Please wait a minute...
, No 9

■ Cover Page (PDF 2.68 MB) ■ Editorial Board (PDF 72.8 KB) ■ Table of Contents, Sept 2019 (PDF 307 KB)

  • Failure Analysis of Acrylonitrile Butadiene Styrene (ABS) Materials and Damage Modeling by Fracture
    Fatima Sabah, Achraf Wahid, Abdelkarim Kartouni, Hamid Chakir, and Mohamed ELghorba
    2019, 15(9): 2285-2293.  doi:10.23940/ijpe.19.09.p1.22852293
    Abstract    PDF (539KB)   
    References | Related Articles
    Polymer materials are distinguished by their simple and economical for-matting, versatility, lightness, and chemical stability. Despite their widespread use both in everyday life and in advanced technologies, these materials are generally still very poorly understood in regards to its chemical, physical and environmental, rheological and mechanical properties. The purpose of this study is to determine the notch effect on the mechanical behavior of Acrylonitrile Butadiene Styrene (ABS), which we carried out tensile tests on ABS rectangular test pieces for different backgrounds. The notch ranges from 1 mm to 18 mm. Subsequently we have based an approach, which consists in following the evolution of static damage as a function of the fraction of life test pieces notched, to know the critical fraction of life and which corresponds to a critical notch radius, which can be authorized. Second, we calculated the stress concentration factor by two methods to determine the critical stress concentration that usually precedes the sudden failure of a component. Finally, we will relate the damage factor Ds to the stress concentration factor through the fraction of life by using a nonlinear correlation, which makes it possible to predict the instant of acceleration of damage for a preventive maintenance.
    Shell Side CFD Analysis of a Small Shell-and-Tube Heat Exchanger with Elliptical Tubes
    Piyush Gupta, Avdhesh Kr. Sharma, and Raj Kumar
    2019, 15(9): 2294-2304.  doi:10.23940/ijpe.19.09.p2.22942304
    Abstract    PDF (748KB)   
    References | Related Articles
    In this article, the thermal and flow characteristics of a small, single pass, STHX fitted with elliptical tubes are resolved using commercial ANSYS Fluent. A 3D CFD model in solid edge was built, while the physical domain was discretized into tetrahedral elements of 50,71,151 with 9,56,469 nodes using ICEM-CFD 14.0. The most suitable k - ε realizable model for turbulence was employed. The influence of baffle spacing and different angle of attack for STHX with elliptical tubes is highlighted while fixing baffle cut at 36%. Results show that a five-baffled STHX with elliptical tube arranged in triangular tube layout is found to be most effective for angle of attack of 0°.
    A Comparison Evaluation of Demographic and Contextual Information of Movies using Tensor Factorization Model
    Anu Taneja, and Anuja Arora
    2019, 15(9): 2305-2317.  doi:10.23940/ijpe.19.09.p3.23052317
    Abstract    PDF (728KB)   
    References | Related Articles
    Recommendation systems have procured massive attention due to the fast and eruptive expansion of information on the internet. Traditionally, the recommendation systems recommend products based only on the rating criteria but nowadays user expects suggestions in accordance with his requirements and might have varying preferences in different circumstances. Thus, this work presents an innovative framework to consider additional information beyond ratings that is demographic details and under what situations user interact with the system known as contextual information. This additional information is modelled as varying dimensions of the tensor factorization model. The main motive of this study is to determine the more influential dimensions among demographic and contextual dimensions and it is observed that contextual dimensions are more influential than demographic dimensions. The results validate that usage of contextual dimensions mitigates the sparsity and cold-start problems by 16% and 22% respectively in comparison to demographic information.
    Modeling and Prediction of Remaining Useful Lifetime for Maintenance Scheduling Optimization of a Car Fleet
    Duc Van Nguyen, Steffen Limmer, Kaifeng Yang, Markus Olhofer, and Thomas Bäck
    2019, 15(9): 2318-2328.  doi:10.23940/ijpe.19.09.p4.23182328
    Abstract    PDF (802KB)   
    References | Related Articles
    The remaining useful lifetime (RUL) is the time remaining until an asset no longer meets operational requirements. An accurate estimation of the RUL is central to prognostics and health management systems. However, the RUL of an asset is usually very difficult to estimate and to achieve in any industry. This is because the RUL strongly depends on manufacturing, the operating environment, and the observed condition monitoring. Here, we use physics-based approaches and data-driven approaches to predict the RUL of four essential components of a passenger car, namely engine, brake pads, springs, and tires. Our results show good agreement of both approaches. In addition, we develop a hybrid framework to generate a data set of RULs of a car fleet. This framework can be used to establish an optimal maintenance schedule for a car fleet, such as the fleet of a taxi company.
    CD3T: Cross-Project Dependency Defect Detection Tool
    Yongming Yao, Song Huang, Cuiyi Feng, Chen Liu, and Chenying Xu
    2019, 15(9): 2329-2337.  doi:10.23940/ijpe.19.09.p5.23292337
    Abstract    PDF (499KB)   
    References | Related Articles
    Nowadays, every software project usually has a large number of third-party components depending on the repository, some of which have some unsafe code. Due to complex references and dependencies, code defects and vulnerabilities in upstream dependent libraries will inevitably affect downstream software. In this paper, we design a cross-project dependency defect detection system based on Java, called CD3T. The entire implementation process of CD3T uses Apache Maven as a project dependent package management tool and uses IntelliJ IDEA as an integrated basic environment for the development of coding, compilation, and packaging. The system uses a full-text search engine and H2 Database that supports the engine that formats and stores vulnerability data, and the Apache Velocity template engine drives report generation. Finally, it obtains and formats the data that stores the U.S. national common vulnerability database, file dependency analysis, file dependency vulnerability checking, and check result output.
    Design of Vehicle Automatic Braking Systems Considering Drivers’ Braking Characteristics
    Zhenhai Gao, Tianjun Sun, MuHammad Hassan, and Liupu Wang
    2019, 15(9): 2338-2345.  doi:10.23940/ijpe.19.09.p6.23382345
    Abstract    PDF (832KB)   
    References | Related Articles
    With the rapid development of advanced driver assistance systems (ADAS), an automatic braking system has become increasingly important when faced with complicated traffic. The conventional decision-making method for the braking system is focused on security but lacks consideration of drivers' characteristics, which generates feelings of fear and frustration. We propose an anthropomorphic braking method based on vehicle kinematic characteristics and dynamic theories to improve the original system and eliminate the sense of jerking. Furthermore, on the basis of the traditional time to collision (TTC) algorithm, we consider the random motion of the target vehicle and develop a dynamic time to collision (DTTC) algorithm to meet different drivers' braking requirements. Therefore, in this study, the braking model is optimized by a series of driving simulator and real-vehicle braking tests. Finally, the validity and feasibility of the method are verified through the simulations of different braking modes.
    Analog Detection of PSD Sensor and Sunshine Position Tracking Performance in Four Quadrant Arrays
    Yajie Wang, Xiaoyu Yu, Daniel Wang, Qiaohua Feng, and Yunbo Shi
    2019, 15(9): 2346-2355.  doi:10.23940/ijpe.19.09.p7.23462355
    Abstract    PDF (562KB)   
    References | Related Articles
    In view of the need to convert solar energy into electrical energy for photovoltaic cells, and using solar tracking technology to improve efficiency, a solar position tracking sensor for core components in a solar tracking system is studied. Based on the analysis of the characteristics of photosensors such as photoresistors, photodiodes, and CMOS photosensitive tubes used for position detection, this paper proposes a position sensitive detector (PSD) based on transverse photoelectric effect to realize solar position tracking detection. By analyzing the basic working principle of the PSD sensor and taking the center of the PSD photosensitive surface as the origin, the plane rectangular coordinate system is established parallel to the direction of the photosensitive surface, and the quadrant array PSD sensor model and equivalent circuit are constructed. According to the needs of the sun position detection, the natural environment interference is avoided, and it is guaranteed to be in a stable working environment. The light-shielding cylinder is designed as its packaging structure, and the calculation mode of the azimuth angle α and the elevation angle θ of the incident light spot of the sunlight are given. A solar lighting simulation experimental device is designed and built to perform sensor performance tests. Through testing, when the measurement accuracy is guaranteed around 0.2°, the height of the light-shielding cylinder is 25mm and the aperture is 4mm. By comparing the measured value with the theoretical value, in the measurement range of 90 ± 10°, the correlation coefficient is 0.9999, and the approximate linear relationship between the angle and the displacement is obtained. The maximum error is 0.102°. The polarizer is used as the optical device for adjusting the intensity of light, avoiding the problem that the sensor reaches the upper limit of saturation output due to the sunlight intensity. Finally, the corresponding relationship between the polarizer angle and the output divided voltage of the sensor is given, and the error tends to change with the light intensity.
    An Improved Genetic Algorithm to Optimize Vehicle Scheduling for Relief Efforts
    You Zhou, Lecheng Sun, Xu Zhou, Milan Parmar, and Liupu Wang
    2019, 15(9): 2356-2363.  doi:10.23940/ijpe.19.09.p8.23562363
    Abstract    PDF (375KB)   
    References | Related Articles
    The vehicle scheduling problem is a typical multi-objective optimization problem. It is a core logistics dispatching problem and the key to realize system optimization. Optimizing vehicle scheduling for relief efforts has important practical significance and can be applied to a broader range of applications. Compared with other vehicle scheduling problems, vehicle optimal scheduling for relief efforts is mostly used to perform spot delivery or security tasks. In this paper, we propose an improved genetic algorithm and apply it to solve the vehicle scheduling problem for relief efforts in the equipment technical area. The experimental results demonstrate the effectiveness and robustness of our proposed algorithm.
    A Survey of Software Trustworthiness Measurements
    Hongwei Tao, Yixiang Chen, Hengyang Wu, and Rumei Deng
    2019, 15(9): 2364-2372.  doi:10.23940/ijpe.19.09.p9.23642372
    Abstract    PDF (207KB)   
    References | Related Articles
    As people depend more and more on software, there exists an increasing demand for software trustworthiness. The quantification of software trustworthiness can not only help users choose the right software, but also provide evidence for increasing the trustworthiness of the design and implementation of software. It has important practical significance to software development and application. In this paper, software trustworthiness measurements are surveyed from two aspects of product and process. The advances in the product-oriented software trustworthiness measurements are summarized in the view of attributes and behaviors, and the research progress of the process-based software trustworthiness measurements is studied from the perspective of expert experience and process data. Lastly, the challenges of software trustworthiness measurements are analyzed.
    A ReliabA Reliability Prediction Method of Novel Grey Model and its Error Analysisility Prediction Method of Novel Grey Model and
    Wei Meng, Bo Zeng, Shuliang Li, and Syed Ahsan Ali Shah
    2019, 15(9): 2373-2381.  doi:10.23940/ijpe.19.09.p10.23732381
    Abstract    PDF (832KB)   
    References | Related Articles
    This study proposed a reliability prediction method of novel fractional-order discrete grey prediction model FODGM (1,1), which is developed on the discrete grey prediction model DGM (1,1). The modeling error distribution of FODGM (1,1) is systematically studied. The sequences of exponential data are generated for numerical simulation. Later, the mean absolute percentage errors (MAPE) of FODGM (1,1), with different values of order and development coefficient, are compared to the modeling errors of GM (1,1) and DGM (1,1) using numerical simulation. The modeling error distribution graph of FODGM (1,1) with the sequences of exponential data is presented. The findings reveal that DGM (1,1) and the direct modeling DGM (1,1) are both special cases of FODGM (1,1). The outcome provides a foundation to further optimize the grey model by using fractional-order operators and to expand the applicable bound of the grey model.
    An Intelligent Identification Algorithm for Obtaining the State of Power Equipment in SIFT-based Environments
    Chao Yang, Xinghua Wu, Weiyong Gong, Qiang Wang, and Lin Li
    2019, 15(9): 2382-2391.  doi:10.23940/ijpe.19.09.p11.23822391
    Abstract    PDF (565KB)   
    References | Related Articles
    The accurate identification and verification of the state of power equipment used in substation operations would allow intelligent substations to be operated unattended under severe weather and complex background conditions. Currently, the main functions of robot or online monitoring systems operated by substations are to provide human-assisted inspections, not automatic identification or calibration. Combined with the actual conditions of smart grid substations and construction requirements, this paper proposes an algorithm based on computer intelligent vision technology that can be used for the automatic identification of typical outdoor circuit breakers and disconnectors and the position state of indoor switchgears. Firstly, a scale invariant feature transform (SIFT) algorithm was used to accurately locate the area to be detected. Then, image preprocessing technology was used to remove noise points and extract edge information. The randomized Hough transform was used to extract the line information of the disconnector and the circle information of the switchgear, and k-NN (k nearest neighbor) was used to extract and identify the written character information on the circuit breaker. Finally, intelligent identification was set up using thresholds for three types of power equipment, and the algorithm was verified for a disconnector in a 500-kV substation in China and at the Qinghe substation. Based on actual measurements at these sites, the algorithm exhibited strong identification performance, stability, and high accuracy in identifying the position state of the switches in severe weather. It can be used to not only solve the current lack of effective automatic online monitoring of power equipment, but also serve as an important extension of many areas of smart grid research.
    A Novel Safety Assessment Method based on Fault Dependent Matrix
    Haiyong Dong, Qingfan Gu, Guoqing Wang, Zhengjun Zhai, and Yanhong Lu
    2019, 15(9): 2392-2399.  doi:10.23940/ijpe.19.09.p12.23922399
    Abstract    PDF (495KB)   
    References | Related Articles
    Most traditional safety analysis methods express safety models with graphical forms, which are difficult to be stored in a computer and have limited analysis capabilities. Referring to the incidence matrix of Petri net, this paper proposes a novel fault dependent matrix for expressing the safety model. In addition, qualitative assessment algorithms are introduced from the top layer and bottom layer, as well as the quantitative assessment method. This paper takes a typical cooling system as an example to describe the process of construction and evaluation of the safety model. Based on the evaluation results, suggestions for improving system safety are proposed. Safety assessment based on a fault dependent matrix is more convenient when expressed and calculated by computers, and it is more likely to be promoted.
    A Degradation Identification Method Combining Cost Matrix and Prediction Window Width for Mechanical Equipment
    Xinbo Qian, and Jian Huang
    2019, 15(9): 2400-2406.  doi:10.23940/ijpe.19.09.p13.24002406
    Abstract    PDF (391KB)   
    References | Related Articles
    To improve the efficiency of preventive maintenance management for complex mechanical equipment or components, it is necessary to identify the degradation state from both historical and online data. It may be more important to recognize the alarming state due to the high downtime cost. However, uncertainties of monitoring data may reduce the prediction accuracy. Therefore, a new self-organizing map-based method combined with misclassification cost matrix and window width of prediction (SOM+COST+WWP) is proposed to improve the prediction accuracy of the alarming state. Case studies show that SOM+COST+WWP has advantages for higher recognition accuracy for the degradation state compared with other SOM-based methods.
    Intrusion Detection based on T Cell Receptor Principle
    Hua Yang, and Tao Li
    2019, 15(9): 2407-2413.  doi:10.23940/ijpe.19.09.p14.24072413
    Abstract    PDF (488KB)   
    References | Related Articles
    Network intrusion detection has become more significant in cyber security. The artificial immune system inspired by the biological immune system can detect unknown abnormal behaviors, which is similar to intrusion detection. In this paper, we introduce the T cell receptor principle and then propose the intrusion detection method from the T cell receptor extraction metaphor. Finally, experiments are carried out on the Iris data set and NSL-KDD data set. The results show that our method can detect abnormal behaviors, but it still has room for improvement. This paper seeks to provide researchers with a new idea of artificial immunity in intrusion detection.
    Fast Mode Decision for Low Complexity Depth Coding in3D-HEVC System
    Qiuwen Zhang, Shuaichao Wei, Tao Wei, and Haixu Niu
    2019, 15(9): 2414-2421.  doi:10.23940/ijpe.19.09.p15.24142421
    Abstract    PDF (328KB)   
    References | Related Articles
    The rapid developments of 3D video techniques and real applications have attracted the attention of consumers, so the demand degree of storage and transformation for 3D video content has become stronger than before. The 3D-HEVC compression structure is the development of HEVC. 3D-HEVC adopts a multi-view video plus depth (MVD) system, where it establishes correspondences between every depth map and every texture frame. Depth modeling modes (DMM) are also developed by 3D-HEVC because they play an important role in sharp edge encoding. However, the distinct trouble of using DMM, which increases computational burdens, will be introduced in the 3D-HEVC encoder. This paper presents a fast mode selection system that researches the texture frames and depth maps in order to attain the edge data of prediction units (PUs), and then a novel early stop according to the flatness of the current block is also adopted. Beyond that, we also introduce a fresh heuristic method in terms of shuffled frog leaping to obtain the best wedgelet pattern in 3D-HEVC. The overall experiment demonstrates that our algorithm surpasses HTM16.0 in terms of coding efficiency with negligible loss.
    Trade-off Costs of Software Trustworthy Attributes
    Mengyue Wang, Yanfang Ma, Haiyu Pan, Hongwei Tao, and Liang Chen
    2019, 15(9): 2422-2431.  doi:10.23940/ijpe.19.09.p16.24222431
    Abstract    PDF (574KB)   
    References | Related Articles
    Software trustworthiness is an important criterion to evaluate software quality. Software trustworthiness consists of reliability, security, availability, etc. In order to improve software trustworthiness, some strategies are used to improve trustworthy attributes. However, the strategy to increase a certain trustworthy attribute will lead to a decrease in other trustworthy attributes. Meanwhile, the loss costs will rise. Therefore, based on the production theory in the field of microeconomics, the relationships between trustworthy attributes are proposed when the strategies are used. Then, the weight of each trustworthy attribute is obtained by using an analytic hierarchy process. When strategies are used, trustworthy attributes with an inhibition relationship are analyzed by utilizing weights of trustworthy attributes. Furthermore, for trustworthy attributes with an inhibition relationship, the optimal trade-off costs mathematical model is established. Finally, an application is given to demonstrate the feasibility of the proposed model.
    Service Recommendation Model based on Rating Matrix and Context-Embedded LSTM
    Chenyang Zhao, and Junling Wang
    2019, 15(9): 2432-2441.  doi:10.23940/ijpe.19.09.p17.24322441
    Abstract    PDF (499KB)   
    References | Related Articles
    Service recommendation based on deep learning has attracted more and more attention in recent years. However, most of the existing works do not make full use of contextual information when acquiring latent preference features of users. Therefore, a personalized service recommendation model based on rating matrix and context-embedded LSTM is proposed in this paper. In this model, for a given user, based on different rating contexts, the rating matrix is firstly improved to have embedded contextual information, and then a sequence of service vectors is obtained from the improved rating matrix according to the order in which the user consumes services. Motivated by the successful use of the LSTM network for processing sequential data, the sequence of service vectors is input into the LSTM network to obtain the preference features of the user. Based on the preference features of the user, the selection probability distribution of all candidate services is output by using a softmax network. Finally, Top-N services that the user may be most interested in are returned to the user. Experimental results demonstrate that the proposed model can achieve better performance than various competitive baseline methods.
    Availability Evaluation of Multi-State Weighted k-out-of-n Systems with Hierarchical Performance Requirements
    Jing Li, Guangyu Chen, Lin Tang, and Xinyu Yang
    2019, 15(9): 2442-2452.  doi:10.23940/ijpe.19.09.p18.24422452
    Abstract    PDF (806KB)   
    References | Related Articles
    The multi-state weighted k-out-of-n system has been widely studied in recent research. In this paper, two improved availability evaluation methods of an extended multi-state weighted k-out-of-n system with hierarchical performance requirements are presented. Such a system is capable of featuring multiple performance requirements at different system hierarchical levels that are not independent of each other, which is more general than the traditional multi-state weighted k-out-of-n system model. To solve the problem of inter-level performance dependencies, a new method combining the universal generating function (UGF) with hierarchical operators is developed to evaluate the system availability. Moreover, a simple recursive algorithm is proposed to reduce the computational complexity to access the lower and upper bounds of availability. Finally, numerical examples and analysis are provided to validate the proposed methods. The results show that the proposed methods are more general and flexible, and they can provide references to designers for the performance improvement of complex systems.
    Application of Improved Feature Pre-processing Method in Prevention and Control of Electricity Charge Risk
    Huaiguang Wu, Yongsheng Shi, Shenyi Qian, Hongwei Tao, and Jiangtao Ma
    2019, 15(9): 2453-2461.  doi:10.23940/ijpe.19.09.p19.24532461
    Abstract    PDF (620KB)   
    References | Related Articles
    With the increase in power data, past data processing technologies cannot meet the needs of rapid processing and intelligent analysis of massive data. In order to solve the problems of current performance bottleneck in the calculation of power big data and recover users' electricity tariff arrears in a timely manner, we use the technology of combining parallel computing with feature expansion to establish a feature expansion method based on Spark distributed computing (FESDC). According to the data generated by the proposed method, we use a parallel logistic regression model to predict the arrears probability of future electricity users, which can effectively prevent and resolve the risk of electricity tariff recovery (ETR). Compared with the data processing method for single process (DPSP), the proposed method not only increased the accuracy of prediction, but also improved the performance of processing data.
    An ANTLR-based Flattening Framework for AltaRica 3.0 Model
    Jun Hu, Shuo Chen, Defeng Chen, Jiexiang Kang, and Hui Wang
    2019, 15(9): 2462-2474.  doi:10.23940/ijpe.19.09.p20.24622475
    Abstract    PDF (1755KB)   
    References | Related Articles
    AltaRica is a modeling language that is capable of hierarchical modelling and fault behavior description for industrial safety-critical system design. AltaRica 3.0 is the latest version, and its semantics are based on a formal GTS (Guarded Transition Systems) model. One of the key steps in the process of safety analysis toward AltaRica 3.0 models is that how to flatten a hierarchical AltaRica 3.0 model into a semantically equivalent GTS semantic model. This paper proposes an AltaRica 3.0 model flattening algorithm framework based on ANTLR (Another Tool for Language Recognition). Firstly, considering the different structural features of Block and Class, the AltaRica 3.0 model is sliced carefully in order to obtain the corresponding AST (Abstract Syntax Tree). Secondly, a set of recursive transformation algorithms are designed to extract and transform the AltaRica model elements, which are stored in the AST nodes based on the traversal technique of the AST. Then, a semantically equivalent flattened GTS model can be obtained. Lastly, several case studies show that the algorithms designed in this paper can effectively implement the flattening process of AltaRica 3.0 models.
    HIMM Fault Diagnosis based on KPI
    Yunjie Li, Yanyu Wang, Jianchuan Zhang, Detai Zhou, and Dan Mo
    2019, 15(9): 2476-2483.  doi:10.23940/ijpe.19.09.p21.24762483
    Abstract    PDF (459KB)   
    References | Related Articles
    The heavy ion medical machine (HIMM) is a medical accelerator device that requires more stability of equipment operation than the general industrial accelerator, because it is related to human life safety. However, in the actual operation, equipment failure is inevitable, so we must have the ability to quickly troubleshoot. It is best to predict the failure in advance. It would be ideal for computers to make intelligent judgments and analyzes based on the data from the underlying sensor, provide the operation and maintenance personnel with the cause and solution of the failure, and even predict the risk in advance. This would improve the safety and stability of heavy ion cancer treatment devices, enhance the efficiency of treatment, and avoid human error. The main research content of this paper is a fault diagnosis system based on KPI (key performance indicator), which is combined with the status quo of the HIMM control system. The HIMM fault diagnosis method is analyzed in detail, and a specific fault detection model is designed. The specific design method and architecture are given in this paper. The construction and application of HIMM is beneficial to society, and research on the fault diagnosis system will contribute to the stable operation of HIMM.
    Using Evolutionary Process for Cross-Version Software Defect Prediction
    Yong Li, Zhandong Liu, and Haijun Zhang
    2019, 15(9): 2484-2493.  doi:10.23940/ijpe.19.09.p22.24842493
    Abstract    PDF (328KB)   
    References | Related Articles
    Cross-version defect prediction can effectively reduce the construction cost of a model, which is of great significance for understanding the causes of defects in subsequent software versions and improving the quality of software products. The objective of this work is to validate the feasibility of the cross-version defect predictor using the evolutionary process in different scenarios and to investigate practical guidelines for the choice of evolutionary process and historical data of a given project. Firstly, we verified the effectiveness of the evolutionary process attributes in the cross-version prediction model. Then, we analyzed the cross-version model prediction performance based on multi-version historical data. Finally, multiple benchmark models were selected for experimental comparison to further verify the effectiveness of the proposed method. The experimental conclusions can not only effectively reduce the construction cost of the defect prediction model in the version evolution scenarios, but also help developers understand the defect generation mechanism in the subsequent versions and improve the software development process in a targeted way.
    Optimization of Multi-Objective Virtual Machine based on Ant Colony Intelligent Algorithm
    Yuping Li
    2019, 15(9): 2494-2503.  doi:10.23940/ijpe.19.09.p23.24942503
    Abstract    PDF (628KB)   
    References | Related Articles
    In order to optimize the virtual machine consolidation process in data centers, improve the physical host utilization, and reduce the virtual machine migration cost, a novel multi-objective virtual machine consolidation algorithm using ant colony intelligence is designed in this paper. It optimizes two objectives that are ordered by their importance. The main objective of the proposed algorithm is to maximize the number of released physical hosts. Moreover, since virtual machine migration is a resource-intensive operation, it also seeks to minimize the amount of virtual machine migration. Our algorithm finally obtains the optimal virtual machine consolidation effect through a modified ant search process. Some contrast experiments are carried out with the other two kinds of typical ant algorithms. The experimental results show that, in all four test scenarios, under the condition of most scenarios and parameter configuration, our new algorithm achieves better performance on a number of released physical hosts in terms of the amount of virtual machine migration, the packing efficiency, and the algorithm running time.
    Wind Turbine Gearbox Fault Diagnosis using SAE-BP Transfer Neural Network
    Yu Wang, Shuai Yang, and René Vinicio Sánchez
    2019, 15(9): 2504-2514.  doi:10.23940/ijpe.19.09.p24.25042514
    Abstract    PDF (881KB)   
    References | Related Articles
    The gearbox is a key component in wind turbines, and the fault diagnosis of gearboxes in wind turbines is a significant process of reliability management. Therefore, a SAE-BP transfer neural network is proposed in this paper for fault diagnosis of gearboxes in wind turbines. The proposed method is conducted by two processes. Firstly, a source task data is served as the training process to pretrain the SAE-BP neural network. The final learned network structure is the transferable weights or parameters that contain the feature information. Then, the learned weights are transferred into a target task with different working and fault conditions as the initial weight of a neural network model. To extract more fault-sensitive features, fast Fourier transform (FFT) is introduced to transform the raw data into a frequency domain. Several comparison experiments are conducted to validate the proposed method, and the results show that the proposed method achieves higher classification accuracy.
    Natural Image Classification based on Multi-Parameter Optimization in Deep Convolutional Neural Network
    Lei Wang, Yanning Zhang, Runping Xi, and Lu Ling
    2019, 15(9): 2515-2521.  doi:10.23940/ijpe.19.09.p25.25152521
    Abstract    PDF (396KB)   
    References | Related Articles
    Traditional machine learning algorithms cannot adequately train the parameters of networks using massive data. A deep convolutional neural network based on multi-parameter optimization by the TensorFlow deep learning framework is designed in this paper. In order to improve the training speed and prevent over-fitting, we improve and optimize the multi-parameters, including the batch value, dropout, and momentum in the network structure. The experiment involves training and testing on the standard natural image data sets in cifar-10 and cifar-100. The experimental results show that the method achieve better classification accuracy in less time compared with other algorithms, such as Conv-KN, ImageNet-2010, SVM, LR, and Boosting.
    Modeling of ATC Operation Process based on Extended Colored Petri Net
    Jiuxia Guo, Shuzhi Sam Ge, Xinping Zhu, and Fangfang Zhao
    2019, 15(9): 2522-2533.  doi:10.23940/ijpe.19.09.p26.25222533
    Abstract    PDF (709KB)   
    References | Related Articles
    As a highly complex social and technological system, the air traffic management (ATM) system of next generation (NextGen) has many new technologies. With more and more changing roles of human beings (such as pilots and controllers) in the ATM system, new potential hazards may emerge. This paper proposes a new safety analysis method using coloured Petri nets (CPN), which alleviates the unsafe interactions between non-fault components. From the control operation point of view, there are some fixed aerodrome control operation units, which can be divided into two typical modules: Tower control position module and General control position module. According to the basic net model, we present a modelling method based on extended colored Petri net (ECPN) to simulate the air traffic control (ATC) operation process. The focus in this paper is on the constructs of the ATC operation process, including the development of a fine model and substitution rule. The model development is supported by a set of model constructs, which represent key aspects of the ATC operation process. The top-level network model of the ATC operation process using the cognitive work analysis (CWA) method is built. The approach is presented for the multi-runway airport control operation process and describes in detail the Petri net model of the tower control process. Finally, we simulate the tower control process by CPN Tools. The availability of the ATC operation control models are verified by generating the full state space and state space report.
    ACO-SOS-based Task Scheduling in Cloud Computing
    Yuxia Li
    2019, 15(9): 2534-2543.  doi:10.23940/ijpe.19.09.p27.2534-2543
    Abstract    PDF (330KB)   
    References | Related Articles
    In order to improve the low task scheduling efficiency of the traditional ant colony algorithm in cloud computing, this paper introduces the symbiotic algorithm into the ant colony algorithm. Firstly, the ant colony algorithm is broken down into two subgroups, and the symbiosis, cohabitation, and parasite mechanisms in the symbiotic algorithm are used to prevent the algorithm from getting into a local optimum and speed it up to obtain the optimal solution. As a result, the cloud computing scheduling simulation results show that the ant colony algorithm-symbiotic algorithm has good performance in terms of virtual machine load balancing, task completion time, and task completion cost, proving that the proposed algorithm can effectively improve the efficiency of cloud computing task scheduling.
    RFID Tag Ownership Transfer Protocol using Blockchain
    Yong Gan, Yuan Zhuang, and Lei He
    2019, 15(9): 2544-2552.  doi:10.23940/ijpe.19.09.p28.25442552
    Abstract    PDF (587KB)   
    References | Related Articles
    Aiming at the security issues of radio frequency identification (RFID) tags during its life cycle, we propose a new RFID tag ownership transfer protocol based on blockchain in this paper. In order to guarantee the safety of session messages, the protocol uses a hash function and blockchain technology to protect information. During the authentication process, a Merkle hash tree can quickly verify the data of blockchain. Due to decentralization of blockchain, the protocol guarantees the security of RFID systems without the participation of a trusted third party (TTP). The identity of tags is confirmed by a pseudonym, and its real identity is not disclosed to an untrusted entity such as the reader. Finally, the formalization analysis based on GNY logic is given. Detailed security analysis has been performed to prove that the proposed protocol can resist impersonation, replay, tracking, and de-synchronization attacks.
    A Modified Comprehensive Learning Particle Swarm Optimizer
    Jinwei Pang, Hongbin Dong, Jun He, and Rui Ding
    2019, 15(9): 2553-2562.  doi:10.23940/ijpe.19.09.p29.25532562
    Abstract    PDF (474KB)   
    References | Related Articles
    To overcome premature convergence and falling into local optima of particle swarm optimization (PSO), a comprehensive learning particle swarm optimizer (CLPSO) has been proposed. However, it is not good at solving unimodal problems. In this paper, we propose a modified CLPSO (MCLPSO) with three improvements. Firstly, we use opposition-based learning (OBL) to improve the initial population. Secondly, we add the best solution of the population to the list of selected particles in order to improve the convergence ability while maintaining the population diversity. Finally, we use the mean velocity of the population with a linearly decreasing probability to update the particle velocity to further improve the performance of CLPSO. The MCLPSO algorithm is tested on CEC2005 in 30 dimensions. Furthermore, the MCLPSO is conducted to solve hydrothermal scheduling problems. The experimental results demonstrate that the solution accuracy of MCLPSO is overall better than those of comparison algorithms.
ISSN 0973-1318