Archive

12 July 2021, Volume 40 Issue 07 Previous Issue   
---
Transport+Big Data and Artificial Intelligence
Transportation Infrastructure Engineering
Transportation Equipment


For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Transport+Big Data and Artificial Intelligence

Select

Interaction between Land Port and Urban Economy Based on System Dynamics LI Jing1,2, ZHONG Peng1, LYU Jing1,2 2021, 40(07): 1-7.  DOI: 10.3969/j.issn.1674-0696.2021.07.01 Abstract ( )   PDF (956KB) ( )   In order to analyze the interaction mechanism between the land port and the urban economy under the “One Belt and One Road” initiative, the system dynamics method was used to build the system model of their interaction. Taking the relevant data of Xian land port and its urban economy from 2010 to 2017 as an example, the simulation was carried out. The results show that simply increasing infrastructure investment of Xian land port has no obvious effect on the throughput driving benefit, but the freight volume of port area has a significant effect on it; the throughput is positively correlated with industrial added value of Xian city, especially the benefit of driving GDP growth is obvious; Xian land port has created an annual average indirect GDP of RMB 10.906 billion, which has driven an average annual employment population of 84 000. References | Related Articles | Metrics

Select

Competitiveness Evaluation of Cruise Ports around Bohai Sea Based on Entropy Weight-Cloud Model LIU Cuilian, ZHUANG Hailin, ZHANG Qunshu 2021, 40(07): 8-15.  DOI: 10.3969/j.issn.1674-0696.2021.07.02 Abstract ( )   PDF (3341KB) ( )   Taking the cruise port around Bohai Sea as the research background, the evaluation index system of port competitiveness was established from six aspects such as economic conditions, traffic conditions, tourism conditions, port conditions, service level and development potential. Entropy weight-cloud model was used to transform qualitative description into quantitative measurement to evaluate the competitiveness of cruise port around Bohai Sea. Cloud similarity algorithm was used to evaluate the competitiveness of Dalian cruise port, Tianjin cruise port and Qingdao cruise port. The results show that the competitiveness evaluation grades of Dalian, Tianjin and Qingdao cruise ports are all “strong”. However, Dalian cruise port is at a competitive disadvantage in terms of service level and development potential, Tianjin cruise port is at a competitive disadvantage in terms of economic conditions and service level, and Qingdao cruise port is at a competitive disadvantage in terms of traffic conditions and development potential. References | Related Articles | Metrics

Select

Application of Comprehensive Evaluation of Triangular Fuzzy Analytic Hierarchy Process in Ship Safety Assessment of the Yellow River Reservoir Area LI Jun1, ZHU Yunsheng2 2021, 40(07): 16-22.  DOI: 10.3969/j.issn.1674-0696.2021.07.03 Abstract ( )   PDF (436KB) ( )   In order to evaluate the safety of ships in the Yellow River reservoir area, a multi-level comprehensive evaluation model using triangular fuzzy analytic hierarchy process was proposed. The triangular fuzzy analytic hierarchy process was used to determine the weights of factors, which effectively solved the problem that the subjectivity of expert scoring was strong and the judgment matrix was difficult to be consistent. The multi-level comprehensive evaluation was used to solve the problem of a large amount of single factor information submerged in a wide range of risk sources, and the model was studied with examples. The results show that the proposed model can assess the ship safety risk scientifically and reasonably, which provides a reference for the ship management company and the maritime bureau to improve the management method. References | Related Articles | Metrics

Select

Estimation of Congestion Costs for Lockage Ship in Three Gorges Dam Area and Its Impact on the Total Value of Goods in the Dam Area DENG Ping1,2, SONG Lian1, HUANG Chengfeng1,2 2021, 40(07): 23-30.  DOI: 10.3969/j.issn.1674-0696.2021.07.04 三峡坝区过闸船舶拥堵成本测算及 Abstract ( )   PDF (471KB) ( )   The Three Gorges Ship Lock is a “bottleneck” restricting the development of shipping in the upper reaches of the Yangtze River. The inefficiency cost of lockage vessels congestion and the impact of congestion on the total value of goods in the dam area have received increasing attention. According to the mathematical description of the problem of lockage vessels congestion, the model hypotheses under Nash Equilibrium were proposed. On the basis of these hypotheses, the distribution law of the departure time of all ships in the dam area was developed. Various kinds of low-efficiency cost models caused by lockage vessels congestion were derived from this. Then combined with the description of the actual congestion cost for the lockage vessels, various kinds of low-efficiency cost models were empirically measured. Finally, by compiling the price index of the cargo waiting to be locked in the Three Gorges, the influence of ship congestion on the total value of cargo in the dam area was analyzed. The research results show that: in 2019, the minimum inefficiency cost of congestion (ie, total travel cost) incurred by container ships ranges from 10,610 yuan to 21,230 yuan, while that of dry bulk carriers ranges from 7,125,900 yuan to 14,251,840 yuan. Among them, the operating time cost of container ships reaches 103.68364 million yuan, and that of dry bulk carriers reaches 203.62449 million yuan; the time cost of cargo transportation reaches 43.43296 million yuan for container ships and 54.13869 million yuan for dry bulk carriers. The total value of goods in the dam area due to ship congestion increases by 1.613% (ie, about 2,536.616 million yuan), and the inhabitant purchasing power decreases by 1.587%. The increase rate of cargo price of ships passing the Three Gorges Dam is higher than the average increase rate of purchase price of industrial producers in the same year. As a result, the profit of the cargo owners has not been compressed. References | Related Articles | Metrics

Select

Short Term Forecast of Rail Transit Passenger Flow Based on Time Series Seasonal Classification Model TANG Jiqiang1,2, ZHONG Xinwei2, LIU Jian1, LI Tianrui3 2021, 40(07): 31-38.  DOI: 10.3969/j.issn.1674-0696.2021.07.05 Abstract ( )   PDF (1999KB) ( )   In the analysis of rail transit passenger flow, the seasonal characteristics of data have a significant impact on the effectiveness of passenger flow forecast. By analyzing the passenger flow curves of rail transit, it was found that the passenger flow of rail transit presented seasonal characteristics. Aiming at this kind of characteristics, a passenger flow forecast approach of rail transit based on seasonal classification model was proposed. Firstly, the seasonal classification template and seasonal time series were established according to the seasonal characteristics of passenger flow. Secondly, the seasonal classification model of passenger flow was established by the multiplicative seasonal autoregressive differential moving average model. Finally, the seasonal classification model was used to forecast the passenger flow on the corresponding dates. The experiment shows that the proposed seasonal classification model can not only effectively predict the passenger flow of rail transit, but also avoid the fluctuation of prediction error. References | Related Articles | Metrics

Select

Travel Mode Choice Behavior Model of Intercity Passengers with Medium and Long Haul — A Case Study of High-Speed Railway and Air Transport CHENG Qian1, ZHU Xiaoning2, LU Wansheng3 2021, 40(07): 39-45.  DOI: 10.3969/j.issn.1674-0696.2021.07.06 Abstract ( )   PDF (709KB) ( )   Aiming at the choice behavior of medium-and-long distance intercity passenger on high-speed rail (H), civil aviation (A), high-speed rail and air combined transport (HA) and civil aviation transit (AA), three typical ODs were selected to carry out passenger flow survey with SP method. Multinomial logit model (MNL) and mixed logit model (ML) were conducted to fit the data, the key factors affecting passengers’ mode choice were analyzed, and the heterogeneity of passengers’ choice behavior was illustrated. The research results show that: compared with MNL model, ML model significantly improves the prediction ability of the model, better describes the heterogeneity of passengers’ choice behavior, and is more suitable for travel mode choice behavior modeling. The time before the trip, the time on the way and the transit time are the main factors affecting passengers’ choice. In addition, the trip purpose and whether reimbursement or not are also important factors impacting passengers’ choice of travel mode. In the range of 1400 ~ 2000km travel distance, reducing transit time can effectively improve the market share ratio of HA and AA travel mode; in the range of 1400 km travel distance, if the transit time is less than 1.5h, the interchangeability of AA and HA is obvious; while, for 2000km travel distance, the market share ratio of AA is significantly higher than that of HA. References | Related Articles | Metrics

Select

Autonomous Driving Choice Behavior Based on Panel Data Mixed Logit Model LIAN Qicai1, LI Han1, SHI Xiaolin1, YAN Zhangcun2 2021, 40(07): 46-52.  DOI: 10.3969/j.issn.1674-0696.2021.07.07 Abstract ( )   PDF (1498KB) ( )   In order to accurately grasp the travel mode selection rule in the autonomous driving environment, the panel data Mixed logit model was introduced to analyze the influence mechanism of the variables representing travelers’ individual socio-economic attributes such as age, income, education degree and the variables representing the travel mode characteristics such as travel cost, waiting time and in-transit time on travel mode choice behavior in an autonomous driving environment. Using 1050 valid sample data of 150 respondents in seven different scenarios from the Singapore Autonomous Driving Willingness Survey, a travel choice behavior model under the automatic driving environment was conducted. The results show that the p-value of the chi-square test of the model is less than 0.000, indicating the proposed model has good applicability. The parameter estimation results show that different individuals in the groups have strong heterogeneity in travel cost, waiting time and travel time. Marginal effect analysis shows that the probability of choosing autonomous driving, public transportation, and walking will rise as the age increases, but the probability of choosing online car hailing will go down. When the travel cost, travel time and waiting time are doubled, the probability of choosing to drive automatically will be reduced by nearly 4.0%. References | Related Articles | Metrics

Select

Traffic Engineering Facility Information Threshold Based on Drivers Visual Area of Interest QI Chunhua, WANG Xiaonan, ZHU Shoulin, LI Hangtian 2021, 40(07): 53-60.  DOI: 10.3969/j.issn.1674-0696.2021.07.08 Abstract ( )   PDF (3186KB) ( )   In view of the problems in setting the information volume of traffic engineering facilities in the straight section of the prairie highway, on the basis of the relevant theories of information quantification, 5 indoor simulation driving tests were established with different information levels by dividing the area of interest (AOI) for drivers. Using the method of mathematical statistics, the fixation and scanning characteristics of drivers with different proficiency in traffic engineering facilities area (AOI4) with different information levels were quantitatively analyzed. The research results indicate that skilled drivers pay more attention to traffic engineering facilities than unskilled drivers with the change of traffic engineering facilities information. At the low level of information, drivers pay less attention to the AOI4 area, pay more attention to the road ahead unconsciously, and are prone to mental fatigue when driving for a long time, which affects the driving safety. When the information level is Z4, according to the change law of driver’s fixation and scanning characteristics, it is considered that the driver’s information processing time is fast, the visual search range is large, and the driving psychological load is small, which is conducive to driving safety. At the high-information level Z5, drivers need to spend a lot of time and mental resources to pay attention to the AOI4 area information, which causes the driver to pay less attention to other areas of the road and weakens the processing ability in dealing with sudden traffic accidents. References | Related Articles | Metrics

Select

Violation Alarm of Dangerous Goods Vehicle Based on TOPSIS and Gray Correlation LI Shengchao, WU Yue, BAI Xuemeng, WANG Yue, ZHANG Hai 2021, 40(07): 61-66.  DOI: 10.3969/j.issn.1674-0696.2021.07.09 Abstract ( )   PDF (467KB) ( )   In order to quantitatively evaluate the traffic violations of road dangerous goods vehicles, the entropy weight method was used to calculate the weight the TOPSIS method was use to perform a macroscopic and vertical ranking of the indicators of each month and the gray correlation analysis method was used to horizontally analyze the degree of association between subsequences and parent sequences. Thus, a comprehensive evaluation model was established. An empirical study was conducted on the violation of road dangerous goods vehicles in Shaanxi Province. The results show that through the increase of the supervision of Shaanxi provincial government and enterprises, the operation of dangerous goods road transportation has been well standardized and the number of violation alarms shows a decreasing trend on the whole, and the safety is gradually improved. The sub-sequences monitored have a high degree of correlation with the parent sequences. Among them, fatigue driving has the greatest impact on the alarm and the offline displacement has the least influence. According to the research results, suggestions for improvement are proposed to reduce the number of illegal operation of road dangerous goods vehicles and improve the safety of road dangerous goods transportation. References | Related Articles | Metrics

Select

Traffic Emission and Fuel Consumption Model of Roundabout YANG Qingfang1,2,3, WANG Liqiang2, ZHENG Lili1,2,3, MENG Fanyun2 2021, 40(07): 67-73.  DOI: 10.3969/j.issn.1674-0696.2021.07.10 Abstract ( )   PDF (1156KB) ( )   Aiming at the problem of establishing the objective function of traffic emission and fuel consumption of roundabout in the study of traffic organization optimization of roundabout considering environmental benefits, a traffic emission and fuel consumption calculation model at roundabout based on VT-micro model was proposed by combining traffic flow parameter model with traffic emission and fuel consumption model, referring to the related modeling ideas. The research shows that the proposed model can accurately estimate the traffic emissions and fuel consumption of roundabout, and can be used for the quantitative analysis of the emissions and fuel consumption of roundabout, which is of great significance for the optimization of roundabout based on environmental benefits. References | Related Articles | Metrics

Transportation Infrastructure Engineering

Select

Two Point Corrosion Test Study of Steel Strands Based on Spontaneous Magnetic Flux Leakage Detection ZHOU Jianting1,2, LI Ya2, ZHANG Hong2, XIA Runchuan2, YANG Wenqi2 2021, 40(07): 74-81.  DOI: 10.3969/j.issn.1674-0696.2021.07.11 Abstract ( )   PDF (3377KB) ( )   In view of the variation rule of magnetic signal of steel strand with two corrosion points and the interaction between corrosion points, four groups of specimens with different spacings were designed. The corrosion degree was controlled by electrochemical corrosion device, and the magnetic leakage signal was measured by three-dimensional magnetic signal scanning device. The research shows that the criterion of single corrosion region is also applicable to two corrosion regions. However, when the two points are close to each other, the superposition of the magnetic signals will occur and the extreme value will appear. Moreover, the intersection distance of the magnetic signal curve is positively correlated with the distance between the corrosion areas at different lift heights. The magnetic signal of the specimen changes abruptly in the corrosion area, and its variation range has a certain width. The distribution of the influence width and the corrosion degree is Boltzmann function. 此后英文替换The influence width of the curve can be used to evaluate the corrosion degree of a single corrosion zone and to determine the minimum spacing between two corrosion zones without superposition under a given degree of corrosion. References | Related Articles | Metrics

Select

Application of BIM Technology in Tunnel Design Based on CATIA QIN Haiyang1, TANG Yongjing1,2, CHEN Zhiyuan3 2021, 40(07): 82-87.  DOI: 10.3969/j.issn.1674-0696.2021.07.12 Abstract ( )   PDF (7519KB) ( )   The development of BIM technology and the theory of CATIA + BIM technology were introduced. The method of applying CATIA + BIM technology in tunnel design modeling was proposed. Taking Fuzhou Jinjishan Tunnel project as an example, CATIA + BIM technology was used to complete the modeling process in design stage, and some functional applications in construction stage and in operation and maintenance stage were improved. The results show that the “skeleton + body” characteristic of CATIA+BIM technology is consistent with the linear characteristics of tunnel engineering, and the modeling process of CATIA+BIM technology in tunnel engineering consists of five steps, which are mountain modeling, route skeleton, component body, parameter-driven and properties addition. And the information-sharing platform greatly facilitates the collaborative communication among design, construction and operation and maintenance departments. References | Related Articles | Metrics

Select

Prediction Method of Leakage State in the Yuxi-Mohan Railway Tunnel Based on TEM DAI Yuhao, WANG Hua, PENG Guibin 2021, 40(07): 88-92.  DOI: 10.3969/j.issn.1674-0696.2021.07.13 Abstract ( )   PDF (4599KB) ( )   he conclusion of TEM detection is subjective and biased because it highly depends on the working experience of the operators. In order to improve the accuracy and objectivity of TEM detection, the Xinping tunnel of the Yuxi-Mohan Railway was taken as the research object, which was prone to water flush accident under the scouring of the groundwater. Based on a large number of the TEM advanced water detection tests, the corresponding relationship between the range of apparent resistivity and the leakage state was determined. Meanwhile, an aqueous model with the size of 80 m×40 m×40 m (length×width×height) was established based on the Voxler software. Finally, the prediction method of the leakage state in the tunnel construction based on TEM was proposed and the quantitative prediction of leakage state in tunnel construction was realized. Through the verification of engineering examples, it is basically consistent with the excavation revealed by the site, which can meet the needs of on-site safety production. References | Related Articles | Metrics

Select

Rational Distance of Pile Foundation in Precipitous Cliff Section of Loess Area ZHANG Hua1, ZHANG Zhengqi2, CHENG Gao3,4, TIAN Boke1 2021, 40(07): 93-98.  DOI: 10.3969/j.issn.1674-0696.2021.07.14 Abstract ( )   PDF (4956KB) ( )   The standard assembly of small or medium span highway girder bridge has short cycle, strong terrain adaptability and remarkable economic effect, which is widely used in mountainous areas of China. However, due to the fixed route, standardized superstructure and the hilly and gully area of mountainous terrain, many bridge piles inevitably stand on precipitous cliffs and other undesirable terrain. On these terrains, the pile-soil interaction is complex and the stability of slope is sensitive. Reasonable distance between pile and slope can ensure the stability of slope and the safety of pile foundation construction. Aiming at the slope stability of precipitous cliff, the nonlinear finite element model was established by ABAQUS, and the strength reduction method was used to analyze the influence of different slope distances on slope stability, soil displacement and pile-soil contact state, taking the distance from pile body to the slope in front of pile as the parameter. The research results show that the high-steep slope belongs to the natural disadvantageous section, the slope safety coefficient is less than 1, and the potential sliding surface is steeper and located at the foot of the slope. With the increase of the distance between adjacent slopes of pile foundation, the overall displacement of the slope and the separation range of the soil in front of the pile in the limit state decrease first and then tend to be constant. Considering the influence of slope distance on the slope stability, displacement and pile-soil contact state, it is suggested that the distance of pile foundation on the top of steep slope should not be less than 10 m. References | Related Articles | Metrics

Select

Triaxial Test Study on Reinforcement Effect of Reinforced Cohesive Soil WANG Zongjian1,2, LI Chang1, XIAO Liang2, LU Liang2 2021, 40(07): 99-106.  DOI: 10.3969/j.issn.1674-0696.2021.07.15 Abstract ( )   PDF (2145KB) ( )   In order to study the reinforcement effect of reinforced cohesive soil in construction period, considering the disadvantages such as fast construction speed and poor drainage conditions of reinforced structures, the isotropic aluminum foil was selected as reinforcement material, and triaxial test was used to study the strength and deformation failure characteristics of reinforced cohesive soil in construction period. The test results show that the stress-strain characteristic curve of reinforced cohesive soil is strain softening type, and the specimens are tensile failure. Under the same axial strain, the greater the confining pressure is, the greater the axial differential stress is. Under the given confining pressure, the more layers of reinforcement, the better reinforcement effect. Under high confining pressure, when a certain axial strain is reached, the reinforcement will play a role; the higher the confining pressure is, the more obvious the hysteresis effect is. The reinforcement effect in cohesive soil is shown by the increase of cohesive strength of soil, which indicates that the quasi-cohesion theory can be used to analyze and evaluate the reinforcement effect of reinforced cohesive soil during construction. References | Related Articles | Metrics

Select

A Kind of Improved Divided Concrete Guardrail of Road Median ZHANG Shubao 2021, 40(07): 107-111.  DOI: 10.3969/j.issn.1674-0696.2021.07.16 Abstract ( )   PDF (5131KB) ( )   When the height of divided concrete guardrail of the road median is insufficient due to the pavement overlay, it is necessary to heighten the guardrail to improve the protective performance of the guardrail. A kind of improved concrete guardrail with steel members installed on the concrete guardrail was proposed. The simulation analysis and real vehicle collision test were carried out for three types of vehicles, namely car, large bus and large truck. The changes of occupant acceleration a and vehicle gravity center height HG after car collision were studied, and the deformation of improved concrete guardrail support beam and crossbeam after large bus or large truck collision were studied. The results show that after car collision, both the longitudinal and the transverse components of vehicle occupant acceleration are not more than 200 m/s2; and after large bus or large truck collision, the supporting beam and crossbeam of the improved concrete guardrail are deformed and partially damaged, and the vehicle could run out normally. The protection level of the improved concrete guardrail can reach SAm level. References | Related Articles | Metrics

Select

Effect of Rubber Powder on Frost-Resistance Durability of Concrete DONG Yuwen1, PENG Liang2, XIE Hui1 2021, 40(07): 112-117.  DOI: 10.3969/j.issn.1674-0696.2021.07.17 Abstract ( )   PDF (8602KB) ( )   Through the indoor test, the dynamic elastic modulus of concrete was measured by using impact elastic wave method. The effect of rubber powder and its content on frost resistance durability of concrete was researched by experiment. The results show that, compared with ordinary concrete, when the number of freeze-thaw times is less, adding appropriate amount of rubber powder will cause the quality of concrete to increase, the dynamic elastic modulus to decrease, the relative dynamic elastic modulus to increase and the compressive strength to decrease; so the content of rubber powder has little effect on the frost resistance of concrete. However, when the number of freeze-thaw times is more, adding appropriate amount of rubber powder will cause the mass loss ratio of concrete to decrease, the dynamic elastic modulus, relative dynamic elastic modulus and the compressive strength of concrete to increase; so the frost resistance of concrete is enhanced, and the optimal mixing amount of rubber powder for concrete is 15~20 kg/m3. Finally, the micro-mechanism of enhancing the frost-resistance durability of concrete by mixing rubber powder was researched through SEM test. The research results can provide theoretical basis and reference for the design of concrete frost resistance durability. References | Related Articles | Metrics

Select

Experimental Study on Performance of Nano-montmorillonite/SBS Composite Mixed Modified Asphalt ZHAO Wei 2021, 40(07): 118-122.  DOI: 10.3969/j.issn.1674-0696.2021.07.18 Abstract ( )   PDF (1844KB) ( )   The modified asphalt was prepared by compound mixing of nano-montmorillonite and SBS, which could improve the comprehensive performance of the modified asphalt and its asphalt mixture. The nano-montmorillonite and SBS modifiers with different dosages were selected for re-doping, and the softening point, penetration, ductility, rotational viscosity and dynamic shear rheological tests were used to evaluate the performance of the modified asphalt. The influence of nano-montmorillonite content on the performance of modified asphalt was explored. The research results show that the ductility of asphalt is greatly affected by the amount of nano-montmorillonite. When the amount of nano-montmorillonite is 3%, the rutting factor of the compound modified asphalt is 1.26 times higher than that of the ordinary SBS modified asphalt; the fatigue factor is 0.68 times lower than that of the ordinary SBS modified asphalt; thus, the performance of compound modified asphalt is the best. References | Related Articles | Metrics

Transportation Equipment

Select

Active Control of the Straddle-Type Monorail Vehicle with Single-Axle Bogie XIN Liang1,2, DU Zixue1, YANG Zhen2, XU Zhouzhou2 2021, 40(07): 123-127.  DOI: 10.3969/j.issn.1674-0696.2021.07.19 Abstract ( )   PDF (1475KB) ( )   In order to improve the operation quality of the straddle-type monorail vehicle with single-axle bogie, the active control dynamic model of 15 DOF single-axle monorail vehicle was established, taking a single-axle bogie straddle type monorail vehicle as the research object. On this basis, an adaptive network-based fuzzy inference system PID (ANFIS-PID) controller was designed to suppress the lateral and vertical vibration of the vehicle body, and was compared with the original monorail and PID control monorail. The research results show that: compared with the original monorail, the root mean square value of lateral acceleration of PID control monorail and ANFIS-PID control monorail is reduced by 48.37% and 89.06%, the root mean square value of vertical acceleration is reduced by 19.41% and 34.32%, the peak value of lateral acceleration is reduced by 53.00% and 90.30%, and the peak value of vertical acceleration is reduced by 21.72% and 37.60%, respectively. ANFIS-PID control monorail is better than PID control monorail, which can significantly improve the operation quality of monorail vehicles. References | Related Articles | Metrics

Select

Multi-objective Optimization of Shift Law for Two-Gear AMT Based on NSGA-Ⅱ Algorithm ZHANG Dongdong, ZONG Zichun, FENG Jinzhi 2021, 40(07): 128-135.  DOI: 10.3969/j.issn.1674-0696.2021.07.20 Abstract ( )   PDF (2514KB) ( )   Two-gear transmission improves pure electric vehicle performance through reasonable gear switching. Taking the two-gear automatic mechanical transmission (AMT) of pure electric vehicle as the research object, considering the power and economy of the whole vehicle, a comprehensive shift law was proposed. The mathematical model of the power and economy shift law of two-gear transmission system was established. Taking 0-100 acceleration capability and energy consumption per mileage as optimization objective, the Paerto optimal solution of shift law was obtained by optimization solution of NSGA-II algorithm; and the motor efficiency was taken as the selection condition of optimal solution, and the optimal shift law of comprehensive performance was obtained. In MATLAB/Simulink, the simulation and evaluation model of shift law was built to compare and evaluate the three kinds of shift laws, such as the best power performance, the best economy and the best shift law of comprehensive performance. The results show that the proposed multi-objective optimization method for gear shift law is effective, and the comprehensive performance optimal shift law takes both power and economy into account. References | Related Articles | Metrics

Select

Defect Recognition Algorithm for Vehicle Metal Materials LI Shengyong1, ZHANG Zhihua1, WANG Shengnan2, WANG Meng2 2021, 40(07): 136-144.  Abstract ( )   PDF (15124KB) ( )   As the main material of important equipment in modern transportation, the defect of metal is of great significance to the safety of transportation. In order to realize the automatic identification of the defect of metal equipment, a visual detection algorithm based on deep convolutional neural network was proposed. The proposed algorithm focused on industrial defect identification. An hourglass type feature fusion module and a pyramid feature refinement module were designed, which considered both accuracy and speed, and effectively improved the efficiency of defect location and classification based on metal image. Finally, with the help of computer platform training discriminant model, automatic detection was realized. The proposed algorithm achieves advanced test results on public image datasets and enables efficient operation for mobile devices. References | Related Articles | Metrics