• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1309-1323
• /
• 2020

Crowd evacuation simulation is an important research issue for designing reasonable building layouts and planning more effective evacuation routes. The social force model (SFM) is an important pedestrian movement model, and is widely used in crowd evacuation simulations. The model can effectively simulate crowd evacuation behaviors in a simple scene, but for a multi-obstacle scene, the model could result in some undesirable problems, such as pedestrian evacuation trajectory oscillation, pedestrian stagnation and poor evacuation routing. This paper analyzes the causes of these problems and proposes an improved SFM for complex multi-obstacle scenes. The new model adds navigation points and walking shortest route principles to the SFM. Based on the proposed model, a crowd evacuation simulation system is developed, and the crowd evacuation simulation was carried out in various scenes, including some with simple obstacles, as well as those with multi-obstacles. Experiments show that the pedestrians in the proposed model can effectively bypass obstacles and plan reasonable evacuation routes.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.461-472
• /
• 2024

We propose a network traffic prediction model based on linear and nonlinear model combination. Network traffic is modeled by an autoregressive moving average model, and the error between the measured and predicted network traffic values is obtained. Then, an echo state network is used to fit the prediction error with nonlinear components. In addition, an improved slime mold algorithm is proposed for reservoir parameter optimization of the echo state network, further improving the regression performance. The predictions of the linear (autoregressive moving average) and nonlinear (echo state network) models are added to obtain the final prediction. Compared with other prediction models, test results on two network traffic datasets from mobile and fixed networks show that the proposed prediction model has a smaller error and difference measures. In addition, the coefficient of determination and index of agreement is close to 1, indicating a better data fitting performance. Although the proposed prediction model has a slight increase in time complexity for training and prediction compared with some models, it shows practical applicability.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.81-89
• /
• 2021

Under natural conditions, Apple detection has the problems of occlusion and small object detection difficulties. This paper proposes an improved model based on SSD. The SSD backbone network VGG16 is replaced with the ResNet50 network model, and the receptive field structure RFB structure is introduced. The RFB model amplifies the feature information of small objects and improves the detection accuracy of small objects. Combined with the attention mechanism (SE) to filter out the information that needs to be retained, the semantic information of the detection objectis enhanced. An improved SSD algorithm is trained on the VOC2007 data set. Compared with SSD, the improved algorithm has increased the accuracy of occlusion and small object detection by 3.4% and 3.9%. The algorithm has improved the false detection rate and missed detection rate. The improved algorithm proposed in this paper has higher efficiency.

• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.469-483
• /
• 2023

The dynamic characteristics of wind turbine blades are usually monitored by contact sensors with the disadvantages of high cost, difficult installation, easy damage to the structure, and difficult signal transmission. In view of the above problems, based on computer vision technology and the improved YOLOv5 (You Only Look Once v5) deep learning model, a non-contact dynamic characteristic monitoring method for wind turbine blade is proposed. First, the original YOLOv5l model of the CSP (Cross Stage Partial) structure is improved by introducing the CSP2_2 structure, which reduce the number of residual components to better the network training speed. On this basis, combined with the Deep sort algorithm, the accuracy of structural displacement monitoring is mended. Secondly, for the disadvantage that the deep learning sample dataset is difficult to collect, the blender software is used to model the wind turbine structure with conditions, illuminations and other practical engineering similar environments changed. In addition, incorporated with the image expansion technology, a modeling-based dataset augmentation method is proposed. Finally, the feasibility of the proposed algorithm is verified by experiments followed by the analytical procedure about the influence of YOLOv5 models, lighting conditions and angles on the recognition results. The results show that the improved YOLOv5 deep learning model not only perform well compared with many other YOLOv5 models, but also has high accuracy in vibration monitoring in different environments. The method can accurately identify the dynamic characteristics of wind turbine blades, and therefore can provide a reference for evaluating the condition of wind turbine blades.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.7
• /
• pp.597-602
• /
• 2015

In this paper, we studied the steering performance of wheelset with primary suspension characteristics of railway vehicle. We carry out dynamic analysis and experimental study for the vehicle models which are different primary suspension characteristics. The steering angle of a vehicle model (Case 1) operating in domestic subway lines is insufficient compared with an objective steering angle for curved track. And the steering angle of a vehicle model (Case 2) with improved self-steering performance of wheelset is a little improved compare to previous vehicle model. But also Case 2 model is still insufficient compared with an objective steering angle and has its limit in steering performance. So to overcome this limit of steering performance of passive type railway vehicle, an active steering technology is being developed. In case of vehicle model with active steering system, the steering performance is improved remarkably compared to passive type vehicle model.

• Geomechanics and Engineering
• /
• v.19 no.3
• /
• pp.217-227
• /
• 2019

This study focuses on an improved prediction model to determine the limiting grouting pressure of compaction grouting considering the ground surface upheaval, which is caused by the three-dimensional conical shearing failure. The 2D-dimensional failure curve in Zou and Xia (2016) was improved to a three-dimensional conical shearing failure for compaction grouting through coordinate rotation. The process of compaction grouting was considered as the cavity expansion in infinite Mohr-Coulomb (M-C) soil mass. The prediction model of limiting grouting pressure of compaction grouting was proposed with limit equilibrium principle, which was validated by comparing the results in El-Kelesh et al. (2001) and numerical method. Furthermore, using the proposed prediction model, the vertical and horizontal grouting tube techniques were adopted to deal with the subgrade settlement in Shao-huai highway at Hunan Provence of China. The engineering applicability and effectiveness of the proposed model were verified by the field test. The research on the prediction model for the limiting grouting pressure of compaction grouting provides practical example to the rapid treatment technology of subgrade settlement.

• Computers and Concrete
• /
• v.29 no.6
• /
• pp.361-374
• /
• 2022

On the premise of ensuring that the automatic and quantitative discharging function of concrete conveyors is met, the accuracy of the weight forecast by the mathematical model of the screw conveying volume is improved, and the error of the weight of the concrete parts and the accumulation thickness is reduced. In this paper, the discrete element method (DEM) is used to simulate the macroscopic flow of concrete. Using the concrete discrete element model, the size of the screw conveyor is set, and establish the response model between the influencing factors (process and structure) and the concrete mass flow rate according to the design points of the screw discharging experiment. The nonlinear data fitting method is used to obtain the volumetric efficiency function under the influence of process and structural factors, and the traditional screw conveying volume model is improved. The mass flow rate of concrete predicted by the improved mathematical model of screw conveying volume is consistent with the test results. The model can accurately describe the conveying process of concrete and achieve the purpose of improving the accuracy of forecasting the weight of discharged concrete.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11a
• /
• pp.372.1-372
• /
• 2002

Although impact hammer is widely used as a convenient excitation tool in structural modal testing, little is known about the dynamic charateristics of its impulse mechanism. Transmission of the impulsive force to the structure depends on the dynamic properties of the impact hammer as well as the stiffness of the tip. An improved dynamic model of the impact hammer is proposed in this study with numerical simulations based on this model. (omitted)

• Geomechanics and Engineering
• /
• v.9 no.4
• /
• pp.499-511
• /
• 2015

The creep property of salt rock significantly influences the long-term stability of the salt rock underground storage. Triaxial creep tests were performed to investigate the creep behavior of salt rock. The test results indicate that the creep of salt rock has a nonlinear characteristic, which is related to stress level and creep time. The higher the stress level, the longer the creep time, the more obvious the nonlinear characteristic will be. The elastic modulus of salt rock decreases with the prolonged creep time, which shows that the creep damage is produced for the gradual expansion of internal cracks, defects, etc., causing degradation of mechanical properties; meanwhile, the creep rate of salt rock also decreases with the prolonged creep time in the primary creep stage, which indicates that the mechanical properties of salt rock are hardened and strengthened. That is to say, damage and hardening exist simultaneously during the creep of salt rock. Both the damage effect and the hardening effect are considered, an improved Maxwell creep model is proposed by connecting an elastic body softened over time with a viscosity body hardened over time in series, and the creep equation of which is deduced. Creep test data of salt rock are used to evaluate the reasonability and applicability of the improved Maxwell model. The fitting curves are in excellent agreement with the creep test data, and compared with the classical Burgers model, the improved Maxwell model is able to precisely predict the long-term creep deformation of salt rock, illustrating our model can perfectly describe the creep property of salt rock.

• Journal of Advanced Marine Engineering and Technology
• /
• v.30 no.5
• /
• pp.572-579
• /
• 2006

Accurate heat release analysis based on the cylinder pressure trace is important for evaluating combustion process of diesel engines. However, traditional single-zone heat release models (SZM) have significant limitations due mainly to their simplified assumptions of uniform charge and homogeneity while neglecting local temperature distribution inside cylinder during combustion process. In this study, a heat release analysis based on single-zone model has been evaluated by comparison with computational simulation result using Fire-code, which is based on multidimensional model (MDM). The limitations of the single-zone assumption have been estimated, To overcome these limitations, an improved model that includes the effects of spatial non-uniformity has been applied. From this improved single-zone heat release model (Improved-SZM), two effective values of specific heat ratios, denoted by ${\gamma}_V$ and ${\gamma}_H$ in this study, have been introduced. These values are formulated as the function of charge temperature changing rate and overall equivalence ratio. Also, it is applied that each equation of ${\gamma}_V$ and ${\gamma}_H$ has respectively different slopes according to several meaningful periods during combustion progress. The heat release analysis results based on improved single-zone model gives a good agreement with FIRE-code results over the whole range of operating conditions of target engine, Hyundai HiMSEN H21/32.