Table of Content

    The Invited Paper of the Editorial Board
    Review of capsule network
    Jucheng YANG,Shujie HAN,Lei MAO,Xiangzi DAI,Yarui CHEN
    Journal of Shandong University(Engineering Science). 2019, 49(6):  1-10.  doi:10.6040/j.issn.1672-3961.0.2019.312
    Abstract ( 2639 )   HTML ( 114 )   PDF (4331KB) ( 1177 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Recently capsule network with dynamic routing was the new neural network model which was considered a significant model in next generation. In recent years, much research evidenced capsule network exceptional ability to fit features. But the high computational overhead made it unable to fit complex and large datasets. Consequently, reducing computational became a research hotspot. There were two methods, including optimized capsule and optimized routing, to solve the issue. Optimized capsule was usually driven by application purpose which was designed as a model of specific classification tasks. And optimized routing was the way to improve the performance of the model from an algorithmic perspective.

    Control Science & Engineering - Special Topic on Robot
    Research status and development trend of autonomous cognition and learning of robot manipulation skills
    Wei WANG,Feng WU,Fengyu ZHOU
    Journal of Shandong University(Engineering Science). 2019, 49(6):  11-24.  doi:10.6040/j.issn.1672-3961.0.2019.229
    Abstract ( 1698 )   HTML ( 31 )   PDF (2077KB) ( 887 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Autonomous cognition and learning of manipulation skills, being one of the most important skills for robots, has been one of the hot issues in the field of robotics research. Combining with the authors' work in the field of robotics, this paper's focus is placed on giving a comprehensive overview of the mainstream modes, methods, algorithms, as well as advantages and disadvantages of different methods in terms of robots' manipulation skill learning. It concludes the challenges faced by autonomous learning and the key issues that need to be addressed for the individual cloud robots learning manipulation skills in the knowledge sharing mode. At the end, a potential solution for the above issues is given, and that is to integrate individual learning mode and shared learning model for the purpose of enhancing autonomous cognition and learning ability for robots.

    A survey of image captioning methods based on deep learning
    Zhifu CHANG,Fengyu ZHOU,Yugang WANG,Dongdong SHEN,Yang ZHAO
    Journal of Shandong University(Engineering Science). 2019, 49(6):  25-35.  doi:10.6040/j.issn.1672-3961.0.2019.244
    Abstract ( 3794 )   HTML ( 102 )   PDF (7881KB) ( 1362 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Image captioning is the cross-research direction of computer vision and natural language processing. This paper aimsed to summarize the deep learning methods in the field of image captioning. Imgage captioning methods based on deep learning was summarized into five categories: multimodal space based method, multi-region based method, enconder-deconder based method, reinforcement learning based method, and generative adversarial networks based method.The datasets and evaluation metrics were demonstrated, and experimental result of different methods were compared. The three key problems and future research direction for image captioning were presented and summarized.

    The composite control of backstepping control based on uncertain model compensation of wheeled mobile robot
    Meizhen LIU,Fengyu ZHOU,Ming LI,Yugang WANG,Ke CHEN
    Journal of Shandong University(Engineering Science). 2019, 49(6):  36-44.  doi:10.6040/j.issn.1672-3961.0.2019.236
    Abstract ( 1237 )   HTML ( 5 )   PDF (4106KB) ( 524 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Given these factors of model uncertainty, non-linearity and unmodeled dynamic characteristics existing in wheeled mobile robots, which seriously affected the stability and accuracy of trajectory tracking, a backstepping composite control strategy based on model uncertainty compensation was proposed. Based on the kinematics model of a nonholonomic wheeled mobile robot, backstepping control and Lyapunov stability criterion were adopted to design virtual velocity control quantity as continuous incentive input for trajectory tracking. Considering the model uncertainty and external bounded moment disturbance of wheeled mobile robots, the uncertainties of the system were derived from the dynamic model of wheeled mobile robots, and the moment control quantity of model was acquired by using the neural network with highly nonlinear fitting characteristics, and then adaptive law of uncertainties was obtained from Lyapunov stability analysis to realize self-adjustment and real-time trajectory tracking. The simulation results showed that the proposed composite control strategy could track the reference trajectory adaptively, and had better robustness and tracking accuracy than the single backstepping control strategy, model uncertainty compensation control strategy and PID controller.

    A robot service recognition mechanism based on ontology in smart home
    Linglong KONG,Guohui TIAN
    Journal of Shandong University(Engineering Science). 2019, 49(6):  45-54.  doi:10.6040/j.issn.1672-3961.0.2018.495
    Abstract ( 1132 )   HTML ( 7 )   PDF (5046KB) ( 646 )   Save
    Figures and Tables | References | Related Articles | Metrics

    In order to enhance the ability of robots to provide different types of services, a classification service reasoning method based on semantic web rule language was proposed for service robots in smart home environments. The ontology model of smart home was established by ontology technology, which integrated data from different data sources and eliminated the heterogeneity between devices. The classification of service types were based on the service characteristics of robot service system in smart home. With historical context information, the service rule bases were set up. The reasoning engine could match the real-time context information and service rules to realize the service reasoning of the robot. The experimental results showed that the robot service reasoning method could achieve different types of service reasoning in smart home environments and further improve the intelligence of the robot service.

    Design of robot cloud service platform based on microservice
    Lei YIN,Fengyu ZHOU,Ming LI,Yugang WANG,Yinbo GUO,Ke CHEN
    Journal of Shandong University(Engineering Science). 2019, 49(6):  55-62, 80.  doi:10.6040/j.issn.1672-3961.0.2019.251
    Abstract ( 1632 )   HTML ( 16 )   PDF (4187KB) ( 805 )   Save
    Figures and Tables | References | Related Articles | Metrics

    To improve the intelligent level of service robots, a cloud service design method for service robots based on micro-service was proposed in this paper. The framework of cloud service based on micro-service was designed based on virtual model of service robot. Kinematics model, sensor model and environment model were proposed to map the robot parameters to cloud center. The interactive interface for cloud services was proposed. The adaptive matching of heterogeneous protocols was realized by using the protocol response of robots. Cloud service development methods were proposed in detail. The experiment result were done to demonstrate the cloud service results, real time and fine-grained quality of service of the proposed cloud service design for service robots.

    Complete coverage path planning for mobile robots based on hyperchaotic synchronization control
    Caihong LI,Chun FANG,Zhiqiang WANG,Bin XIA,Fengying WANG
    Journal of Shandong University(Engineering Science). 2019, 49(6):  63-72.  doi:10.6040/j.issn.1672-3961.0.2019.173
    Abstract ( 1214 )   HTML ( 7 )   PDF (6359KB) ( 394 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Based on the requirements of randomness and completeness of the mobile robots under special tasks such as the surveillance, patrol, etc., a complete coverage path planning method for robots by the hyperchaotic synchronization control strategy was proposed. The four-dimensional hyperchaotic Lorenz system was used as the main driving equation, and the hyperchaotic synchronization response equation was constructed by the single-coupled hyperchaotic synchronization control. A path planner of the chaotic robot was constructed by combining synchronized hyperchaotic synchronous response system with kinematics equation of mobile robot to produce the complete coverage path and satisfy the requirements of the special tasks. The mirror mapping method was used to limit the running range of the coverage trajectory and to avoid the static obstacles at the workspace boundary. Qualitative analysis and quantitative calculations of the planned trajectories showed that the coverage trajectories produced by hyperchaotic synchronization method had better coverage rate and randomness, which could meet the requirements of autonomous mobile robots for special tasks.

    Control Science & Engineering-Special Topic on Robot
    Configuration design and interference analysis of multi-arm robot for mandible reconstruction
    Honghua ZHAO,Jian ZHAO,Xingguang DUAN,Zhitong HU,Qianqian TIAN,Yaohua ZHAO
    Journal of Shandong University(Engineering Science). 2019, 49(6):  73-80.  doi:10.6040/j.issn.1672-3961.0.2019.185
    Abstract ( 1303 )   HTML ( 3 )   PDF (5769KB) ( 575 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Based on the requirements of mandible reconstruction surgery and the design criteria of surgical robots, a seven degree of freedom three-arm configuration with active and passive combination was proposed. In order to meet the requirement of high efficiency of interference analysis for manipulator of surgical robot, the linear swept sphere element model was used to simplify the manipulator with complex structure. The interference mathematical models between two cylinders, between cylinders and hemispheres, and between two hemispheres were constructed. The concept of effective interference points and the method of judging the effectiveness of interference points were proposed. The interference judgment of the manipulator at any position was obtained. The experiment of non-interference control verified the correctness of the method by robot platform. The method simplified the criterion and process of interference analysis of basic geometric model, reduced the number of interference judgments between models, and improved the efficiency of interference analysis.

    Electrical Engineering
    Study on a low-speed direct drive transverse-flux switched reluctance motor
    Zhenwei ZHAO,Zhigang DONG,Yongbin LI
    Journal of Shandong University(Engineering Science). 2019, 49(6):  81-85.  doi:10.6040/j.issn.1672-3961.0.2019.339
    Abstract ( 1479 )   HTML ( 12 )   PDF (2985KB) ( 509 )   Save
    Figures and Tables | References | Related Articles | Metrics

    In order to improve the torque density of switched reluctance motor (SRM), achieve low speed and large torque output, and meet the requirements of direct electrical drive systems such as servo and electric vehicle, a new type of transverse magnetic flux switch reluctance motor (TFSRM) was proposed. The principle of transverse flux motor was applied to switch reluctance motor, which simplified the complexity of the motor structure and improved the torque density of the motor. The working principle and structural characteristics were introduced in detail. The magnetic field distribution of the stator and rotor in different relative positions were analyzed by the three-dimensional equivalent magnetic network method, and the torque angle characteristics of the motor were calculated under constant current control. A closed-loop current control system based on digital signal processor was designed, and the prototype was tested. The experimental results were consistent with the theoretical analysis, which verified the feasibility and validity of the theoretical analysis and design method.

    Analysis of wind power convergence trend quantitation based on sub-scene reconstruction
    Yuanxi YAO
    Journal of Shandong University(Engineering Science). 2019, 49(6):  86-92.  doi:10.6040/j.issn.1672-3961.0.2019.117
    Abstract ( 1201 )   HTML ( 4 )   PDF (3095KB) ( 475 )   Save
    Figures and Tables | References | Related Articles | Metrics

    The output power of wind power was fluctuating. Due to the output of unit stabilized each other, with the increase of wind power cluster size, the fluctuation of wind power gradually decreased and the wind power showed "convergence effect". Grasping the trend of the convergence effect had an important guiding significance for transmission capacity configuration of large-scale wind power network. In this paper, the scene of wind power output was defined, and the convergence characteristics of wind power in each scene were analyzed. By fitting the continuous output curve in each scene, a scene reconstruction method based on convergence characteristics analysis was proposed. The validity of the method was verified by the measured. The example showed that the sub-scene reconstruction method analyzed the trend of convergence for wind power more accurately. The number of scenarios affected the fitting accuracy of continuous output curve, comparing to the scene divided by 5, 10 and 20, scene reconstruction in 10 scenes was more accurate for the description of wind convergence trend.

    Weighted value of solar tariff based on time-of-use electricity price
    Fangyun HAN,Liang QIAO,Bincheng ZHAO,Li ZHANG
    Journal of Shandong University(Engineering Science). 2019, 49(6):  93-97,106.  doi:10.6040/j.issn.1672-3961.0.2019.617
    Abstract ( 1361 )   HTML ( 7 )   PDF (1384KB) ( 353 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Value of solar tariff is a new way to solve the problem of unfair allocation of power supply costs and revenue decrease of power grid company caused by distributed photovoltaic power generation. Because the existing model did not consider the change of power supply cost under different operating conditions of power grid, a weighted solar energy value calculation method based on time-of-use electricity price was proposed in the paper. The operation conditions of the grid were typificated as peak, flat and valley periods, the setting of relevant parameters was discussed and an improved model was established. The new model accounted more for the time consistency of photovoltaic power generation and grid operation, and could reflect the value of photovoltaic power generation more accurately. Simulation analysis were done, the results demonstrated the effectiveness of the proposed model.

    Mechanical, Energy and Power Engineering
    Design and verification of power system for ECVT hybrid electric city bus
    Youming TANG,Kun DONG,Yuanwei ZHANG
    Journal of Shandong University(Engineering Science). 2019, 49(6):  98-106.  doi:10.6040/j.issn.1672-3961.0.2019.072
    Abstract ( 1376 )   HTML ( 13 )   PDF (2354KB) ( 624 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Aiming at the problem that the integrated starter/generator(ISG) hybrid power system was not ideal in fuel saving effect, this study selected the electronic continuously variable transmission(ECVT) hybrid power system scheme, which was applied and verified in plug-in hybrid electric city bus. Based on the equivalent lever analysis of the kinematics characteristics of a single planetary line, the parameters of key components of a plug-in ECVT power system were matched and calculated. According to the calibration test data, Matlab/Simulink software was used to establish the engine simulation model, drive motor simulation model and generator simulation model, to build the vehicle simulation model. Under typical urban bus cycle conditions in China, the fuel economy, dynamic performance and pure electric maximum continuous voyage characteristics of the target vehicle were studied, and the road tests of economy and dynamic performance were completed. The results showed that the ECVT hybrid system vehicle designed in this study could achieve fuel saving rate of 57.47% compared with traditional vehicles, and 24.12% higher than ISG hybrid system vehicle. Therefore, the adoption of ECVT hybrid power system for plug-in hybrid city bus was feasible and effective, and had obvious fuel saving effect.

    Size-dependenct intrinsic properties of the bilayer piezoelectric microbeam
    Yu LIU,Shenjie ZHOU,Kanghui WU
    Journal of Shandong University(Engineering Science). 2019, 49(6):  107-112.  doi:10.6040/j.issn.1672-3961.0.2019.061
    Abstract ( 1250 )   HTML ( 7 )   PDF (1188KB) ( 323 )   Save
    Figures and Tables | References | Related Articles | Metrics

    A size-dependent dynamic model of a bilayer piezoelectric microbeam was established based on the couple stress piezoelectric theory incorporating flexoelectric effects to explore the variation of the intrinsic properties of the bilayer piezoelectric microbeam with the characteristic size. The natural frequency of the bilayer piezoelectric microbeam was obtained. The influence of piezoelectric effects and flexoelectric effects on the natural frequency of the microbeam was discussed by numerical analysis method. The results indicated that the dimensionless natural frequency of the bilayer piezoelectric microbeam increased significantly as the beam thickness decreased. It was also found that the dimensionless natural frequency of the bilayer piezoelectric microbeam showed stronger size-dependency than that of the model without considering electromechanical coupling effects, which mainly resulted from flexoelectric effects, and piezoelectric effects exerted minor influence on the beam natural frequency.

    Analysis of factors affecting heat transfer of double U-shaped buried tubes based on TRNSYS
    Tao LIU,Ye TIAN,Yongzhi MA
    Journal of Shandong University(Engineering Science). 2019, 49(6):  113-118.  doi:10.6040/j.issn.1672-3961.0.2019.317
    Abstract ( 1396 )   HTML ( 14 )   PDF (1908KB) ( 770 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Because the horizontal buried tubes covered a large area, the heat transfer effect was poor, and the initial investment of the vertical buried tubes was high, the construction was difficult. A transient real-time simulation model of double U-shaped buried tubes heat exchanger was established with TRNSYS software. The factors, which could affect the heat transfer capacity of double U-shaped buried tubes heat exchanger, including the number and the spaceing of holes, and the depth of the buried tubes were analyzed under the condition of unique variable. The simulation experiment results showed that the heat transfer effect of buried tubes could be improved by increasing the number of holes, deepening drilling depth and increasing the spacing of the holes. It provided an analytical basis for the balance between the heat transfer effect of the buried tubes and the construction difficulty.

    Flow resistance characteristics of wire mesh porous media channel based on pore-scale
    Wei HU
    Journal of Shandong University(Engineering Science). 2019, 49(6):  119-126.  doi:10.6040/j.issn.1672-3961.0.2019.503
    Abstract ( 1496 )   HTML ( 32 )   PDF (2325KB) ( 625 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Through the pore-scale of the mesh porous media channel numerical analysis, the flow resistance characteristics of wire mesh channel with different geometric parameters were studied, including pressure drop ΔP, viscous resistance Au and inertial resistance Bu2. A three-dimensional steady-state modified k-ωturbulence model was developed by CFD software, and five four-cell pore models with different wire diameters and pore diameters were selected. Numerical analysis on flow resistance characteristics in wire mesh velocity numbers, i.e., from 0.2 m/s to 1.0 m/s were performed. The characteristics of flow in pore-level channels with different configurations under the range of low velocity numbers were obtained. It was shown that the configuration had a significant influence on the nonlinear flow characteristics of the wire mesh channel. The results showed that the smaller the mesh configuration angle (θ=45°~90°), the greater flow resistance in the channel, however, the partial pressure ratio was the same. It also indicated that faster the flow velocity (v=0.2~1.0 m/s), the greater the nonlinear effect and more inertial resistance would be.