• 한국정보시스템학회지:정보시스템연구
• /
• 제31권3호
• /
• pp.197-220
• /
• 2022

Purpose The purpose of this study is to identifies the demand pattern categorization of repair parts of Automotive After-sales Service(A/S) and proposes a demand prediction model for Auto repair parts using Long Short-Term Memory (LSTM) of artificial neural networks (ANN). The optimal parts inventory quantity prediction model is implemented by applying daily, weekly, and monthly the parts demand data to the LSTM model for the Lumpy demand which is irregularly in a specific period among repair parts of the Automotive A/S service. Design/methodology/approach This study classified the four demand pattern categorization with 2 years demand time-series data of repair parts according to the Average demand interval(ADI) and coefficient of variation (CV²) of demand size. Of the 16,295 parts in the A/S service shop studied, 96.5% had a Lumpy demand pattern that large quantities occurred at a specific period. lumpy demand pattern's repair parts in the last three years is predicted by applying them to the LSTM for daily, weekly, and monthly time-series data. as the model prediction performance evaluation index, MAPE, RMSE, and RMSLE that can measure the error between the predicted value and the actual value were used. Findings As a result of this study, Daily time-series data were excellently predicted as indicators with the lowest MAPE, RMSE, and RMSLE values, followed by Weekly and Monthly time-series data. This is due to the decrease in training data for Weekly and Monthly. even if the demand period is extended to get the training data, the prediction performance is still low due to the discontinuation of current vehicle models and the use of alternative parts that they are contributed to no more demand. Therefore, sufficient training data is important, but the selection of the prediction demand period is also a critical factor.

• 대한교통학회지
• /
• 제30권1호
• /
• pp.31-43
• /
• 2012

한국이 UN 자동차 법규 표준화 기구(WP29) 주관의 소형차 배출가스 시험방법 국제 표준화(WLTP/DHC) 연구에 참여하게 됨에 따라 우리나라의 도로 종류 별, 주행 시간대 별 주행패턴 측정이 요구되었다. 이에 본 연구에서는 WP29에서 제안한 주행패턴 표준화 방법을 토대로, 우리나라의 도로 교통 특성을 반영한 실 도로 주행패턴을 측정하고, 대표성을 갖는 도로 종류 별 주행 시간대별 총 7가지 유형의 주행패턴을 분석하였다. 이를 위해 이동식 차량활동도 모니터링 장비(PAMS)를 이용하여 35,410km의 실주행자료를 수집하였으며, 각 유형별로 분석된 주행패턴은 서로 유의한 차이가 있는 것으로 나타났다.

• 한국도로학회논문집
• /
• 제17권4호
• /
• pp.1-9
• /
• 2015

PURPOSES : The purpose of this study is to revise the weight to power ratio of the representative truck in S. Korea. So far, S. Korea has been using the unit lb/hp, and the construction machines were not considered in the evaluation of the performance of trucks. METHODS : This study was performed to recommend the use of ISO system of units, and to analyze the weight to power ratios of the representative trucks in S. Korea, including the dump trucks, concrete mixer trucks, and asphalt and concrete diffusers. RESULTS: From this study, the 85 percentile value of the weight to power ratio of the trucks in S. Korea's was found to be 103.6 kg/kw. CONCLUSIONS : The performance standard for the representative truck has to be increased upward, considering the travel pattern of the dump trucks, concrete mixers, and asphalt and concrete diffuser trucks, travel distances, narrow area (work zone) of operation, and the saving in construction budget for climbing lane. Based on this study, the weight to power ratio of the representative truck in S. Korea could possibly be revised to 100~110 kg/kW.

• 한국전기전자재료학회논문지
• /
• 제24권12호
• /
• pp.1018-1022
• /
• 2011

Nowadays, with improvement of economical income and life qualities, life pattern changes have been brought such as increasing of avocational activities. Consequently, following those life trends, utilization of car is getting increased. Thus, the perceptions of car have been changed from the only means of transport in the past to a 2nd residental space. that is why the car's endo environmental factors are getting so important. Air conditioner regulating air ventilization in vehicle's indoor automatically sets the right temperature based on the differences of indoor and outdoor's temperature with development of advanced functions to provide better environmental qualities in vehicle. However, even those advanced techniques for functional development are got so diverse though, the essential technique for preventing the growth of bateria and mold inside of the air conditioner are not even severals. Especially, evaporator one of the vehicle air conditioning equipments generates cooled air by vaporizing refrigerant in liquid state with the water as the adduct for this reactions. It has structural difficulties for water vaporation then cause the growth of germs. That's why this reseach was focused on the way of eliminating germs in the vehicle air conditioner efficiently. Direct air sterilizer by using UVC(Ultraviolet C) is manufactured and that performances are evaluated.

• 한국지능시스템학회논문지
• /
• 제13권4호
• /
• pp.409-415
• /
• 2003

Recently, the modular learning are very popular and receive much attention for pattern classification. The modular learning method based on the "divide and conquer" strategy can not only solve the complex problems, but also reach a better result than a single classifier′s on the learning quality and speed. In the neural network area, some researches that take the modular learning approach also have been made to improve classification performance. In this paper, we propose a simple modular neural network for characters recognition of vehicle number plate and evaluate its performance on the clustering methods of feature vectors used in constructing subnetworks. We implement two clustering method, one is grouping similar feature vectors by K-means clustering algorithm, the other grouping unsimilar feature vectors by our proposed algorithm. The experiment result shows that our algorithm achieves much better performance.

• 한국기계가공학회지
• /
• 제19권4호
• /
• pp.93-98
• /
• 2020

Washboarding is a phenomenon in which a wavy shape occurs periodically and naturally on an unpaved road made of soil or gravel. This phenomenon causes high-frequency vibration of the traffic traveling on the road because of the height difference of the wave pattern, which may lead to vehicle failure. Consequently, associated research is needed concerning vehicle safety. Therefore, in this study, a numerical simulation was conducted using the discrete element method, which is often used for powder simulation. In contrast to previous studies, the results of this study demonstrate that washboarding can occur even in an environment of 1.5 m/s or less. However, the amount of washboarding is minimal. The study revealed that washboarding develops over time, such that sufficient development time is required before measurements are taken.

• 전기학회논문지
• /
• 제63권3호
• /
• pp.431-436
• /
• 2014

In this paper, temperature change properties on the 210kW-class Interior Permanent Magnet Synchronous Motor (IPMSM) are performed with the cooling performance of a water cooling device through the thermal characteristic analysis of the IPMSM considering a real driving pattern of urban railway vehicles. First, the thermal analysis modeling of 210kW-class IPMSM, which is an alternative to the conventional induction motor, and its water cooling device is conducted. Next, the thermal characteristic analysis of the IPMSM considering a real driving pattern of urban railway vehicles is performed using 2-Dimensional FEM tool. Finally, the calculated characteristic results are analyzed. Consequently, it is confirmed that the internal temperature of the 210kW-class IPMSM may be lowered to about 42~52% by maintaining the coolant flow rate of the water cooling device (Cross sectional shape of the pipe has 220mm width and 10mm height) for 0.2kg/s level.

• 한국자동차공학회논문집
• /
• 제22권1호
• /
• pp.165-173
• /
• 2014

The method of emission inspection for Heavy-duty diesel vehicles has been engine speed type Lug-down 3mode. This method could bring damage to decrepit vehicles under high speed and high load condition and it could not apply the driving pattern on the road. For these reasons, this study has started to create new emission inspection which is appropriate for Korea's road infrastructure. KD 147 would be applied to light-duty diesel vehicles from july 2010 after model operations. Therefore, this study has investigated new emission inspection system for heavy-duty diesel vehicles, except for light-duty diesel vehicles. In consideration of domestic conditions to meet the new load test method in this study, the Lug-down3 mode vehicle speed method was developed for the first time in korea.

• 대한교통학회지
• /
• 제7권1호
• /
• pp.19-34
• /
• 1989

In general, Shopping centers are located in the center of transportation, which induce more traffic concentration than other facilities. As a result, it becomes to one of the aggravating factors of urban ＆ transportation problem such as traffic conjestion, parking problems. Thus, in planning shopping-center, it is desirable that consumer\`s trip pattern is should lie more carefully analyzed in order to alleviate the above problems. This study is aimed at finding the characteristics of shopping tripes and analyzing the choice behavior of shopping center and mode-to-shop. This study has developed a nested logit model in which consumers choose shopping center and mode-to-shop with a sequential structure. The model was estimated using household data from the 1989 May, Seoul metropolitan area and the 18 alternatives of shopping center and 5 mode alternatives. The estimated model have been evaluated and it may be concluded that this model for shopping trips is effective and fesible. The conclusion of this study are as fellows. 1. Out-of-vehicle travel time is more important factor affecting behavior of mode choice than in-vehicle travel time. 2. All of direct-elasticities for mode with respect to the travel time is more elastic than travel cost. 3. Accessibility to shop is more important factor affecting the choice of shopping center than parking space. 4. The value of out-of-vehicle travel time exceeds the value of in-vesicle travel time by 1.64 times.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2005년도 추계 학술대회논문집(수송기계편)
• /
• pp.105-108
• /
• 2005

The radiated noise from the automotive intake system should be predicted at the design stage. To this end, the precise measurement of in-duct acoustic source parameters of the intake system, i.e., the source strength and source impedance, is essential. Most of previous works on the measurement of acoustic source parameters were performed under a fixed engine speed condition. However, the requirement of vehicle manufacturer is the noise radiation pattern as a function of engine speed. In this study, the direct method was employed to measure the source parameters of engine intake system under a fixed engine speed and engine run-up condition. It was noted that the frequency spectra of source impedance hardly changes with varying the engine speed. Thus, it is reasonable to calculate the source strength under the engine run-up condition by assuming that source impedance is invariant with engine speed. Measured and conventional source models, i.e., constant pressure source, constant velocity source, and non-reflective source, were utilized to predict insertion loss and radiated sound pressure level. A reasonable prediction accuracy of radiated sound pressure level spectra from the intake system was given in the test vehicle when using the measured source characteristics which were acquired under the operating condition.