Journal of Intelligent & Fuzzy Systems - Volume 35, issue 4

Authors: Wang, Xiangmin | Wang, Jun | Privault, M.

Article Type: Research Article

Abstract: The traditional fault detection system of complex electronic equipment based on image analysis theory only analyzes the image characteristics of complex electronic equipment for artificial intelligent fault diagnosis. It cannot deal with the system diagnosis problem of qualitative fault data and has the problems of low accuracy and long time consuming of fault detection. To address these problems, an artificial intelligent fault diagnosis system of complex electronic equipment based on BP neural network is designed in this paper. BP neural network model for artificial intelligent fault diagnosis of complex electronic equipment is built based on system overall structure. The structure …of BP neural network and learning algorithm is determined according to the actual fault problem. Learning and training of BP neural network are carried out by using sample data of fault. Artificial intelligent fault diagnosis algorithm of complex electronic equipment based on BP neural network and qualitative fault data is used, which combines the BP neural network and qualitative fault data. The preprocessing method is applied to quantify the fault data. Fault diagnosis is achieved by BP neural network technology. The system database and the implementation process of the BP neural network are designed. Experimental results show that the designed system can significantly improve the accuracy of fault detection of complex electronic equipment, improve the effect of fault detection, and reduce the time consuming of fault detection. Show more

Keywords: Complex electronics, equipment fault, artificial intelligence, diagnostic system, BP neural network, residual signal

DOI: 10.3233/JIFS-169735

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 4, pp. 4141-4151, 2018

Authors: Liu, Shuying | Zou, Yanfei | Terasvirta, A.M.

Article Type: Research Article

Abstract: The traditional data query algorithm based on clustering strategy library ignores the association features of social network data, characteristic data acquisition exist a large number of redundant features and frequent relationship among features is low, resulting in the social network data query efficiency and the accuracy is poor, so a fast query algorithm for social network data based on fuzzy degree function based on association features is proposed, it is based on Apriori algorithm for data association feature mining of social network to obtain the maximum frequent association feature set; for association feature preprocessing, it reduce the maximum frequent association …feature set by feature dimension reduction and de redundancy algorithm, to obtain better social network maximal frequent associated feature set; when using fuzzy function to query social network data quickly, it uses data of a single gene ambiguity function to build a fast data query diagram, input the best frequent feature set of social network, and output the query results of social network data with the highest priority. The experimental results show that the proposed algorithm has the advantages of high efficiency and high accuracy in social network data query. Show more

Keywords: Association features, apriori algorithm, social network data, data set, maximum frequent association features, ambiguity function, query algorithm

DOI: 10.3233/JIFS-169736

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 4, pp. 4153-4162, 2018

Authors: Zhang, Chao | Liu, Shuai | Gao, Yan | Zhang, Zongsheng | Baltagi, S.

Article Type: Research Article

Abstract: In traditional multi-infeed AC/DC transmission systems, decentralized and coordinated controllers are usually used to achieve AC/DC transmission control without considering the state and output of the system. Therefore, it cannot reasonably regulate the state of output based on the demand of multi-target control, which leads to poor control effect and weak adaptability. Therefore, a multi- sliding mode adaptive fuzzy controller is designed for the multi-infeed AC/DC transmission system. When the controller is designed, the state equation and the output equation of the multi-infeed AC/DC transmission system are considered. Based on the three different design parameters and the multi-sliding mode surface …of the thickness of the saturated layer, the adaptive controller based on multi-sliding mode is designed. This controller is used to set up the dynamic characteristics of some observable measurements in the multi-infeed AC/DC transmission system. Based on the setting results, the results of the comprehensive decision of the system are obtained by the adaptive fuzzy controller. According to the results of a comprehensive decision, the disturbance degree of feedback point is judged. Through the fuzzy algorithm based onthe second component function, the weighting matrices of the output feedback gain matrix are modified, so that the optimal control feedback gain is variable gain, to ensure that the control effect of the system meet the multi-objective control of engineering, and realizing the multi-sliding mode adaptive fuzzy controller ofthe multi-infeed AC/DC transmission system. The experimental results show that the designed multi-sliding mode adaptive fuzzy controller has good control effect on multi-infeed AC/DC transmission system, and has strong adaptability, and it can improve the dynamic performance of the system. Show more

Keywords: Multi-infeed, AC/DC transmission system, multi-sliding mode, adaptive, fuzzy controller, state weight matrix

DOI: 10.3233/JIFS-169737

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 4, pp. 4163-4172, 2018

Authors: Zhu, Yuye | Bi, Yanliang | Su, Xiaomin | Kouritzin, C.M.

Article Type: Research Article

Abstract: For the current shipborne anti-collision sounding system, when multiple detection signals are transmitted, it is difficult to avoid collision with each other. In addition, there are shortcomings of insufficient energy consumption, low sounding precision, and slow response. To address this problem, a shipborne anti-collision sounding system based on ACT algorithm and Internet of things is designed in this paper. With ZigBee wireless communication technology and embedded technology, the function of anti-collision and sounding is realized by modular design. For the problem of the signal collision of each node of the wireless network, the ACT algorithm is introduced for system optimization …to prevent signals from conflict when receiving, and ensure the synchronization and accuracy of the whole system. STM32F103 VET6 embedded chip is used as the control core of the system. CC2530 is responsible for the implementation of ZigBee wireless network communication. Experimental results show that the designed system has the advantages of low energy consumption, fast response, and high precision. Show more

Keywords: ACT algorithm, internet of things, shipborne, anti-collision system, sounding optimization

DOI: 10.3233/JIFS-169738

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 4, pp. 4173-4182, 2018

Authors: Wu, Guoqiang | Saghir, V.

Article Type: Research Article

Abstract: The current resource integration algorithm lacks the consideration of users’ needs, which can cause high violation of service-level agreement and poor data quality after integration. It affects the energy consumption and service quality of data center. To address this problem, a financial resource integration algorithm of virtual enterprise based on improved artificial bee colony in big data environment is proposed in this paper. The improved PageRank algorithm is used to extract the financial resource of virtual enterprise. The extracted resource is transformed. From the unified data resource centralization after transformation, service resources that satisfy users’ needs and constraints are selected …and combined. An improved artificial bee colony algorithm is applied to dynamically integrate service resources for different needs. Experimental results show that the proposed algorithm can effectively reduce the energy consumption of the data center, improve the data quality and user service satisfaction. The advantages and feasibility of the proposed algorithm in the integration of virtual enterprise financial resources under the big data environment are verified. Show more

Keywords: Big data environment, virtual resource, enterprise financial resource, resource integration, PageRank algorithm

DOI: 10.3233/JIFS-169739

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 4, pp. 4183-4194, 2018

Authors: Guo, Yuxiu | Li, Jie | Liu, Na | Riley, E.S.A.

Article Type: Research Article

Abstract: At present, weak signal detection algorithm detects parallel weak signals under Gauss noise interference, which has the problems of low denoising performance, inaccurate detection results and low detection efficiency. To this end, a parallel weak signal detection algorithm based on Gauss noise interference is proposed. Wavelet transform is applied to detect weak signals with Gauss noise by wavelet threshold denoising method, and the weak signal is denoised based on the set threshold function and threshold. The EMD decomposition method is used to decompose the weak signal after denoising, and the weak signal is filtered through the imitation Cauchy convergence filter …stopping criterion to extract the characteristics of weak signal. The weak signal detection under the interference of Gauss noise is completed based on the Doffing oscillator and the characteristic of the weak signal extracted. The experimental results show that the proposed method has high signal-to-noise ratio, accurate detection of weak signal, and the time of detection is below 8 s. The results show that the proposed method has high denoising performance, high detection accuracy and high detection efficiency. Show more

Keywords: Gauss noise, noise interference, weak signal, signal

DOI: 10.3233/JIFS-169740

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 4, pp. 4195-4203, 2018

Authors: Li, Xin | Hsiao, J.

Article Type: Research Article

Abstract: The current traffic evacuation path control system has high risk coefficient and path congestion, and low efficiency and system error coefficient. For this problem, a fuzzy control system of traffic evacuation path based on genetic method is proposed and designed in this paper. The data server, geographic information server, computing server, and application server are used to construct the system framework. The logical structure is divided into data source layer, data access layer, scheduling layer, computing model layer, and application interface layer. The function module is mainly composed of static data management module, emergency management module, dynamic data interface module, …dynamic traffic assignment module, guidance information release module, and user management module. The system hardware is designed by using the logical structure in combination with the function module. In the system software, the coordinator-operator mode is introduced into the real-time computing operation mechanism. The interaction of the coordinator and the operator is to implement the user specified operational function. Traffic data is forecast by autoregressive model. It is substituted into the objective function of intelligent traffic evacuation and the genetic method is used to solve the objective function. At last, fuzzy control result of optimal traffic evacuation path is obtained. Experimental results show that the average risk coefficient in the evacuation process is about 0.27, the average time consuming is 0.3 h, and the congestion of the evacuation path is relatively low, so the fault tolerance coefficient of the system can be controlled within a reasonable range. The system has a good overall operation effect and is feasible. Show more

Keywords: Big data, intelligent transportation, evacuation path, fuzzy control, system

DOI: 10.3233/JIFS-169741

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 4, pp. 4205-4213, 2018

Authors: Liang, Peng | Zhao, Huimin | Caner, G.

Article Type: Research Article

Abstract: When the network resource information is scheduled with the current algorithm, the execution time of the resource scheduling task cannot be improved. The utilization of network resources is reduced in the case of the heavy scheduling task. To address this problem, a network resource information scheduling based on non-convex function optimization algorithm is proposed in this paper. The network resource is modeled as a non-convex function. The execution interval of task is divided into subspaces of multiple units. Task density is introduced into network resource scheduling model. In this model, computing resources and storage resources of the network are considered. …Ant colony particle swarm optimization algorithm is used for scheduling with the built network resource scheduling model. The initial solution is obtained by initial search with the particle swarm algorithm. Then the initial solution is transformed into the initial pheromone distribution of the ant colony. The resource information is searched by using ant colony algorithm until the optimal solution is found, so as to achieve network resource information scheduling. Experimental results show that the proposed algorithm can reduce the execution time of task and improve the utilization rate of network resource information. Show more

Keywords: Non-convex function, network resource, information scheduling, joint scheduling algorithm

DOI: 10.3233/JIFS-169742

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 4, pp. 4215-4224, 2018

Authors: Tong, Yunxu | Li, Guihua | Racine, M.

Article Type: Research Article

Abstract: The current method does not take full account of multiple hybrid tasks in fuzzy control system and the problems of the balance between the requirements of the system reliability and the maximum completion time of the scheduling and the high cost of resource occupancy. To address these problems, a fault-tolerant scheduling algorithm of multiple hybrid tasks based on supporting multilevel criticality is proposed in this paper. The models of fuzzy control system and multiple hybrid tasks are built respectively. Multiple hybrid tasks in the model are divided into periodic task and non-periodic task, task with fault-tolerant requirement and with no …fault tolerance requirement. According to the priority of each task and the relationship of the response time and time limit of each task, whether to start its supplementation task and the fault tolerance priority allocation is determined. The worst response time of each task in the model is calculated and fault-tolerant scheduling for multiple hybrid tasks is realized. Experimental results show that the proposed algorithm can further reduce the maximum completion time of task scheduling on the basis of satisfying the reliability requirements of the fuzzy control system. The cost of computer resource occupancy and the overhead of communication resources have been greatly reduced. Show more

Keywords: Fuzzy control, system, multiple, mixed task, fault tolerance, scheduling

DOI: 10.3233/JIFS-169743

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 4, pp. 4225-4233, 2018

Authors: Ren, Xinglong | Bedini, T.H.

Article Type: Research Article

Abstract: Currently, the fuzzy clustering algorithm of customer group behavior data had the poor effect of data clustering. Therefore, a fuzzy clustering algorithm of Internet customer group behavior data based on fuzzy C means clustering was proposed. By constructing the feature vector of behavior data, this algorithm realized the feature extraction of behavior data, and then it used the nearest neighbor chain to extract data features for the reduction and sample equilibrium. The classification of Internet customer group behavior data was achieved. According to the fuzzy C means clustering algorithm, the interval estimation of classification results of behavior data was carried …out. Meanwhile, the membership values of each data sample were updated. Finally, the classification interval was adjusted. Thus, the fuzzy clustering of Internet user group behavior data was completed. Experiment results show that the proposed algorithm has high accuracy in data classification, short execution time in clustering, less memory footprint and low computational complexity, which improves clustering effect. Show more

Keywords: Internet, customer group, behavior data, fuzzy clustering

DOI: 10.3233/JIFS-169744

Citation: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 4, pp. 4235-4243, 2018