• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.11 no.4
• /
• pp.154-159
• /
• 2012

Condition monitoring(CM) is a method based on Non-destructive test(NDT). Therefore, recently many kind of NDT were applied for CM. Acoustic emission(AE) is widely used for the early detection of faults in rotating machinery in these days also. Because its sensitivity is higher than normal accelerometers and it can detect low energy vibration signals. A machine tool consist of many parts such as the bearings, gears, process tools, shaft, hydro-system, and so on. Condition of Every part is connected with product quality finally. To increase the quality of products, condition monitoring of the components of machine tool is done completely. Therefore, in this paper, acoustic emission method is used to detect a machine fault seeded in a gearbox. The AE signals is saved, and power spectrums and feature values, peak value, mean value, RMS, skewness, kurtosis and shape factor, were determined through Matlab.

• International Journal of Korean Welding Society
• /
• v.1 no.1
• /
• pp.7-12
• /
• 2001

Real time monitoring has become critical as the use of laser welding increases. Plasma and spatter are measured and used as the signal for estimating weld quality. The estimating algorithm was made using the fuzzy pattern recognition with the area of data that is beyond the tolerance boundary. Also, an algorithm that detects the spatter and the localized defect was created in order to kd the partially produced pit and the sudden loss of weld penetration. These algorithms were used in quality monitoring of the $CO_2$ laser tailored blank weld. Statistical program that can display the laser weld quality result and the signal transition was made for the first stage of the remote control system.

• Industrial Engineering and Management Systems
• /
• v.14 no.4
• /
• pp.392-400
• /
• 2015

Monitoring of plasma etch processes for fault detection is one of the hallmark procedures in semiconductor manufacturing. Optical emission spectroscopy (OES) has been considered as a gold standard for modeling plasma etching processes for on-line diagnosis and monitoring. However, statistical quantitative methods for processing the OES data are still lacking. There is an urgent need for a statistical quantitative method to deal with high-dimensional OES data for improving the quality of etched wafers. Therefore, we propose a robust relevance vector machine (RRVM) for regression with statistical quantitative features for modeling etch rate and uniformity in plasma etch processes by using OES data. For effectively dealing with the OES data complexity, we identify seven statistical features for extraction from raw OES data by reducing the data dimensionality. The experimental results demonstrate that the proposed approach is more suitable for high-accuracy monitoring of plasma etch responses obtained from OES.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.3
• /
• pp.193-197
• /
• 2012

This paper focuses on identifying which appliance is currently operating by analyzing electrical load signature for home energy monitoring system. The identification framework is comprised of three steps. Firstly, specific appliance features, or signatures, were chosen, which are DC (Duty Cycle), SO (Slope of On-state), VO (Variance of On-state), and ZC (Zero Crossing) by reviewing observations of appliances from 13 houses for 3 days. Five appliances of electrical rice cooker, kimchi-refrigerator, PC, refrigerator, and TV were chosen for the identification with high penetration rate and total operation-time in Korea. Secondly, K-NN and Naive Bayesian classifiers, which are commonly used in many applications, are employed to estimate from which appliance the signatures are obtained. Lastly, one of candidates is selected as final identification result by majority voting. The proposed identification frame showed identification success rate of 94.23%.

• International Journal of Korean Welding Society
• /
• v.3 no.1
• /
• pp.45-50
• /
• 2003

Welding using lasers can be mass-produced in high speed. In the laser welding, performing real-time monitoring system of the welding quality is very important in enhancing the efficiency of welding. In this study, the plasma and molten metal which are generated during laser welding were measured using the UV sensor and IR sensors. The results of laser welding were classified into five categories such as optimal heat input, little low heat input, low heat input, partial joining due to gap mismatch, and nozzle deviation. Also, a system was formulated which uses the measured signals with a fuzzy pattern recognition method which is used to perform real-time evaluation of the welding quality and the defects which can occur in laser welding.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.1
• /
• pp.185-193
• /
• 1997

This paper presents the on-line monitoring of the surface roughness in a face milling operation. The cut- ting force was used to monitor the surface roughness, since the insert run-outs not only deteriorate surface roughness but also change cutting force. AR model and band energy method were taken to extract the fea- tures from the cutting force. The features extracted from AR modelling are more accurate about the moni- toring than those from band energy method, whereas, the computing speed of the former is slow. An artifi- cal neural network discriminated the level of the surface roughness by using the features extracted via signal processing.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.124-128
• /
• 2023

Semiconductor engineers have long sought to enhance the energy efficiency of mobile semiconductors by reducing their voltage. During the final stages of the semiconductor manufacturing process, the screening and evaluation of voltage is crucial. However, determining the optimal test start voltage presents a significant challenge as it can increase testing time. In the semiconductor manufacturing process, a wealth of test element group information is collected. If this information can be controlled to predict the test voltage, it could lead to a reduction in testing time and increase the probability of identifying the optimal voltage. To achieve this, this paper is exploring machine learning techniques, such as linear regression and ensemble models, that can leverage large amounts of information for voltage prediction. The outcomes of these machine learning methods not only demonstrate high consistency but can also be used for feature engineering to enhance accuracy in future processes.

• Journal of Korean Institute of Industrial Engineers
• /
• v.42 no.6
• /
• pp.370-376
• /
• 2016

Manufacturing data analysis and its applications are getting a huge popularity in various industries. In spite of the fast advancement in the big data analysis technology, however, the manufacturing quality data monitored from the automated inspection system sometimes is not reliable enough due to the complex patterns of product quality. In this study, thus, we aim to define the level of trusty of an automated quality inspection system and improve the reliability of the quality inspection data. By correlation analysis and feature selection, this paper presents a method of improving the inspection accuracy and efficiency in an SVM-based automatic product quality inspection system using thermal image data in an auto part manufacturing case. The proposed method is implemented in the sealer dispensing process of the automobile manufacturing and verified by the analysis of the optimal feature selection from the quality analysis results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.265-269
• /
• 2008

Home health care with compact wearable units sounds to be a convenient solution for the elderly people living independently. This paper presents a method to detect fall from the other activities of daily living and also to classify those activities. This kind of ambulatory monitoring enables them to get an emergency help in the case of the fatal fall event and can provide their general health status by observing the activities being performed in daily life. A tri-axial accelerometer sensor is used to get the acceleration anomalies associated with the user's movements. The three axis acceleration data are transferred to the base station sensor node via an IEEE 802.15.4 compliant zigbee module. The base station sensor node sends the data to base station PC for an offline processing. This work shows the feature set preparation using the principal component analysis (PCA) for the designing of neural network. The work includes the most common activities of daily living (ADL) like Rest, Walk and Run along with the detection of fall events from ADL. The angle from the vertical is found to be the most significant feature parameter for classification of fall while mean, standard deviation and FFT coefficients were used as the feature parameter for classifying the other activities under consideration. The accuracy for detection of fall events is 86%. The overall accuracy for ADL and fall is 94%.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.9
• /
• pp.433-440
• /
• 2016

Railway point machines act as actuators that provide different routes to trains by driving switchblades from the current position to the opposite one. Since point failure can significantly affect railway operations with potentially disastrous consequences, early stress detection of point machine is critical for monitoring and managing the condition of rail infrastructure. In this paper, we propose a stress detection method for point machine in railway condition monitoring systems using sound data. The system enables extracting sound feature vector subset from audio data with reduced feature dimensions using feature subset selection, and employs support vector machines (SVMs) for early detection of stress anomalies. Experimental results show that the system enables cost-effective detection of stress using a low-cost microphone, with accuracy exceeding 98%.