Volume 44,Issue 1,2021 Table of Contents

1 Development of driving simulation system based on virtual reality test scene

YANG Yalian , DAI Jishun , XIE Xiao

2021, 44(1):1-10. DOI: 10.11835/j.issn.1000-582X.2019.003

[Abstract](850) [HTML](1188) [PDF 7.17 M](1219)

Abstract:
In order to solve the problems of vague sight and unchangeable driver's perspective in the visual display of driving simulation system, the 3D model of Dianjiang Vehicle Proving Ground(VPG) is built by 3Ds Max. Then, the virtual reality display system is built based on Unity 3D and HTC Vive, which realizes the rendering and VR display of the whole environment of the VPG. Finally, the car dynamic simulation platform is built with Carsim and Labview RT. Thus, all the driving simulation system construction steps based on VR are completed. The simulation results show that the driving simulation system based on virtual VPG has high definition sight, and the driver has high elevation angel and flexible observation angle, which effectively improves the driver's immersion.

2 Geometric element error modeling considering multi-tolerance coupling and accuracy prediction of product assembly

LIU Yuxin , ZHANG Genbao , RAN Yan

2021, 44(1):11-19. DOI: 10.11835/j.issn.1000-582X.2020.215

[Abstract](624) [HTML](643) [PDF 955.68 K](1062)

Abstract:
In order to accurately and effectively realize the geometrical element error modeling of parts, a geometric element error modeling method based on multi-tolerance coupling is proposed in this paper. Small displacement torsor (SDT) was adopted to describe the tolerance, and the geometric element error model for the translation of the translational tolerance and the fixed tolerance was established. By using the failure rate p of the constraint equation, the actual distribution of the parameters of each error component was derived and the geometric element error model was built. The method was extended to the assembly error modeling of complex assemblies by using the Jacobian spin model, realizing the prediction of assembly accuracy. The rationality and feasibility of the method are verified by the prediction of the assembly accuracy of the top tailstock.

3 A co-prime nested array algorithm in reducing mutual coupling and DOA estimation

LIU Sheng , ZHAO Jing , CAO Hailin , TIAN Changhai , WU Decheng

2021, 44(1):20-28. DOI: 10.11835/j.issn.1000-582X.2021.01.003

[Abstract](561) [HTML](709) [PDF 1.96 M](1075)

Abstract:
In order to reduce the mutual coupling between sensors, a kind of co-prime nested array with adjustable element spacing is proposed. The proposed array consists of two nested arrays with different element spacing and the smallest intervals of two sub-arrays are determined by two co-prime positive integers. As long as the positive integers are big enough, the smallest intervals of each sub-array can be far more than half the wave length of incident signal, hence the reduction of the mutual coupling effect between sensors to a negligible level. To eliminate the direction ambiguity caused by large element spacing, a direction of arrival (DOA) estimation algorithm based on fourth-order cumulants is proposed to get unambiguous direction estimation. Compared with some classical self-correcting methods, the proposed algorithm has a higher angle resolution and estimation precision. Simulation results have proved the improved performance of proposed algorithm.

4 A SVM algorithm based on convex hull sparsity and genetic algorithm optimization

QIAN Hongbing , LI Yanli

2021, 44(1):29-36. DOI: 10.11835/j.issn.1000-582X.2021.01.004

[Abstract](569) [HTML](867) [PDF 1.80 M](1034)

Abstract:
SVM algorithm for support vector involves the calculation of N-order matrix. N is the number of samples. When the number of samples is large, the calculation of high-order matrix will consume a lot of computing time. At the same time, the performance of SVM model depends on the optimization of penalty parameters and kernel parameters. The traditional cycle verification method of parameter optimization has high time complexity. In order to solve these two problems, this paper proposes a high-performance SVM model training algorithm by convex hull algorithm to sparse the training samples and by genetic algorithm to optimize the selection of penalty parameters and kernel parameters.

5 An urban ring road traffic signal control algorithm based on multi-agents

CHEN Xiaoli , HAN Fengbin

2021, 44(1):37-45,118. DOI: 10.11835/j.issn.1000-582X.2021.01.005

[Abstract](566) [HTML](598) [PDF 2.95 M](1093)

Abstract:
Aiming at the solution of urban ring road traffic signal control problem, this paper proposes a green wave coordination method for loop intersections based on multi-agent system's autonomy, distribution, coordination and active learning. Every intersections is regarded as an intelligent body and the adjacent agents can communicate and exchange information. Using the intelligent system memory storage and reasoning learning ability, the green wave coordination optimization of multiple intersections is performed on the loop. The algorithm is described and deduced from the perspective of algorithm model, parameter description and phase selection strategy under coordinated mode. The effectiveness of the proposed algorithm is verified by experimental simulation.

6 Extraction of bilingual parallel sentence pairs constrained by consistency of structural features

MAO Cunli , GAO Xu , YU Zhengtao , WANG Zhenhan , GAO Shengxiang , MAN Zhibo

2021, 44(1):46-56. DOI: 10.11835/j.issn.1000-582X.2021.01.006

[Abstract](606) [HTML](697) [PDF 1.17 M](913)

Abstract:
Parallel sentence pair extraction is an effective way to solve the shortage of low-resource neural machine translation. The main method based on Siamese neural network is to judge whether two sentences are parallel through cross-language semantic similarity, which has achieved remarkable results on similar language pairs. However, for English- Southeast Asia language sentence pairs extraction tasks, there are not only great differences in language space but also great differences in sentence length. Considering only cross-language semantic similarity and ignoring sentence length features will lead to misjudgment of non-parallel sentence pairs with only semantic inclusion. Therefore, this paper proposes a parallel sentence pairs extraction method constrained by consistency of structural features. The method is an extension of the model based on Siamese neural network. Firstly, using the multilingual BERT to embed the two languages into the same semantic space in the embedding layer, so as to reduce the language differences in the semantic space. Secondly, embedding the length features of sentences respectively, and fusing it with the semantic vectors of sentences encoded by Siamese networks to enhance the representation of parallel sentence pairs in semantic and structural features, so as to solve the misjudgment problem. We experiment on the English-Burmese data sets. The results show that the precision is increased by 4.64%, the recall is increased by 2.52%, and the F₁ value is increased by 3.51% compared with the baseline.

7 Air conditioning terminal and new air volume classification control based on crowd density estimation

LI Tongyue , MENG Yuebo , LIU Guanghui , XU Shengjun , JI Tuo

2021, 44(1):57-66. DOI: 10.11835/j.issn.1000-582X.2021.01.007

[Abstract](508) [HTML](762) [PDF 3.74 M](907)

Abstract:
Load forecasting is a key part of system optimization control of air conditioning system, and the randomness and uncertainty of personnel movement make it difficult to accurately estimate the load of building space personnel, resulting in poor control effect of existing control strategies, the slow response of the system, the waste of energy and the reduction of thermal comfort of the building interior environment. To solve these problems, an air conditioning terminal and new air volume classification control strategy based on crowd density estimation is proposed in this paper. Firstly, the image information of building space was collected and a model of multi-column convolution neural network crowd density estimation was established to obtain the number and dynamic distribution of personnel and calculate the real-time load of building space personnel. Secondly, the personnel load control factor was introduced and the air conditioning grading control strategy was put forward to realize the air conditioning terminal and fresh air supply. The experimental results show that the method proposed in this paper can better maintain the internal environment stability of the building, at the same time, the system has faster response speed and greater energy saving potential.

8 An edge computing-based network traffic measurement of the Internet of Things

LING Min , ZHANG Wenjin , YUAN Liang , XIONG Jiping

2021, 44(1):67-77. DOI: 10.11835/j.issn.1000-582X.2020.224

[Abstract](721) [HTML](1140) [PDF 3.95 M](1247)

Abstract:
In the Internet of Things, edge computing can provide real-time performance of IoT computing and reduce the amount of data transmitted in the network. In order to satisfy the development of the IoT technology, the IoT network with software defined network (SDN) architecture was studied in this paper, and the method provided by SDN was used to measure the traffic in the network. Fine-grained traffic measurement can accurately describe traffic in the network, but it also consumes a lot of measurement overhead generated in the measurement process. To reduce the overhead and obtain approximate fine-grained measurements, an IoT network traffic measurement scheme based on edge computing was proposed. The new measurement architecture involved coarse-grained measurements and interpolation optimization. The random sampling method was used to measure coarse-grained network traffic through Open Flow protocol. Then, the coarse-grained network traffic was interpolated and restored, and the interpolation result was optimized by the multi-constraint optimization method to obtain the optimal fine-grained flow measurement result that satisfied the condition constraint. Finally, the feasibility and effectiveness of the proposed measurement method were verified by experiments.

9 Personalized recommendation system based on matrix factorization and XGBoost algorithm

HE Jing , HU Jie

2021, 44(1):78-87. DOI: 10.11835/j.issn.1000-582X.2021.01.009

[Abstract](820) [HTML](1277) [PDF 4.76 M](1336)

Abstract:
In order to solve the data sparsity problem and improve the recommendation accuracy, we proposed a new matrix factorization XGBoost(MFXGB) recommendation algorithm which combined the matrix factorization method and the XGBoost (Extreme Gradient Boosting) algorithm. SVD++ algorithm (SVD, singular value decomposition) was used to fill the user-item score matrix to lessen the influence on the accuracy of the algorithm due to too many missing values and XGBoost was used to build a supervised learning model to predict the user's score. To reduce the computation time, feature extration based on the K-means clustering method was proposed to train XGBoot. The proposed MFXGB algorithm was applied to MovieLens dataset for experimental analysis and the results show that the recommendation accuracy was improved by 8.91%,10.18% and 11.79% respectively, compared with the three traditional algorithms.

10 A structure similarity based quality prediction approach for Web service in the spatial-temporal scenario

XIA Hui , GAO Min , ZOU Shu

2021, 44(1):88-96. DOI: 10.11835/j.issn.1000-582X.2021.01.010

[Abstract](307) [HTML](814) [PDF 3.56 M](1095)

Abstract:
With the rapid development of new service computing types like cloud computing, the amount of Web services becomes increasingly massive, as is also the case for Web services with the same or similar functions. One of the most important issues in high-quality Web services recommendation is to identify the QoS value of Web services. Traditional collaborative filtering approaches have been widely employed in QoS prediction and Web Service recommendation. However, they suffer from the sparse and noisy data issues, which definitely cause the low performance of QoS predictions. In order to attain high prediction performance, the paper proposed a novel sparse matrix factorization approach based on the spatial-temporal features of user-service QoS matrix,in which the proposed model took the occurence of similar network environment between similar users in neighbor moment into consideration, and constructed a global and local structure similarity based sparse matrix factorization machine. With the decomposed factors, we could get a low rank matrix completion, which helped to eliminate the impacts of sparse and noisy data in QoS prediction. To evaluate the performance of the proposed approach, a set of extensive experiments were conducted using real-world dataset. The experimental results show that the proposed model outperforms the traditional collaborative filtering approaches (the MAE value decreases by 3.25% and RMSE value by 6.65% compared with those of NMF; MAE value decreases by 3.67%, and RMSE by 7.01% compared with those of SVD), which indicates that it can effectively resolve sparse and noisy data issues.

11 Feasibility study of engineered cementitious composites (ECC) with self-healing capacity for airfield pavement

ZHANG Zhigang , ZHANG Renyi , ZHANG Pei , ZHAO Lin

2021, 44(1):97-105. DOI: 10.11835/j.issn.1000-582X.2021.01.011

[Abstract](1104) [HTML](1085) [PDF 6.53 M](1478)

Abstract:
Under the effects of mechanical and environmental loading, airfield pavement is prone to distresses of cracking, joints damage and vertical displacement of panels, which results in frequent maintenance. In order to control propagation of cracks and achieve jointless function, this study attempts to use engineered cementitious composites (ECC) as an airfield pavement material for its high ductility and intrinsic self-healing capacity. Damage in ECC can be healed by secondary hydration, thus reducing the maintenance cost and prolonging service life. In this paper, the mechanical properties of ECC and its self-healing behavior as well as the cracking potential at early age of ECC were investigated. The result shows that the tensile strain of ECC can reach 3.67% under the action of tensile load, (about 400 times higher than that of ordinary concrete) and the vertical deflection can reach 6.33 mm under flexural load. The flexural and compressive strength is 12.68 MPa and 43.9 MPa, respectively, which meets requirements of airfield pavement. Under restrained shrinkage, ECC is expected to have a low tendency towards fracture failure. With self-healing, the tensile stiffness, tensile strain and tensile strength of damaged ECC can almost be restored to the extent that it was not cracked. The water permeability coefficient of pre-damaged ECC decreases gradually to that of a virgin one. It can be concluded that ECC material has strong feasibility for jointless airfield pavement.

12 Study on deteriorating moment-curvature model based on modified Ibarra-Medina-Krawinkler hysteretic rules

LIU Sai , GU Dongsheng

2021, 44(1):106-118. DOI: 10.11835/j.issn.1000-582X.2021.01.012

[Abstract](909) [HTML](777) [PDF 5.46 M](1683)

Abstract:
Based on Modified Ibarra-Medina-Krawinkler (ModIMK) hysteretic rules, a new moment-curvature model is proposed in this paper, which can be used to define the section of plastic hinge zone of Beam With Hinges Element in OpenSees. The envelope curve of the moment-curvature model is idealized as tri-linear curve and equations that are capable of predicting the key points of skeleton curve are given. The accuracy of the model is calibrated by the test results of 62 RC columns, and it is found that both the yield displacement and longitudinal rebar buckling displacement can be well predicted. ModIMK hysteresis model can be used to simulate the degradation of the strength and stiffness in plastic hinge area under cyclic loading. The numerical simulations are conducted to model the columns tested by cyclic load and shaking table test, and the results show that the moment-curvature model in conjunction with plastical hinge element can accurately predict the response of RC columns under seismic loadings.

13 The research on the smallest rise-span ratio of large span cavern

XU Quan , WU Jiayao , CHU Weijiang

2021, 44(1):119-130. DOI: 10.11835/j.issn.1000-582X.2021.01.013

[Abstract](546) [HTML](775) [PDF 7.33 M](1247)

Abstract:
The smallest rise-span ratio of large span cavern is an important reference to design the dimension of large span cavern. Based on both cavehoek constitutive model which can take some response characteristics during the excavation into consideration,such as the softening behavior of rock mass, dilation, volume expansion, density change, etc., and the critical strain which can reflect the influence of rock mass quality and UCS of the intact rock, the smallest rise-span ratio of 60 m long span caverns with different values of GSI, buried depth, lateral pressure coefficient of in-situ stress, structural planes, etc. were studied.The results show that: among the three factors of GSI value, lateral pressure coefficient and burial depth, the value of GSI has the biggest influence on the smallest rise-span ratio of large-span cavern, followed by the lateral pressure coefficient and burial depth. The better the rock mass, the smaller the ratio of smallest rise-span, and the minimum rise-span ratio is not linear with the lateral pressure coefficient and burial depth. The structure plane and UCS of intack rock also has great influence on the minimum rise-span ratio of large span cavern, especially the gently inclined structural plane which is not conducible to the arch forming of large-span caverns.

14 Effect of on-line cleaning on the heat transfer performance of shell and tube heat exchanger

MA Xiaoyu , LIN Xueyin , MA Hongting

2021, 44(1):131-142. DOI: 10.11835/j.issn.1000-582X.2021.01.014

[Abstract](518) [HTML](611) [PDF 4.99 M](1190)

Abstract:
In order to improve descaling efficiency and heat transfer performance of shell and tube heat exchanger, a gas-fired lithium bromide absorption chiller is selected as the research object. By installing rubber ball online cleaning system, the influence of rubber ball online cleaning on the heat transfer performance of absorber and heat exchanger was experimentally studied. The results show that the fouling resistance of heat exchanger increases with the increase of operation time while the performance coefficient (COP) of direct-fired unit decreases with time under the condition of no rubber ball online cleaning system. The ball rate, service time and start /stop ratio of on-line cleaning system have significant effects on fouling resistance of shell and tube heat exchanger. When the input rate is 10%, 20%, and 30%, the thermal resistance of the scale increases by 32.8%, 20.8% and 8.9%, respectively. When the running time is 20 s, 40 s and 60 s respectively, the thermal resistance of the scale increases correspondingly by -20.8%, 17.9% and 10.7%. When the start-stop ratios are 1:1, 1:2 and 1:3 respectively, the thermal resistance of scale increases correspondingly by 16.1%, 23.0%and 29.0%. With the running cost and the service life of the rubber ball taken into account, the best working condition is when the input rate is 20%, the running time is 60 s with an interval of 120 s, and the start-stop ratio is 1:2.

Home

Volume 44,Issue 1,2021 Table of Contents

Current Issue

Volume

Issue

Most Read

Most Cited

Most Downloaded