Loading...

Table of Content

    Machine Learning & Data Mining
    Image-dependent fusion method for saliency maps
    Ye LIANG,Nan MA,Hongzhe LIU
    Journal of Shandong University(Engineering Science). 2021, 51(4):  1-7.  doi:10.6040/j.issn.1672-3961.0.2020.266
    Abstract ( 173 )   HTML ( 26 )   PDF (4939KB) ( 88 )   Save
    Figures and Tables | References | Related Articles | Metrics

    A saliency fusion method based on ridge regression was proposed to obtain better detection performance. The nearest neighbor set of the image to be detected was searched in the training set. The ridge regression method was used to estimate the fusion coefficients of different saliency maps. The saliency maps of different detection methods were fused. This method fully considered the differences of detection methods, and solved the problem of saliency map fusion in the absence of benchmark binary annotations. The AUC value of the proposed method was 0.911 on ECSSD dataset. The AUC value of the proposed method was 0.987 on HKU-IS dataset. The AUC value of the proposed method was 0.953 on DUT-OMRON dataset. The efficiency of the proposed method was verified by experimental results.

    Housing price prediction based on improved lion swarm algorithm and BP neural network model
    DING Fei, JIANG Mingyan
    Journal of Shandong University(Engineering Science). 2021, 51(4):  8-16.  doi:10.6040/j.issn.1672-3961.0.2020.482
    Abstract ( 198 )   PDF (944KB) ( 63 )   Save
    References | Related Articles | Metrics
    The lion swarm optimization algorithm combined the migration mechanism and spiral search mechanism of seagull algorithm to enhance the local search ability; the global search performance of lion swarm optimization algorithm was enhanced by adding supervision mechanism. The particle swarm optimization algorithm and the lion swarm optimization algorithm were used as the comparison algorithm, and the advantages of the improved algorithm were verified on the common test functions. The improved lion swarm optimization algorithm was used to optimize the BP neural network model to study the problem of housing price prediction, and the price of second-hand housing in Qingdao could be effectively predicted through relevant indicators such as house type and area. The improved lion swarm optimization algorithm was used to optimize the weights and biases of the BP neural network to improve the convergence speed and training accuracy of the BP neural network. The test results showed that the SLSO-BP model proposed in the study had a better prediction effect on the problem of housing price prediction.
    Optimization of digital twin job scheduling problem based on lion swarm algorithm
    HUANG Cheng, YUAN Dongfeng, ZHANG Haixia
    Journal of Shandong University(Engineering Science). 2021, 51(4):  17-23.  doi:10.6040/j.issn.1672-3961.0.2021.091
    Abstract ( 135 )   PDF (2554KB) ( 59 )   Save
    References | Related Articles | Metrics
    A digital twin job shop scheduling method based on lion swarm optimization algorithm was proposed aiming at the flexible job shop scheduling problem, which could effectively improve the utilization of equipment and solve the production delay caused by dynamic factors such as equipment failure in discrete manufacturing. The lion swarm optimization algorithm was used to generate the initial scheme based on the requirements of the actual production process. A digital twin flexible job shop scheduling model with real-time interaction between physical shop floor and virtual shop floor was established. The initial scheduling scheme was optimized according to the equipment utilization in the virtual shop floor. The digital twin model was used to solve the delay of production process caused by shop floor emergency such as equipment failure. By using real workshop data to test the machine tool production scheduling process in machining workshop, the results showed that the flexible job shop scheduling problem based on lion swarm optimization algorithm had strong search ability and fast search speed, and could find better solutions in different scale problems. The flexible job shop scheduling scheme with digital twin could optimize the system performance as a whole, and effectively deal with the problem of prolonging production time caused by disturbance.
    Adaptive semi-supervised neighborhood clustering algorithm
    ZHU Hengdong, MA Yingcang, DAI Xuezhen
    Journal of Shandong University(Engineering Science). 2021, 51(4):  24-34.  doi:10.6040/j.issn.1672-3961.0.2020.398
    Abstract ( 140 )   PDF (9402KB) ( 43 )   Save
    References | Related Articles | Metrics
    In order to make full use of the supervision information to guide the clustering process, an adaptive semi-supervised neighborhood clustering algorithm(SSCAN)was proposed. The combination of supervision matrix and distance measurement was introduced to construct a reasonable similarity matrix; The supervision information was fully utilized to adjust the model through the combination of the label information matrix and the manifold regular term to improve the clustering effect. Through experiments on various data sets and comparison with other clustering algorithms, the results showed that the SSCAN algorithm could make full use of the supervision information and improve the accuracy of clustering.
    An improved OPTS algorithm in FBMC-OQAM system
    WANG Xing, MA Tianming, ZHAO Qinghua
    Journal of Shandong University(Engineering Science). 2021, 51(4):  35-42.  doi:10.6040/j.issn.1672-3961.0.2020.400
    Abstract ( 131 )   PDF (1191KB) ( 24 )   Save
    References | Related Articles | Metrics
    To solve the problem of high computational complexity in the process of suppressing PAPR of filter bank multicarrier-offset quadrature amplitude modulation(FBMC-OQAM)applying the algorithm of overlapping partial transmit sequence(OPTS), a method of improved parallel tabu search overlapping partial transmit sequence algorithm(parallel-TS-OPTS)was proposed,which further increased the probability of finding the best phase factor vector by the operation of genetic crossover of the optimal solution of h-path traditional tabu search algorithm to optimize its initial solution. Theoretical analysis and simulation results showed that the proposed algorithm could not only achieve a PAPR suppression effect close to that of OPTS algorithm, but also significantly reduced the computational complexity of the algorithm, and further improved the robustness of FBMC-OQAM system applied in 5G scenarios.
    Civil Engineering
    Distribution law and calculation method of earth pressure in culvert under reinforced embankment
    Xiuguang SONG,Yimin ZHAO,Hongbo ZHANG,Zhenyu YANG,Qiang YANG
    Journal of Shandong University(Engineering Science). 2021, 51(4):  43-53.  doi:10.6040/j.issn.1672-3961.0.2021.125
    Abstract ( 156 )   HTML ( 9 )   PDF (9207KB) ( 42 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Based on the scale model test, the difference settlement between the embankment and the culvert was simulated by changing the foundation compression modulus on both sides of the culvert to reveal the mechanism of reinforcement and subsidence reduction on the culvert roof, determine the distribution law of earth pressure on the culvert roof under the condition of embankment overloading, and deduce and establish the calculation formula of earth pressure.The results showed that the soil pressure at the top of the reinforced embankment was obviously higher than that of the ordinary embankment under the same foundation modulus. The embankment-culvert relative displacement decreased with the increase of the number of grid layers.Under the same reinforcement condition, the smaller the foundation compression modulus was, the higher the embankment-culvert relative displacement and the soil pressure on the culvert top would be.Combined with the soil arching effect and the mechanism of reinforcement and subsidence reduction, the calculation formula of earth pressure under the roof of reinforced embankment was established, and the reliability was verified with the model test results.

    The pullout features of reinforced strips of waste tires in sandy media
    LI Xiaoliang, LIU Yuan, LI Yuxin, JIANG Jianhong, WEI Kun, ZHANG Hongbo
    Journal of Shandong University(Engineering Science). 2021, 51(4):  54-60.  doi:10.6040/j.issn.1672-3961.0.2021.036
    Abstract ( 141 )   PDF (5049KB) ( 29 )   Save
    References | Related Articles | Metrics
    In order to reduce the serious pollution to the environment and the potential safety hazards caused by the large amount of accumulated waste tires, a new method was proposed by cutting tires into strips to utilize the strips as reinforced material due to the good tensile stiffness, strong aging resistance and rough interface properties of waste tire. By adjusting the conditions of different density of sand, a comparative study on the pull-out characteristics of waste tire strips and geogrids was carried out. It was observed that the pullout load-displacement curve showed a tendency of linear increase before the strip of waste tires in the sand medium reaching the maximum pullout resistance. The static analysis of peak pullout resistance revealed that the shear properties of the tire strip-sand interface complied with mohr-coulomb criterion, thus the linear relationship between interface shear strength and interface friction angle, like-cohesion was established. By comparing the reinforcement performance of geogrid, it was found that the peak shear stress of scrap tire strip was about 2.5~3.2 times that of geogrid; the displacement of the peak shear stress was about 5 times that of geogrid. The research results verified the feasibility of used tire strips as reinforcing materials, and laid the foundation for further theoretical research and engineering applications.
    Stability analysis and construction mechanics of shallow buried bias tunnel openings
    LU Guangzhao, ZHOU Bo, XU Feng, SHANGGUAN Wei, WANG Gang, ZHANG Shubo
    Journal of Shandong University(Engineering Science). 2021, 51(4):  61-70.  doi:10.6040/j.issn.1672-3961.0.2020.523
    Abstract ( 137 )   PDF (11767KB) ( 39 )   Save
    References | Related Articles | Metrics
    In view of the stability of the surrounding rock of the shallow buried unsymmetrical pressure tunnel in broken rock mass and the selection of the tunnel construction method, the ABAQUS finite element software was selected for numerical simulation study to analyze the stress, strain and plastic zone distribution changes of surrounding rock and supporting structure under different construction methods. The results showed that: due to the obvious shallow buried and biased effects of the tunnel, the use of center diaphragm method and the double-side heading method for the entry of the tunnel could better ensure the stability of the tunnel. Under the engineering conditions, center diaphragm method had better control on the settlement and deformation of the vault and the ground surface, while the double-side pilot tunnel method had better control on the deformation of the arch waist. The internal force and bending moment of the support structure of center diaphragm method were mainly concentrated on the left side of the vault. The internal forces and bending moments of the double-side pilot pit support structure were symmetrically distributed on the left and right sides, and the anchor rod directly above the tunnel vault bore less force. The excavation step should not be too large, and each excavation should be within 2 m.
    Mechanical, Energy and Power Engineering
    Gas-liquid mixing in a dual grid-disc impeller stirred vessel
    Cuixun ZHANG,Mingjian CAO,Fengling YANG
    Journal of Shandong University(Engineering Science). 2021, 51(4):  71-76, 83.  doi:10.6040/j.issn.1672-3961.0.2020.296
    Abstract ( 132 )   HTML ( 3 )   PDF (4232KB) ( 22 )   Save
    Figures and Tables | References | Related Articles | Metrics

    In order to improve the gas-fluid mixing efficiency in the stirred vessel, by replacing the solid disc of standard Rushton impeller (RT) with a grid disc, the grid-disc Rushton impeller (RT-G) was designed. Grid independence test was completed. Gas holdup distributions of dual RT were numerically studied by the computational fluid dynamics (CFD) technique and compared with the literature data so as to validate the reliability of the numerical model and simulation method. The same numerical strategy was used to investigate the gas-liquid hydrodynamics of dual RT-G. Results were compared with those of dual RT and it was found that, under the operating condition studied here, dual RT-G had the same double-circulation flow field structure as RT. However, fluid axial velocity around the two RT-G impellers and axial pumping capacity could be enhanced, which contributed to improve the gas distribution state especially in regions adjacent to the impellers, between the upper and lower impeller, as well as in the top area of the stirred vessel. In terms of power consumption, the power number of dual RT-G before gassing was about 5% lower than that of dual RT, which indicated that RT-G was more energy-saving. The relative power demand (RPD) of dual RT-G after gassing was about 8% higher than dual RT, and accordingly was more efficient in gas dispersing.

    Optimization of heating load distribution of combined unit based on EBSILON simulation software
    GONG Weiping, GUAN Hongjun, LI Hongwei, LIU Jieben, SHI Yuetao
    Journal of Shandong University(Engineering Science). 2021, 51(4):  77-83.  doi:10.6040/j.issn.1672-3961.0.2020.157
    Abstract ( 128 )   PDF (6365KB) ( 28 )   Save
    References | Related Articles | Metrics
    In view of the high heat energy consumption of a power plant, the system model of 200 MW and 300 MW combined unit was built by EBSILON simulation software, and the optimal operation mode of the unit was obtained, which effectively alleviated the problems of large energy consumption and high operation cost of combined unit. In simulation process, different distribution of heat and power load was calculated. When the proportion of heat and power load of 300 MW unit changed, the corresponding change curves of the total coal consumption of the unit and the standard coal consumption for generation power were obtained. The simulation results showed that, the economy and safety of the unit were the best when the generating capacity of 300 MW unit was 250 MW to 280 MW. The results provided theoretical support for determining the optimal heat and power load distribution of combined unit, and achieved the goals of energy saving, emission reduction and energy consumption reduction.
    Operating characteristics of oil-free twin-screw air compressor
    LI Peng, LIU Zhaoqiang, YANG Fengling, LIU Xin
    Journal of Shandong University(Engineering Science). 2021, 51(4):  84-90.  doi:10.6040/j.issn.1672-3961.0.2020.267
    Abstract ( 120 )   PDF (1882KB) ( 16 )   Save
    References | Related Articles | Metrics
    In order to improve the operating efficiency of the oil-free twin-screw air compressor, the operating characteristics of the compressor were studied. Polytropic exponent, optimal intermediate pressure, exhausted-air pressure and temperature of the oil-free twin-screw air compressor during the operating processes were systematically studied. The theoretical analyses and experimental measurements were carried out. Results showed that the first-stage compression polytropic index was slightly lower than the second stage, both were higher than the iso-entropy exponent. With the increase of motor load rate, they firstly decreased gradually and then tended to be stabilized. If the intermediate cooler were taken into account, the first-stage compression polytropic index was slightly higher than the second stage. Both were lower than the iso-entropy exponent and increased slightly with the increase in the motor load rate. The optimal intermediate pressure of the oil-free twin-screw air compressor was quite complex, and it could not be simply considered as square root of the product of the compressed and the initial pressure. With the increase in motor load rate, the first-stage compression exhausted-air temperature gradually decreased, the second-stage compression exhausted-air temperature gradually increased, the first-stage exhausted-air pressure slightly decreased and the second-stage exhausted-air pressure slightly increased. Results of this work laid the foundation for better design and use of the oil-free twin-screw air compressor.
    Electrical Engineering
    Short-term load forecasting of iron and steel industry area based on combination model of SVM and LSTM
    Xiaoyan QI,Hengjie LIU,Qiuhua HOU,Xiaoyu LIU,Yanchao TAN,Liancheng WANG
    Journal of Shandong University(Engineering Science). 2021, 51(4):  91-98.  doi:10.6040/j.issn.1672-3961.0.2020.539
    Abstract ( 160 )   HTML ( 6 )   PDF (5138KB) ( 29 )   Save
    Figures and Tables | References | Related Articles | Metrics

    A short-term load forecasting algorithm combining long short-term memory (LSTM) and support vector machine (SVM) was proposed to solve the low accuracy problem of short-term load forecasting due to the large-scale iron and steel enterprise power consumption impact on regional load. The research thoroughly analyzed the load characteristics of the selected region with predominant iron and steel mill load, which divided the load into the impulse load and others based on its various components.Covariance algorithm and Pearson algorithm were used to analyze the correlation and differentiation of load influence factors. Six attributes of historical load, temperature, date type, steel price, electricity price and iron ore price were selected as load forecasting. The fuzzy weight assignment was used to fuse LSTM and SVM which got the final load forecasting result. The simulation results showed that the proposed method could predict the short-term load more accurately than the single LSTM or SVM.

    Uncertainty analysis of transmission tower-line system under wind load
    XU Zhen, ZHANG Tao, GE Xiangdong, GAO Feng, ZHANG Laiyi, ZHANG Xin, TIAN Li
    Journal of Shandong University(Engineering Science). 2021, 51(4):  99-105.  doi:10.6040/j.issn.1672-3961.0.2020.475
    Abstract ( 111 )   PDF (4920KB) ( 33 )   Save
    References | Related Articles | Metrics
    Considering the parameter uncertainty of tower-line architecture and collapse analysis, the collapse process of the whole structure could be described more accurately. The sensitivity of the collapse process of the transmission tower-line system under wind load to the material and geometric uncertain parameters of the structure was analyzed. The collapse criterion of transmission tower-line system was established, and the global damage index(GDI)was proposed. The uncertain model of structural parameters was established by Latin hypercube sampling method, and the internodes and collapse probability of transmission tower collapse were counted. The results showed that the yield strength of steel was the biggest change in the critical wind speed of structural collapse among the six uncertain parameters. When calculating the wind-induced vulnerability of the transmission tower-line system considering the uncertainty of structural parameters, the critical wind speed of structural collapse increased.
    Flow characteristics of dual inner-tube chimney in thermal power plant
    LI Xu, AN Chunguo, WANG Zhaoyang, WANG Zhan, JI Wanxiang
    Journal of Shandong University(Engineering Science). 2021, 51(4):  106-110.  doi:10.6040/j.issn.1672-3961.0.2020.306
    Abstract ( 127 )   PDF (4422KB) ( 18 )   Save
    References | Related Articles | Metrics
    Computational fluid dynamics method was used to analyze the flow characteristics of conventional chimney, including the distribution of flow dead zone, the distribution of pressure drop, and the influence of cross-sectional area and side area on flow resistance. According to the large pressure drop in semicircular inner tube, a kind of superior arcuate inner tube was proposed, which could effectively combine the advantages of circular tube and semi-circular tube, and had the characteristics of compact structure, small cross-sectional area and low flow pressure. The results showed that, under the same cross-sectional area, the pressure drop of the superior arcuate tube was smaller than that of the semicircular tube, and slightly larger than that of the circular tube. In order to ensure the same pressure drop as the circular tube, the cross-sectional area of the semicircular tube was increased by about 5%, while the superior arcuate tube should be increased by about 3%. The results provided a reference for the design of the inner tube of power plant chimney.
    Analysis on the dynamic response of multi-bundle transmission line subjected to ice-shedding
    ZHAI Bin, ZHANG Sixiang, LIU Kaiming, TIAN Li, ZHANG Laiyi
    Journal of Shandong University(Engineering Science). 2021, 51(4):  111-117.  doi:10.6040/j.issn.1672-3961.0.2020.487
    Abstract ( 143 )   PDF (3383KB) ( 13 )   Save
    References | Related Articles | Metrics
    In order to explore the dynamic response of transmission lines under ice-shedding and improve the existing empirical formula for ice-shedding jumping, the finite element software ABAQUS was used to establish the finite element(FE)model of a 4-bundle conductor. Utilizing the implicit dynamic method, the dynamic response of transmission line after ice-shedding was determined. The result of FE analysis was compared with that was calculated by empirical formulae, based on which the empirical formulae were evaluated and improved. In addition, the influence of ice-shedding occurring on partial sub-wires was investigated, through which the most unfavorable case was obtained. The results showed that when the thickness of ice coating was relatively small, the reaction force at the suspension point of the wire increased monotonously with the ice-shedding rate. If the ice coating was relatively thick, the reaction force would decrease slightly when the ice-sheding rate exceeds a certain value. Additionly, the ice-shedding rate could be used as a parameter in the empirical formula for ice-shedding jumping to improve the accuracy of the formula. When ice-shedding only occured on partial sub-wires, the ice-shedding on lower sub-wire would increase the risk of turning over and thus enlarge the probability of wire abrasion and rupture.
    Correction method for historical output data of photovoltaic power plant considering spatial correlation based on artificial neural network
    YIN Xiaomin, MENG Xiangjian, HOU Kunming, CHEN Yaxiao, GAO Feng
    Journal of Shandong University(Engineering Science). 2021, 51(4):  118-123.  doi:10.6040/j.issn.1672-3961.0.2020.431
    Abstract ( 143 )   PDF (2198KB) ( 24 )   Save
    References | Related Articles | Metrics
    The increase of photovoltaic(PV)system penetration rate brought great challenges to the stable operation of power system. Considering that the accuracy of photovoltaic power prediction was highly dependent on data accuracy, this paper proposed a correction method for historical output data of photovoltaic power plant by taking the advantages of strong ability of artificial neural network in mapping complex nonlinear relations. Person correlation coefficient was employed to select reference PV plants for dimensionality reduction. The inaccurate and missing data of photovoltaic power station could be identified and corrected by taking the spatial correlation characteristics of PV output into consideration based on the output power of reference PV plants, which could solve the problem of PV data inaccuracy caused by human factors or data acquisition system aging. The proposed method was analyzed and verified by the historical output data of Liaocheng City in Shandong Prvoince.
    Prediction of converter valve cooling capacity and water inlet temperature based on LSTM
    LIAO Yi, LUO Wei, JIANG Fengwei, LI Yajin, YU Dayang
    Journal of Shandong University(Engineering Science). 2021, 51(4):  124-130.  doi:10.6040/j.issn.1672-3961.0.2020.538
    Abstract ( 129 )   PDF (1464KB) ( 22 )   Save
    References | Related Articles | Metrics
    In order to solve the problems of lacking of intelligent prediction means for the condition of converter valve cooling system and the difficulty of evaluating the cooling capacity under extreme conditions, a prediction method of cooling margin of converter valve based on LSTM(long short-term memory,LSTM)was proposed. On the basis of quantitative evaluation of cooling margin index of valve cooling system, the long-term and long-term memory network was used to establish the prediction model. Considering the multi-source influencing factors, the feature quantity was selected through the correlation strength and the data sample set was constructed, which was used to train the model. Training was carried out to predict the development trend of water inlet temperature and cooling margin.The analysis model of cooling margin under extreme conditions was provided,which provided the basis for on-site treatment decision. The effectiveness and feasibility of the algorithm were analyzed and verified by an example of converter station.