Journal of Intelligent & Fuzzy Systems - Volume 28, issue 6

Authors: Ali, Syed Abbas | Saraswati, Samir

Article Type: Research Article

Abstract: Cylinder pressure based control of internal combustion (IC) engine uses variables derived from cylinder pressure trace as a feedback input to the engine control and diagnostic systems. Direct measurement of such variables using cylinder pressure sensor is quite expensive. This paper proposes an indirect method of estimating two of such variables namely peak pressure (PP) and indicated mean effective pressure (IMEP) using crankshaft speed measurements. Discrete Fourier Transformation (DFT) is used to transform crankshaft speed fluctuation in time domain to frequency domain. Real and imaginary parts of frequency domain signal, at different harmonics of engine firing frequency, are used as …input to multilayer perceptron (MLP). The output being PP and IMEP. Various combinations of inputs starting from signals at first harmonic to signals at first five harmonics are tested. Training and validation of MLP is done using data generated on a test rig consisting of single cylinder engine with eddy current dynamometer. The results show that the MLP is suitable for estimation of cycle-by-cycle values of PP and IMEP for most of the operating points where cyclic variations are within driveability limits. Show more

Keywords: Engine control, combustion parameters, cylinder pressure, neural networks, Discrete Fourier Transform

DOI: 10.3233/IFS-151553

Citation: Journal of Intelligent & Fuzzy Systems, vol. 28, no. 6, pp. 2761-, 2015

Authors: Tsai, Tsung-Nan | Yeh, Jun-Hsien

Article Type: Research Article

Abstract: This study presents a case study using a hybrid failure mode and effect analysis (FMEA) and a fuzzy inference system (FIS) extract critical soldering failure sources and assess their risks in surface mount assembly (SMA). The desired level of soldering quality in SMA plays an important role of achieving a defect-free printed circuit board assembly to fabricate many types of modern electronic products. FMEA is an effective method for identifying potential failures in the product and process in the design stage. However, the traditional FMEA has several disadvantages. To improve soldering quality and overcome the drawbacks in traditional FMEA, the …entropy measurement method is integrated with grey relational analysis (GRA) to investigate the correlations between the three FMEA decision factors, chance of failure occurrence, degree of severity, and detection probability, and to determine their importance weights. Finally, an assessment tool for quickly predicting risks of soldering failure sources corresponding to quantitative or qualitative values of the three FMEA decision factors through a developed FIS. The proposed hybrid measurement framework also can be applied for solving other risk evaluation problems. Show more

Keywords: Printed circuit assembly, surface mount assembly, FMEA, grey relational analysis, fuzzy inference system

DOI: 10.3233/IFS-151556

Citation: Journal of Intelligent & Fuzzy Systems, vol. 28, no. 6, pp. 2771-2784, 2015

Authors: Yu, Dejian

Article Type: Research Article

Abstract: The triangular Atanassov’s intuitionistic fuzzy set (TAIFS), whose membership and non-membership degrees are described by triangular fuzzy numbers, is more suited to real world problems. In this paper, two different aggregation operators based on Bonferroni mean are proposed for aggregating TAIF numbers (TAIFNs). Our proposed operators differ from existing ones because they have the ability to describe the relationships between the aggregated arguments. In addition, relationship between proposed operators and the previous work are disused. After that, an example about supplier selection in the field of supply chain management is given to show the practicability and effectiveness of the proposed …operators. Show more

Keywords: AIFS, aggregation operator, supplier selection, decision making

DOI: 10.3233/IFS-151557

Citation: Journal of Intelligent & Fuzzy Systems, vol. 28, no. 6, pp. 2785-2791, 2015

Authors: Hong, Lu | Kamruzzaman, Joarder

Article Type: Research Article

Abstract: Artificial immune algorithm has been used widely and successfully in many computational optimization areas, but the theoretical research exploring the convergence rate characteristics of artificial immune algorithm is yet inadequate. In this paper, instead of the traditional eigenvalue estimation of state transition matrix, stochastic processes theory is introduced to study the convergence rate of general artificial immune algorithm. The method begins by analyzing the necessary condition for convergence of artificial immune algorithm and takes it as the sufficient condition for a class of general artificial immune algorithm. Through the definition of Markov chain convergence rate, a probability strong convergence rate …estimation method of general artificial immune algorithm is proposed. This method is judged by the final convergence of the best antibody, which overcomes the conservative defect of traditional estimation methods. The simulation results show the correctness of the proposed estimation method, and the estimation method can be used to judge the convergence and convergence rate of a class of artificial immune algorithms. This research has a certain theoretical reference value to optimize the convergence rate in the practical application of artificial immune algorithm. Show more

Keywords: Artificial immune algorithm, clonal selection theory, idiotypic immune network theory, convergence rate estimation, markov chain

DOI: 10.3233/IFS-151559

Citation: Journal of Intelligent & Fuzzy Systems, vol. 28, no. 6, pp. 2793-2800, 2015

Authors: Ozkan, Omer | Ermis, Murat

Article Type: Research Article

Abstract: Wireless Sensor Network (WSN) comprises a large number of spatially distributed sensor devices that can retrieve valuable information via low-cost, low-powered, tiny sensors, and send the data to a sink through its wireless communication units. In order to prolong network lifetime at minimum cost, a small number of powerful relay nodes can be deployed in the sensing area. The connectivity between the sensor nodes and the base stations is one of the most crucial design considerations for WSNs. In this paper, mixed-integer linear programming model of the constrained relay node placement problem is defined. Since the problem has NP-hard nature, …novel nature-inspired meta-heuristic methods (Genetic Algorithm (GA) and Simulated Annealing (SA)) are presented to find the number and position of the relay nodes in a heterogeneous WSN. The algorithms have new problem specific representation and operators. The results of proposed GA is compared with exact, SA and minimum spanning tree solutions. Experimental analysis has shown that presented GA and SA approaches can find a near-optimal or efficient solution in a reasonable computation time. Show more

Keywords: Relay node placement, wireless sensor networks, meta-heuristics

DOI: 10.3233/IFS-151560

Citation: Journal of Intelligent & Fuzzy Systems, vol. 28, no. 6, pp. 2801-2809, 2015

Authors: Tavakkoli-Moghaddam, R. | Sadri, S. | Pourmohammad-Zia, N. | Mohammadi, M.

Article Type: Research Article

Abstract: A closed-loop supply chain (CLSC) network consists of both forward and reverse supply chains. In this paper a CLSC network is investigated that involves four echelons in a forward direction including suppliers, manufacturer, distribution center and demand market, and three echelons in a backward direction including disposal, rework and collection centers. This paper presents a bi-objective model in order to design a network of bi-directional facilities in logistics network under uncertainties. Its objectives are to minimize the total costs as well as the total defective rate, disposal rate and pollution production rate. To solve the model, a hybrid solution approach …is applied that combines fuzzy possibilistic programming and fuzzy multi-objective programming. Furthermore, in order to illustrate the validity of the model and applicability of the proposed solution approach, numerical experiments and the related sensitivity analysis are provided. Finally, the conclusion is provided. Show more

Keywords: Closed-loop supply chain, fuzzy possibilistic programming, fuzzy multi-objective programming, uncertainty

DOI: 10.3233/IFS-151561

Citation: Journal of Intelligent & Fuzzy Systems, vol. 28, no. 6, pp. 2811-2826, 2015

Authors: Reza Afshari, Ali

Article Type: Research Article

Abstract: Selecting a suitable project manager for construction projects is one of the most important decisions made by construction firms. Although many studies have investigated this problem, no systematic and valid method for specifying the requirements criteria has been presented in criteria selection stage. The main objective of this paper is to develop a systematic method in order to identify the best candidate for construction project manager selection by using Delphi method and fuzzy linguistic evaluation. The models were validated using a case study of construction project manager selection in a project based company. The results show that the proposed model …performs very well in selecting construction project manager and can improve efficiency in decision making process. Show more

Keywords: Delphi method, criteria selection, construction project manager selection, fuzzy linguistic, multi criteria decision making (MCDM)

DOI: 10.3233/IFS-151562

Citation: Journal of Intelligent & Fuzzy Systems, vol. 28, no. 6, pp. 2827-2838, 2015

Authors: Premkumar, K. | Manikandan, B.V.

Article Type: Research Article

Abstract: This paper deals with the application of GA-PSO optimized online Adaptive Neuro Fuzzy Inference System (ANFIS) for the speed control of Brushless DC motor. Learning parameters, i.e., Learning Rate (η ), forgetting factor (λ ) and steepest descent momentum constant (α ) of online ANFIS controller is optimized for different speed-torque operating conditions of Brushless DC motor using hybrid GA-PSO algorithm. The overall speed control system is simulated and validated using MATLAB. The performance of the proposed controller is analyzed and compared with offline ANFIS controller and Proportional Integral Derivative (PID) controller. In order to validate the effectiveness of the …proposed controller, simulation is performed under constant load conditions, varying load conditions and varying set speed conditions. Also speed tracking response is investigated for different set speed conditions and different loading conditions. In addition, for effective comparison of the controllers, four performance measures such as maximum overshoot, steady state error, integral of absolute error, and integral of time multiplied absolute error are evaluated and tested for the considered controllers. It has been proved that the proposed controller easily overcomes the drawbacks of offline ANFIS controller and Proportional Integral Derivative (PID) controller. Show more

Keywords: Brushless DC motor, proportional integral derivative controller, offline ANFIS controller, online ANFIS controller, genetic algorithm, particle swarm optimization

DOI: 10.3233/IFS-151563

Citation: Journal of Intelligent & Fuzzy Systems, vol. 28, no. 6, pp. 2839-2850, 2015

Authors: Mingai, Li | Shuoda, Guo | Guoyu, Zuo | Yanjun, Sun | Jinfu, Yang

Article Type: Research Article

Abstract: Ocular movements are inevitable in electroencephalograme (EEG) collection, and the resulting Ocular Artifact (OA) becomes one of the main interferences of EEG due to its great amplitude. Many methods have been proposed to remove OA from EEG recordings based on Blind Source Separation (BSS) algorithm. Often regression is performed in time or frequency domain by completely deleting the OA components. This can cause the overestimation of OA and the information loss of EEG, because EEG and electrooculogram (EOG) mix or spread bidirectionally. Furthermore, there exists a variety of noises, except for OA, and interference coupling in EEG, this also affects …the OA removal performance, such as the robustness and anti-interference ability. Here, we propose a novel and generally applicable method, denoted as FKD, for removing OA from mixed EEG signals with the Fast Kernel Independent Component analysis (FastKICA) and Discrete Wavelet Transform (DWT). In two cases of linear and nonlinear mixed models, many experiments are conducted with Brain Computer Interface (BCI) data set. The experiment results show that FKD has good performance comparing with other BBS-based OA removal methods, and it is more acceptable in actual BCI system. Show more

Keywords: Ocular artifact removal, fast kernel independent component analysis, discrete wavelet transform, overestimation, robustness

DOI: 10.3233/IFS-151564

Citation: Journal of Intelligent & Fuzzy Systems, vol. 28, no. 6, pp. 2851-2861, 2015

Authors: Mahdipour Pirbazari, Mahmoud | Mesri, Alireza | Khoei, Abdollah | Hadidi, Khayrollah

Article Type: Research Article

Abstract: Analog implementation of fuzzy logic controllers (FLCs) is the most efficient method when speed, power, and area are critical. Inference engine (IE) usually takes a large part of total die area when the FLC has a large number of rules. In this paper, a method is proposed to reduce size of the IE in analog implementations of FLCs. Since only a small number of rules may be fired simultaneously, thus a few inference blocks (IBs) may work at the same time in an IE. In the proposed method, reduction in size of the IE is achieved by sharing a few …IBs between a large number of rules. To test the proposed method, a standard FLC is designed using both the regular method and the proposed method. By using the proposed method, total power consumption and active area are reduced by factors of 2.31 and 2.15, respectively. Moreover, inference speed is improved by a factor of 3.8 and output error is reduced by a factor of 2.5. All simulations have been performed in HSPICE using level 49 models for 0.35 um CMOS process with a 3.3 V power supply. Show more

Keywords: Fuzzy hardware, analog CMOS implementation, inference engine, current mode

DOI: 10.3233/IFS-151565

Citation: Journal of Intelligent & Fuzzy Systems, vol. 28, no. 6, pp. 2863-2874, 2015