• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.2
• /
• pp.129-143
• /
• 2019

As the importance of autonomous vehicle safety is emphasized, the application of ISO-26262, a development verification guideline for improving safety and reliability, and the safety verification of autonomous vehicles are becoming increasingly important, in particular, SAE standard level 3 or higher level autonomous vehicles detect and decision the surrounding environment instead of the human driver. Therefore, if there is and failure or malfunction in the autonomous driving function, safety may be seriously affected. So autonomous vehicles, it is essential to apply and verity the safety concept against failure and malfunctions. In this study, we study the fault injection scenarios for safety evaluation and verification of autonomous vehicles using ISO-26262 part3 process and STPA were studied and safety measures for safety concept design were studied through simulation bases fault injection test.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.280-288
• /
• 2022

This study examined the diagnostics of abnormalities and faults of equipment, whose rotational speed changes even during regular operation. The purpose of this study was to suggest a procedure that can properly apply machine learning to the time series data, comprising non-stationary characteristics as the rotational speed changes. Anomaly and fault diagnosis was performed using machine learning: k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest. To compare the diagnostic accuracy, an autoencoder was used for anomaly detection and a convolution based Conv1D was additionally used for fault diagnosis. Feature vectors comprising statistical and frequency attributes were extracted, and normalization & dimensional reduction were applied to the extracted feature vectors. Changes in the diagnostic accuracy of machine learning according to feature selection, normalization, and dimensional reduction are explained. The hyperparameter optimization process and the layered structure are also described for each algorithm. Finally, results show that machine learning can accurately diagnose the failure of a variable-rotation machine under the appropriate feature treatment, although the convolution algorithms have been widely applied to the considered problem.

• Proceedings of the Society of Korea Industrial and System Engineering Conference
• /
• 2002.05a
• /
• pp.387-396
• /
• 2002

Batch processes are a significant class of processes in the process industry and play an important role in the production of high quality speciality materials. Examples include the production of semiconductors, chemicals, pharmaceuticals, and biochemicals. With on-line sensors connected to most batch processes, massive amounts of data are being collected routinely during the batch on easily measured process variables such as temperatures, pressures, and flowrates. In this paper, multivariate SPC charts for on-line monitoring of the progress of new batches are developed which utilize the information in the on-line measurements in real-time. We propose the formation of statistical model which describes the normal operation of a batch at each time interval during the batch operation. An on-line monitoring scheme based on the proposed method can handle both cross-correlation among process variables at any one time and auto-correlation over time. And the control limits for the monitoring charts are established from sound statistical framework unlike previous researches which use the external reference distribution. The proposed charts perform real-time, on-line monitoring to ensure that the batch is progressing in a manner that will lead to a high-quality product or to detect and indicate faults that can be corrected prior to completion of the batch. This approach is capable of tracking the progress of new batch runs, identifying the time periods in which the fault occurred and detecting underlying cause.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2009.06a
• /
• pp.11-12
• /
• 2009

In this paper, we propose a high voltage driver IC(HVIC) for LCD and PDP TV power supply. The proposed circuit is included novel a shoot-through protection and a pulse generation circuit for the high voltage driver IC. The proposed circuit has lower variation of dead time and pulse-width about a variation of a process and a supply voltage than a conventional circuit. Especially, the proposed circuit has more excellent pulse-width matching of set and reset signals than the conventional circuit. Also the proposed pulse generation circuit prevent from fault operations using a logic gate. Dead time and pulse-width of the proposed circuit are typical 250 ns, and its variation is maximum 170 ns(68 %) about a variation of a process and a supply voltage. The proposed circuit is designed using $1\;{\mu}m$ 650 V BCD process parameter, and a simulation is carried out using Spectre.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.2
• /
• pp.94-102
• /
• 2000

This paper presents a new FDI scheme based on dynamic fuzzy model(DFM) for the unknown nonlinear system, which can detect and isolate process faults continuously over all ranges of operating condition. The dynamic behavior of a nonlinear process is represented by a set of local linear models. The parameters of the DFM are identified by an on-line methods. The residual vector of the FDI system is consisted of the parameter deviations from nominal model and the set of grade of membership values indicating the operating condition of the nonlinear process. The detection and isolation of faults are performed via a neural network classifier that are learned the relationship between the residual vector and fault type. We apply the proposed FDI scheme to the FDI system design for a two-tank system and show the usefulness of the proposed scheme.

• Journal of the Korean Institute of Gas
• /
• v.7 no.3 s.20
• /
• pp.1-6
• /
• 2003

This study has suggested a decision method which determine optimum investment level for safety management by process risk assessment at gas governor station. Hazard and operability study(HAZOP), fault tree analysis(FTA) and consequence analysis(CA) were carried out and potential accident cost and benefit for safety management were estimated. As a result, we could be found the trend of safety cost and benefit by the nonlinear regression method and could be determined the optimum investment level for safety management from analysis of safety management cost and potential accident cost.

• Journal of Advanced Navigation Technology
• /
• v.19 no.1
• /
• pp.80-84
• /
• 2015

This paper suggested an error detection process based on multimedia computer supported cooperative works (CSCW) for industry safety environment. This system is suitable for detecting software fault for multimedia CSCW. It is necessary of detecting an error for the system to be protected by reactivity of media service instance instead of breaking process of session. This paper describes a performance analysis of an error detecting system of function comparison of proposed method with other method based multimedia CSCW for explosives as an example of industry safety environment.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.3
• /
• pp.372-381
• /
• 2006

The purpose of this study was to develop a process management system to manage ingot fabrication and improve ingot quality. The ingot is the first manufactured material of wafers. Trace parameters were collected on-line but measurement parameters were measured by sampling inspection. The quality parameters were applied to evaluate the quality. Therefore, preprocessing was necessary to extract useful information from the quality data. First, statistical methods were used for data generation. Then, modeling was performed, using the generated data, to improve the performance of the models. The function of the models is to predict the quality corresponding to control parameters. Secondly, rule extraction was performed to find the relation between the production quality and control conditions. The extracted rules can give important information concerning how to handle the process correctly. The dynamic polynomial neural network (DPNN) and decision tree were applied for data modeling and rule extraction, respectively, from the ingot fabrication data.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2010.02a
• /
• pp.473-473
• /
• 2010

Plasma is widely used in various commercial etchers and chemical vapor deposition. Unfortunately, real-time plasma process monitoring is still difficult. Some methods of plasma diagnosis is improved, however, it is possible for real-time plasma diagnosis to use non-intrusive probe only. In this research, the object is to investigate the suitability of using impedance analysis and optical emission spectroscopy (OES) for real-time plasma process monitoring. It is assumed that plasma system is a equivalent circuit. Therefore, V-I probe is used for measuring impedance, which can be a new non-intrusive probe for plasma diagnosis. From impedance data, we tried to analyse physical properties of plasma. And OES, the other method of plasma diagnosis, is a typical non-intrusive probe for analyzing chemical properties. The amount of the OES data is typically large, so this poses a difficulty in extracting relevant information. To solve this problem, principal component analysis (PCA) can be used. For fundamental information, Ar plasma and $O_2$ plasma are used in this experiment. This method can be applied to real-time endpoint and fault detections.

• Nuclear Engineering and Technology
• /
• v.52 no.12
• /
• pp.2687-2698
• /
• 2020

Most of the machine learning-based intrusion detection tools developed for Industrial Control Systems (ICS) are trained on network packet captures, and they rely on monitoring network layer traffic alone for intrusion detection. This approach produces weak intrusion detection systems, as ICS cyber-attacks have a real and significant impact on the process variables. A limited number of researchers consider integrating process measurements. However, in complex systems, process variable changes could result from different combinations of abnormal occurrences. This paper examines recent advances in intrusion detection algorithms, their limitations, challenges and the status of their application in critical infrastructures. We also introduce the discussion on the similarities and conflicts observed in the development of machine learning tools and techniques for fault diagnosis and cybersecurity in the protection of complex systems and the need to establish a clear difference between them. As a case study, we discuss special characteristics in nuclear power control systems and the factors that constraint the direct integration of security algorithms. Moreover, we discuss data reliability issues and present references and direct URL to recent open-source data repositories to aid researchers in developing data-driven ICS intrusion detection systems.