Deep learning-based computer vision anomaly detection algorithms are widely utilized in various fields. Especially in the manufacturing industry, the difficulty in collecting abnormal data compared to normal data, and the challenge of defining all potential abnormalities in advance, have led to an increasing demand for unsupervised learning methods that rely on normal data. In this study, we conducted a comparative analysis of deep learning-based unsupervised learning algorithms that define and detect abnormalities that can occur when transparent contact lenses are immersed in liquid solution. We validated and applied the unsupervised learning algorithms used in this study to the existing anomaly detection benchmark dataset, MvTecAD. The existing anomaly detection benchmark dataset primarily consists of solid objects, whereas in our study, we compared unsupervised learning-based algorithms in experiments judging the shape and presence of lenses submerged in liquid. Among the algorithms analyzed, EfficientAD showed an AUROC and F1-score of 0.97 in image-level tests. However, the F1-score decreased to 0.18 in pixel-level tests, making it challenging to determine the locations where abnormalities occurred. Despite this, EfficientAD demonstrated excellent performance in image-level tests classifying normal and abnormal instances, suggesting that with the collection and training of large-scale data in real industrial settings, it is expected to exhibit even better performance.

Smart factory companies are installing various sensors in production facilities and collecting field data. However, there are relatively few companies that actively utilize collected data, academic research using field data is actively underway. This study seeks to develop a model that detects anomalies in the process by analyzing spindle power data from a company that processes shafts used in automobile throttle valves. Since the data collected during machining processing is time series data, the model was developed through unsupervised learning by applying the Holt Winters technique and various deep learning algorithms such as RNN, LSTM, GRU, BiRNN, BiLSTM, and BiGRU. To evaluate each model, the difference between predicted and actual values was compared using MSE and RMSE. The BiLSTM model showed the optimal results based on RMSE. In order to diagnose abnormalities in the developed model, the critical point was set using statistical techniques in consultation with experts in the field and verified. By collecting and preprocessing real-world data and developing a model, this study serves as a case study of utilizing time-series data in small and medium-sized enterprises.

본 연구는 네트워크 이상 감지 및 예측을 위해 벡터 자기회귀(VAR) 모델의 사용을 비교 분석한다. VAR 모 델에 대한 간략한 개요를 제공하고 네트워크 이상 체크로 사용 가능한 두 가지 버전을 검토하며 두 종류의 VAR 모델을 통한 경험적인 평가를 제시한다. VAR-Filtered moving-common-AR 모델이 단일 노드 이상 감지 성능에서 우수하며, VAR-Adaptive Learning 버전은 몇 개의 노드 간 이상을 효과적으로 식별하는 데 특히 효 과적이며 두 가지 주요VAR 모델의 전반적인 성능 차이에 대한 근본적인 이유도 분석한다. 각 기술의 장단점 을 개요로 제공하고 성능 향상을 위한 제안도 제시하고자 한다.

Recently, many studies have been conducted to improve quality by applying machine learning models to semiconductor manufacturing process data. However, in the semiconductor manufacturing process, the ratio of good products is much higher than that of defective products, so the problem of data imbalance is serious in terms of machine learning. In addition, since the number of features of data used in machine learning is very large, it is very important to perform machine learning by extracting only important features from among them to increase accuracy and utilization. This study proposes an anomaly detection methodology that can learn excellently despite data imbalance and high-dimensional characteristics of semiconductor process data. The anomaly detection methodology applies the LIME algorithm after applying the SMOTE method and the RFECV method. The proposed methodology analyzes the classification result of the anomaly classification model, detects the cause of the anomaly, and derives a semiconductor process requiring action. The proposed methodology confirmed applicability and feasibility through application of cases.

When developing a new motor, a high-speed load test is performed using dynamo equipment to calculate the efficiency of the developed motor using the collected dynamo data. When connecting the test motor and the dynamo used as a load, abnormal noise and vibration may occur in the test equipment rotating at high speed due to misalignment of the connecting shaft and looseness of the connection, which may lead to a safety accident. In this study, three vibration sensors are attached to the surface of bearing parts of the test motor to measure the vibration value, and statistics such as kurtosis, skewness, and percentiles are obtained in order to clearly express the pattern of the measurement data. With these statistics, machine learning models are developed. The developed model in this way can be used as a diagnostic system that can detect abnormal conditions of the motor test equipment through monitoring the motor vibration data during the motor test.

본 연구는 선박용 공기압축기의 상태기반보전 시스템에 필요한 이상치 탐지 알고리즘 적용에 대한 실험적 연구로서 고장모사 실험을 통해 시계열 전류 센서 데이터를 이용한 이상탐지 적용 가능성을 확인하였다. 고장 유형 10개에 대해 실험실 규모의 고장 모사 실험을 수행하여 정상 운전데이터와 고장 데이터를 구축하였다. 실험 결과 구축된 이상탐지 모델은 시계열 데이터의 주기에 변화를 유발하는 이상은 잘 탐지하는 반면 미세한 부하 변동에 대한 탐지 성능은 떨어졌다. 또한 오토인코더를 이용한 시계열 이상탐지 모델은 입력 시 퀀스의 길이와 초모수 조정에 따라 이상 탐지 성능이 상이한 것으로 나타났다.

This paper proposes an outlier detection model based on machine learning that can diagnose the presence or absence of major engine parts through unsupervised learning analysis of main engine big data of a ship. Engine big data of the ship was collected for more than seven months, and expert knowledge and correlation analysis were performed to select features that are closely related to the operation of the main engine. For unsupervised learning analysis, ensemble model wherein many predictive models are strategically combined to increase the model performance, is used for anomaly detection. As a result, the proposed model successfully detected the anomalous engine status from the normal status. To validate our approach, clustering analysis was conducted to find out the different patterns of anomalies the anomalous point. By examining distribution of each cluster, we could successfully find the patterns of anomalies.

Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.

Multivariate control charts are widely needed to monitor the production processes in various industry. Among the several multivariate control charts, control chart have been used of the typical technique. The control chart shows a statistic that represents observed variables and monitors the process through the statistic. In this case, the statistic generally have the limit that any variables affect to that statistic. To solve this problem, some studies have been progressed in the meantime. The representative method is to disassemble total statistic into each of the variable value and make a decision the parameters with large values than threshold value as a main cause. However, the means is requested to follow the normal distribution. To settle this problem, the bootstrap technique that don't be needed the probability distribution was introduced in 2011. In this paper, I introduced the detection technique of the fault variables using multiple regression analysis. There are two advantages; First, it is possible to use less samples than the ascertainment technique applying to bootstrap. Second, the technique using the regression analysis is easy to apply to the actual environment because the global threshold value is used.

구조물 이상 탐지를 위해 외력에 의한 광섬유의 모드변환을 이용한 새로운 광섬유 센서를 고안하고 제작하였다. 이러한 광섬유 센서는 민감도가 매우 좋으며, 크기가 작고, 전자파에 매우 둔감한 장점들이 있다. 이 센서는 적외선영역에서의 단일모드 광섬유와 635nm의 레이저 다이오드로 구성하였기 때문에 광섬유의 끝단에서의 횡모드는 가우시안 분포가 아닌 다른 형태의 횡모드 형태가 생긴다. 이 광섬유 중간을 구조물에 부착한 후, 구조물에 외력을 인가하면 광섬유 횡모드의 분포 변화가 생기고, 이를 감지함으로써 구조물 이상 유무를 판독할 수 있다. 본 논문에서는 광섬유 센서를 부착한 알루미늄 보를 변형시킴으로써 광섬유 센서의 횡모드 변화를 조사하였다. 이 실험결과 구조물의 이상상태를 감지할 적당한 신호를 얻을 수 있었으며, 구조물의 이상유무를 측정할 수 있는 광섬유 센서로의 가능성을 확인할 수 있었다.

Recently, measurement monitoring is actively used for safety management of facilities. However, since the field measurement data contains many outliers, a preprocessing process is required for reliable behavior analysis of the data. In this paper, we present a detection method of time series outliers and its applications. And we propose the precaution for the preprocessing process.

상수도관의 파열은 과도한 압력, 노후화, 온도변화나 지진 등에 의한 지반이동에 의해 발생한다. 상수도관 파열이 대규모 단수, 싱크홀 등과 같은 더 심각한 피해 이어지지 않도록 신속하게 탐지 및 대응하는 것이 중요하다. 본 연구에서는 상수도관 파열 탐지를 위해 개선 Western Electric Company (WECO) 방법을 개발하였다. 개선 WECO 방법은 통계적공정관리기법 중 하나인 기존 WECO 방법에 임계치 조정자(w)를 추가하여 대상 네트워크에 적합한 이상탐지 의사결정을 할 수 있도록 했다. 개발된 개선 WECO 방법을 미국 텍사스 오스틴 관망에 적용 및 검증하였다. 상수도관 파열 발생 시 측정한 비정상데이터와 수요량 변동만 고려한 정상데이터를 이용하여 기존 및 개선 WECO 방법을 비교하였다. 최적 임계치 조정자 w값을 결정하기 위해 민감도 분석을 수행하였으며, 다양한 계측시간 간격 데이터(dt = 5, 10, 15분 등)의 영향도 분석하였다. 각 경우 별 탐지 성능은 탐지확률, 오경보확률, 평균탐지시간을 계산하여 비교하였다. 본 연구에서는 도출된 결과를 바탕으로 WECO 방법을 실제 상수도관 파열 탐지에 적용하기 위한 가이드라인을 제공한다.