Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Wind Turbine Gearbox Fault Diagnosis Method Based on Wavelet Packet and SVM

欧淇源, 姚为星, 周求湛, 程文阁, 吴艳茹
Open Journal of Acoustics and Vibration (OJAV) , 2013, DOI: 10.12677/OJAV.2013.14006
In order to monitor gearbox real-timely, which is the core component of wind turbine, a method is put forward. This method is based on some vibration signals that are caused by different parts of gearbox at work and common faults of gearbox. Firstly, a gearbox working signal acquiring system is created. It uses high precision sensors to acquire signals when the wind turbine gearbox is working. Secondly, according to features of vibration signals of gearbox at work, using wavelet packet transform method can extract characteristics from working signals. Sending those data to Support Vector Machine (SVM), the system can implement intelligent fault diagnosis. At last, through experiments under laboratory condition, this method can reach more than 97.5% classification accuracy in the case of small sample.
Developing an Intelligent Fault Diagnosis of MF285 Tractor Gearbox Using Genetic Algorithm and Vibration Signals  [PDF]
Ebrahim Ebrahimi, Payam Javadikia, Nasrolah Astan, Majid Heydari, Mojtaba Bavandpour, Mohammad Hadi Jalili, Ali Zarei
Modern Mechanical Engineering (MME) , 2013, DOI: 10.4236/mme.2013.34022

This article investigates a fault detection system of MF285 Tractor gearbox empirically. After designing and constructing the laboratory set up, the vibration signals obtained using a Piezoelectric accelerometer which has been installed on the Bearing housings are related to rotary gear number 1 in two directions perpendicular to the shaft and in line with the shaft. The vector data were conducted in three different speeds of shaft 1500, 1000 and 2000 rpm and 130 repetitions were performed for each data vector state to increase the precision of neural network by using more data. Data captured were transformed to frequency domain for analyzing and input to the neural network by Fourier transform. To do neural network analysis, significant features were selected using a genetic algorithm and compatible neural network was designed with data captured. According to the results of the best output mode for each position of the sensor network in 1000, 1500 and 2000 rpm, totally for the six output models, all function parameters for MATLAB Software quality content calculated to evaluate network performance. These experiments showed that the overall mean correlation coefficient of the network to adapt to the mechanism of defect detection and classification system is equal to 99.9%.

Diversification and Specialization of Plant RBR Ubiquitin Ligases  [PDF]
Ignacio Marín
PLOS ONE , 2012, DOI: 10.1371/journal.pone.0011579
Abstract: RBR ubiquitin ligases are components of the ubiquitin-proteasome system present in all eukaryotes. They are characterized by having the RBR (RING – IBR – RING) supradomain. In this study, the patterns of emergence of RBR genes in plants are described.
Efficient and Intelligent Information Retrieval using Support Vector machine (SVM)  [PDF]
Monika Arora,Uma Kanjilal,Dinesh Varshney
International Journal of Soft Computing & Engineering , 2012,
Abstract: The information access is the rich data available forinformation retrieval, evolved to provide principal approachesor strategies for searching and browsing. The search has becomethe leading paradigm to find the information on World WideWeb. For building the successful information retrieval, there area number of prospects that arise at the different levels wheretechniques can be considered. The present investigations explorethe Support vector machine identified its level and classifies thedocuments on web. This paper attempts to develop a model forthe efficient and intelligent retrieval. This paper attempts topropose the implement model for efficient and intelligentretrieval. In model it attempted to figure out the importantfactors for the successful efficient and intelligent retrieval. Theproposed model is designed to collate all the differing views oninformation retrieval so as to construct a holistic theoreticalwhich is considered to be the source of a system. This paperconsiders the application of Support Vector Machine fordesigning the model for efficient and intelligent retrieval. Thiswill also consider a proposed model for developing successfulretrieval.
Diagnosing client faults using SVM-based intelligent inference from TCP packet traces  [PDF]
Chathuranga Widanapathirana,Y. Ahmet Sekercioglu,Paul G. Fitzpatrick,Milosh V. Ivanovich,Jonathan C. Li
Computer Science , 2012, DOI: 10.1109/IB2Com.2011.6217894
Abstract: We present the Intelligent Automated Client Diagnostic (IACD) system, which only relies on inference from Transmission Control Protocol (TCP) packet traces for rapid diagnosis of client device problems that cause network performance issues. Using soft-margin Support Vector Machine (SVM) classifiers, the system (i) distinguishes link problems from client problems, and (ii) identifies characteristics unique to client faults to report the root cause of the client device problem. Experimental evaluation demonstrated the capability of the IACD system to distinguish between faulty and healthy links and to diagnose the client faults with 98% accuracy in healthy links. The system can perform fault diagnosis independent of the client's specific TCP implementation, enabling diagnosis capability on diverse range of client computers.
Intelligent Agent-Based Intrusion Detection System Using Enhanced Multiclass SVM  [PDF]
S. Ganapathy,P. Yogesh,A. Kannan
Computational Intelligence and Neuroscience , 2012, DOI: 10.1155/2012/850259
Abstract: Intrusion detection systems were used in the past along with various techniques to detect intrusions in networks effectively. However, most of these systems are able to detect the intruders only with high false alarm rate. In this paper, we propose a new intelligent agent-based intrusion detection model for mobile ad hoc networks using a combination of attribute selection, outlier detection, and enhanced multiclass SVM classification methods. For this purpose, an effective preprocessing technique is proposed that improves the detection accuracy and reduces the processing time. Moreover, two new algorithms, namely, an Intelligent Agent Weighted Distance Outlier Detection algorithm and an Intelligent Agent-based Enhanced Multiclass Support Vector Machine algorithm are proposed for detecting the intruders in a distributed database environment that uses intelligent agents for trust management and coordination in transaction processing. The experimental results of the proposed model show that this system detects anomalies with low false alarm rate and high-detection rate when tested with KDD Cup 99 data set. 1. Introduction Mobile ad hoc networks (MANETs) consist of mobile nodes that work independently without an infrastructure. They are useful in application areas like disaster management emergency and rescue operations where it is not possible to have well-defined infrastructure. MANETs are characterized by its great flexibility. However, MANET’s inherent vulnerability increases their security risks. Though MANETs are dynamic and cooperative in nature, it needs efficient and effective security mechanisms to safeguard the mobile nodes. Intrusion detection and prevention are primary mechanisms to reduce possible intrusions. Intrusion detection using classification algorithms effectively discriminates “normal” behavior from “abnormal” behavior. Therefore, intrusion detection and prevention system can be used as a secondary mechanism of defense in any wireless environment and mobile databases so that it can be a part of the reliable communication in MANETs [1]. Intrusion detection systems (IDS) play a major role in providing security to networks. In this paper, we introduce a new intelligent agent-based intrusion detection model for securing the mobile ad hoc networks. The main function of the proposed intrusion detection system is to monitor the computer system and network in order to find the intrusion activities in the system. In such system, attacks are divided into two categories, namely, host-based attacks and network-based attacks. Hence, IDSs are also
Modeling of Wind Turbine Gearbox Mounting
Morten Haastrup,Michael R. Hansen,Morten K. Ebbesen
Modeling, Identification and Control , 2011, DOI: 10.4173/mic.2011.4.2
Abstract: In this paper three bushing models are evaluated to find a best practice in modeling the mounting of wind turbine gearboxes. Parameter identification on measurements has been used to determine the bushing parameters for dynamic simulation of a gearbox including main shaft. The stiffness of the main components of the gearbox has been calculated. The torsional stiffness of the main shaft, gearbox and the mounting of the gearbox are of same order of magnitude, and eigenfrequency analysis clearly reveals that the stiffness of the gearbox mounting is of importance when modeling full wind turbine drivetrains.
Facial expression recognition based on principal component analysis and support vector machine applied in intelligent wheelchair

LUO Yuan,WU Cai-ming,ZHANG Yi,
罗 元
,吴彩明,张 毅

计算机应用研究 , 2012,
Abstract: In order to realize the control of intelligent wheelchair based on the facial expression recognition, this paper adopted a hybrid method of principal component analysis PCA based support vector machine for facial expression recognition and classification. In this hybrid approach, it used PCA for feature selection in order to reduce the model complexity of SVM and the input data. It used an image preprocessing method based on eight eyes for facial effective area extraction. Experimental results indicate that this method can classify different expressions effectively and its recognition rate is obviously superior to that of general SVM and PCA. Finally, the control of intelligent wheelchair based on facial expression recognition can be well realized.
The ring between ring fingers (RBR) protein family
Birgit Eisenhaber, Nina Chumak, Frank Eisenhaber, Marie-Theres Hauser
Genome Biology , 2007, DOI: 10.1186/gb-2007-8-3-209
Abstract: The ring between ring fingers (RBR) proteins are a large and diverse group of proteins characterized by a compact sequence module that is predicted to form three ring finger-type, or 'ring', domains separated by loops [1,2]. The RBR domain usually occurs as part of a multidomain protein with diverse functional modules, and appears to mediate protein-protein interaction. The function of most of the family members has not yet been explored experimentally, but a subset of RBR proteins is known to have E3 ubiquitin ligase activity.The sequence of each ring domain in the RBR region contains a cluster of, typically, eight cysteine and histidine residues that potentially bind metal ions. The amino-terminal ring domain (RING1 or N-RING) is thought to bind two zinc ions and to fold into a classical cross-braced ring finger, whereas the carboxy-terminal ring (RING2 or C-RING) appears to bind only one metal ion and forms a hydrophobic core different from that of classical ring fingers [3]. The central cysteine/histidine cluster is likely to also form a ring finger-type structure. Morett and Bork [4] derived a general sequence profile-based characterization of this domain and called it IBR (in between rings). Independently, van der Reijden et al. [5] identified this domain - with a more restricted PROSITE-like pattern [6] C6HC - as DRIL (double ring finger linked) domain, and called the family of RING-DRIL-RING-containing proteins TRIAD. The two definitions are largely overlapping but not identical. The approach of Morett and Bork [4] is consistent with the concept of sequence homology and the criterion of statistically significant sequence similarity and is therefore the preferred one.RBR proteins make up a large, diverse family with, at present, around 400 representatives in sequence databases. On the basis of sequence conservation within the RBR segment, RBR proteins are assigned to 15 subfamilies (A-I, P, S, T, U, X, Z; Figure 1). There are also some 10 orphan sequences tha
Genome-Wide Identification and Characterization of RBR Ubiquitin Ligase Genes in Soybean  [PDF]
Pei Chen, Xiaolian Zhang, Tuanjie Zhao, Yan Li, Junyi Gai
PLOS ONE , 2014, DOI: 10.1371/journal.pone.0087282
Abstract: RBR (RING1-IBR-RING2) proteins play an important role in protein ubiquitination and are involved in many cellular processes. Recent studies showed plant RBR genes were induced by abiotic and biotic stresses. However, detailed studies on RBR genes in the important oil crop, soybean (Glycine max (L.) Merr.), is still lacking. Here we performed a genome-wide search and identified 24 RBR domain-containing genes from the soybean genome sequence and cloned 11 of them. Most soybean RBR proteins contain a highly conserved RBR supra-domain. Phylogenetic analyses indicated all 24 soybean RBR proteins are most related to the RBR proteins from Phaseolus vulgaris, and could be classified into seven groups including Ariadne A, Ariadne B, ARA54, Plant IIA, Plant IIB, Plant IIC, and Helicase. Tandem duplication and block duplication were found among the Ariadne B and Plant IIC group of soybean RBR genes. Despite the conserved RBR supra-domain, there are extensive variations in the additional protein motifs and exon-intron structures between different groups, which indicate they might have diverse functions. Most soybean RBR proteins are predicted to localize in nucleus, and four of them were experimentally confirmed by GFP fusion proteins. Soybean RBR genes are broadly expressed in many tissue types with a little more abundant in the roots and flowers than leaves, stems, and seeds. The expression of GmRTRTP3 (Plant IIB) and GmRTRTP5 (Plant IIC) are induced by NaCl treatment, which suggests these RBR genes might be involved in soybean response to abiotic stresses.
Page 1 /100
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.