Fault Diagnosis & Anomaly Detection
Prognostics and health management (PHM) / Sensor Fusion & Bigdata Analysis
IoT based equipment monitoring & detection, machine learning based anomaly detection
This study performs to establish a guideline for machinery condition monitoring, equipment condition monitoring and diagnosis system, building a dataset for machine learning, and analyzing multi-source heterogeneous data(image, sound, vibration, etc.) integration and fusion. We focus on the statistical model and machine learning based abnormal state classification, and data-driven anomaly detection using AI.
Advanced Deep Temporal Clustering Model with Unsupervised Data for Fault Diagnosis
This study proposes an ensemble model that combines unsupervised learning and supervised learning.
To verify this model, data augmentation was applied to the original time-series-based mechanical vibration dataset, which had unbalanced samples that lowered the performance of the abnormal anomaly detection model in this study. In addition, an image-based analysis was performed by converting time-series-based raw-signal data to Mel-spectrogram images, thereby achieving better performance in the fault diagnosis system to which data augmentation was applied. This indicates that the proposed anomaly detection model can be expected to improve the productivity of mechanical equipment in industrial settings.
Anomaly Detection in Semiconductor Manufacturing Process: Boosted Stacking Ensemble Machine Learning Method
This study aims to classify wafer map defects more effectively and to derive robust algorithms even for datasets with insufficient defect patterns.
Since the proposed algorithm shows better performance than the existing ensemble classifiers even for insufficient defect patterns, the results of this study will have a great effect on improving the product quality and yield of the actual semiconductor manufacturing process.
Anomaly Detection & ML based Analysis
Machine anomaly detection using sound spectrogram images in industrial processes
This study focus on the improvement of the equipment condition and operation efficiency by using ML. In this study, we investigate the abnormality detection in the industrial process state based on time series analysis. Beside, we develop the ensemble models in machine learning combine the decisions from multiple models to improve the overall performance. This study is able to guarantee high accuracy performance compared to the previous statistical methods, which are traditional analysis methods and model-based studies.