Archive

21 June 2022, Volume 41 Issue 06 Previous Issue    Next Issue
---
Transportation+Big Data & Artificial Intelligence
Transportation Infrastructure Engineering
Transportation Equipment


For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Transportation+Big Data & Artificial Intelligence

Select

Influencing Factors of Waterway Traffic Accidents Based on Clustering Analysis ZHANG Qingnian1, ZHANG Jin1, YANG Jie2, YANG Jiao1, YE Mengwen1 2022, 41(06): 1-7.  DOI: 10.3969/j.issn.1674-0696.2022.06.01 Abstract ( )   PDF (946KB) ( )   In order to analyze the main factors affecting the severity of waterway traffic accidents, factor analysis method was used to transform independent variables into mutually independent public factors. Then, according to the obtained main factor, the K-means clustering algorithm was used to cluster waterway traffic accident data. Finally, the Logistic model was used to establish the severity classification model for the accident data. The results show that compared with Logistic regression of potential categories, the Logistic regression model based on clustering analysis has higher accurate identification rate and prediction accuracy. Season, accident cause, ship ownership etc. are only significant in a certain category; the time period, gross tonnage and ship type etc. are significant in multiple categories. Although gross tonnage is significant in multiple categories, it has different influence directions on the severity of the accident. References | Related Articles | Metrics

Select

Model of Empty Container Transportation with Time Window Based on GASA MIN Dequan, SUN Haiping 2022, 41(06): 8-13.  DOI: 10.3969/j.issn.1674-0696.2022.06.02 Abstract ( )   PDF (1475KB) ( )   Empty container transportation is an indispensable link in shipping container transportation. When the container arrives at the port too early, the port storage cost will be incurred, and when the container arrives at the port too late, there will be opportunity loss cost. Based on this, considering the diversity of container types and transportation modes, an empty container transportation model with time window constraints was established with the goal of minimizing the total cost. On the basis of genetic algorithm, the simulated annealing algorithm was introduced to solve the proposed model, and a certain annealing probability was used to determine whether to accept the mutation. The elitist retention policy was adopted by fitness ranking to prevent the optimal individual from being destroyed, and the penalty term processing constraint conditions were constructed. The research results show that the genetic simulated annealing algorithm can effectively solve the problem of empty container transportation. References | Related Articles | Metrics

Select

Determination of Public Transport Network Potential Transportation Capacity Based on Bi-level Programming WU Lei1, DONG Keyang2, ZHOU Xiaoxiang3 2022, 41(06): 14-21.  DOI: 10.3969/j.issn.1674-0696.2022.06.03 Abstract ( )   PDF (2586KB) ( )   The capacity of urban publie transport system, its corresponding robustness and resilience, are the hot researching issues recently. According to the characteristics of urban public transport system, a bi-level programming model (BLP) was proposed to determine the reserved transportation capacity of the urban transit network, whose goal was to maximize the interests of both the operation department and travelers. In the bilevel programming model, the upper model was a minimum cost maximum flow model, and the lower model was a stochastic user equilibrium (SUE) allocation model. For the proposed model, a solution algorithm based on OD quantity expansion was designed, and a simple network was given to illustrate the effectiveness of the proposed model and the solution algorithm. The results show that the proposed model and solution algorithm can effectively find the balance of interests between operators and travelers. References | Related Articles | Metrics

Select

Short-Term Traffic Flow Forecast Method Based on EEMD-Wavelet Threshold MA Yingying, JIN Xuezhen 2022, 41(06): 22-29.  DOI: 10.3969/j.issn.1674-0696.2022.06.04 Abstract ( )   PDF (6659KB) ( )   In order to overcome that the existing short-term traffic flow prediction methods failed to fully consider the randomness and nonlinearity of traffic flow, a short-term traffic flow prediction model construction method based on ensemble empirical mode decomposition algorithm (EEMD) combined with wavelet threshold was proposed. Firstly, EEMD was used to decompose the original traffic flow data into N intrinsic mode functions (IMF) and a residual component (Res). Secondly, wavelet analysis was used to process the eigenmode function of noisy signal. Finally, two types of model construction methods were proposed. Method 1: the N IMF and Res processed by wavelet analysis were reconstructed and input into long short-term memory (LSTM) model, sequence to sequence (Seq2seq) model and Seq2seq-Attention model respectively, and their output were the final predicted values. Method 2: the N IMF and Res processed by wavelet analysis were input into long short-term memory (LSTM) model, sequence to sequence (Seq2seq) model and Seq2seq-Attention model respectively, and the output of these models was the predicted value of each component, which was the final predicted value after reconstruction. The two types of model prediction methods were compared with the initial LSTM model, Seq2seq model and Seq2seq-Attention model as well as the combined prediction models based on wavelet analysis and LSTM model, Seq2seq model and Seq2seq-Attention model. The results show that the two types of model construction methods can significantly improve the prediction performance of the initial prediction model. Compared with the combined prediction model based on wavelet analysis, its prediction performance has been improved; and compared with method ①, method ② has a more significant effect on improving the performance of the model. References | Related Articles | Metrics

Select

Lane-Changing Decision Model Based on Prospect Theory GU Jingang1, PU Kechen2, YANG Da1,2, LYU Meng2, ZHU Zibo1 2022, 41(06): 30-36.  DOI: 10.3969/j.issn.1674-0696.2022.06.05 Abstract ( )   PDF (1881KB) ( )   Lane-changing behavior is one of the basic driving behaviors and a basic algorithm of traffic simulation. It is of great significance to study lane-changing behavior. At present, there is a strong assumption in many lane-changing models established by scholars, that is, all drivers are completely rational, which cant reflect the drivers bounded rationality in evaluating the effectiveness of lanes and makes the model inconsistent with the actual situation. In view of this, the prospect theory was introduced to establish a new lane-changing decision-making model, which could reflect the potential irrational behavior of drivers in the process of lane -changing decision-making. The established model could reflect more realistic driving behavior. According to current research, the two indicators such as front vehicle speed and headway distance were selected to evaluate the drivers satisfaction with the lane. Considering the drivers risk preference and the trade-off of objective probability, the foreground values of different lanes were calculated, and the Logit model was established. Finally, the probability of the driver making a lane-changing decision was obtained. The study found that the proposed model has better accuracy and stronger applicability than the model based on random utility theory does, and the drivers received information and cognition of the behild vehicle on the target lane are relatively limited during the lane-changing decision process. References | Related Articles | Metrics

Select

Setting of Left-Turn Waiting Area Based on Mixed Traffic Environment CHENG Wei, ZHAO Jie, LI Bing 2022, 41(06): 37-45.  DOI: 10.3969/j.issn.1674-0696.2022.06.06 Abstract ( )   PDF (5226KB) ( )   In order to optimize the design of the left-turn waiting area in the mixed traffic environment, the compound relationship between left-turn motor vehicle delay and left-turn non-motor vehicle row width and swell number was determined by fitting the actual data. And the model of the number of the expansion conflicts between left-turn motor vehicle and non-motor vehicle in the waiting area and the traffic capacity calculation model of the left-turn waiting area under the influence of non-motor vehicles were proposed. Meanwhile, according to the severity of the conflict between left-turn motor vehicle and non-motor vehicle, the organization optimization methods of direct left turn and early release of non-motor vehicles were put forward respectively. Finally, taking the actual intersection as an example, the geometric settings of the waiting area and the organization of non-motorized vehicles were optimized, and the changes of the number of the expansion conflicts between left-turn motor vehicle and non-motor vehicle and the traffic capacity of the waiting area before and after the improvement were compared. The results show that when the conflict between motor vehicles and non-motor vehicles is serious, the intersection traffic efficiency is significantly improved; and the traffic capacity of the left-turn waiting area of the optimized intersections is basically unchanged, but the total number of conflicts decreases by 46.2% and 23.6%, respectively. The research shows that the proposed method of setting the left-turn waiting area under the influence of non-motorized vehicles can effectively reduce the safety hazards of mixed left-turn traffic flow at urban road intersections. References | Related Articles | Metrics

Select

Evaluation of Regional Parking Lot for Resource Management and Comprehensive Service HAN Yan1, PENG Yuqing1, DUAN Xiaoning1, ZHAO Shen2, CHEN Xumei2 2022, 41(06): 46-52.  DOI: 10.3969/j.issn.1674-0696.2022.06.07 Abstract ( )   PDF (2866KB) ( )   In order to improve the operation efficiency of regional parking lots and improve the public travel service level, the resource management and comprehensive service requirements of regional parking lots were discussed from the perspectives of the government, operators and users respectively, a comprehensive evaluation index system of regional parking lot considering six aspects such as operation efficiency, service level, traffic impact and informatization level was constructed. Based on the fuzzy comprehensive evaluation method, the evaluation model of regional parking lot was established, and a regional parking lot was taken as an example. The example analysis results show that: the comprehensive service ability of parking lots in zone 1 and zone 2 are rated between B and C, and the weakest index is operation efficiency, which is 1.92 and 1.15 respectively. References | Related Articles | Metrics

Select

Economic Analysis of Shading Sheds for Expressway Tunnels HAN Zhi1,2, GUAN Yuyan2 2022, 41(06): 53-57.  DOI: 10.3969/j.issn.1674-0696.2022.06.08 Abstract ( )   PDF (3183KB) ( )   In order to reduce the energy consumption and project cost during the tunnel operation, the visual adaptation curve was used to determine whether or not to erect the tunnel shading shed. The luminance mathematical model and the required luminous flux difference model of single tunnel and adjacent tunnel were established, and the difference of lighting power between them was calculated based on the difference model. Taking the construction cost of the shading shed and its subsequent operation and maintenance cost into account, the lighting economy of setting shading shed was analyzed and the conditions of setting shading shed are proposed. The research shows that if only the construction cost of shading shed is considered, when the saved luminous flux cost of lamps is greater than or equal to the construction cost, the establishment of shading shed is more lighting economic; if the construction and subsequent maintenance costs of the shading shed are considered, when the sum of the saved luminous flux cost, electricity cost and maintenance cost of the lamps is greater than or equal to the construction cost and maintenance cost of the shading shed, the establishment of the shading shed is more lighting economic. References | Related Articles | Metrics

Transportation Infrastructure Engineering

Select

Dynamic Characteristics of Station Structures with Different Sections under Earthquake REN Qingyang1, PENG Zijian2, WANG Feifei2, ZHAO Mengyuan2 2022, 41(06): 58-65.  DOI: 10.3969/j.issn.1674-0696.2022.06.09 Abstract ( )   PDF (10312KB) ( )   Under the action of vertical earthquake, the overlying soil of the station is easy to be sheared and produce inertial force effect, which increases the load of the station structure and affects the ability of the key structure to resist external force and deformation. Referring to the section size of Dakai metro station in Japan, ABAQUS was used to establish 2D and 3D models of the metro station, and the nonlinear dynamic time-history analysis was carried out to obtain the relative displacement time-history response of the end of the central column and the distribution of vertical load on the central column and side walls. A 3D refined model of the central column was established. By applying the relative displacement response at the end of the central column obtained in 2D analysis as a load on the top surface of 3D refined model of the central column, the bearing ratio of the central column and the stress of the side wall under different section forms, as well as the failure mode of the central column after the earthquake were obtained. The research results show that: after the shear resistance of the overlying soil fails, under the vertical earthquake, its inertial force acts on the roof of the station structure; the coupling effect of the inertial force and the shear load generated by the side wall soil under the horizontal earthquake makes the middle column under the rectangular section suffer compression shear failure, and then withdraw from the force. The use of the arched section can alleviate the high axial compression ratio of the center column structure under earthquake action, change the slenderness ratio and improve the ductility of the central column, which keeps the central column in the state of bearing force after the earthquake and avoids the overall damage of the station structure. References | Related Articles | Metrics

Select

Calculation Method of Deflection of Steel Truss Web Concrete Composite Beam CHEN Jianbing1, JIANG Mingli1, ZHOU Chen2, KUANG Guanhua1 2022, 41(06): 66-72.  DOI: 10.3969/j.issn.1674-0696.2022.06.10 Abstract ( )   PDF (3745KB) ( )   In order to study the deformation performance of the steel truss web concrete composite beam under vertical load, the shear deformation of the steel truss web member was considered, the shear deformation displacement function of the steel truss web concrete composite beam was introduced and the Timoshenko beam theory and the energy variation principle were used, to derive the deflection calculation equation of steel truss web concrete composite beam under different loading conditions. Combined with the ABAQUS finite element analysis example, the deflection values of the simply supported steel truss web concrete composite beam under different loading conditions were compared and analyzed. The research results show that the results of the deflection calculation formula for steel truss web concrete composite beams agree well with the finite element analysis values. The influence of shear and bending deformation on the deflection of steel truss web concrete composite beams is over 98%, and the additional deflection caused by the shear lag effect is only about 1.2%. References | Related Articles | Metrics

Select

Construction Control Technology for Closure of Side Span and Large Section of Yumenkou Bridge WEI Jiale1, SHU Tao1,2, WANG Xu3 2022, 41(06): 73-78.  DOI: 10.3969/j.issn.1674-0696.2022.06.11 Abstract ( )   PDF (3902KB) ( )   In the construction of closure section of long-span steel-concrete composite girder cable-stayed bridge, there are a series of problems, such as high demand of control accuracy and large control difficulty. Taking a steel-concrete composite girder cable-stayed bridge with double pylons and double cable planes with a main span of 565m as an example, the method of side span and large segment closure was applied. The sample bridge had the characteristics of long closure section of side span design and large height difference of closure mouth. For smooth closure, firstly, the spatial beam-plate combination model was established to finely simulate the assembly process of parts and accurately calculate the closure counterweight. Secondly, 48h joint measurement was carried out for the spacing, elevation and axis deviation of the main girder at the upstream and downstream closure openings to determine the optimal closure temperature. Finally, the accurate manufacturing parameters of each closure section steel girder were determined. The practice shows that the matching and cutting method has good applicability to the closure construction of large section, and the closure accuracy of the proposed bridge is high. References | Related Articles | Metrics

Select

Bonding Performance between Waterborne Epoxy Slurry Lower Seal Layer and Semi-rigid Base of Cement Pavement YANG Jianhua, FANG Ying, ZHANG Zhengqi 2022, 41(06): 79-86.  DOI: 10.3969/j.issn.1674-0696.2022.06.12 Abstract ( )   PDF (5454KB) ( )   In order to explore the bonding performance between waterborne epoxy slurry lower seal layer and semi-rigid base of cement pavement, the composite test specimens consisting of “semi-rigid base, waterborne epoxy slurry seal and cement concrete plate” were firstly fabricated by selecting raw materials and designing the mix proportion. On this basis, by means of direct shear test with vertical load, the effects of seal gradation, post seal curing temperature, seal forming temperature and surface contamination degree of semi-rigid base on the bonding performance between waterborne epoxy slurry seal and semi-rigid base were compared and analyzed under different slurry seal binder conditions, and the measures to ensure the bonding performance between the above two were put forward. The experiment results show that compared with matrix emulsified asphalt and SBR modified emulsified asphalt, the bonding performance between waterborne epoxy SBR modified emulsified asphalt slurry seal and semi-rigid base is obviously better. All factors have the same influence on the bonding performance between the seal coat and semi-rigid base course of different binders, which shows that the seal gradation, molding temperature and pollution degree have a great influence on the interlayer bonding performance, while the curing temperature at the late stage has a small influence on the interlayer bonding performance. It is recommended to select the fine-grained slurry seal, lay the seal layer at a molding temperature of 20 ℃ and clean the semi-rigid base before laying to guarantee the bonding performance between the slurry seal and semi-rigid base. References | Related Articles | Metrics

Select

Effect of Surface Texture at Micro-surface Pavement on Driving Noise KONG Linyun1, WANG Jian2, LUO Yadan3 2022, 41(06): 87-91.  DOI: 10.3969/j.issn.1674-0696.2022.06.13 Abstract ( )   PDF (4610KB) ( )   The traffic noise of micro-surface pavement is larger than that of hot mix asphalt concrete pavement, and the excessive noise seriously restricts the popularization and application of micro-surfacing pavement technology. Through the indoor accelerated loading test and the self-developed noise test system on the linoleum specimen, the influence of the micro-surfacing gradation and the admixture type on the road noise of the micro-surfacing pavement was studied. The results show that: the finer the gradation at the micro-surfacing, the smaller the vibration acceleration of the road tire. The noise value and vibration acceleration change value during the test are relatively stable, and do not fluctuate greatly with the increase of time. The incorporation of rubber particles and fibre particles can effectively reduce the road noise on the original micro-surfacing pavement. References | Related Articles | Metrics

Select

Influence of Biological Rejuvenator on Molecular Agglomeration Behavior of Aged Asphalt TANG Wen, GUO Yingjun, LYU Yuejing, CHEN Hua 2022, 41(06): 92-97.  DOI: 10.3969/j.issn.1674-0696.2022.06.14 Abstract ( )   PDF (5640KB) ( )   The 12-molecule model of the aged asphalt was established based on analyzing the functional groups changes in the aging process of asphalt by ATR-FTIR. Two kinds of aging asphalt-regenerant molecular dynamics models were constructed by adding steroids and carboxylic acids. The radial distribution function of asphaltene centroids at different temperatures was calculated, and then its aggregation behavior was investigated. The results show that the aggregation degree of asphaltene molecules decreases with the increment of temperature. Both rejuvenators exhibit better deagglomeration performance at ordinary temperature, and the performance of steroid is better than that of carboxylic acid. The deagglomeration effect is weakened at high temperature. And the optimal dosage of both two rejuvenators is 10% at ordinary temperature. References | Related Articles | Metrics

Select

Coupling Influence of Rainfall Infiltration and Traffic Load on Silt Roadbed GENG Daxin, MENG Cheng, WANG Jun, YANG Zechen 2022, 41(06): 98-104.  DOI: 10.3969/j.issn.1674-0696.2022.06.15 Abstract ( )   PDF (13950KB) ( )   The coupling influence of rainfall infiltration and traffic load on the roadbed was analyzed by model test. The stress state and settlement development of low liquid limit silt roadbed under cyclic traffic load and the coupling effect of rainfall infiltration and traffic load were analyzed respectively. The impact of rainfall and traffic load on the bearing performance of roadbed was studied from the macro level. Subsequently, the initial state of the roadbed, the roadbed under the action of cyclic traffic load, the roadbed under the coupling of rainfall infiltration and traffic load were respectively sampled and scanned by the electron microscope scanning experiment. And the causes of the weakening of the roadbed bearing performance were studied from the meso-structure level. The results show that there is no significant change of the bearing performance of the roadbed under the action of the single-circle traffic load of the two-wheel group, but the bearing performance of the roadbed is significantly reduced under the coupling action of rainfall infiltration and traffic load. The dynamic stress on the upper surface of the base layer is reduced by about 17%, and the settlement increases by about 20%. References | Related Articles | Metrics

Select

Optimization Application of Line Field Analysis Method in Tensile Fracture Failure of Intermittent Periodic Cracked Rock Mass TANG Hongmei, ZHOU Fuchuan, YAN Ning, SHANG Chao 2022, 41(06): 105-112.  DOI: 10.3969/j.issn.1674-0696.2022.06.16 Abstract ( )   PDF (6782KB) ( )   A large number of tensile cracks are developed in the rock mass of anticline core. Scientific interpretation of this special and common geological phenomenon is conducive to the evaluation, utilization and deepening the understanding of the evolutionary mechanism of geological hazards in this area. The geological model of intermittent cracked rock mass located in the tensile stress zone of the anticline core was generalized into a periodic crack model, and the central crack mechanics model was further obtained, and the optimized linear field analysis method was introduced for research. The results show that: the higher the crack coalescence rate, the greater the increase effect of shape modified coefficient on the stress intensity factor at the crack tip. The stress modified value has the characteristics of nonlinear monotonic increase with respect to the crack coalescence rate and linear monotonic increase with respect to the external load. Taking limestone rock mass as an example, the tensile strength of rock mass obtained by various theoretical calculations shows that the obtained solution is reasonable. When the crack half-length is constant, the tensile strength of rock mass decreases with the increase of crack coalescence rate. When the crack coalescence rate is constant, the tensile strength decreases with the increase of the crack half-length. The tensile strength of rock mass is inversely proportional to the square root of crack half-length, which shows that the tensile strength of rock mass is nonlinear with the linear change of crack half-length. When the crack half-length is between 0.2 m and 2.0 m, the tensile strength of the limestone rock mass does not exceed 1.0 MPa. The optimized line field analysis method of fracture mechanics is more convenient and faster. And the static equilibrium factor of rock bridge is a key to solve the modified stress value, tensile stress, the stress intensity factor and the shape modified coefficient of rock bridge as well as the rock mass fracture characteristic parameters such as the tensile strength of rock mass with central crack. Meanwhile, the research results have certain theoretical value and engineering significance. References | Related Articles | Metrics

Select

Application of Engineering Survey and Design BIM Technology in Landslide Control Project PENG Haiyou1, CHEN Yu2, REN Xiuwen3, CHEN Bolin1, GUO Qi1, ZOU Changsheng3 2022, 41(06): 113-118.  DOI: 10.3969/j.issn.1674-0696.2022.06.17 Abstract ( )   PDF (23619KB) ( )   D geology has been widely used in oil and gas, water conservancy and hydropower, minerals and other fields, while the application examples of engineering survey and design BIM technology developed from 3D geology in landslide treatment engineering are relatively few. By integrating the existing software and giving full play to the characteristics of each software, an application method of BIM technology for investigation and design of landslide treatment engineering was formed. Firstly, the survey data such as topographic mapping, geological drilling and geological profile were processed; secondly, with the help of the process modeling method of GOCAD software, the 3D geological model was constructed; finally, the 3D geological model was imported into the numerical analysis software to carry out the landslide treatment engineering design. Taking Chongqing Zhoujiayan landslide treatment project as an example, a practical application of the proposed BIM technical method for engineering survey and design was proposed. The practical effect of the project demonstrates the feasibility and practicability of the proposed technical method. References | Related Articles | Metrics

Select

Reservoir Carbon Dioxide Flux Prediction Based on CNN-LSTM Model and Small Sample Datas QIN Yu1, OUYANG Changyue1, FANG Peng2 2022, 41(06): 119-125.  DOI: 10.3969/j.issn.1674-0696.2022.06.18 Abstract ( )   PDF (4207KB) ( )   The data of the surface carbon dioxide partial pressure ［p(CO2)］ and corresponding physicochemical properties in water of a karst deep-water reservoir in Yunnan Guizhou Plateau—Wanfeng Lake Reservoir from 2016 to 2017 was collected to analyze the correlation between the CO2 flux and physicochemical properties in water. The convolutional neural network and long-short-term memory neural network hybrid model (CNN-LSTM model) was established to predict the CO2 flux in reservoir, which was based on the collected sample data. Research shows that the CO2 flux in summer in Wanfeng Lake Reservoir only has a significant correlation with pH and oxidation-redox potential (ORP), while in winter it is significantly related to water temperature (T), pH, alkalinity (ALK), total dissolved solid (TDS) and conductivity (Cond). In a complete year, all physicochemical properties in water are important factors influencing CO2 flux. Finally, 80% of the training data are used to train the CNN-LSTM model and 20% of the test data to test the absolute mean error (MAE), root mean square error (RMSE) and correlation (R2) of the model. The CNN model, LSTM model and DNN model were established to compare with the CNN-LSTM model, the R2 between the predicted value and the measured value of the four models are higher than 0.90, and the MAE and RMSE of the proposed CNN-LSTM model were 2.64 and 3.85 mmol/(m2·d), which was lower than those of the other three models. The CNN-LSTM model can perform more effectively in feature extraction and data prediction. References | Related Articles | Metrics

Transportation Equipment

Select

Driving Construction of Electric Vehicles Based on t-SNE and Fuzzy Clustering WANG Jingang1,2,3, XU Hang1,2, LIU Hai1,2, YU Hanzhengnan4, LIU Yu4 2022, 41(06): 126-132.  DOI: 10.3969/j.issn.1674-0696.2022.06.19 Abstract ( )   PDF (6629KB) ( )   By constructing the driving conditions of electric vehicles in typical cities, the laws of driving and energy consumption can be predicted. Taking Tianjin as an example, 20 feature parameters and 24 distribution parameters were extracted from the actual road data of 10 battery electric passenger cars for one month. And t-distributed domain embedding algorithm, fuzzy c-means clustering and grey correlation analysis were used to construct the working condition. The validity of the driving conditions was verified by MAPE and K-S tests. Moreover, the typical driving conditions at home and abroad were compared and analyzed. The research results show that the MAPE error between the constructed working condition and the actual road data is 3.82%; K-S test values are 0.0471 and 0.0126. The constructed working conditions are consistent with the actual driving conditions. References | Related Articles | Metrics

Select

Path Following Control for Intelligent Connected Vehicle Based on QPSO Algorithm CAO Qingsong1, YI Xing2, XU Li2 2022, 41(06): 133-139.  DOI: 10.3969/j.issn.1674-0696.2022.06.20 Abstract ( )   PDF (2457KB) ( )   The problem of path following is one of the research hotspots of intelligent connected vehicle, and the quality of design for path following controller has a direct impact on the reliability of intelligent connected vehicle. Comprehensively considering the vehicles path following accuracy and lateral stability, the 2-DOF vehicle handling dynamics model and path following error model were established. The desired yaw rate was determined by inverse method, and the path following controller was designed by using quadratic optimal control method. The parameters c1, c2 and k in the expression for desired yaw rate were optimized by using QPSO. Taking lane-changing behavior and curved road driving as examples, the control effect of the optimized controller parameters and the robustness of the controller under different vehicle speeds and different path curvature frequencies were simulated. The results show that after optimizing the parameters c1, c2 and k, the controller improves the control effect of vehicle centroid sideslip angle and yaw rate. When the vehicle speed and the frequency of path curvature change, the controller has obvious robustness. This study can further improve the vehicles path following accuracy and lateral stability, which provides a certain reference for the research of path following control of intelligent connected vehicle. References | Related Articles | Metrics

Select

Optimization of Neural Network Inverse Model of Magnetorheological Damper HU Qiguo, GOU Zhonghua, YU Zhiwei 2022, 41(06): 140-146.  DOI: 10.3969/j.issn.1674-0696.2022.06.21 Abstract ( )   PDF (3366KB) ( )   Aiming at the problem that it is difficult to determine the input control current by calculating the expected damping force of semi-active suspension with automotive magnetorheological damper, the forward model was established by adopting the generalized Spencer phenomenon model, firstly considering the obvious nonlinear hysteresis characteristics of the magnetorheological damper forward dynamics model. Combined with the BP neural network, the magnetorheological damper inverse model was established. Then the BP neural network with strong mapping ability was optimized by using the rapid convergence and overall optimization ability of particle swarm optimization algorithm to improve the accuracy of input control current. Finally, the optimized magneto-rheological damper inverse model was combined with the semi-active suspension control system for simulation verification. The simulation results show that: compared with the actual control current, the optimized magneto-rheological damper inverse model can calculate the input control current more accurately, and its relative error is greatly reduced; in addition, all the performance indexes of the optimized suspension system are improved. References | Related Articles | Metrics