Volume 45,Issue 5,2022 Table of Contents

1 Short term power load forecasting model based on improved deep forest

PENG Fei , MA Yu , ZHANG Xiaohua , WU Yi , DENG Wenchen , CHENG Zhikui

2022, 45(5):1-8. DOI: 10.11835/j.issn.1000-582X.2020.303

[Abstract](336) [HTML](665) [PDF 9.69 M](782)

Abstract:
Deep learning method can help to learn the deep features of power load data and improve the accuracy of prediction, but it also brings problems, such as large amounts of super parameters and poor interpretability of the model. To solve these problems, this paper introduces the deep forest model for short-term load forecasting. Based on the multi-Grained Cascade forest model, the multi-granularity window scanning method is improved with adjusted window size and sliding step size, so that the model can extract the periodicity characteristics of power load data in different time scales. In addition, the calculation method of deep forest output layer is improved with changing the output result from discrete class vector to continuous predicted value, improving the accuracy of the model. Finally, the feasibility and effectiveness of the proposed method are verified with the measured data of northeast China power grid. The experimental results show that the improved deep forest algorithm can achieve higher accuracy with higher prediction accuracy, and has faster learning speed than the deep neural network.

2 Voltage regulation and battery energy storage SoC balancing method for low voltage distribution network with distributed PV and BESS

MA Xing , XU Ruilin , KANG Wenfa , WEI Chengzhi , LUO Yanyu , CHEN Minyou

2022, 45(5):9-20. DOI: 10.11835/j.issn.1000-582X.2020.225

[Abstract](436) [HTML](518) [PDF 13.17 M](690)

Abstract:
With the increasing penetration of renewable energy sources, the problems of the voltage fluctuation and limitation violation has become very serious. In order to solve this problem, this paper proposes a voltage regulation method for low voltage distribution network with distributed photovoltaic(PV) and battery energy storage system(BESS). First, the impact of distributed PV sources to network voltage is analyzed and the relationship between node voltage magnitude and node injection power is deduced and linearized. Then the power mileage based voltage regulation model is constructed, with which the output of distributed battery energy storage system (DBESS) is calculated by solving the optimization target. Finally, state of charge(SoC) balancing strategy of DBESS is designed to enhance the efficiency of BESS. Furthermore, a simulation model, which is derived from a real 0.4 kV feeder in Wuxi, Chongqing, is built on Matlab/Simulink to test the effectiveness of the proposed method with four different cases. Simulation results shows that the proposed method can keep the system voltage in a normal range and can also guarantee the balance of SoC.

3 A reverse firewall protocol for identity-based authenticated key agreement

LIU Chang , WANG Jin , TIAN Li , WANG Jie , YE Jingyu , QIN Fan , ZHOU Yuyang

2022, 45(5):21-32,42. DOI: 10.11835/j.issn.1000-582X.2022.05.003

[Abstract](306) [HTML](395) [PDF 10.76 M](648)

Abstract:
Identity-based authenticated key agreement allows two or more parties to establish secure session keys over insecure channels. Current authenticated key agreement protocols are unable to resist the backdoor attacks that lead to random number disclosure, such as known session-specific temporary attack. Therefore, we propose a reverse firewall protocol for identity-based authenticated key agreement. The protocol is secure under the random oracle model. In addition, it can resist strong temporary session secret value leakage attack and can provide message leakage resistance. Meanwhile, the protocol saves the system’s running time because it does not use bilinear pairing. Finally, we implement the protocol using JPBC library. The experimental results show that the protocol has smaller bandwidth and shorter running time compared with other protocols of the same type. It is very suitable for resource-constrained systems.

4 An intelligent substation logic mode metwork failure chain model based on CML

Wang Sheng , Zhang Jie , Tang Chao , Zhang Linghao , Wang Hai , Tang Yong , Chai Jiwen , Zheng Yongkang , Deng Ping , Cao Liang , Ke Yawen

2022, 45(5):33-42. DOI: 10.11835/j.issn.1000-582X.2022.05.004

[Abstract](254) [HTML](566) [PDF 10.77 M](530)

Abstract:
In order to ensure the safety of intelligent substation and avoid information security risks, it is necessary to evaluate and manage the vulnerability in the substation. The mainstream risk assessment methods use asset importance, threat level and vulnerability level as quantitative indicators. Through these three indicators, the value of the impact and possibility of security events is obtained, and then the risk of the object is calculated. This paper proposes a CML-based intelligent substation logic node network failure chain model, Through the establishment of a network of intelligent substation logical nodes and logical connections between nodes, the impact of different logical nodes on the overall logical network of intelligent substation in the event of a fault is evaluated, so that the intelligent substation information security risk can be effectively analyzed. The intelligent substation information security risk analysis and management subsystem based on this model can help managers manage information security risk data of intelligent substation and realize data visualization. The results show that the information security risk analysis and management of intelligent substation can be improved.

5 Influence of hydrogenation at different temperatures on hydrocarbon generation of source rocks

WU Yunhao , LEI Tianzhu

2022, 45(5):43-51. DOI: 10.11835/j.issn.1000-582X.2022.05.005

[Abstract](242) [HTML](774) [PDF 8.21 M](541)

Abstract:
Thermal simulation experiments before and after hydrogenation of organic rich mudstone in Huanglong area of Shaanxi Province in closed system show that hydrogenation has a significant impact on the generation of saturated hydrocarbons and aromatics in source rocks, and the action stages are in the ranges of 200 ℃ to 400 ℃ and 400 ℃ to 500 ℃. At relatively low temperature, hydrogenation can inhibit the formation of saturated hydrocarbons, especially low carbon number saturated hydrocarbons; at high temperature, hydrogenation can promote the formation of low carbon number saturated hydrocarbons. The study on the product characteristics of different temperature stages of source rock evolution under different conditions is helpful to better understand the evolution process of source rock and the change of source rock after the change of external conditions, providing ideas for oil and gas exploration and fine evaluation.

6 Study on natural lighting simulation and optimization design of railway station in alpine region

ZHANG Xingyan , YAN Jianwei

2022, 45(5):52-66. DOI: 10.11835/j.issn.1000-582X.2020.064

[Abstract](270) [HTML](607) [PDF 36.10 M](639)

Abstract:
Railway station building is a kind of special tall space building with large construction amount, high frequency usage and huge lighting energy consumption. There are abundant sunshine resources in alpine regions in China. In the design of railway stations, natural light should be fully used to create a good architectural light environment, reduce indoor lighting energy consumption, and achieve the purpose of protecting the ecological environment in alpine regions. According to the local climate conditions, this paper uses the parametric software Rhino to simulate the dynamic daylighting of railway station buildings in alpine regions. It is found that there are some problems in the use of natural lighting, such as low lighting uniformity, overexposure and glare. To address these issues, the optimization measures are put forward: the effective daylighting in the middle of the station building can be improved by controlling the effective depth of daylighting or setting high side windows; the illumination near the window can be effectively controlled by properly adjusting the light transmittance of the low side window to prevent overexposure; the glare can be prevented and the light environment comfort can be improved by using adjustable photosensitive horizontal sunshade or curtain; the waiting hall can obtain good daylighting self-sufficiency when the light transmittance of high side window reaches above 0.75.

7 Standardization simulation of energy saving potential of passive design in shopping centers

WEI Lai , DANG Rui , LIU Gang , YUAN Ye , HUANG Wenlong

2022, 45(5):67-78. DOI: 10.11835/j.issn.1000-582X.2020.221

[Abstract](281) [HTML](565) [PDF 16.24 M](574)

Abstract:
In this paper, the energy saving potential of passive design for shopping centers in the early design stages is quantitatively evaluated through standardized modeling and simulation. With cold regions taken as an example, three common standard geometric models and operating parameters of shopping centers with typical climatic characteristics were extracted. Grasshopper and EnergyPlus were chosen as the standard parametric modeling software and the energy simulation software, respectively, while 24 passive design parameters from the site, building and envelope that affect the energy-saving potential of shopping centers were summarized. Finally, by simulation, the energy saving potential rankings of the 24 passive design parameters in three standard models were obtained. The result shows that the entrance wind speed, corridor space, the ratio of skylight area to roof area and roof heat transfer coefficient are four important design parameters that affect the energy saving potential of shopping centers in cold regions, providing designers with quantitative guidance for design optimization in the early design stages.

8 Selection of building energy consumption prediction machine learning algorithms and parameter setting based on quality of samples

LIU Gang , LI Xiaoqian , HAN Zhen

2022, 45(5):79-95. DOI: 10.11835/j.issn.1000-582X.2020.058

[Abstract](360) [HTML](710) [PDF 13.85 M](653)

Abstract:
Machine learning algorithms are playing a more important role in building energy consumption prediction during the conceptual design. The selection of the machine learning algorithms and parameter setting have become a focus in the field of building performance design. However, the algorithms and their parameters are usually determined by the principle of algorithms rather than the features of the training samples which also have an effect on the performance of algorithms. Therefore, a classification method based on the quality of training samples which is evaluated by sample size and sample distribution characteristics is proposed. The performance of different machine learning algorithms for different quality sample sets is tested, and algorithm selection and parameter setting strategies for different quality sample sets are formulated. The relationship between sample quality and algorithm performance is investigated to provide effective guidance for architects.

9 Dynamic response and control analysis of construction trestle under ship waves excitation

CHEN Yongliang , LIU Gang

2022, 45(5):96-106. DOI: 10.11835/j.issn.1000-582X.2022.05.009

[Abstract](199) [HTML](496) [PDF 8.59 M](458)

Abstract:
Under the excitation of ship waves, a large displacement and acceleration response could be generated to the construction trestle, which will affect the construction operation, cause panic among workers, and even lead to an excessive deformation, thus laying potential safety risks. In this paper, using the construction trestle of a large bridge on Zhengwan high-speed railway as the experimental subject, the dynamic response and control analysis of construction trestle under ship waves excitation were examined. Firstly, the calculation of ship waves load simplified by linear wave theory was used. Then, the effect of water on structure frequency was investigated by additional mass method, and the restraining effect of water on steel pipe pile vibration was calculated by additional damping method. To study the dynamic response of steel pipe piles, the analysis of harmonic response was used to discuss the effect of two classes of ship waves, causing by small and medium-sized passenger ships or barges separately. The results show that the influence of water on the frequency of trestle steel pipe pile was great, while the effect of external damping on the dynamic response of steel pipe pile could be neglected. The mechanism of excessive displacement of the trestle caused by small and medium-sized passenger ships was resonance response, while the reason of excessive displacement of the trestle caused by barges was heavy load. To ensure the safety of trestle construction, it is suggested that the speed limit of passenger ships be 15 km/h to prevent resonance, and barges’ speed limit be 10 km/h to reduce the wave load.

10 Experimental study on the thermal performance of a hot air phase change thermal storage module

NIE Xiu , CUI Wenzhi

2022, 45(5):107-113. DOI: 10.11835/j.issn.1000-582X.2022.05.009

[Abstract](258) [HTML](864) [PDF 5.46 M](454)

Abstract:
A module integrated with the phase change material-decanoic acid and copper tube heating by hot air was proposed. Using its one cell as experimental subject, the temperature variation of the phase change material was evaluated using thermocouples. The heat transfer characteristics of the module was acquired by comparing the phase changing process of the horizontally arranged cell with that of the vertically arranged one. The results show that the decanoic acid’s melting rate of the module placed horizontally is higher than the one placed vertically in the same experimental conditions, which provides a reference for the installation of it in practical applications. An improved module, containing S-shaped cooper tube which enhances the natural convection in the outside wall, has better energy storage efficiency.

11 ESRGAN network for super-resolution reconstruction of anisotropic 3D-MRI images

ZHANG Jian , JIA Yuanyuan , HE Xiangqian , HAN Banru , ZHU Huazheng , DU Jinglong

2022, 45(5):114-124. DOI: 10.11835/j.issn.1000-582X.2022.05.011

[Abstract](562) [HTML](559) [PDF 8.04 M](931)

Abstract:
High-resolution(HR) magnetic resonance images (MRI) can improve the accuracy of disease diagnosis, but it is very difficult to obtain high-resolution MRI. Image super-resolution (SR) technology based on deep learning can effectively improve image resolution. In recent years, the generative adversarial networks (GANs) have provided new ideas for 3D-MRI SR reconstruction. Compared with the traditional SR algorithm based on deep convolutional neural network (DCNN), the GANs network targets the human visual mechanism and introduces a discriminant function to make the reconstructed 3D-MRI closer to the real image. We introduced the enhanced super-resolution generative adversarial network (ESRGAN) to perform SR reconstruction of 3D-MRI, and used the cross-layer self-similarity of 3D-MRI to reduce the dimensionality of the reconstruction task to 2D. On the basis of ensuring the reconstruction effect, the proposed method can reduce network training time and memory requirements. Compared with other traditional algorithms and DCNN-based techniques, experimental results show that our proposed method can further improve the visual quality of SR 3D-MRI.

12 An ensemble learning algorithm for feature selection based on solution to multi-class imbalance data classification

SU Chen , XU Hua , CUI Xin , WANG Lingdi

2022, 45(5):125-134. DOI: 10.11835/j.issn.1000-582X.2022.05.012

[Abstract](350) [HTML](616) [PDF 7.84 M](586)

Abstract:
In order to solve the problem of unbalanced multi-classification, a feature selection and AdaBoost integration method is proposed. First, the data is preprocessed. The WSPSO algorithm is used to select features, and the initial population is constructed according to the importance of the feature. The initial algorithm can be carried out along the correct search direction to reduce the influence of incoherent features. Secondly, the AdaBoost algorithm is more sensitive to sample weights, and the attention to small samples is enhanced. And using AUCare is used, as the evaluation standard, because compared with other evaluation criteria, AUCare has the advantage of visualization and is more sensitive to poor AUC. Finally, compared with several other unbalanced classification algorithms on the unbalanced data set, the algorithm can effectively deal with the unbalanced multi-classification problem.

13 Study on yield mechanism of spherical plate branch joints in lattice concrete-filled steel tube wind turret

WEN Yang , YU Jiao , MENG Chuncai

2022, 45(5):135-146. DOI: 10.11835/j.issn.1000-582X.2022.05.013

[Abstract](256) [HTML](606) [PDF 11.55 M](485)

Abstract:
In order to study the yield mechanism of branched spherical plate joints wrapped in lattice concrete filled steel tubular wind power tower,static load experiment was conducted on 4 full-scale models of CFST universal joints.Then,software ABAQUS was used for non-linear finite element analysis.By changing the radius-thickness ratio of the inclusion,thickness of gusset plats,the failure mode of joints and the equivalent stress of gusset plates and the equivalent stress of joints intersection area were analyzed. The results indicate that the damage of the universal joint was caused by the failure of the weld failure between gusset plate and steel ball and buckling of compressive bar.The bearing capacity of the universal joint is sensitive to the thickness of the gusset plat, but it is weak sensitive to the radius-thickness ratio of the inclusion. The thicker the nodal plate, the better the dissipation of the equivalent force; when the radius-thickness ratio of the inclusion is no more than 38.5(γ<38.5), the bearing capacity of joints decreases large amplitude with the increase of γ; when the radius-thickness ratio of the inclusion is greater than 38.5, the bearing capacity of joints decreases small amplitude with the increase of γ. It is suggested that the radius-thickness ratio of the inclusion is 38.5;when the thickness of the joint plate is no more than 14, the bearing capacity of joints increase large amplitude with the increase of n, when the thickness of the joint pate is greater than 14, the bearing capacity of joints increase small with the increase of n.

14 Incremental multi-modal clustering methods for text data in archives administration

LIU Lihua

2022, 45(5):147-156. DOI: 10.11835/j.issn.1000-582X.2020.305

[Abstract](322) [HTML](681) [PDF 7.87 M](512)

Abstract:
With the continuous growth of modern archive management data, the effective clustering of archive text can significantly improve the efficiency of archive classification and retrieval. This paper proposes two incremental multi-modal text data clustering methods. By multi-perspective analysis of the text content, the potential topic features of texts are integrated to improve the accuracy of text clustering. In addition, the corresponding incremental multi-modal feature learning models for text clustering are designed to improve the efficiency of massive and dynamic text partition. Experimental results on real-world text data sets show that the proposed incremental multimodal text clustering methods outperform the compared stated-of-the-art methods, being able to effectively classify text data.

Home

Volume 45,Issue 5,2022 Table of Contents

Current Issue

Volume

Issue

Most Read

Most Cited

Most Downloaded