• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1328-1336
• /
• 2019

To maintain the safe and optimal performance of batteries, accurate estimation of state of charge (SOC) is critical. In this paper, Long short-term memory network (LSTM) based on the artificial intelligence algorithm is applied to address the problem of the conventional coulomb-counting method. Different discharge cycles are concatenated to form the dataset for training and verification. In oder to improve the quality of input data for learning, preprocessing was performed. In addition, we compared learning ability and SOC estimation performance according to the structure of LSTM model and hyperparameter setup. The trained model was verified with a UDDS profile and achieved estimated accuracy of RMSE 0.82% and MAX 2.54%.

• Journal of Bio-Environment Control
• /
• v.23 no.4
• /
• pp.391-400
• /
• 2014

The number of large scale greenhouses has recently been increasing to cope with mass consumption of agricultural product. Korean government announced a new development plan for constructing greenhouse complex in reclaimed lands for the purpose of improvement in exports and activation of domestic market of agricultural product. Wind environment in the reclaimed land is totally different from that of inland area, and it can give a strong influence on ventilation performance of naturally ventilated greenhouse facilities. In this study, internal airflow analysis of naturally ventilated greenhouse built on a reclaimed land was conducted using wind tunnel and PIV for validation research. Later, the PIV measured results will be used to improve the accuracy of 3 dimensional CFD simulation in the future. Wind profile at a reclaimed land was produced using ESDU program and it was applied to the wind tunnel. The calculated error was only 5% and 0.96 of correlation coefficient, implying that the computed profiles were designed properly. From the measured results, when external wind speed changed from $1m{\cdot}s^{-1}$ to $1.5m{\cdot}s^{-1}$, air velocities inside the greenhouse which PIV measured were also increased proportionately in case of both side vent open and side-roof vent open. Considering reduced ratio of air velocity inside the greenhouse, it was measured a minimum of 40% in case of side vent and 30% in case of side-roof vent compared with external wind speed from each vent type. From the quantitative and qualitative PIV analysis, the PIV measured results indicated that there were well ventilated and stagnant areas in the greenhouse according to external wind condition as well as ventilation design.

• Composites Research
• /
• v.17 no.4
• /
• pp.68-73
• /
• 2004

An analytical study was conducted to characterize the fatigue crack growth behavior of pre-cracked aluminum plates repaired with asymmetric bonded composite patch. For single-sided repairs, due to the asymmetry and the presence of out-of$.$plane bending, crack front shape would become skewed curvilinear started from a uniform through-crack profile, as observed from Previous studies. Therefore, for the accurate investigation of fatigue behavior, it is necessary to predict the actual crack front evolution and take it into consideration in the analysis. In this study, the fatigue analysis of single-sided repairs considering crack front shape development was conducted by implementing three-dimensional successive finite element method coupled with linear elastic fracture mechanics (LEFM) concept, which enables the growing crack front to be directly traced and modeled in a step by step way. Through conducting present analysis technique, crack path of the patched plate as well as the fatigue life was evaluated with sufficient accuracy. The analytical predictions of both the crack front shape evolution and the fatigue life were in good agreement with the experimental observations.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.2
• /
• pp.237-243
• /
• 2010

This paper presents a study on the helical gear inspection system for application to vehicle transmission gear manufacturing lines. The special gear profile inspection system is not suitable for manufacturing lines due to the measuring time. The master gear method, which was used in this study and compared with the machined gear in the line, is more efficient and economical. In this paper, three helical gear inspection parameters were of concern: nick, run-out, and PCD (pitch circle diameter) error. To evaluate its influence on the accuracy, the gear measuring system was also studied. This system can be useful in practical vehicle transmission gear manufacturing lines, where imported equipment is currently being used.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.599-603
• /
• 2003

This paper present an error compensation system and On-Machine Measurement(OMM) system for improving the machining accuracy of ultra-precision lathe. The Fast-Tool-Servo(FTS) driven by a piezoelectric actuator is applied for error compensation system. The controller is implemented on the 32bit DSP for feedback control of piezoelectric actuator. The control system is designed to compensates three kinds of machining errors such as the straightness error of X-axis slide, the thermal growth error of the spindle. and the squareness between spindle and X-axis slide. OMM is preposed to measure the finished profile of workpiece on the machine-tool using capacitive sensor with highly accurate ruby tip probe guided by air bearing. The data acquisition system is linked to the CNC controller to get the position of each axis in real-time. Through the experiments, it is founded that the thermal growth of spindle and tile squareness error between spindle and X-axis slide influenced to machining error more than straightness error of X-axis slide in small travel length. These errors were simulated as a sinusoidal signal which has very low frequency and the FTS could compensate the signal less than 30 m. The implemented OMM system has been tested by measuring flat surface of 50 mm diameter and shows measurement error less than 400 mm

• Transactions of the KSME C: Technology and Education
• /
• v.3 no.3
• /
• pp.175-181
• /
• 2015

Because internal space of combat vehicle reachs about $80^{\circ}C$ at high temperature period, Proximity Sensor exposed high temperature and humidity, which has function to sense the distance and transfer signal for control unit, have enlarged sensing distance and finally locked on. Malfunction of sensing itself occur frequently, therefore we carried out cause analysis and improvement. We accomplish improvement activity secondly. Through-out many trial and error, we find out that malfunction of sensor occur at high temperature circumstance. To improve, the another Emitter Coil is added to increase voltage difference and improve sensing accuracy about 5~10 times. And we accomplish design improvement to dull temperature and humity change after increasing molding surface to add vibration and shock resistance. We prove that the improved product do not fail after enduring 136hr at $85^{\circ}C$ temperature and 85% relative humidity circumstance chamber.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2006.06a
• /
• pp.281-284
• /
• 2006

The resistive V dipole (RVD) is a V antenna with both arms loaded with the continuous Wu-King resistive profile. The RVD has many advantages for surface and subsurface probing, such as the ability to radiate a short pulse in a desired direction. The radiated pulse is simply related to the input pulse, e.g., derivative. In addition, it mostly eliminates the multiple reflections between the surface of the ground and the antenna because of its low radar cross section. The drawbacks of the RVD include the high input impedance and the difficulty in implementation. This paper presents ways to improve the accuracy and easiness of the implementation and to improve the low-frequency performance while maintaining the characteristics of the V antenna that are good for probing applications. The implemented antenna is used to form a bistatic radar to scan targets underground, and the result is imaged.

• Korean Journal of Optics and Photonics
• /
• v.28 no.2
• /
• pp.53-58
• /
• 2017

This paper presents the design and fabrication of a planar nano-diffraction grating for an integrated miniature spectrometer module. The proposed planar nano-diffraction grating consists of nonuniform periods, to focus the reflected beams from the grating's surface, and an asymmetrical V-shaped groove profile, to provide uniform diffraction efficiency in the wavelength range from 400 to 650 nm. Also, to fabricate the nano-diffraction grating using low-cost UV-NIL technology, we analyzed the FT-IR spectrum of a uvcurable resin and optimized the conditions for the UV curing process. Then, we precisely fabricated the polymeric nano-diffraction grating within 5 nm in dimensional accuracy. The integrated spectrometer module using the fabricated polymeric planar nano-diffraction grating provides spectral resolution of 5 nm and spectral bandwidth of 250 nm. Our integrated spectrometer module using a polymeric planar nano-diffraction grating serves as a quick and easy solution for many spectrometric applications.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.5
• /
• pp.47-52
• /
• 2011

Vehicle classification data are considerably used in the almost all fields of transportation planning and engineering. Highway agencies use a large number of vehicle classification schemes. Vehicles on the national highway are classified by 12-Category classification system, using number of axles, distances between axles, vehicle length, overhang, and other factors. In the case of using existing axle-sensor-based classification counters (that is, 12-category classification system), two-axle vehicles(Class 1 to 4) can be erroneously classified because a passenger vehicle becomes larger and similar with class 3 and 4. In this reason, this study proposes the vehicle classification scheme based on using vehicle height profiles obtained by a laser sensors. Also, the accuracy of the proposed method are tested through a field study.

• Journal of the Korea Convergence Society
• /
• v.9 no.10
• /
• pp.21-28
• /
• 2018

To help users who are experiencing difficulties finding the right learning course corresponding to their level of proficiency, we developed a recommendation model for personalized learning course for Intelligence Tutoring System(ITS). The Personalized Learning Course Recommendation model for ITS analyzes the learner profile and extracts the keyword by calculating the weight of each word. The similarity of vector between extracted words is measured through the cosine similarity method. Finally, the three courses of top similarity are recommended for learners. To analyze the effects of the recommendation model, we applied the recommendation model to the Women's ability development center. And mean, standard deviation, skewness, and kurtosis values of question items were calculated through the satisfaction survey. The results of the experiment showed high satisfaction levels in accuracy, novelty, self-reference and usefulness, which proved the effectiveness of the recommendation model. This study is meaningful in the sense that it suggested a learner-centered recommendation system based on machine learning, which has not been researched enough both in domestic, foreign domains.