• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.11a
• /
• pp.1063-1066
• /
• 1996

On the prediction of driving performance, an acceleration performance is normally simulated in stall starting condition which is the engine status of full-throttle and high-speed. The lack of transient engine torque data makes the difficulty of predicting an acceleration performance on engine-idle start condition. A experimental equation of transient engine torque is derived from vehicle performance test data. It is applied to simulation the accleration performance prediction on idle starting condition.

• Journal of Biosystems Engineering
• /
• v.37 no.3
• /
• pp.131-139
• /
• 2012

In this study, we developed a simulation program for the prediction of tractive performance of a tractor, by applying a widely used empirical model for tractive performance prediction of single tire, Brixius. The tractive performance prediction program can readily predict and estimate tractive performance according to various soil conditions and different specifications of tractors. The program was developed with the considerations of tractor's specification-related parameters (e.g., weight, tire size, and wheelbase of the tractor), a soil parameter (i.e., cone index which represents the soil strength), and operating conditions of the tractor (e.g., theoretical speed and driving types such as 2WD and 4WD). Also, the program was designed to provide tractive performance prediction results of tractors such as gross traction, motion resistance, net traction, and tractive efficiency, in the form of not only numerical values but also graphical visualization. To evaluate the feasibility of the program, we input three different soil conditions (which have different cone indexes each other) and tractor operating conditions to the program and analyzed the tractive performance from each input condition. From the analysis, it can be concluded that the developed program can be effectively utilized to predict the tractive performance under various soil conditions and driving types of tractors with different specifications.

• Journal of the Society of Naval Architects of Korea
• /
• v.55 no.2
• /
• pp.153-160
• /
• 2018

In order to develop the driving pump for High-speed Cavitation Tunnel(HCT) which can experiment the super-cavitating submerged body, KRISO decided on the pump specification, designed the mixed-flow pump on the basis of the existing pump data and predicted the performance of the design pump using commercial CFD code (CFX-10). After the manufacture and installation of the driving pump, KRISO conducted the trial-test for HCT, analyzed the pump performance and compared trial-test results to those of design stage. The trial-test items for the HCT driving pump are measurements of output current/voltage at the inverter of the driving pump and the flow velocity in the HCT test section. The trial-test results showed the decrease in the flow rate of about 4.6% and the increase in pump head of about 8%, compared with those of the pump prediction. After the trial-test, the performance of the driving pump is predicted using CFX-10 with measured flowrates and pump rotational velocities. Though there is some difference between trial-test and prediction results due to inadequate motor data, it is thought that the tendency is reasonable. It is found that CFX-10 is useful to predict a mixed-flow pump.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.7
• /
• pp.974-981
• /
• 2012

This paper studied about the measurement method of the instantaneous dynamic load characteristics. this experimental study, we derived the instantaneous washing load characteristics and inertial moment characteristics according to the amount of laundry and water level. Also, this studied about the dynamic driving characteristics simulation method for the prediction of washing performance based on this load characteristics analysis. For this study, the design parameters of the driving motor are obtained by FEM analysis and the experiment. By using theses motor parameters and load characteristics, the instantaneous driving characteristics simulation is accomplished and it is verified with the experimental result of various driving conditions. The results of this paper would be very useful to the prediction of washing mode operation characteristics, and it can be also utilized to the washer motor control algorithm design for the washing performance improvement.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.5 no.1
• /
• pp.174-185
• /
• 1997

The performance of the solenoid actuated hydrogen injector and the capacitive peak-hold type driving circuit was predicted through the modeling of the injector and the driving circuit the modeling was composed of the driving circuit, the solenoid, the moving parts of the injector, and the hydrogen injection system. The performance of the injector through the modeling was compared with the results of the solenoid and injector rig tests, and those were consistent with each other. Through the prediction of the injector performance, the effects of the components such as electrical resistor, capacitor, and injector spring are easily known to the injector performance required.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3330-3344
• /
• 2023

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.951-969
• /
• 2017

In this paper, we newly propose a traffic information service model that collects traffic information sensed by an individual vehicle in real time by using a smart device, and which enables drivers to share traffic information on all roads in real time using an application installed on a smart device. In particular, when the driver requests traffic information for a specific area, the proposed driver-personalized service model provides him/her with traffic information on the driving directions in advance by predicting the driving directions of the vehicle based on the learning of the driving records of each driver. To do this, we propose a traffic information management model to process and manage in real time a large amount of online-generated traffic information and traffic information requests generated by each vehicle. We also propose a road node-based indexing technique to efficiently store and manage location-based traffic information provided by each vehicle. Finally, we propose a driving learning and prediction model based on the hidden Markov model to predict the driving directions of each driver based on the driver's driving records. We analyze the traffic information processing performance of the proposed model and the accuracy of the driving prediction model using traffic information collected from actual driving vehicles for the entire area of Seoul, as well as driving records and experimental data.

• Korean Journal of Culture and Social Issue
• /
• v.11 no.4
• /
• pp.83-95
• /
• 2005

The purpose of the present study was to investigate the relationship between spatial-erceptual ability and several aspects of driving-related situation awareness(in particular, recognition and prediction). Video clips of real driving were used in both recognition and prediction tasks, and the digit calculation task during driving the simulator was required as the integration task of recognition and prediction. The results showed that the subjects of higher spatial-perceptual ability performed better in recognition task, especially in terms of sensitivity measured in d'(as signal detection theory), prediction task, and digits calculation performance than those of lower spatial-perceptual ability.

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.346-350
• /
• 2023

Trajectory prediction is an essential element for driving autonomous vehicles, and various trajectory prediction models have emerged with the development of deep learning technology. Convolutional neural network (CNN) is the most commonly used neural network architecture for extracting the features of visual images, and the latest models exhibit high performances. This study was conducted to identify an efficient CNN backbone model among the components of deep learning models for trajectory prediction. We changed the existing CNN backbone network of multiple-trajectory prediction models used as feature extractors to various state-of-the-art CNN models. The experiment was conducted using nuScenes, which is a dataset used for the development of autonomous vehicles. The results of each model were compared using frequently used evaluation metrics for trajectory prediction. Analyzing the impact of the backbone can improve the performance of the trajectory prediction task. Investigating the influence of the backbone on multiple deep learning models can be a future challenge.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.5
• /
• pp.188-195
• /
• 2000

This study was conducted to develop the mathematical model and the computer simulation program(TPPMWV) for predicting the tractive performance of off-road wheeled vehicles operated on various soil conditions. The model takes into account main design parameters of a wheeled vehicle, including the radius and width of front and rear tires, the weight of vehicle, wheelbase and driving type(4WD, 2WD). Soil characteristics, such as the peressure-sinkage and shearing characteristics and the response to repetitive loading, are also taken into consideration. The effectiveness of the developed model was verified by comparing the predicted drawbar pulls using TPPMWV with measured ones obtained by field tests for two different driving types of wheeled vehicle. As a results, the drawbar pulls predicted by the TPPMWV were well matched to the measured ones within the absolute errors of 5.25%(4WD) AND 9.42%(2WD)for two different driving types, respectively.