) 값을 추출해낸다. 피크의 거리정보를 이용해 히스토그램화 하며 시편의 표면과 바닥의 백월에코(back-wall echo)를 결정한다. 이를 통해 C-scan 영상을 생성한다. 검출된 피크의 평균과 분산을 이용해 임계값을 정하고 그 값으로 결함여부를 판단한다. 결함의 종류를 구분하기 위해서는 주성분 분석(PCA; principal component analysis)와 이차 판별 분석(QDA; quadratic discriminant analysis)를 수행하였다. PCA를 통한 512개의 차원은 주성분으로 변환 시 30개의 주성분에 99% 이상의 분산이 포함되었다. 주성분 개수를 한정시킴으로써 차원 축소를 통해 계산량을 크게 줄였고 오분류를 최소화하였다. 이차 판별 분석을 적용해 결정경계(decision boundary)의 방정식을 얻었고 이를 통해 결함을 분류할 수 있음을 실험을 통해 보였다.

In this paper, we propose a ultra sound inspection technique for automatic defect detection and classification in aircraft composite materials. Using local maximum values of ultra sound wave, we choose peak values for defect detection. Distance data among peak values are used to construct histogram and to determine surface and back-wall echo from the floor of composite materials. C-scan image is then composed through this method. A threshold value is determined by average and variance of the peak values, and defects are detected by the values. PCA(principal component analysis) and QDA(quadratic discriminant analysis) are carried out to classify the types of defects. In PCA, 512 dimensional data are converted into 30 PCs(Principal Components), which is 99% of total variances. Computational cost and misclassification rate are reduced by limiting the number of PCs. A decision boundary equation is obtained by QDA, and defects are classified by the equation. Experimental result shows that our proposed method is able to detect and classify the defects automatically.

본 연구는 최신 딥러닝 아키텍처를 활용하여 도배 하자의 자동 분류 시스템을 제안한다. 특히 데이터 불 균형과 하자 유형 간 유사성이라는 기술적 과제를 효과적으로 해결하기 위한 새로운 방법론을 제시한다. 데이터 불균형과 하자 유형 간 유사성 문제를 해결하기 위해 ConvNeXt 아키텍처를 기반으로 하되, 하자 유형별 특성을 고려한 맞춤형 데이터 증강 기법과 앙상블 학습을 도입하였다. 총 19개 하자 유형에 대해 3,457개의 이미지로 구 성된 데이터셋을 활용하였으며, 데이터 불균형 해소를 위해 Focal Loss와 Class-Balanced Loss를 결합한 하이브 리드 손실 함수를 적용하였다. 실험 결과, 제안된 모델은 Weighted F1 Score 0.889를 달성하여 기존 ResNet50 기반 모델 대비 8.8%의 성능 향상을 보였으며, 45.2ms의 평균 추론 시간은 실제 하자 검수 업무에 적용 가능한 수준임을 검증하였다. 본 연구의 결과는 건설 현장에서의 도배 하자 검수 자동화 가능성을 제시하며, 품질 관리 프로세스의 효율성 향상에 기여할 것으로 기대된다.

This study proposes an automated classification system for wallpaper defects using state-of-the-art deep learning architectures. In particular, it introduces novel methodologies to effectively address technical challenges such as data imbalance and similarities between defect types. To address challenges such as data imbalance and similarity between defect types, the model is based on the ConvNeXt architecture and incorporates customized data augmentation methods and ensemble learning tailored to the characteristics of each defect type. A dataset of 3,457 images across 19 defect types was utilized, and a hybrid loss function combining Focal Loss and Class-Balanced Loss was applied to mitigate data imbalance. Experimental results demonstrate that the proposed model achieves a weighted F1 score of 0.889, representing an 8.8% performance improvement over existing ResNet50-based models, with an average inference time of 45.2ms validating its feasibility for practical defect inspection tasks. These findings suggest the potential for automating wallpapering defect inspection in construction sites, thereby contributing to enhanced efficiency in quality control processes.

Design and construction technology of apartment building project is progressing, but the defect management has not been improved relatively since move in. At the time of construction completion, various finishing works are intensively performed, and similar defects occur repeatedly because systematic defect management cannot be performed due to lack of quality managers. In addition, precede related studies, it was carried out focusing on the establishment of defect management system, and analysis of relationship of defect occurrence factors (defect location, originalcause material, etc.) and specific defect cause was insufficient. From this point of view, the objective of this study is to formalize the combination of defect occurrence factors and propose the methodology of collaboration for defect prevention targeting 44 cases of defect screening. In order to carry out the purpose of this study, classification structure of defect cause and serial process of defect occurrence were considered, and relationship of defect occurrence factors for each priority management defect was analyzed. Based on related law and case study, we developed the linkage type of defect occurrence information involving defect judgment criteria for each priority management defect and proposed the plans of organization job assignment for main defect management.

본 논문에서는 하부 조명 AOI 환경에서 촬영된 나사 헤드부 영상의 특성을 고려하여, 비지도 이상 표현과 지도학습 기반 판정을 결합한 표면 이상 검출 및 분류 프레임워크를 제안한다. 제안 기법은 도메인 특화 전처리를 통해 분석 영역을 나사 헤드부 표면으로 정렬한 후, Dinomaly 기반 비지도학습을 통해 정상 분포 대비 구조적 편차를 이상 맵 형태로 추출한다. 생성된 이상 맵을 RGB 영상과 결합하여 지도학습 기반 분류기에 입력함으로써, 임계값 설정 에 의존하지 않는 안정적인 정상/이상 판정을 수행한다. 실험 결과, 제안 기법은 다양한 CNN 및 Transformer 백 본 전반에서 일관되게 우수한 성능을 보였다. 특히 Dinomaly 기반 이상 맵은 단독 입력만으로도 평균 F1-score 99.17%을 기록하여 기존 기법보다 강인한 성능을 보였으며, RGB와 이상 맵을 결합한 다중 채널 구성에서는 평균 정확도 및 F1-score 99.40%를 달성하여 최상의 분류 안정성을 확인하였다. 이를 통해 이상 맵이 단순한 시각화를 넘어 분류 성능을 실질적으로 향상시키는 고신뢰 특징 표현임을 정량적·정성적으로 확인하였다.

This study presents a surface anomaly detection and classification framework that integrates unsupervised anomaly representation with supervised learning-based decision-making, tailored to the specific characteristics of screw head images acquired under low-light automated optical inspection (AOI) conditions. The proposed methodology employs domain-specific preprocessing to accurately align the region of interest with the screw head surface, followed by the extraction of structural deviations from the normative distribution as anomaly maps via Dinomaly-based unsupervised learning. These anomaly maps are subsequently fused with RGB images and supplied to a supervised classifier, facilitating robust OK/NG classification independent of threshold selection. Experimental evaluations reveal consistently superior performance across diverse CNN and Transformer architectures. Notably, the Dinomaly-generated anomaly map, when utilized in isolation, surpasses existing approaches, achieving an average F1-score of 99.17%. In a multi-channel setting that integrates both RGB and anomaly maps, the proposed framework attains average accuracy and F1-score values of 99.40%, underscoring its exceptional classification stability. These results quantitatively and qualitatively substantiate that the anomaly map serves as a high-confidence feature representation, advancing beyond mere visualization to significantly enhance classification outcomes.

A study of fracture to material is getting interest in nuclear and aerospace industry as a viewpoint of safety. Acoustic emission (AE) is a non-destructive testing and new technology to evaluate safety on structures. In previous research continuously, all tensile tests on the pre-defected coupons were performed using the universal testing machine, which machine crosshead was move at a constant speed of 5mm/min. This study is to evaluate an AE source characterization of SM45C steel by using k-nearest neighbor classifier, k-NNC. For this, we used K-means clustering as an unsupervised learning method for obtained multi -variate AE main data sets, and we applied k-NNC as a supervised learning pattern recognition algorithm for obtained multi-variate AE working data sets. As a result, the criteria of Wilk's , D&B(Rij) & Tou are discussed.

콘크리트 구조물의 적절한 유지관리를 위해서 다양한 결함에 대해 사전에 파악하고 유지관리하는 것이 필요하 다. 현재 방법으로는 규모가 큰 사회기반시설물의 점검 시 효율성, 안전성, 신뢰성에 문제가 있어 새로운 점검 방식의 도입이 필요하다. 최근에는 영상에 대한 딥러닝 기술이 발달함에 따라 콘크리트 결함 분류 연구가 활발히 진행되고 있다. 하지만, 균열 외에 오염과 박락 등에 대한 연구는 제한적이다. 본 연구에서는 사전에 학습된 딥러닝 모델에 대 한 전이학습을 통한 다양한 콘크리트 결함 유형 분류 모델을 개발하고, 정확도를 저하시키는 요인을 도출 및 향후 발 전 방향을 제시하였다. 이는 향후 콘크리트 유지관리 분야에서 활용도가 높을 것으로 예상된다.

For maintenance of concrete structures, it is necessary to identify and maintain various defects. With the current method, there are problems with efficiency, safety, and reliability when inspecting large-scale social infrastructure, so it is necessary to introduce a new inspection method. Recently, with the development of deep learning technology for images, concrete defect classification research is being actively conducted. However, studies on contamination and spalling other than cracks are limited. In this study, a variety of concrete defect type classification models were developed through transfer learning on a pre-learned deep learning model, factors that reduce accuracy were derived, and future development directions were presented. This is expected to be highly utilized in the field of concrete maintenance in the future.

Effective identification of wood decay and crack defects by using support vector machine (SVM) theory. Extracting wood defect image through the image acquisition system, then processing the defect image by using gray level change, equalization, and median filtering et al. So as to achieve the purpose of improve the image quality and detection accuracy. Segment the target images, and then measures the area, perimeter, and diameter of the wood defects. Three eigenvalues, area and perimeter square ratio, length to diameter ratio and circumference and area ratio, which can be identified the wood defects was obtained. Separating these eigenvalues into training set and testing set. Training Support vector machine by using training set, establish a preliminary model of support vector machine. Using support vector machine model for accuracy test, if the test accuracy is low, repeatedly adjust the parameters of support vector machine for training and testing until reach the test accuracy. Making sure the kernel function and various parameters of support vector machine, constructing the support vector machine, which using for wood defect classification. The experimental results showed that this method has fast calculation speed, high precision, and helps to raise the utilization rate of wood.

This paper proposes an automatic defect classification (ADC) system to detect and classify bare wafer edge defects that occur during the extreme wafer thinning process required for advanced chip stacking technologies such as TSV and HBM. The proposed system combines a convolutional neural network (ResNet) with traditional image processing techniques (OpenCV-based frequency domain filtering) to effectively classify and visualize wafer edge defects. Experimental results demonstrate that the system achieves high accuracy in defect classification and detection, providing an efficient solution to prevent wafer damage and yield reduction.

Recently, the fourth industrial revolution has been presented as a new paradigm and additive manufacturing (AM) has become one of the most important topics. For this reason, process monitoring for each cross-sectional layer of additive metal manufacturing is important. Particularly, deep learning can train a machine to analyze, optimize, and repair defects. In this paper, image classification is proposed by learning images of defects in the metal cross sections using the convolution neural network (CNN) image labeling algorithm. Defects were classified into three categories: crack, porosity, and hole. To overcome a lack-of-data problem, the amount of learning data was augmented using a data augmentation algorithm. This augmentation algorithm can transform an image to 180 images, increasing the learning accuracy. The number of training and validation images was 25,920 (80 %) and 6,480 (20 %), respectively. An optimized case with a combination of fully connected layers, an optimizer, and a loss function, showed that the model accuracy was 99.7 % and had a success rate of 97.8 % for 180 test images. In conclusion, image labeling was successfully performed and it is expected to be applied to automated AM process inspection and repair systems in the future.

Semiconductor wafer maps provide vital information and clues to monitor and better understand the quality issues in the underlying manufacturing process. In post-fabrication, each chip undergoes a series of quality checks to determine whether the chip is in functional or defective state. Since each defect pattern is unique, automatically characterizing the various defect patterns in wafer map can provide significant insights to process engineers towards mitigating manufacturing defects and improve the effective yield rate. In this paper, we present a novel data mining and optimization-based supervised learning algorithm, called support vector machines with weighted dynamic time warping kernel (SVM-WDTWK), to classify defect patterns on semiconductor wafers. SVM-WDTWK provides a flexible and robust matching algorithm for time series classification, leading to an accurate match between non-aligned time series data. We present a numerical comparison to show that the proposed SVM-WDTWK algorithm is superior to several existing techniques on defect pattern classification on semiconductor wafer maps.

본 논문에서는 복합소재 생산 분야에서 수요가 높은 프리프레그 섬유 제조 공정에 딥러닝 기반의 결함 검출 및 분류 시스템을 적용하여 생산성을 높이는 과정을 제안한다. 다양한 조건별 다량의 불량 발생으로 해결방안이 필요한 토우 프리프레그 제조 장비에 적용하기 위해 우선 결함 감지와 분류 모델 제작에 필요한 카메라 및 조명을 선정하여 최적의 환경을 구축하였다. 그리고 다중 분류 모델 제작에 필요한 데이터를 수집하고 정상 및 불량 조건에 따라 라벨링을 진행하였다. 다중 분류 모델은 CNN 기반으로 제작하였으며 VGGNet과 MobileNet, ResNet 등의 사전 학습모델을 적용하여 성능을 비교하고 정확도 및 손실 그래프로 개선 방향을 파악한다. 주요 문제로 과적합 문제를 확인하여 개선하기 위해 데이터 증강 및 Dropout 기법을 적용하여 보완하였다. 모델에 대한 성능 평가를 위해 혼돈행렬을 성능지표로 한 성능 평가를 진행하였으며 99% 이상의 성능을 확인하였다. 또한, 실제 공정에 적용하여 실시간 획득된 이미지에 대한 분류 결과를 확인해보며 판별 값이 정확히 도출되는지 확인한다.

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

본 논문에서는 컴퓨터 비전을 사용하여 6가지 측정값(눌린 단자의 길이, 단자 끝의 치수(폭), 눌린부분(와이어 부분, 코어 부분)의 폭)을 계산하여 와이어 하네스의 결함을 정확하고 빠르게 탐지할 것을 제안한다. 두 가지 유형의 데이터에서 Harris 코너 검출을 활용하여 물체의 위치를 탐지하고 측정 영역별 특징과 배경과 물체 사이의 음영 차이를 활용하여 각 샘플의 기울기를 반영하는 측정값을 추출하기 위한 기준점을 생성한다. 이후 유클리드 거리 방법과 보정 계수를 사용하여 예측값을 계산하는 방법을 통해 와이어의 위치 변화에 관계 없이 측정값을 예측할 수 있다. 각 측정 유형별로 99.1%, 98.7%, 92.6%, 92.5%, 99.9%, 99.7% 정확도를 달성하였으며, 모든 측정값에서 평균 97%의 정확도로 우수한 결과를 얻었다. 해당 검사 방법은 기존 검사 방법인 육안 검사의 문제점을 보완하고, 작은 양의 데이터만을 이용하여 우수한 결과를 도출 가능하다. 또한 이미지 처리만 이용하기 때문에 딥러닝 방법보다 더 적은 데이터와 비용으로 적용 가능할 것으로 기대된다.

In this paper, we propose a method for accurately and rapidly detecting defects in wire harnesses by utilizing computer vision to calculate six crucial measurement values: the length of crimped terminals, the dimensions (width) of terminal ends, and the width of crimped sections (wire and core portions). We employ Harris corner detection to locate object positions from two types of data. Additionally, we generate reference points for extracting measurement values by utilizing features specific to each measurement area and exploiting the contrast in shading between the background and objects, thus reflecting the slope of each sample. Subsequently, we introduce a method using the Euclidean distance and correction coefficients to predict values, allowing for the prediction of measurements regardless of changes in the wire's position. We achieve high accuracy for each measurement type, 99.1%, 98.7%, 92.6%, 92.5%, 99.9%, and 99.7%, achieving outstanding overall average accuracy of 97% across all measurements. This inspection method not only addresses the limitations of conventional visual inspections but also yields excellent results with a small amount of data. Moreover, relying solely on image processing, it is expected to be more cost-effective and applicable with less data compared to deep learning methods.

Molecular dynamics simulations were performed to predict the behavior of graphite atoms under neutron irradiation using large-scale atomic/molecular massively parallel simulator (LAMMPS) package with adaptive intermolecular reactive empirical bond order (AIREBOM) potential. Defect structures of graphite were compared with results from previous studies by means of density functional theory (DFT) calculations. The quantitative relation between primary knock-on atom (PKA) energy and irradiation damage on graphite was calculated. and the effect of PKA direction on the amount of defects is estimated by counting displaced atoms. Defects are classified into four groups: structural defects, energy defects, vacancies, and near-defect structures, where a structural defect is further subdivided into six types by decision tree method which is one of the supervised machine learning techniques.

철강 표면 결함의 검출 및 분류는 철강 산업의 제품 품질 관리에 중요하다. 그러나 정확도가 낮고 속도가 느리기 때문에 기존 방식은 생산 라인에서 효과적으로 사용할 수 없다. 현재 널리 사용되는 알고리즘(딥러닝 기반)은 정확도 문제가 있으며 아직 개발의 여지가 있다. 본 논문에서는 이미지 분류를 위한 EfficientNetV2와 물체 검출기로 YOLOv5를 결합한 강철 표면 결함 검출 방법을 제안한다. 이 모델의 장점은 훈련 시간이 짧고 정확도가 높다는 것이다. 먼저 EfficientNetV2 모델에 입력되는 이미지는 결함 클래스를 분류하고 결함이 있을 확률을 예측한다. 결함이 있을 확률이 0.3보다 작으면 알고리즘은 결함이 없는 샘플로 인식한다. 그렇지 않으면 샘플이 YOLOv5에 추가로 입력되어 금속 표면의 결함 감지 프로세스를 수행한다. 실험에 따르면 제안된 모델은 NEU 데이터 세트에서 98.3%의 정확도로 우수한 성능을 보였고, 동시에 평균 훈련 속도는 다른 모델보다 단축된 것으로 나타났다.

Detection and classification of steel surface defects are critical for product quality control in the steel industry. However, due to its low accuracy and slow speed, the traditional approach cannot be effectively used in a production line. The current, widely used algorithm (based on deep learning) has an accuracy problem, and there are still rooms for development. This paper proposes a method of steel surface defect detection combining EfficientNetV2 for image classification and YOLOv5 as an object detector. Shorter training time and high accuracy are advantages of this model. Firstly, the image input into EfficientNetV2 model classifies defect classes and predicts probability of having defects. If the probability of having a defect is less than 0.25, the algorithm directly recognizes that the sample has no defects. Otherwise, the samples are further input into YOLOv5 to accomplish the defect detection process on the metal surface. Experiments show that proposed model has good performance on the NEU dataset with an accuracy of 98.3%. Simultaneously, the average training speed is shorter than other models.

BACKGROUND: Perimembranous ventricular septal defects (VSDs) has proximate relation to the aortic and tricuspid valves as well as the conduction tissues. Transcatheter closure utilizes various off-label device designs. METHODS: Perimembranous VSD without aortic margin were classified as group A, with thick aortic margin as group B, with membranous septal aneurysm as group C and defects restricted by tricuspid valve attachments as group D. The proposed ideal design was asymmetric device in group A; duct occluder I (ADOI) and muscular ventricular septal occluder (MVSO) in group B; thin profile duct occluder II (ADOII) in group C and ADOI in group D. Device was 0?2 mm larger than the defect. RESULTS: Eighty patients with VSD measuring 6.83 ± 2.87mm underwent successful closure. Device was retrieved before release in one group A and one group C patient due to aortic regurgitation. Asymmetric device was used in 16 group A defects. Among group B defects, ADOI was used in 5, ADOII in 5, MVSO in one and asymmetric device in 3. Group C defects were closed with ADOI in 7, ADOII in 10 and asymmetric device in 3. Three patients with multiple exits had 2 ADOII devices. Group D defects were closed using ADOI in 20 and ADOII in 10 patients. There was no late aortic regurgitation or heart block on a follow-up exceeding 7 years. CONCLUSIONS: This echocardiographic classification helps device selection in every single patient. While asymmetric device is uniquely suited for group A defects, different designs are appropriate in the other groups.

.

진동 정보를 통해 기계 설비의 상태나 고장 유무를 판단하는 연구들이 다수 진행 중에 있는데, 대부분의 연구에서는 설비에 대한 진동을 모니터링하거나 고장 유무를 판별하여 사용자에게 알리는 수준이다. 본 논문에서는 진동에 의한 고장 진단과 판별을 보다 정교하게 수행하는 선박 엔진의 고장 감지 기법과 시스템을 제안하였다. 일차적으로 이중적 진동 정보 판별 기법을 적용하여 진동 정보를 확인한 다음에 고장 유무를 검사한다. 만일 고장이 발생한 경우에는 진동 정보의 오류 부분만을 이용하여 고장 진동 파형에 대한 오차 범위를 기준으로 어떤 유형의 고장인지를 판별할 수 있는 기법을 적용하였다. 또한 선박의 진동 경향 분석과 엔진 안전 보존을 목적으로 진동 정보를 데이터베이스에 저장하고 추적할 수 있도록 시스템을 구현하였다. 제안 시스템을 선박 엔진의 고장 판별 유무와 고장 진동 파형 감별 인자에 대해 실험을 수행한 결과 고장 유무 판별은 약 100% 정확성을 가졌고 고장 진동 파형의 유형 인식에서는 약 96% 정확성을 가졌다.

There has been some research in the equipment defect detection based on vibration information. Most research of them is based on vibration monitoring to determine the equipment defect or not. In this paper, we introduce more accurate system for engine defect detection based on vibration information and we focus on detection of engine defect for boat and system control. First, it uses the duplicated-checking method for vibration information to determine the engine defect or not. If there is a defect happened, we use the method using error part of vibration information basis with error range to determine which kind of error is happened. On the other hand, we use the engine trend analysis and standard of safety engine to implement the vibration information database. Our simulation results show that the probability of engine defect determination is 100% and the probability of engine defect classification and detection is 96%.