• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.11
• /
• pp.2446-2452
• /
• 2012

In order to meet the recently enhanced emission standards at home and abroad, it is necessary to develop the CRDI ECU control algorithm that users can adjust fuel injection timing and amount in response to their needs. Therefore, this study developed the simulator for knocking analysis that enables knocking discrimination and engine balance correction applicable to the ECU exclusive to the industrial CRDI engine. The purpose of this study is to provide the driver-oriented diagnostic service that enable drivers to diagnose vehicles directly by developing diagnostic devices for vehicles with ths use of the results of the developed simulator for knocing analysis according to the OBD-II standards. For this purpose, this study aims to improve the fuel efficiency of vehicles by proposing the S/W design method of the OBD-II diagnosis device that can provide real-time communcations with the use of wired system and bluetooth module as a wireless system to send and recevice automobile fault diagnosis signal and sensor output signal, and to suggest an improvement for engine efficiency by minimizing the generation of harmful exhaust gas.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.299-306
• /
• 2022

In recent, sensors embedded in robots, equipment, and circuits have become common, and research for diagnosing device failures by learning measured sensor data is being actively conducted. This failure diagnosis study is divided into a classification model for predicting failure situations or types and a regression model for numerically predicting failure conditions. In the case of a classification model, it simply checks the presence or absence of a failure or defect (Class), whereas a regression model has a higher learning difficulty because it has to predict one value among countless numbers. So, the reason that regression modeling is more difficult is that there are many irregular situations in which it is difficult to determine one output from a similar input when predicting by matching input and output. Therefore, in this paper, we focus on input and output data with periodicity, analyze the input/output relationship, and secure regularity between input and output data by performing sliding window-based input data patterning. In order to apply the proposed method, in this study, current and temperature data with periodicity were collected from MMC(Modular Multilevel Converter) circuit system and learning was carried out using ANN. As a result of the experiment, it was confirmed that when a window of 2% or more of one cycle was applied, performance of 97% or more of fit could be secured.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.10
• /
• pp.5899-5905
• /
• 2014

Faults in electric power system can be a critical problem for vehicles. The system durability is determined mainly by the durability of their components and operating conditions. Monitoring the conditions of the electric power system may be necessary because it is very difficult to predict precisely when it will fail. Therefore, the aim of this study was to develop a diagnosis system for an electric power system of a vehicle. The alternator voltage, excitation voltage, lamp voltage, battery voltage, and engine rpm from a crank angle sensor are monitored continuously and the system fault can be then detected in real time. NI USB- 9201 DAQ and LabVIEW SW have been used to measure the voltages and analyze the data. Compared to conventional measurements for only each component, an integrated and portable measurement method was developed. In addition to the monitoring the electric power system in real time, the saved data from the measurement also provides valuable information to improve the durability of the components.