检索结果-内蒙古大学图书馆

Application of advanced algorithms for enhancement in machining performance of Inconel 718

INDIAN JOURNAL OF ENGINEERING AND MATERIALS SCIENCES 2018年第5期25卷 366-376页

作者： Deshpande, Yogesh V. Andhare, Atul B. Padole, P. M. Sahu, N. K. Shri Ramdeobaba Coll Engn & Management Dept Ind Engn Nagpur 440013 Maharashtra India Visvesvaraya Natl Inst Technol Dept Mech Engn Nagpur 440010 Maharashtra India

Inconel 718 is the most promising nickel-based alloy finding wide usage in engineering applications because of its good mechanical properties. However, this alloy is difficult to machine and results in poor surface quality after machining. optimization of parameters is essential for improving machining performance of this costly and hard to cut material. The research discusses estimation of optimum parameters using teaching-learning based optimization (TLBO) and compares them to those obtained by genetic algorithm (GA) in turning of Inconel 718. The parameters cutting speed, feed rate and depth of cut are selected as independent variables. The experiments are designed using central composite design of response surface methodology for the modelling of turning process. Surface roughness, tool flank wear and cutting temperature are selected as response parameters for minimization. The adequacy of modified models developed by response surface methodology are tested and then utilized for formulation of multi-objective optimization function. The function is solved by GA and TLBO. After comparing optimization results, the best algorithm is used for confirmation test. Convergence of TLBO algorithm is much faster as compared to GA even though there is very little difference in the optimum values of parameters.

关键词： Inconel 718 Response surface methodology teaching-learning based optimization Genetic algorithm Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid MOL-TLBO optimized techno-economic-socio analysis of renewable energy mix in island mode

引用

APPLIED SOFT COMPUTING 2016年 43卷 187-198页

作者： Khare, Ranjeeta Kumar, Yogendra Maulana Azad Natl Inst Technol Dept Elect Engn Bhopal India

In this paper, a novel hybrid many optimizing liaisons (MOL) and teaching-learning based optimization(TLBO) i.e. MOL-TLBO based optimization of integrated hybrid renewable energy sources (IHRES) is proposed for techno-economic-socio analysis. IHRES consists of PV, wind turbine, battery storage banks and diesel generator. The methodology was constructed by using meteorological data from Renewable Energy Laboratory of electrical engineering department, MANIT, Bhopal situated in Madhya Pradesh, India. Optimal sizing of IHRES is done on the basis of solar irradiation, wind speed, demand load, reliability index, loss of load probability (LOLP) and CO2 emission through diesel generator. Three different crystalline silicon PV modules are considered: ASE-300(mi-Si based EFG), Kyocera-120(mc-Si based wafer) and Astro-Power AP-120(thin-film Si). Results show that AP-120 gives better result as compared with other two for PV-wind-battery-DG combination. Annual cost of the system (ACS) is evaluated by using the proposed hybrid MOL and TLBO (MOL-TLBO) algorithm. Supremacy of the suggested MOL-TLBO hybrid method for optimal sizing of hybrid system is proved by comparing the results with other optimization techniques i.e. TLBO, ITLBO, PSO, MOL and SGA. Finally it is seen that MOL-TLBO based techno-economicsocio analysis for IHRES exhibit superior performance and fast as compared to SGA, PSO, TLBO, ITLBO and MOL. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Annual cost of the system Loss of power supply probability Hybrid MOL-TLBO Many optimizing liaisons (MOL) Simple genetic algorithm teaching-learning based optimization

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic optimization of Reinforced Concrete Footings

引用

KSCE JOURNAL OF CIVIL ENGINEERING 2018年第11期22卷 4555-4563页

作者： Nigdeli, Sinan Melih Bekdas, Gebrail Yang, Xin-She Istanbul Univ Dept Civil Engn TR-34320 Istanbul Turkey Middlesex Univ Sch Sci & Technol London England

The primary goal of an engineer is to find the best possible economical design and this goal can be achieved by considering multiple trials. A methodology with fast computing ability must be proposed for the optimum design. Optimum design of Reinforced Concrete (RC) structural members is the one of the complex engineering problems since two different materials which have extremely different prices and behaviors in tension are involved. Structural state limits are considered in the optimum design and differently from the superstructure members, RC footings contain geotechnical limit states. This study proposes a metaheuristic based methodology for the cost optimization of RC footings by employing several classical and newly developed algorithms which are powerful to deal with non-linear optimization problems. The methodology covers the optimization of dimensions of the footing, the orientation of the supported columns and applicable reinforcement design. The employed relatively new metaheuristic algorithms are Harmony Search (HS), teaching-learning based optimization algorithm (TLBO) and Flower Pollination Algorithm (FPA) are competitive for the optimum design of RC footings.

关键词： reinforced concrete footings optimization metaheuristic algorithms harmony search algorithm teaching-learning based optimization flower pollination algorithm

来源：评论

学校读者我要写书评

暂无评论

A TLBO based gradient descent learning-functional link higher order ANN: An efficient model for learning from non-linear data

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2018年第1期30卷 120-139页

作者： Naik, Bighnaraj Nayak, Janmenjoy Behera, H. S. Veer Surendra Sai Univ Technol Dept Comp Sci Engn & Informat Technol Burla 768018 Odisha India Govt India New Delhi India

All the higher order ANNs (HONNs) including functional link ANN (FLANN) are sensitive to random initialization of weight and rely on the learning algorithms adopted. Although a selection of efficient learning algorithms for HONNs helps to improve the performance, on the other hand, initialization of weights with optimized weights rather than random weights also play important roles on its efficiency. In this paper, the problem solving approach of the teaching learning based optimization (TLBO) along with learning ability of the gradient descent learning (GDL) is used to obtain the optimal set of weight of FLANN learning model. TLBO does not require any specific parameters rather it requires only some of the common independent parameters like number of populations, number of iterations and stopping criteria, thereby eliminating the intricacy in selection of algorithmic parameters for adjusting the set of weights of FLANN model. The proposed TLBO-FLANN is implemented in MATLAB and compared with GA-FLANN, PSO-FLANN and HS-FLANN. The TLBO-FLANN is tested on various 5-fold cross validated benchmark data sets from UCI machine learning repository and analyzed under the null-hypothesis by using Friedman test, Holm's procedure and post hoc ANOVA statistical analysis (Tukey test & Dunnett test). (C) 2016 King Saud University. Production and hosting by Elsevier B.V.

关键词： teaching-learning based optimization Functional link artificial neural network Gradient descent learning Classification Data mining

来源：评论

学校读者我要写书评

暂无评论

Comparison of different optimized machine learning algorithms for daily river flow forecasting

引用

EARTH SCIENCE INFORMATICS 2023年第1期16卷 533-548页

作者： Samui, Pijush Yesilyurt, Sefa Nur Dalkilic, Huseyin Yildirim Yaseen, Zaher Mundher Roy, Sanjiban Sekhar Kumar, Sanjay Natl Inst Technol Patna Dept Civil Engn Patna 800005 India Erzincan Binali Yildirim Univ Dept Civil Engn TR-24000 Erzincan Turkey King Fahd Univ Petr & Minerals Civil & Environm Engn Dept Dhahran 31261 Saudi Arabia Vellore Inst Technol Sch Comp Sci & Engn Vellore 632014 India

River flow modeling is essential for critical aspects such as effective water management and structure planning, together with flood and drought analysis. There has been a growing interest in modeling hydrological systems via machine learning (ML) models. Various optimization techniques are utilized to develop the applications of ML-based hydrological models. The ultimate aim of this research is to establish high performance forecasting model. Therefore, this study conducts river flow modeling by using the daily data attained from a gauge station situated in the Euphrates Basin. For this purpose, Artificial Neural Network (ANN) model was hybridized with five different optimization algorithms i.e., Artificial Bee Colony (ABC), teaching-learning based optimization (TLBO), Ant Colony optimization (ACO), Ant-Lion optimization (ALO), and Imperialist Competitive Algorithm (ICA). In determining the inputs used to create the models, the distribution graph and correlation of the data with the previous period data were examined. The results were evaluated with eleven different statistical parameters and an error matrix. Examining the obtained results, the study revealed all models present high performance. When the results were reviewed in general, it was seen that all determination coefficient (R-2) and Nash-Sutcliffe coefficient (NSE) values were higher than 0.962, and other parameters were very close to the optimum. By comparing all the developed hybrid models, ANN-ALO model reported the highest performance for river flow forecasting.

关键词： Artificial Neural Network Artificial Bee Colony Ant Colony optimization Ant-Lion optimization Imperialist Competitive Algorithm teaching-learning based optimization

来源：评论

学校读者我要写书评

暂无评论

Quasi-oppositional JAYA optimized 2-degree-of-freedom PID controller for load-frequency control of interconnected power systems

引用

INTERNATIONAL JOURNAL OF MODELLING AND SIMULATION 2022年第1期42卷 63-85页

作者： Guha, Dipayan Roy, Provas Kumar Banerjee, Subrata Motilal Nehru Natl Inst Technol Allahabad Elect Engn Dept Prayagraj India Kalyani Govt Engn Coll Dept Elect Engn Kalyani W Bengal India Natl Inst Technol Durgapur Durgapur W Bengal India

An effort is given in this paper, for the first time, to discuss the load-frequency control (LFC) problem of an interconnected power system by implementing a novel heuristic optimization method called quasi-oppositional-based JAYA (QOJAYA). The proposed algorithm houses the knowledge of quasi-oppositional-based learning to enhance convergence speed and find the best solutions to the LFC problem. To show the effectiveness, the proposed QOJAYA scheme is, individually, applied to a two-area multi-unit multi-source power plant and a three-area hydrothermal power plant considering the system nonlinearities. The structural simplicity and performance adequacy of the well-known proportional-integral (PI) controller enforces to optimally design it as a secondary controller at the first instant. Afterward, the dynamic stability of the concerned power systems is increased with a 2DOF-PID controller. The proposed algorithm is employed to search the optimal settings of the said controllers by minimizing the time-based single-valued fitness functions. Simulation results validate the success of the proposed QOJAYA scheme and demonstrate its dominance over original JAYA, teaching-learning-based optimization (TLBO), and other recently introduced optimization techniques in the state-of-the-art for the same power system. Finally, the robustness of the designed controller is established by performing sensitivity analysis considering parameters and loading uncertainties.

关键词： Load-frequency control JAYA algorithm quasi-oppositional based learning 2DOF-PID controller teaching-learning based optimization competitive algorithms

来源：评论

学校读者我要写书评

暂无评论

An improved teaching-learning based robust edge detection algorithm for noisy images

引用

JOURNAL OF ADVANCED RESEARCH 2016年第6期7卷 979-989页

作者： Thirumavalavan, Sasirooba Jayaraman, Sasikala Annamalai Univ Dept Comp Sci & Engn Annamalainagar Tamil Nadu India

This paper presents an improved teaching learning based optimization (TLO) and a methodology for obtaining the edge maps of the noisy real life digital images. TLO is a population based algorithm that simulates the teaching-learning mechanism in class rooms, comprising two phases of teaching and learning. The 'teaching Phase' represents learning from the teacher and 'learning Phase' indicates learning by the interaction between learners. This paper introduces a third phase denoted by "Avoiding Phase" that helps to keep the learners away from the worst students with a view of exploring the problem space more effectively and escaping from the sub-optimal solutions. The improved TLO (ITLO) explores the solution space and provides the global best solution. The edge detection problem is formulated as an optimizationproblem and solved using the ITLO. The results of real life and medical images illustrate the performance of the developed method. (C) 2016 Production and hosting by Elsevier B.V. on behalf of Cairo University.

关键词： Evolutionary algorithms teaching-learning based optimization Edge detection Canny and Sobel operators

来源：评论

学校读者我要写书评

暂无评论

Prediction of Parameters which Affect Beach Nourishment Performance Using MARS, TLBO, and Conventional Regression Techniques

引用

THALASSAS 2020年第1期36卷 245-260页

作者： Karasu, Servet Kankal, Murat Nacar, Sinan Uzlu, Ergun Yuksek, Omer Recep Tayyip Erdogan Univ Civil Engn Dept TR-53100 Rize Turkey Bursa Uludag Univ Civil Engn Dept TR-16059 Bursa Turkey Karadeniz Tech Univ Civil Engn Dept TR-61080 Trabzon Turkey

Artificial beach nourishment is one of the most important environmentally friendly coastal protection methods since it protects the aesthetic and recreational values of the beach and increases its protective properties. Therefore, the main aim of the current study is to assess the accuracy of multivariate adaptive regression splines (MARS) in predicting the parameters, namely sediment transport coefficients (K) and the diffusion rate (omega), which affect beach nourishment performance. The performance of the MARS was determined by comparison of the models using exponential, linear, and power regression equations trained by conventional regression analyses (CRA) and the teaching-learning based optimization (TLBO) algorithm. In all models, two different input data obtained from the experimental study were used, one dimensional and one non-dimensional. The results presented that the MARS models gave lower error values than the CRA and TLBO models according to the root mean square error, mean absolute error, and scattering index criteria. When the models were evaluated, it was revealed that dimensional and non-dimensional models gave approximate results. We proved that the dimensional and non-dimensional MARS models can be used to estimate the (K) and (omega) values.

关键词： Beach nourishment Multivariate adaptive regression splines Sediment transport Shore protection teaching-learning based optimization

来源：评论

学校读者我要写书评

暂无评论

An integrated approach for distributed resource allocation and network reconfiguration considering load diversity among customers

引用

SUSTAINABLE ENERGY GRIDS & NETWORKS 2016年 7卷 37-46页

作者： Kanwar, Neeraj Gupta, Nikhil Niazi, K. R. Swarnkar, Anil Malaviya Natl Inst Technol Dept Elect Engn Jaipur Rajasthan India

In this paper a new dedicated search teaching learning based optimization (DSTLBO) method is proposed for simultaneous allocation of distributed resources keeping in view the practical aspect of network reconfiguration to maximize annual energy loss reduction while maintaining a better node voltage profiles. The accuracy of distributed resource allocation and their benefits depend on proper modeling of system loads. Distribution system planners usually provide dedicated feeders to different classes of customers;each has its own characteristic load pattern which varies hourly and seasonally. There exists diversity in customers' load demands. Therefore proper modeling of annual load profile is crucial to obtain realistic allocation of distribution resources (shunt capacitors and distributed generations). In the proposed formulation of the optimization problems the diversity in customers' load patterns has been taken into account. In the proposed dedicated search teaching learning based optimization (DSTLBO), new learning approaches are suggested to enhance convergence, accuracy and efficiency of the standard TLBO. The proposed method is investigated on the benchmark IEEE 33-bus test distribution system. The application results are presented. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Customers' load patterns Distributed energy resources Distribution network reconfiguration teaching-learning based optimization Smart grid

来源：评论

学校读者我要写书评

暂无评论

A Hybrid TLBO-Particle Filter Algorithm Applied to Remaining Useful Life Prediction in the Presence of Multiple Degradation Factors

A Hybrid TLBO-Particle Filter Algorithm Applied to Remaining...

引用

IEEE Congress on Evolutionary Computation (CEC) as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

作者： Rodrigues, Leonardo R. Coelho, Daniel B. P. Gomes, Joao Paulo P. Aeronaut Inst Technol Elect Engn Div Sao Jose Dos Campos Brazil Embraer SA Performance Software Dept Belo Horizonte MG Brazil Univ Fed Ceara Dept Comp Sci Fortaleza Ceara Brazil

ISBN: (纸本)9781728169293

One of the end goals of a Prognostic and Health Monitoring (PHM) algorithm is to provide accurate Remaining Useful Life (RUL) predictions for the monitored component or system. Most of the PHM algorithms found in the literature are based on the assumption that the degradation process is governed by only one degradation factor. However, some components and systems may be subject to multiple degradation factors. In this paper, we propose a hybrid algorithm that incorporates a teaching-learning based optimization (TLBO) step into a Particle Filter (PF) framework. PF is an algorithm that can handle multiple degradation factors. However, it has some drawbacks such as sample degeneracy and sample impoverishment. The hybrid TLBO-PF algorithm proposed in this paper improves the performance of the standard PF algorithm by reducing the effects of sample degeneracy and sample impoverishment. A case study is presented to evaluate the performance of the proposed algorithm for estimating the degradation factors and predicting the RUL of a Lithium-ion battery, which is affected by two degradation factors. The results show that the proposed algorithm presented a better performance for both the tasks (degradation factor estimation and RUL prediction) when compared with the standard Particle Filter algorithm.

关键词： Prognostics health monitoring remaining useful life particle filter teaching-learning based optimization Lithium-ion battery

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：