Archive

19 August 2022, Volume 41 Issue 08 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

Location Selection of Multiple Level Marine Emergency Material Reserves Based on Gravity Model CHANG Zheng, FAN Hanwen, ZHANG Lingye 2022, 41(08): 1-7.  DOI: 10.3969/j.issn.1674-0696.2022.08.01 Abstract ( )   PDF (1197KB) ( )   In order to meet the needs of emergency rescue and reduce unnecessary construction of the reserve, the location of emergency material reserve under multiple capability levels was studied. A gravity model reflecting the service level and spatial distance characteristics of the emergency material reserve under different construction levels was introduced, and a multi-objective location model under the full coverage theory was constructed, and an improved bat algorithm was designed to solve the model. The improved algorithm and model were used to calculate the example to obtain the Pareto solution set that met the requirements of the problem, and then the TOPSIS method was used to obtain the optimal solution of the problem. In order to verify the effectiveness of the proposed model, it was compared with the optimal solution of the location model under the fixed capacity level. The results show that on the premise of meeting emergency needs, the multiple capability level location model can effectively save a lot of fiscal costs and improve the efficiency of emergency rescue compared with the fixed capability level location model. References | Related Articles | Metrics

Select

Prediction of Transportation Capacity of Urban Agglomeration Based on Gray Model-Generalized Regression Neural Network Model WANG Yihong1, LI Yaxuan1, TIAN Pingye1, LUO Jiugang2 2022, 41(08): 8-16.  DOI: 10.3969/j.issn.1674-0696.2022.08.02 Abstract ( )   PDF (3048KB) ( )   The transportation capacity of urban agglomerations is the strategic cornerstone of building a national comprehensive three-dimensional transportation net. In view of the fact that traditional forecasting methods were difficult to adapt to many influencing factors and had the characteristics of time-varying, coupling and strong uncertainty, a gray model-generalized regression neural network compound model was proposed to predict the transportation capacity of urban agglomerations in the long-term. Firstly, the LASSO method was used to screen out the main influencing factors to reduce data complexity. GM (1,1) model was used to weaken the randomness of data series, predict the change trend of time series of influencing variables and fill in the lack of data. Then, GRNN model was trained by the dataset of Beijing-Tianjin-Hebei urban agglomeration from 2000 to 2019. According to the influencing factors predicted by GM (1,1) from 2020 to 2025, the dynamic trend of transportation capacity in the future years was obtained. The results show that the accuracy of the compound prediction model is better than that of traditional methods, which effectively reduces the uncertainty of the small sample prediction. Finally, combined with prediction results, the development direction of the core location cities of Beijing-Tianjin-Hebei urban agglomeration is analyzed, which makes a forward-looking discussion in order to help build a new development pattern with urban agglomeration as an important starting point. References | Related Articles | Metrics

Select

Short-Term Traffic Flow Forecasting Based on XGBoost JIAO Pengpeng1, AN Yu1,2, BAI Zixiu1, LIN Kun1,3 2022, 41(08): 17-23.  DOI: 10.3969/j.issn.1674-0696.2022.08.03 Abstract ( )   PDF (5627KB) ( )   In view of the contradiction between the complexity and the prediction accuracy of short-term traffic flow forecasting model, an ensemble learning XGBoost (eXtreme Gradient Boosting) model was proposed to predict traffic flow, making full use of its advantages of high prediction accuracy and fast calculation speed for high-dimensional characteristic data. Firstly, the outliers of the original data were processed by median filtering. Then, a forecasting model was established based on XGBoost model, which used the method of cross-validation to determine the optimal value of the super-parameter and obtain the importance of each feature by predicting the test set. Finally, the prediction results of the model were compared with those of other short-term traffic flow prediction methods. The results show that using median filter to reduce noise and making full use of traffic flow data of adjacent sections can significantly improve the prediction accuracy of the model. The prediction accuracy of XGBoost model is 96.6%. In comparison with the other short-term traffic flow forecasting models, the proposed model can more fully utilize the temporal characteristics and spatial correlation of traffic flow. References | Related Articles | Metrics

Select

Adaptive Traffic Signal Control Based on Deep Reinforcement Learning XU Jianmin1, ZHOU Xiangpeng1, SHOU Yanfang2 2022, 41(08): 24-29.  DOI: 10.3969/j.issn.1674-0696.2022.08.04 Abstract ( )   PDF (2506KB) ( )   In order to improve the robustness and adaptability of traffic control algorithms and ease urban traffic congestion, an adaptive traffic signal control method based on improved D3QN (dueling double deep Q-network, D3QN) was proposed. Firstly, several adaptive traffic control modes based on reinforcement learning were analyzed. Subsequently, a variable step-size action mode was proposed based on the fixed step-size action mode and a reward function based on space occupancy was constructed. Finally, an intersection in East Street of Zhongshan was simulated by software Sumo in steady flow and stochastic flow. The simulation results show that the proposed method exhibits excellent convergence and effectively reduces the delay time and the queue length. References | Related Articles | Metrics

Select

Roadside Parking Planning Model and Algorithm in Urban Built-up Area YANG Shengwen1, LI Te1, LIU Qinghua2, XI Wenhui1, YANG Min3 2022, 41(08): 30-36.  DOI: 10.3969/j.issn.1674-0696.2022.08.05 Abstract ( )   PDF (2707KB) ( )   In order to alleviate urban traffic congestion, a rational planning of roadside parking berths on urban roads was carried out. While solving the demand for roadside parking in the region, a berth setting scheme was proposed to maximize the traffic capacity of the road network. Firstly, the parking situation in the study area was investigated and the demand for roadside parking was calculated. Then, based on the road conditions, the ratio of traffic volume to basic traffic capacity and the distance between the road and the surrounding residential areas, the priority of the road in the area that met the requirement of setting roadside berths was determined. Finally, based on the road capacity and road priority after setting roadside parking berths, taking the maximum road capacity as the objective function and the maximum roadside parking space that the road can accommodate as the constraint, the road network capacity model was constructed, and the number of parking berths that should be planned for each road was calculated by using sequential quadratic programming method. VISSIM was used to simulate the road network in the study area under the conditions of flat peak traffic volume and peak traffic volume. Five indexes including total stop delay, number of stops, delay per vehicle, total delay time and total travel time were selected to compare the delay of the roadside parking berth setting method. The research results show that compared with the traditional roadside berths setting method, the delay of road network capacity model is lower than that of the conventional setting scheme, which effectively reduces the impact of setting roadside parking spaces on road capacity. References | Related Articles | Metrics

Select

Influence Mechanism of Ambient Temperature and Vehicle Speed on Drivers Cognition JIN Tao, WU Zhengxin, HE Jiamin, WANG Wenrui, GU Haoran 2022, 41(08): 37-42.  DOI: 10.3969/j.issn.1674-0696.2022.08.06 Abstract ( )   PDF (3821KB) ( )   The combined effect experiment adopts the perceptual perception paradigm method to analyze the impact of ambient temperature and vehicle speed on the drivers cognition. Based on the optimal vehicle speed under different ambient temperatures, the cognitive mechanism of the combined effects of low temperature-low speed, medium temperature-high speed and high temperature-low speed was further revealed. The EEG experiment used an auditory stimulation paradigm unrelated to driving tasks to trigger ERP. The results show that there are significant differences in the average amplitudes of the N100 waveform and P200 waveform in the frontal lobe region of the subjects in the three combined effects. From the perspective of brain cognitive neural mechanism, the cognitive mechanism of the three combined effects was explained. The research results show that the combined effect of ambient temperature and vehicle speed has a significant impact on cognitive performance. The differences in the activity of the drivers brain regions are monitored by brain electrophysiological technology to provide guidance for intelligent regulation of the ambient temperature in the vehicle. References | Related Articles | Metrics

Select

Numerical Simulation of the Coupling Effect of Water Mist and Longitudinal Ventilation on Tunnel Fire WANG Yaqiong1, 2, LI Peijun1, 2, REN Rui1, 2, LI Yong1, 2, SONG Xiao1, 2 2022, 41(08): 43-52.  DOI: 10.3969/j.issn.1674-0696.2022.08.07 Abstract ( )   PDF (5957KB) ( )   Aiming at the automatic water mist firefighting system of highway tunnel, a full-scale model with 20 MW fire source was established by FDS software to study the coupling effect of water mist and different longitudinal ventilation on smoke exhaust and cooling effect of tunnel fire. The research results show that when there is no water mist, with the acceleration of wind speed, the temperature above the fire source and 10m downstream of the fire source decreases, but the temperature at 5 m downstream of the fire source increases. When there is no longitudinal wind, the temperature reduction effect of water mist is limited, and the temperature fluctuates greatly after turning on water mist. Under the combined action of water mist and longitudinal ventilation, the temperature above the fire source and 10m downstream of the fire source can be well controlled, but the temperature at the lower position 5m downstream of the fire source shows an increasing trend (the wind speed is 2 m/s). When the longitudinal wind speed is 2 m/s, the water mist makes the smoke sink to about 5 m downstream of the fire source. References | Related Articles | Metrics

Select

Safety Assessment of Long-Span Multi-arch Tunnel Passing under Ancient Buildings GUO Jiajia1,2, ZHANG Guohao1,2, CHU Cun1,2,3,4 2022, 41(08): 53-57.  DOI: 10.3969/j.issn.1674-0696.2022.08.08 Abstract ( )   PDF (11059KB) ( )   Based on the large-span muti-arch tunnel project that goes through the ancient fortress site, based on the fine 3D geological modeling technology, the surface deformation caused by the tunnel going through the ancient building was analyzed by using FLAC3D simulation software, and the deformation and damage of the ancient building was evaluated. The research results show that the ground surface deformation is small when the middle guide tunnel is excavated, and it has little influence on the ancient buildings. When the front tunnel is excavated through, the settlement deformation of the ancient fort is greatly affected, but the horizontal deformation is little affected. The surface settlement deformation caused by excavation is the largest in the central area and decreases to the surrounding area, while the surface horizontal deformation is the smallest in the central area and larger in the surrounding area. The maximum settlement value of the ancient fort is 2.1 cm, and the maximum horizontal displacement value is 0.3 cm. The whole ancient fort is in elastic deformation state, indicating that the supporting parameters and construction scheme of the tunnel design are reasonable and feasible, and will not cause serious damage to the ancient building. References | Related Articles | Metrics

Transportation Infrastructure Engineering

Select

Application and Prospect of Machine Learning in the Field of Magnetic Memory Nondestructive Testing YANG Mao1,2，ZHANG Hong1, ZHOU Jianting1, LIU Renming1, CHEN Jun1 2022, 41(08): 58-66.  DOI: 10.3969/j.issn.1674-0696.2022.08.09 Abstract ( )   PDF (3030KB) ( )   As a newly emerged nondestructive testing technology, magnetic memory testing has the advantages of rapid and convenient detection of stress concentration and micro defects. Machine learning has strong learning ability and self-adaptive ability, which is suitable for processing large amount of non-linear data generated by magnetic memory detection. This article mainly reviewed the application status of machine learning algorithms in the field of magnetic memory nondestructive testing and considered the application of machine learning in magnetic memory detection of reinforcement damage inside bridges. Finally, the development trend of machine learning in this field was prospected. The results show that various machine learning algorithms represented by SVM, ANN and clustering have been widely used in magnetic memory testing, which are mainly used for damage grade evaluation and defect size inversion of steel specimens and have no relevant application in magnetic memory detection of bridge reinforcement damage. A single algorithm has great limitations, and the combination of multiple algorithms can improve prediction accuracy. To achieve the breakthrough development of magnetic memory in the detection of reinforcement damage inside bridges, it is necessary to consider the complex structure and detection environment. In the future, machine learning algorithm will be used to establish the relationship model between various influencing factors and magnetic signals. The regression algorithm in machine learning can also be further applied to the evaluation of defect degree. References | Related Articles | Metrics

Select

Defect Detection of Steel Tube Tunnel Based on Elastic Wave Image Recognition Method WU Peng, YUAN Ganglie, CHE Ailan 2022, 41(08): 67-72.  DOI: 10.3969/j.issn.1674-0696.2022.08.10 Abstract ( )   PDF (8390KB) ( )   In view of the structural characteristics of steel tube tunnels and the patterned characteristics of defects, based on the propagation characteristics of elastic waves in layered media, k-means clustering analysis was carried out on the response energy of elastic waves, which took the response energy of elastic waves E as the evaluation index and used the clustering analysis method in pattern recognition. And the defect pattern was evaluated with the result of clustering analysis as the threshold. The 22 meter long area of a steel tube tunnel with obvious deformation was taken as the research object, and the measuring points were arranged. 3D scanning measurement and elastic wave test were used to carry out the clustering analysis on the measured elastic wave signals at the defects. And the response energy threshold was divided to identify the void area, and the deformation characteristics of the inner wall of the steel pipe were evaluated. The research shows that defects in steel tube tunnels are randomly distributed, and some defects are connected to form a large disease area. The elastic wave response in the defect region is significantly amplified. The evaluation results of elastic wave signal response energy cluster analysis are in good agreement with 3D scanning results, which verifies the effectiveness of elastic wave image recognition method. References | Related Articles | Metrics

Select

Experimental Study on Shear Resistance of High Strength Bolt Shear Key of Steel UHPC Composite Beam HUANG Haixin1, ZHANG Dengke1, CHENG Shoushan2 2022, 41(08): 73-78.  DOI: 10.3969/j.issn.1674-0696.2022.08.11 Abstract ( )   PDF (6677KB) ( )   In order to improve lightweight and full assembly of steel-concrete composite girder bridges and the convenience of later replacement, the combination mode of easily removable bolt shear keys and UHPC (ultra-high performance concrete) bridge decks and their cooperative working performance are worth exploring. Two sets of push-out specimens with different opening structures were designed and fabricated to study the shear properties of high-strength bolt shear keys of steel UHPC composite beams under vertical shear loads. The test results show that the steel-UHPC push-out specimen exhibits the shear failure of the steel-concrete interface screw. Different from the steel-ordinary concrete push-out specimen, the pressure bearing concrete embedded in front of the nut doesn’t appear crushing and falling off when it is damaged. Compared with the wedge-shaped opening specimens, the stepped opening structure has a better limiting effect on the lifting behavior of UHPC plate relative to the steel beam contact surface, and the final lifting displacement of UHPC plate is reduced by nearly 14.5% compared with the former. The sliding stiffness of steel-UHPC is about 32.5% higher than that of steel-ordinary concrete push out specimens. References | Related Articles | Metrics

Select

Cantilever Casting Construction Mechanical Behavior of Lower Chord Arch Beam of Long-Span Beam-Arch Composite Rigid Frame Bridge LI Yayong1,2, YANG Peicheng3, ZHOU Xueyong1,2, CHEN Shengkai1,2, DING Yanchao4,5 2022, 41(08): 79-87.  DOI: 10.3969/j.issn.1674-0696.2022.08.12 Abstract ( )   PDF (13171KB) ( )   Based on MIDAS-FEA software, a finite element analysis model was established for the lower chord arch beam of Lijia Jialing River Bridge in the west section of the second horizontal line of Chongqing expressway. Four calculation conditions were established to compare and analyze the mechanical state of the lower chord arch beam with or without a support system. Stress, strain and deformation monitoring elements were installed in key parts such as pier arch joints, arch beam webs and support systems to master the law of stress and strain changing with the construction process. The research results show that, without the support system, the axial principal tensile stress of the pier arch joints reaches 2.8 MPa, which is about 43% higher than the designed tensile strength of C60 concrete (1.96 MPa), and there is a risk of tensile cracking. After the active jacking of the support system is adopted, the axial tensile stress decreases from 1.18 MPa to 0.26 MPa. The active jacking significantly improves the stress state of the arch beam. When cantilever casting 2# segment, the plastic zone of the arch beam is greatly reduced compared with that without support system. The monitoring data show that the stress and displacement of the supporting system (steel tube and bracket) change linearly with the lifting force during jacking. After jacking, the axial stress of the steel tube is about 98 MPa, the shear stress of the bracket is about 89 MPa, and the maximum settlement of the bracket is about 6 mm. In the preloading stage of bracket surcharge, the increase amplitude of stress and displacement of the support system is far less than the tensile stress of the root and web of the arch beam, and the load in the preloading stage is mainly borne by the lower chord arch beam itself. References | Related Articles | Metrics

Select

Mechanical Properties of Concrete Bridge Piers Based on SEA DU Qing, LUO Yalin, QING Longbang 2022, 41(08): 88-94.  DOI: 10.3969/j.issn.1674-0696.2022.08.13 Abstract ( )   PDF (3783KB) ( )   Super-elastic Alloys (SEA) are widely used in civil engineering because of its special super-elastic properties. In order to research the mechanical properties of concrete pier with built-in sea bar under cyclic load, the finite element model for bridge columns was established by finite element analysis software ABAQUS. The material constitutions of SEA rods and concrete were defined respectively by the built-in super elasticity and concrete damage plastic model of ABAQUS. In the modeling process, the hysteretic model of ordinary reinforcement was introduced, and the mechanical parameters of the pier, such as hysteretic curve, structural stiffness, yield stress and energy dissipation capacity were analyzed numerically. The numerical analysis results show that the finite element analysis can accurately simulate the stress state of high-performance materials under earthquake, which can be applied to the seismic analysis of high-performance materials and the design and improvement of corresponding structures. References | Related Articles | Metrics

Select

Seismic Fragility Analysis of Double-Deck Viaducts Frame Piers XU Chengxiang1,2, LUO Heng1, WANG Zhanjin1 2022, 41(08): 95-101.  DOI: 10.3969/j.issn.1674-0696.2022.08.14 Abstract ( )   PDF (4132KB) ( )   In order to study the fragility of the double-deck viaducts frame piers under seismic action, based on the destructive test under low cyclic reciprocating loading, a nonlinear finite element model was built on the OpenSees platform. A probabilistic seismic demand analysis was performed on the structural model by selecting 100 actual ground shaking records as input. Through the fragility analysis of the four kinds of defined damage limit states, the seismic fragility curves of frame piers were obtained. The effects of the column reinforcement ratio (ρ) and the stirrup reinforcement ratio (ρsv) on the seismic fragility of the frame piers were analyzed by varying the structural parameters. The research results show that the displacement ductility ratio of the double-deck viaducts frame piers for slight damage, moderate damage, severe damage, and complete destruction of the structure are 1.0, 2.0, 3.5 and 5.0 respectively, and the median spectral accelerations are 0.46g, 0.66g, 0.88g and 1.06g respectively. From the perspective of safety and economy, the reasonable reinforcement ratio and stirrup reinforcement ratio of the columns are 1.6%~2.2% and 1.0%~1.5% respectively. References | Related Articles | Metrics

Select

Transient Temperature Field and Fine Analysis Model of Concrete Cap Containing Cold Pipe HUANG Haidong1, XU Mingyao1, LI Ming2, LUO Chao1 2022, 41(08): 102-111.  DOI: 10.3969/j.issn.1674-0696.2022.08.15 Abstract ( )   PDF (9043KB) ( )   Setting cooling water pipe is a common method to reduce hydration heat of mass concrete cap. In the calculation and analysis, the equivalent algorithm is generally adopted, ignoring the heating effect of cooling water along the way and exaggerating the cooling effect of cooling water pipe to some extent. In order to accurately analyze the cooling effect of temperature variation along cooling water pipe on the hydration heat of concrete caps, a fine analysis model of concrete caps was proposed, which took the temperature variation of cold pipe along the process into account. Making use of ANSYS APDL programming language, the convection coefficient was determined by Gnielinski formula. The parametric model was established, and the automatic modeling of rectangular pile cap was realized. The effects of different algorithms, flow velocity, pipe length and pipe material on the transient temperature field of concrete were analyzed, the rule of concrete temperature change under the influence of many factors was studied and the optimal combination of pipe diameter and pipe spacing was discussed. The research indicates that the temperature field distribution of bearing platform concrete can be simulated more accurately after considering the temperature change along the cold pipe, and the reasonable flow rate, pipe length and pipe material can achieve more ideal cooling effect. In addition, the smaller the pipe diameter and pipe spacing are, the lower the maximum temperature of concrete is under the condition that the amount of water pipe material remains unchanged. References | Related Articles | Metrics

Select

Influence of Fine Aggregate Properties on the Technical Performance of GAC-16 Asphalt Mixture YANG Jun1, TANG Shengang1, XU Xinquan1,2 2022, 41(08): 112-119.  DOI: 10.3969/j.issn.1674-0696.2022.08.16 Abstract ( )   PDF (3225KB) ( )   In order to study the influence of fine aggregate properties on the technical performance of GAC-16 asphalt mixture, scanning electron microscope (SEM), suction column test and boiling test were used to analyze the properties of two types of fine aggregates including limestone and diabase. The high and low temperature performance, water stability and fatigue performance of GAC-16 asphalt mixture specimens formed by two kinds of fine aggregates under three preparation schemes were evaluated. The variation rule of dynamic modulus of three types of GAC-16 asphalt mixture at different loading frequencies was analyzed, and the dynamic modulus master curves of three types of GAC-16 mixture were fitted according to the time-temperature equivalent principle and nonlinear least square method. Thus, the influence of different fine aggregate properties on the technical performance of GAC-16 mixture was comprehensively analyzed. The research results show that diabase fine aggregate has higher surface roughness and surface free energy than limestone does, but it has poor resistance to boiling and peeling. Compared with limestone fine aggregate, the GAC-16 asphalt mixture with diabase fine aggregate has great high-temperature rutting resistance, but also has poor fatigue life and low-temperature cracking resistance. And there is little effect of the two fine aggregates on the water stability of GAC-16 mixture. Fine aggregate has some influence on the dynamic modulus of GAC-16 mixture, and the deformation resistance of GAC-16 asphalt mixture with diabase fine aggregate decreases significantly under low frequency (high temperature) conditions. Based on the results of boiling test, rutting test and dynamic modulus test, it is preliminarily concluded that the GAC-16 mixture prepared from diabase fine aggregate has higher temperature sensitivity under high temperature conditions. References | Related Articles | Metrics

Select

Experimental Study on Shear Strength of Phyllite Soil-Red Clay Mixed Soil ZHAO Xiushao, FU Zhitao, GENG Daxin, SHI Yufeng, WANG Ziyao 2022, 41(08): 120-126.  DOI: 10.3969/j.issn.1674-0696.2022.08.17 Abstract ( )   PDF (5450KB) ( )   There are a lot of phyllite soil and red clay in the middle and north of Jiangxi Province. Among them, phyllite soil can’t meet the strength requirements due to its low strength and is often treated as spoil. The method of using red clay to cement phyllite soil to improve the strength was proposed for the first time, the tests of immersion and non-immersion shear strength of phyllite soil-red clay mixed soil were carried out. The test results show that in the state of immersion and non-immersion, the cohesion (c) and the internal friction angle (φ) of the mixed soil samples increase significantly with the increase of mixing ratio, when the mixing ratio of the red clay λ≤60%. When λ > 60%, the shear strength index doesn’t increase significantly or even decreases. After the mixed soil is soaked in water, both the cohesion and internal friction angle decrease to a certain extent, and the reduction coefficient is used to describe the reduction range of shear strength. The cohesion reduction coefficient increases with the increase of the red clay mixing ratio, and the maximum cohesion reduction coefficient is 4.63 when the water content is 14%. The variation law of cohesion reduction coefficient is not obvious, and 2.7 can be taken as the conservative cohesion reduction coefficient when the water content is 18% and 22%. The variation range of internal friction angle reduction coefficient of the mixed soil samples is 1.04 ~ 1.72. The variation range is small when red clay mixing ratio are 40% and 60%, and the maximum value of 1.44 can be taken as the conservative reduction coefficient when the mixing ratio is 40% ~ 60%. Based on the strength and liquid plastic limit tests, it is proposed that the optimal range of red clay mixing ratio is 40% ~ 50%. References | Related Articles | Metrics

Select

Mechanical Response Test of SFRC Segment under Jacking Construction DENG Yisan, LI Deming, CHEN Daibing 2022, 41(08): 127-133.  DOI: 10.3969/j.issn.1674-0696.2022.08.18 Abstract ( )   PDF (8713KB) ( )   The material constitutive law of SFRC was established by the 3-point bending test on a notched beam, and plastic axial tensile strength was obtained. The full-scale SFRC segments with different steel fiber content and reinforcement configuration were used in the jacking test, and the failure process curve of shield segment under the jacking force was obtained. The failure mode, cracking load, initial crack location and crack propagation path of unreinforced and less reinforced SFRC segments were studied. Through numerical simulation, the mechanical response law of the jacking test was simulated, and the corresponding relationship between jacking load and segment stress was established. Then, taking the stress reaching the plastic axial tensile strength as the cracking criterion, the jacking control load obtained from the test was verified. The research results show that both unreinforced and less reinforced SFRC segments can meet the bearing capacity requirements under the reciprocating action of common construction jacking forces. Under the action of jacking load, the initial failure position of segment is in the tensile stress area on the opposite side of the loading point. The reinforcement configuration has a significant effect on the crack resistance toughness of SFRC segments under the action of jacking load. The ability of crack control of unreinforced SFRC segment is poor, so the crack load should be taken as the control load under the jacking condition. References | Related Articles | Metrics

Transportation Equipment

Select

NOx Emission Prediction Model of Heavy-Duty Vehicle Based on DBSCAN and CNN Algorithm YU Shu1,2, YANG Zhigang2 2022, 41(08): 134-141.  DOI: 10.3969/j.issn.1674-0696.2022.08.19 Abstract ( )   PDF (5843KB) ( )   Heavy vehicle emission post-treatment system includes complex tail gas treatment units and supporting sensors. In order to simplify and optimize the post-treatment system, a NOx emission prediction model was established based on the improved DBSCAN algorithm and CNN model. The proposed prediction model could be deployed in the controller of the post-treatment system of heavy vehicles to simplify the sensors of the system, realize the concentration prediction function of NOx and ensure the normal operation of the post-treatment system. In view of different application scenarios, the prediction accuracy of the proposed model was analyzed through the evaluation indicators such as NOx emission concentration, Urea injection volume and NOx specific emission value. The research results show that the error between the predicted concentration of NOx emission after simplification and the measured concentration of the sensor is less than 3%. The change of Urea injection amount of the simplified post-treatment system is less than 2.08%, and the specific emission change of NOx is kept within 0.75%. And the original specific emission value of the simplified vehicle is 7.53 g/ kWh (it is 7.59g/ kWh when not simplified). The prediction of the post-treatment system embedded in the algorithm model meets the accuracy requirements. References | Related Articles | Metrics

Select

Path Following Technology Based on Model Predictive Control ZHAO Fengkui, CHENG Haifei, ZHU Shaohua, ZHANG Yong 2022, 41(08): 142-148.  DOI: 10.3969/j.issn.1674-0696.2022.08.20 Abstract ( )   PDF (2455KB) ( )   Path tracking control is one of the key contents of automobile intelligent driving, and its purpose is to reduce the deviation between the theoretical reference path and the actual path of the vehicle. Based on the established three-degree-of-freedom vehicle dynamics model, the dynamic model was simplified and then the corresponding model predictive control algorithm was designed to carry out path tracking of the vehicle model. By adding multiple constraints, the path tracking problem was transformed into a problem of solving the optimal value under a variety of constraints. Different vehicle speeds were set under different road adhesion coefficients, and the proposed algorithm was verified and analyzed through Simulink and CarSim co-simulation. The simulation results show that the designed controller tracks the reference path better, which greatly increases the coincidence between the vehicle driving path and the theoretical planning path, and also improves the steering stability of the vehicle during driving. References | Related Articles | Metrics

Select

Parameters of AlSi10Mg Alloy Selection Laser Melting Large Thickness Forming and Heat Treatment Process ZHANG Jixiang, LIU Jiayuan, LI Huan, HE Guangchuan 2022, 41(08): 149-156.  DOI: 10.3969/j.issn.1674-0696.2022.08.21 Abstract ( )   PDF (12335KB) ( )   The large thickness (60 μm) AlSi10Mg alloy was formed by selective laser melting (SLM) technology, and the optimal printing parameters were determined by orthogonal experiments with density as the index. The microstructure, phase analysis and mechanical properties of AlSi10Mg alloy formed at different annealing temperatures (200, 300, 400, 500 ℃) were studied. The results show that when the laser power is 310 W, the scanning speed is 1 450 mm/s, and the scanning spacing is 95 μm, the density of AlSi10Mg alloy is the highest, reaching 99.92%. With the increase of annealing temperature, the weld pool boundary of the longitudinal section of AlSi10Mg molded part gradually becomes blurred, and the eutectic structure at the weld pool boundary gradually homogenizes. In the X-ray diffraction spectrum, the diffraction peak of AlSi10Mg powder corresponding to the forming part and annealed part is obviously shifted. When the annealing temperature is 500 ℃, the tensile strength of annealed samples decreases from 355 MPa to 102 MPa with the fracture of Si network, and the elongation rate increases from 1.65 % to 13.25 % with the increase of dimples. References | Related Articles | Metrics