检索结果-内蒙古大学图书馆

Probabilistic Neural Network Based Incipient Fault Identification Using DGA Dataset

Procedia Computer Science 2015年 58卷 665-672页

作者： Hasmat Malik Ajay Khatri Ruchi Dohare Instrumentation & Control Engineering Division Netaji Subhas Institute of Technology (NSIT) Delhi UniversityNew Delhi India Electrical Engineering Department Rajiv Gandhi Proudyogiki VishwavidyalayaBhopal India Electrical Engineering Department Gautam Buddha University Greater NoidaU.P India

Transformers are expensive and important equipment in the whole power system. Fault in transformers not only affect electric utilities but also customers by interrupting the power supply. The maintenance and servicing of transformers is usually time consuming and costly. If we can somehow predict the incipient faults, its maintenance and servicing can be planned before faults actually happens. Dissolve gas analysis is an important method which can detect the incipient fault conditions. In earlier times faults were monitored by conventional methods, which were time taking and sometimes even need transformer to be out of service, which was a big drawback. Artificial Intelligence is a technique that can help in detecting the incipient fault conditions in lesser time with high accuracy as compared to the conventional techniques available. Key Gas, Dual Triangle, Rogers Ratio, IEC Ratio and, Doernenburg Method, percentage of gases like %C 2 H 2 , %C 2 H 4 , %CH 4 , and combination of gases are applied as an input to ANN models (PNN and MLP). MLP and PNN techniques are trained and compared to get the input parameter that gives most accurate fault predictions.

关键词： Key Gas Method Duval Triangle Method Doernenburg Ratio IEC Ratio Method Rogers Ratio Method ANN MLP PNN

来源：评论

学校读者我要写书评

暂无评论

Comparative study of controller optimization techniques for a robotic manipulator 3

Comparative study of controller optimization techniques for ...

引用

3rd International Conference on Soft Computing for Problem Solving, SocProS 2013

作者： Sharma, Richa Rana, K.P. Kumar, Vineet Instrumentation and Control Engineering Division Netaji Subhas Institute of Technology Dwarka New Delhi110078 India

ISBN: (纸本)9788132217701

A robotic manipulator is a highly nonlinear, highly coupled, Multi-Input Multi-Output (MIMO) and dynamic system. Being complex in nature conventional Proportional-Integral-Derivative (PID) controller tuning methods, in general, are not applicable to these systems. For the past two decades, with the advent of efficient and high speed computing power, optimization techniques are being applied for complex non-linear processes for tuning of controllers. These techniques yield optimized performance for customised performance indexes. This paper presents a detailed comparative study of performances of three optimization techniques for the tuning of PID controllers for a two-link planar rigid robotic manipulator. In this work tuning of PID controllers has been carried out using three techniques namely Particle Swarm Optimization (PSO), Simulated Annealing (SA) and Genetic Algorithm (GA). Two performance indices namely Integral of Absolute Error (IAE) and Integral of Absolute Change in control Output (IACCO) with equal weightage for both the links are considered for optimization. The robustness testing of optimized controllers is done for the trajectory tracking, model uncertainties and disturbance rejection. The simulation results clearly indicate that the PSO outperforms both SA and GA. © Springer India 2014.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Development of a genetic algorithm toolkit in LabVIEW 3

Development of a genetic algorithm toolkit in LabVIEW

引用

3rd International Conference on Soft Computing for Problem Solving, SocProS 2013

作者： Kumar, Vineet Rana, K.P.S. Kumar, Amit Sharma, Richa Mishra, Puneet Nair, Sreejith S. Division of Instrumentation and Control Engineering Netaji Subhas Institute of Technology Sector-3 Dwarka New Delhi110078 India Bhabha Atomic Research Centre Trombay Mumbai400085 India

ISBN: (纸本)9788132217701

It is a well known fact that LabVIEW is one of the finest tools for measurement and control applications. Requirement of intelligent controller tuning methods like Genetic Algorithm (GA) has been felt at times in the LabVIEW environment as there is no standard LabVIEW GA toolkit supplied with the package. In this paper, a GA Toolkit developed in LabVIEW environment, has been presented. The developed toolkit is used for optimizing the gains of the PID (Proportional plus Integral plus Derivative) controller for the given performance indices of a closed loop system. For the purpose of tuning, the algorithm mimics the biological evolution and is used to find the suitable values of PID gains in order to improve the response of the given system. An integrated performance index comprising of rise time, settling time, overshoot, integral absolute error (IAE), integral square error (ISE), integral time weighted absolute error (ITAE) or a combination of these forms the objective function for the optimization. In this toolkit four selection methods, three crossover methods and three mutation methods have been incorporated. To test the developed toolkit a simulation example is also performed and results have been presented. © Springer India 2014.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Bidirectional DC/DC converter for hybrid electric vehicle

Bidirectional DC/DC converter for hybrid electric vehicle

引用

International Conference on Advances in Computing, Communications and Informatics (ICACCI)

作者： Atul Kumar Prerna Gaur Division of Instrumentation and Control Engineering Netaji Subhas Institute of Technology New Delhi India

ISBN: (纸本)9781479930814

Hybrid electric vehicle (HEV) technology is an effective and efficient alternative for conventional vehicles. It provides fuel efficiency, reduces harmful emission and enhances performance. The technology has gain enormous attention because of depleting conventional resources and measured carbon emission. This paper proposes a bidirectional buck boost converter with interleaved control, which minimizes input current and output voltage ripples. This leads to reduce size of passive components with higher efficiency and make whole system more reliable.

关键词： Hybrid electric vehicles Batteries Inductors Acceleration Generators control systems

来源：评论

学校读者我要写书评

暂无评论

Comparative study of some optimization techniques applied to DC motor control

Comparative study of some optimization techniques applied to...

引用

IEEE International Advance Computing Conference, IACC

作者： Vikrant Vishal Vineet Kumar K.P.S. Rana Puneet Mishra Division of Instrumentation and Control Engineering Netaji Subhas Institute of Technology New Delhi India

ISBN: (纸本)9781479925735

Traditional tuning techniques for classical Proportional-Integral-Derivative (PID) controller suffer from many disadvantages like non-customized performance measure and insufficient process information. For the past two decades nature inspired optimization algorithms are efficiently being implemented for tuning of PID controllers. In this paper, four optimization methods namely Genetic Algorithm (GA), Accelerated Particle Swarm Optimization (APSO), Differential Evolution (DE) and Cuckoo Search (CS) are studied and used to optimize the controller gains of a Proportional-Integral (PI) controller for set point tracking in speed control of a DC motor by minimizing Integral Time Absolute Error (ITAE). Hardware validation of the efficiency of above mentioned optimization algorithms is studied and presented. The plant under study is a DC motor control module (MS15) from M/S LJ CREATE™. M/S National Instruments (NI) based software and hardware components i.e. LabVIEW™ and its add-ons toolkit and data acquisition (DAQ) card has been utilized for the closed loop control in real time. The system identification is done in LabVIEW™ and then offline performance optimization is carried out in MATLAB™. The tuned gains are further used to study the run time performances in LabVIEW™ environment. This is done because MATLAB™ has very good optimization tools and on the other hand LABVIEW™ makes the measurement very easy. From the results obtained it can be clearly inferred that CS algorithm outperformed other algorithms studied in this paper, particularly in disturbance rejection.

关键词： DC motors Optimization Algorithm design and analysis Tuning Genetic algorithms Vectors Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Comparative study of dc-dc converters in solar energy systems

Comparative study of dc-dc converters in solar energy system...

引用

International Conference on Advances in Computing, Communications and Informatics (ICACCI)

作者： Ahana Malhotra Prerna Gaur Division of Instrumentation and Control Engineering Netaji Subhas Institute of Technology New Delhi India

ISBN: (纸本)9781479930814

The object of this paper is to design, simulate and compare the performance of different dc-dc converters in solar energy systems. This is designed for using single phase asynchronous motors in home appliances such as washing machines, refrigerator etc. and is simulated in MATLAB 8.1 using simulink, SimPower system. Perturb and Observe algorithm is used as MPPT algorithm to achieve the maximum power transfer from solar array. The PV input voltage is fed to the dc-dc converter and given to the single phase inverter.

关键词： Torque Inductors MATLAB

来源：评论

学校读者我要写书评

暂无评论

Online PI controller tuning for a nonlinear plant using genetic algorithm

Online PI controller tuning for a nonlinear plant using gene...

引用

Computational Intelligence on Power, Energy and controls with their impact on Humanity (CIPECH), Innovative Applications of

作者： Vikrant Vishal Vineet Kumar K. P. S. Rana Puneet Mishra Jitendra Kumar Division of Instrumentation and Control Engineering Netaji Subhas Institute of Technology New Delhi India

Proportional - Integral - Derivative (PID) controller performs well for linear systems. For systems with nonlinearity, controller parameters need to be tuned every time for new operating point to obtain `local gain parameters'. These local gain parameters are not sufficient to get satisfactory performance at other operating points. In this paper a novel approach `Aggregate Fitness Function' is presented to obtain the `global gain parameters' that works satisfactorily at various operating points. Online optimization scheme with Genetic Algorithm (GA) is adopted to tune the Proportional-Integral (PI) controller parameters for setpoint tracking of DC Motor by minimizing Integral-Time-Absolute-Error (ITAE). Hardware validation of the results is presented and studied. The plant under study is DC Motor control Module (MS15) from M/S LJ CREATE™. M/S National Instrument (NI) based software and hardware components i.e. LabVIEW™ and its add-ons toolkit and Data Acquisition (DAQ) Card has been utilized for online tuning and closed loop run time control. The simulation and run time results clearly show the efficiency of the proposed approach.

关键词： DC motors Tuning Genetic algorithms Optimization Data acquisition Aggregates

来源：评论

学校读者我要写书评

暂无评论

Low frequency recursive digital differentiator

Low frequency recursive digital differentiator

引用

Computational Intelligence on Power, Energy and controls with their impact on Humanity (CIPECH), Innovative Applications of

作者： Nitisha Shrivastava Pragya Varshney Instrumentation & Control Engineering Department Netaji Subhas Institute of Technology New Delhi India

In this paper, modified Schneider operator and modified AL-SKG rule based recursive digital differentiators have been analyzed in the low frequency range. The first order s-to-z transformations obtained are in close conformity to the ideal differentiator in terms of magnitude. The phase response shows a linear variation in this range which is also desirable for several applications. MATLAB simulation results are presented to validate the effectiveness of the proposed analysis. These models can be used for discrete realizations of low frequency differentiators.

关键词： Approximation methods Computational intelligence Sliding mode control Acceleration Conferences control engineering Simulation

来源：评论

学校读者我要写书评

暂无评论

External fault identification experienced by 3-phase induction motor using PSVM

External fault identification experienced by 3-phase inducti...

引用

IEEE Power India Conference

作者： A. P. Mittal Hasmat Malik Saarang Rastogi Vihan Talur Department of Instrumentation & Control Engineering Netaji Subhas Institute of Technology (NSIT) New Delhi India

ISBN: (纸本)9781479960439

Fault diagnosis and condition assessment (FDCA) of rotating machines becomes important due to the age of machine in service. Proper FDCA enhance the machine's operational life, efficiency and reducing catastrophic failure. This paper describes a realistic FDCA method for three phase induction motors (IMs) using readily available data. External faults experienced by IM are monitored by proximal support vector machine (PSVM) and compared its performance with standard support vector machine and artificial neural network which revealed that PSVM algorithm is quite faster in investigations leading to reduction in computational load. RMS value of 3-phase voltages and currents are utilized as input variable in PSVM model to identify six types of external faults experienced by IM and normal operating (NF) condition. Testing analysis of 160 samples has been carried out to represent the robustness of the investigated seven status conditions for wide changes in operating and loading condition perturbation.

关键词： Support vector machines Induction motors Fault diagnosis Artificial neural networks Noise measurement Mathematical model Accuracy

来源：评论

学校读者我要写书评

暂无评论

Comparison of Different Artificial Neural Network Techniques in Prediction of Solar Radiation for Power Generation Using Different Combinations of Meterological Variables

Comparison of Different Artificial Neural Network Techniques...

引用

IEEE International Conference on Power Electronics, Drives and Energy Systems

作者： Amit Kumar Yadav Hasmat Malik Centre for Energy and Environment National Institute of Technology Department of Instrumentation & Control Engineering Netaji Subhas Institute of Technology (NSIT)

ISBN: (纸本)9781479963744

The main objective of present study is to compare ANN model develop with neural network fitting tool (nftool), Radial Basis Function Neural Network (RBFNN) in predicting solar radiation for power generation. The three combinations of input variables are considered for prediction. The RBFNN utilizing input parameters as latitude, longitude, height above sea level and sunshine hours has mean absolute percentage error (MAPE) of 4.94% and absolute fraction of variance (R~2) of 96.18% respectively and it give better results than conventional solar radiation prediction models (Angstrom, Akinoglu and Ecevit, Bahel, Almorox and Hontoria). Therefore RBFNN can be used for prediction of solar radiation for solar power generation.

关键词： RBFNN Solar radiation Conventional models ANN

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：