Journal of Jiangsu University(Natural Science Eidtion)

[an error occurred while processing this directive]

Journal of Jiangsu University(Natural Science Eidtion)

Home | About Journal | Editorial Board | Subscriptions | Instruction | Contacts Us | 中文

　

Office Online

　

　

　

　

　

　

Editor-in-chief

　

Journal Online

　

　

Forthcoming Articles

　

　

　

　

　

Download Articles

　

　

Quick Search

Advanced Search

Journal of Jiangsu University(Natural Science Eidtion)

	2020 Vol.41 Issue.2 Published 2020-03-10

	125	Vehicle behavior prediction based on attention mechanism
		CAI Yingfeng1, ZHU Nannan2, TAI Kangsheng2, LIU Qingchao1, WANG Hai2
		To predict the future behavior of surrounding vehicles in intelligent driving scenarios, the vehicle behavior prediction method was investigated based on the attention mechanism of long and short-term memory(LSTM) network model. The time series data division method of non-uniform step-size was proposed to classify the vehicle time series information of specific behaviors. With LSTM as the basic neural network framework, the attention mechanism was used to assign different weight values for each time step according to the importance in the time series information. The historical trajectory information of the target vehicle and its surrounding vehicles was used as algorithm input to predict the future motion behavior of the target vehicle. The results show that the algorithm can solve the problems of information omission and increasing of computing resource burden caused by the fixed step-size classification method. The algorithm can effectively improve the accuracy of behavior prediction and reduce the time using of vehicle behavior prediction.
		2020 Vol. 41 (2): 125-130 [Abstract] ( 26 ) [HTML 1KB] [ PDF 2505KB] ( 578 )

	131	Multi-objective planning of high-speed lane changing trajectory based on V2V
		ZHANG Xinfeng1,2, XIA Bake1,2, ZHANG Fucheng1,2
		To solve the problems of poor flexibility and low safety of sensor-type intelligent vehicles on lane changing, a high-speed lane changing model was proposed based on vehicles to vehicles（V2V）mode. At the start of lane changing, all conditions of the surrounding traffic vehicles were determined through V2V, and the minimum safe distance of lane changing with the surrounding traffic vehicles was obtained to judge the feasibility of lane changing. A polynominal function was used to describe the trajectory under the permission of lane changing conditions. The objective function for balancing the comfort and efficiency was established to implement the multi-objective planning of lane changing trajectory for selecting an optimal trajectoty under the traffic environment. The results show that when the lane changing space is not enough, compared with the non-V2V lane changing model, the vehicle can maintain larger safe distance from surrounding vehicles by V2V mode. In the CarSim simulation, the trajectory tracking error and dynamic parameters of the vehicle are controlled within reasonable range, which indicates that the multi-objective optimized trajectory can comprehensively improve the effect of lane changing and enable the vehicle to adapt to the flexible traffic environments.
		2020 Vol. 41 (2): 131-137 [Abstract] ( 39 ) [HTML 1KB] [ PDF 6372KB] ( 505 )

	138	Lane detection algorithm based on row distance and particle filter
		YANG Jinxin, FAN Ying, XIE Chunlu
		To solve the problems of complex modeling and low detection accuracy of lane under different environments, a lane detection algorithm was proposed based on row distance and particle filter under complex road conditions. The RGB images were converted to HSV color space, and the inverse perspective transformation image of lane was obtained by vehicles cameras after calibration to calculate the row distance of every pix. The simple lane road model and the particle filter were used to get the location of lane road. The results show that by calculating the row distance of the binary image, the dotted part of lane can be connected, which is beneficial to establish continuous lane context relation and provide running environment for particle filters. By the particle filter algorithm, without establishing strict lane road model, the problem of low robustness in single lane road model under complex urban road conditions can be solved. The proposed algorithm has good robustness under complex environment.
		2020 Vol. 41 (2): 138-142 [Abstract] ( 23 ) [HTML 1KB] [ PDF 6797KB] ( 439 )

	143	Classification methods of traffic standard terms based on BLSTM and CNN chain model
		FAN Weike, ZHANG Shaoyang, CHEN Boyuan, WANG Ke
		To effectively obtain the conformance clauses in the transportation information standards and simplify the standard methods, combining the bidirectional long short-term memory （BLSTM）based text enhancement representation with the CNN based sentence classification, the classification method was proposed to classify the conformance clauses for solving the problems of lack of context meaning in convolution neural network and gradient disappearance and gradient dispersion in cyclic neural network in the existing text classification methods. The core idea was to add the vectors generated by the forward and backward processes of BLSTM, and the added vectors were spliced with the original vector as vector representation of the text. The text was classified as the input of CNN network. To verify the proposed model, the comparative test with traditional TF-IDF+SVM machine model, single CNN, BLSTM neural network model and classic hybrid model was set up. According to the test of the data set of standard terms of transportation information, the accuracy of the chain-mixed neural network model based on the improved BLSTM and CNN reaches 93.77%.
		2020 Vol. 41 (2): 143-148 [Abstract] ( 32 ) [HTML 1KB] [ PDF 1385KB] ( 459 )

	149	Layout mode analysis and applicability of integrated passenger transportation hub
		XU Yang1, KANG Jialin2, WU Wenjing1, HAO Pan2
		Through survey methods of data collection, on-site discussions and field surveys, the passenger flow of near 20 typically integrated passenger transportation hubs currently in operation in China was surveyed and counted. Focusing on the analysis of the typical layout patterns of Shenzhen North Station, Tianjin Station, Beijing South Station and Nanjing South Station, according to the transfer mode of passenger flow in the integrated passenger transportation hubs, the existing railway-led connection layout modes in China were classified. The advantages and disadvantages of the connection layout modes among different transfer modes were compared and analyzed, and the scope of application was defined. The results show that the layout modes of integrated passenger transportation hubs in China are mainly divided into four categories of planar integrated layout, planar separated layout, three-dimensional layout and comprehensive layout. With the continuous increasing in the requirements of urban comprehensive transportation service levels and the demand for social public satisfaction, the three-dimensional layout mode has obvious future development advantages.
		2020 Vol. 41 (2): 149-153 [Abstract] ( 38 ) [HTML 1KB] [ PDF 4880KB] ( 651 )

	154	Quantification method of traffic conflict based on pupil diameter
		XU Yi1, LI Shiwu2, WANG Yuqiong1, MA Xiaotian1
		Traffic conflict data, illumination data and pupil diameter data of drivers were statistically analyzed to show that the pupil diameter could be influenced by illumination with consistent changing trends of conflict severity and pupil diameter. The traffic conflict quantification method with pupil diameter as quantitative index was proposed. The illumination-pupil diameter model was established and used for the data compensation of pupil diameter to reduce the effect of illumination. The data in real vehicle tests were collected and used to quantify traffic conflicts by the proposed method. The results show that the q value from quantification method and the driver subjective scores are increased with the increasing of vehicle speed, and the increasing rates are decreased with the increasing of vehicle speed. The quantification results and the driver subjective scores in traffic conflict are consistent, and the proposed method can provide a way for traffic safety evaluation on the basis of driver cognition.
		2020 Vol. 41 (2): 154-159 [Abstract] ( 33 ) [HTML 1KB] [ PDF 3964KB] ( 444 )

	160	Obstacle identification method based on lidar data for warehousing logistics AGV
		WU Fei, HUANG Wei
		To solve the problem of AGV obstacle avoidance in intelligent warehousing, the method with lidar to identify the obstacle category in front of AGV was proposed to make reasonable decision by combining obstacle position information to assist AGV. The lidar data was filtered and clustered to obtain clusters with high purity. The feature vector was extracted by the proposed feature extraction method. The particle swarm optimization (PSO) algorithm was used to find the optimal parameters of the radial basis kernel (RBF) support vector machine (SVM) on the training set, and the model was trained. The method was tested on the data set of the intelligent warehousing simulation environment. The results show that the accuracy reaches 94.58%, which can accurately and effectively identify the categories of obstacles in front of the AGV.
		2020 Vol. 41 (2): 160-165 [Abstract] ( 41 ) [HTML 1KB] [ PDF 3814KB] ( 460 )

	166	Crashworthiness optimization design of automobile B-pillar structure based on negative Poisson′s ratio structure
		ZHAO Wanzhong, ZHAO Hongyu, WANG Chunyan
		To improve the side crashworthiness of automobile, based on the traditional B-pillar basic structure, a new B-pillar structure with negative Poisson′s ratio inner core was proposed. According to the requirements of C-NCAP, the side impact model was established based on the new B-pillar structure. Taking sample points by the optimal Latin hypercube test design method, the response surface model between each evaluation index and design variable of B-pillar was established. On this basis, the invasion displacement and the invasion speed of B-pillar were used as optimization objective, and the NSGA-Ⅱ optimization algorithm was adopted to improve the new B-pillar structure by the multi-objective optimization design. The results show that the new B-pillar structure can reduce the invasion displacement by 7.44％ with decreased invasion speed by 5.10％, which illuminates that the side crashworthiness of vehicle is significantly improved.
		2020 Vol. 41 (2): 166-171 [Abstract] ( 35 ) [HTML 1KB] [ PDF 4755KB] ( 426 )

	172	Design of differential braking control system of travel trailer based on multi-objective PID
		XU Xing1,2, MI Jie1, WANG Feng1,2, MA Shidian1,2, TAO Tao3
		To achieve good yaw stability and trajectory of travel trailer during braking, a differential braking control method was proposed to optimize the hinged angle and the yaw angular velocity performance for the travel trailer. Considering the electromechanical coupling characteristics of electromagnetic brake, a 6 DOF tractor-travel trailer braking model was established. The model of articulation angle of travel trailer in steady state was established, and the multi-objective PID weighted control algorithm and the multi-objective PID coordinated control algorithm were introduced. The principle of differential braking was applied to control the yaw moment and make the articulated angle and yaw velocity of travel trailer accurately follow the expected value of the target, and the good trajectory and yaw stability was achieved during the braking of travel trailer. Based on the co-simulation of TruckSim and Simulink, the simulation tests of step and pulse steering were carried out. The simulation results show that weighted control and coordinated control can guarantee the tractor trailer with good trajectory and yaw stability during braking. Compared with non-differential braking control, the two control algorithms can reduce the relative yaw rate of travel trailer by about 25％. Compared with the differential braking with yaw rate as control target, the trajectory deviation of travel trailer under the two control algorithms is reduced by about 20％.
		2020 Vol. 41 (2): 172-180 [Abstract] ( 40 ) [HTML 1KB] [ PDF 2953KB] ( 436 )

	181	Self-adaptive control of slope work equipment hitch based on lateral angle prediction
		CHEN Chen, XIA Changgao, HAN Jiangyi, YANG Hongtu
		To solve the problem that the traditional electro-hydraulic hitch could not adapt the lateral angel for tillage on slope, a feedback control system of adaptive electro-hydraulic hitch was designed. The method of predicting the hitch lateral inclination angle was proposed by Kalman prediction algorithm. The dynamic model of lateral inclination angle adaptive electro-hydraulic hitch was set up. The control system model with the above dynamic model of hitch was established in Simulink. The actual measured transverse slope was used as model input signal to verify the performance of control system. The results show that the fluctuation of lateral tillage error can be controlled within±10 mm.
		2020 Vol. 41 (2): 181-186 [Abstract] ( 37 ) [HTML 1KB] [ PDF 2693KB] ( 452 )

	187	Characteristic parameters of high frequency harmonics caused by combustion excitation in cylinder pressure signal
		ZHAO Xiuliang, KONG Lingyi, WANG Ruochen, LI Xiaohua, WANG Limei
		To solve the problems of existing lag angle between the phase combustion parameters identified by vibration signal and cylinder pressure signal and of existing different lag angles under different working conditions, the parameters for characterizing the high-frequency harmonics of in-cylinder pressure signal were investigated. The S-transformation of cylinder pressure was analyzed to determine the range of frequency distribution caused by the combustion excitation. The one-dimensional simulation model of the single-cylinder diesel engine was established to analyze the maximum pressure. The results show that the maximum pressure rise rate, the peak pressure, the ratio of the maximum pressure rise rate to the interval between the start of combustion and the maximum pressure rise rate and the interval between the start of combustion and the peak pressure are approximately linear to the high frequency energy of the cylinder pressure signal. In the vibration velocity signal, the corresponding parameters of pirA′B′,pirA′B′δφ′ and δθ′ can be used to represent the high-frequency energy. A reference is provided for correcting lag angle based on characteristic parameters of vibration velocity signals.
		2020 Vol. 41 (2): 187-191 [Abstract] ( 45 ) [HTML 1KB] [ PDF 2708KB] ( 426 )

	192	Peak power estimation of power battery discharge based on SA+BP hybrid algorithm
		ZHU Hao, ZHANG Wenbo, DENG Yuanwang, LI Meng, JI Xiang
		To solve the problems that only single factor was considered for battery peak power estimation and the battery model was simple, a new estimation method was proposed. Taking the ternary lithium power lithium batteries as research object, considering the comprehensive effects of battery temperature, charging state and ohm resistance on the power state, a neural network battery model on simulated annealing and back propagation（SA+BP）hybrid algorithm was eatablished based on data statistics and machine learning by neural network toolbox and Matlab programming. Hybrid pulse power characteristic (HPPC) method was used to conduct the experiments. 245 groups valid experimental data were obtained with selected 200 groups experimental data as training samples, and the rest experimental data were used as test samples. The simulation results of the training model by single BP algorithm were compared with those by SA+BP hybrid algorithm. The results show that the trained model based on SA+BP hybrid algorithm has better estimation accuracy, which can more accurately describe the peak power of battery.
		2020 Vol. 41 (2): 192-198 [Abstract] ( 63 ) [HTML 1KB] [ PDF 9584KB] ( 497 )

	199	Effect of EGR on soot precursor formation in combustion of biodiesel/diesel with different blending ratios
		WU Xudong1, WANG Zhong1, LIU Shuai1, LI Ruina1, QU Lei2
		Taking biodiesel/diesel as research object, by AVL-Fire software and Chemkin software, the biodiesel/diesel chemical reaction kinetics model was constructed to investigate the effects of blending ratio and EGR rate of biodiesel/diesel on the soot precursor formation of acetylene, benzene, naphthalene, phenanthrene and pyrene. The results show that the soot precursor is mainly formed in the premixed combustion stage. With the increasing of crank angle, the soot precursor content is increased with latter decreasing. With the increasing of biodiesel blending ratio, the initial formation time of soot precursor is advanced, and the peak amount of production and the final amount of production are reduced. With the increasing of EGR rate, the peak formation timing is delayed, and the production peak of acetylene is reduced with gradually increased final amount. The final amount of benzene, naphthalene, phenanthrene and pyrene is increased.
		2020 Vol. 41 (2): 199-205 [Abstract] ( 28 ) [HTML 1KB] [ PDF 2213KB] ( 478 )

	206	Analysis of instantaneous pressure in oil return stage of electro-hydraulic variable valve system
		WU Xueshun1, ZHANG Hongchuan1, DU Defeng1, HAN Zhiqiang1, ZHAO Jiahui2
		Based on a certain type of marine diesel electro-hydraulic variable valve system, through the combination of experiment and simulation, the pressure fluctuation evaluation system was established when the simulation results and experimental data were in good agreement. The effects of the opening slope, the maximum opening, the opening phase and the supply pressure of the oil return solenoid valve in plunge interval, stable interval and free drop interval on the characteristic time of instantaneous pressure for the hydraulic oil circuit after solenoid valve were investigated. The results show that the characteristic time of plunge interval is decreased with the increasing of opening slope of oil return solenoid valve and increased with the increasing of the largest opening. The characteristic time of stable interval is increased with the increasing of opening slope of oil return solenoid valve and decreased with the increasing of the largest opening. The effects of the oil return valve open slope and the largest opening on characteristic time of plunge interval and stable interval are greater than those of open phase position and oil-supply pressure. The oil return solenoid valve open slope, the largest opening, the open phase position and the oil-supply pressure have slight effects on the characteristic time of free drop interval.
		2020 Vol. 41 (2): 206-213 [Abstract] ( 29 ) [HTML 1KB] [ PDF 3016KB] ( 415 )

	214	Design of a power lithium battery simulator for function verification of BMS
		LI Meng, GONG Jinke, ZHU Hao, JI Xiang, ZHANG Wenbo
		A second-order equivalent circuit model of battery was established based on Simscape module of Matlab ＆ Simulink, and the parameters were identified and verified. The design of hardware circuit and software were completed, and a new power lithium battery simulator was constructed. The simulation and test results show that the accuracy of battery model can be further improved by adding the state of charge interval between 0 and 0.10 when the battery model is parameterized. Under HPPC cyclic discharge condition, the maximum error of voltage does not exceed 0.07 V, while under dynamic operation conditions, it does not exceed 0.12 V. The maximum error of output voltage of power lithium battery simulator is 1.9 mV, and the relative error is 0.53‰ under different charge state. The designed power lithium battery simulator has high accuracy and can be used for battery management system function verification.
		2020 Vol. 41 (2): 214-220 [Abstract] ( 56 ) [HTML 1KB] [ PDF 8302KB] ( 460 )

	221	Effect of etching conditions on anisotropic etch rates of quartz and KMC simulation
		ZHANG Hui1,2, MAN Qingshan1, BEN Wei1, LU Shifang1, QIN Xuan1, XING Yan2
		The complex anisotropic etching characteristics of the anisotropic wet etching for quartz make it difficult to predict and control the evolution process and the etching results. By etching hemispherical method, the effects of concentration and temperature of solution on anisotropic etch rates of quartz were investigated. Based on the activation energy, the cause of anisotropic etching characteristics was analyzed in detail. In morphology prediction, according to the particular atomic arrangements and the facet specific etch rates of several crystal planes parallel to the electric x and mechanical y axes, the KMC etching process model was established based on a suitable quartz-based removal probability function (QUARTZ-RPF). The prediction of the etch rates at wide range of crystallographic facets is successfully realized, and the three-dimensional microstructures and topography etched on Z-cut substrate with arbitrary mask patterns are accurately simulated.
		2020 Vol. 41 (2): 221-229 [Abstract] ( 42 ) [HTML 1KB] [ PDF 10340KB] ( 425 )

	230	Dynamic spectrum access strategy based on improved polymorphic ant colony algorithm in cognitive radio
		TENG Zhijun1,2, TENG Lixin2, XIE Luying2, QU Fujuan2
		To improve the network profit of system and the utilization of network resources as much as possible, the polymorphic ant colony optimization algorithm was proposed based on time efficiency to solve the existing problems with long searching time, slow convergence speed and single pheromone of original ant colony algorithm. With the enhancement of pheromone accumulation, a basis was provided for the ant action in the ant colony algorithm and applied into the dynamic spectrum access in cognitive radio. The simulation results show that the improved algorithm can improve the network efficiency and ensure the system fairness evidently, and the search time of cognitive users is saved to make cognitive users access the available spectrum more quickly. The improved algorithm not only speeds up the convergence speed, but also increases the system throughput significantly, which improves the overall performance of the system.
		2020 Vol. 41 (2): 230-236 [Abstract] ( 38 ) [HTML 1KB] [ PDF 1640KB] ( 403 )

	237	Temperature calculation and test verification of wind turbine main bearing
		DENG Zhidang1,2, SUN Tao2
		During the generating of turbine, the temperature tests of the front and rear bearings on the generator were conducted to obtain temperature curve and temperature rise curve. According to the relationship between the power curve and the temperature rise curve, the temperature rise values of the front and rear bearings under the full power generation were calculated. The load at the center of the hub was obtained according to the blade root load. The frictional torques in the front and rear bearings and the generating heat by the frictional torque were calculated. Based on the calculated frictional heat, the temperature values of the front and rear bearings of the main shaft system under the full power generation were calculated by finite element method. The difference between the theoretical temperature and the test temperature was analyzed. The effects of radial load, bearing preload, bearing size, grease viscosity and bearing speed on bearing temperature were analyzed in detail. The results show that the radial load and the temperature rise of the front bearing are much larger than those of the rear bearing. Among the four friction torques, the thermal power loss caused by the sliding friction torque is significantly higher than those by other friction torques. The temperature rise of the bearing varies with the preload force, and the greater the pretension force is, the greater the temperature rises. The increasing of pretension force has great effect on the temperature rise of front bearing and has small effect on the temperature rise of rear bearing.
		2020 Vol. 41 (2): 237-242 [Abstract] ( 44 ) [HTML 1KB] [ PDF 5432KB] ( 674 )

	243	Asymptotic analysis of heat transfer behavior of metal sheet irradiated by ultra-short pulse laser based on DPL model
		WANG Yingze, ZAN Chen
		Based on the dual phase lag heat conduction model (DPL model), the asymptotic analysis of the transient heat conduction behavior of a thin metal sheet irradiated by ultra-short pulse laser was conducted . The governing equation with temperature representation of a thin metal plate was proposed in the context of the DPL model. The asymptotic solutions of temperature distribution through the whole thin plate induced by external ultra-short pulse laser were derived by combing the Laplace transform and the inverse transform techniques. The results were compared with those from the numerical methods in the literature to verify the accuracy of the analytical method. The effects of the phase-lag terms τq,τT and the sheet metal thickness on heat transfer behavior were also investigated. The results show that the peak value of heat wave and the change rate of temperature are increased with the increasing of τq. On the contrary, as the τT increases, the peak value of heat wave and the temperature change rate are decreased. The metal plate thickness has slight effect on the temperature change.
		2020 Vol. 41 (2): 243-248 [Abstract] ( 40 ) [HTML 1KB] [ PDF 1493KB] ( 452 )

江苏大学学报（自然科学版）

　

News

　

·	关于近期网络不稳定情况的说明

·	Our journal has be included in JSTChina Database

·	Our journal has be selected for the 2015-2016 China Science Citation Database (CSCD)

　　　　　　　　　　More

　

Links

　

·	Chinese Library Classification Number

·	Society of China University Journals

·	China National Knowledge Infrastructure

·	Chinese Sciencepaper Online

·	Transactions of the Chinese Society for Agricultural Machinery

·	Journal of Southeast University：Natural Science Edition

　　　　　　　　　　More

Copyright © 2011 Journal of Jiangsu University(Natural Science Eidtion)
Support by Beijing Magtech Co.Ltd E-mail：support@magtech.com.cn