Teaching And Learning Based Optimization Research Articles

An experimental investigation for parametric appraisal of electrohydrodynamic-driven microfabrication approach using teaching and learning-based optimization

Electrohydrodynamic (EHD)-based microfabrication process is a novel high-resolution pattern generation technology for micro/nanoscale system fabrication. Achieving tiny droplets during deposition has been a critical issue for the further development of this new emerging technology. It is imperative to identify the proper fabrication parameters to get the desired resolution operation. In the current study, first, an experimental EHD microfabrication setup is developed, and then experiments are carried out to search for an operating condition, which can promote high-resolution droplet generation. The experiments are planned by design of experiment scheme. The influence of the operating control parameters such as nozzle to substrate gap, voltage and the supply rate of the material on deposited droplets diameter is investigated in the current work. Characterization study reveals that nozzle to substrate gap and supply rate have a positive effect on deposition behavior, whereas voltage has a negative association with the droplet resolution. For better control of the EHD process, a causal relationship is developed between process control and performance parameter. A metaheuristic search algorithm named teaching and learning-based optimization (TLBO) is employed to find out the optimal operating environment of the EHD process. The results are compared with the traditional robust parameter design approach, and the authors found that TLBO performs more effectively for resolution improvement in the EHD-driven microfabrication process. Moreover, the sequence in which the control parameters govern the fabrication process is identified and reported.

Offline Selective Harmonic Elimination With (2N+1) Output Voltage Levels in Modular Multilevel Converter Using a Differential Harmony Search Algorithm

(2N+1) selective harmonic elimination pulse-width modulation (SHE-PWM) is an effective switching strategy of the modular multilevel converter in medium-voltage cases. In these cases, the number of sub-modules (SMs) is not high. Compared to the traditional (N+1) SHE-PWM, (2N+1) SHE-PWM has N more voltage levels, thus it can yield much better harmonic performance. However, the task of selective harmonic elimination also becomes much more complicated since there are more switching angles to be determined. This paper proposes a differential harmony search algorithm (DHS) with a novel harmony improvisation procedure for solving this problem. The Bayesian optimization method is applied to find the optimal parameter configuration for DHS. The performance of DHS is compared with 6 other metaheuristic algorithms including differential evolution (DE), harmony search (HS), genetic algorithm (GA), particle swarm optimization (PSO), teaching and learning-based optimization (TLBO), and ant colony optimization (ACO). The comparison is conducted on a set of 100 (2N +1) SHE-PWM instances by varying the modulation index from 0.01 to 1.0 with a step of 0.01. The numerical results show that the proposed DHS outperforms other compared methods in terms of objective function values, algorithm robustness, the magnitude of fundamental harmonic, and the calculated total harmonic distortion values. The switching angles obtained by DHS are further validated by both Matlab/Simulink simulation and hardware experiment.

THE PERFORMANCE COMPARISON OF THREE METAHEURISTIC ALGORITHMS ON THE SIZE, LAYOUT AND TOPOLOGY OPTIMIZATION OF TRUSS STRUCTURES

The structural optimization problem mostly deals with the weight minimization of the structural system. This issue can be assessed from the size, layout and topology aspects. No matter which of these aspects are targeted, to solve them an optimization technique is required. In the last decades the metaheuristic techniques, as the non-gradient optimization algorithms, are widely applied on solving these classes of problems. In the structural optimization, the most time consuming part of the process is the objective function evaluation. Based on this fact, in the current work, these techniques are divided into three main groups as single phase, double phase and multi-phase algorithms. Then based on the author knowledge, three representative methods are picked for each group and their search performance comparatively inspected on solving size, shape and topology optimization of truss structures. To meet this aim, Integrated Particle Swarm Optimization (iPSO), Teaching and Learning Based Optimization (TLBO) and Drosophila Food-Search Optimization (DSO) algorithms are selected, respectively. Different properties like accuracy, convergence rate and complexity of the algorithms are investigated. The outcomes are provided via illustrative diagrams and tables. Based on the achieved results, DSO shows the most complexity level among the other algorithm while the iPSO and TLBO can outperform it on both accuracy and convergence rate. Consequently, iPSO presents a higher accuracy level on finding optimal solutions and TLBO with the lowest standard deviation value through the process shows the highest level of stability on finding optimal solutions.

Modified Firefly Algorithm for Vector Quantization Codebook Design in Image Compression

In the recent days, the importance of image compression techniques is exponentially increased due to the generation of massive amount of data which needs to be stored or transmitted. Numerous approaches have been presented for effective image compression by the principle of representing images in its compact form through the avoidance of unnecessary pixels. Vector quantization (VA) is an effective method in image compression and the construction of quantization table is an important process is an important task. The compression performance and the quality of reconstructed data are based on the quantization table, which is actually a matrix of 64 integers. The quantization table selection is a complex combinatorial problem which can be resolved by the evolutionary algorithms (EA). Presently, EA became famous to resolve the real world problems in a reasonable amount of time. This chapter introduces Firefly (FF) with Teaching and learning based optimization (TLBO) algorithm termed as FF-TLBO algorithm for the selection of quantization table and introduces Firefly with Tumbling algorithm termed as FF-Tumbling algorithm for the selection of search space. As the FF algorithm faces a problem when brighter FFs are insignificant, the TLBO algorithm is integrated to it to resolve the problem and Tumbling efficiently train the algorithm to explore all direction in the solution space. This algorithm determines the best fit value for every bock as local best and best fitness value for the entire image is considered as global best. When these values are found by FF algorithm, compression process takes place by efficient image compression algorithm like Run Length Encoding and Huffman coding. The proposed FF-TLBO and FF-Tumbling algorithm is evaluated by comparing its results with existing FF algorithm using a same set of benchmark images in terms of Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Signal to Noise Ratio (SNR). The obtained results ensure the superior performance of FF-TLBO and FF-Tumbling algorithm over FF algorithm and make it highly useful for real time applications.

Controlled showering optimization algorithm: an intelligent tool for decision making in global optimization

In this study a novel population based meta-heuristic, called controlled showering optimization (CSO) algorithm, for global optimization of unconstrained problems is presented. Modern irrigation systems are equipped with smart tools manufactured and controlled by human intelligence. The proposed CSO algorithm is inspired from the functioning of water distribution tools to model search agents for carrying out the optimization process. CSO imitates the mechanism of projection of water units by sprinklers and the movements of their platforms to the desired locations for scheming optimum searching procedures. The proposed method has been tested using a number of diverse natured benchmark functions with low and high dimensions. Statistical analysis of the empirical data demonstrates that CSO offers solutions of better quality in comparison with several well-practiced algorithms like genetic algorithm (GA), particle swarm optimization (PSO), differential evolution (DE), artificial bee colony (ABC), covariance matrix adaptation evolution strategy (CMA-ES), teaching and learning based optimization (TLBO) and water cycle algorithm (WCA). The experiments on high-dimensional problems reveal that CSO algorithm also outperforms significantly a number of algorithms designed specifically for high dimensional global optimization problems.

Solution of structural and mathematical optimization problems using a new hybrid swarm intelligence optimization algorithm

In this investigation a new optimization algorithm named as interactive search algorithm (ISA) is presented. This method is developed through modifying and hybridizing the affirmative features of recently developed integrated particle swarm optimization (iPSO) algorithm with the pairwise knowledge sharing mechanism of the teaching and learning based optimization (TLBO) method. Proposed ISA provides two different navigation schemes as Tracking and Interacting. Each agent based on its tendency factor can pick one of these two schemes for searching the domain. Additionally, ISA utilizes an improved fly-back technique to handle problem constraints. The proposed method is tested on a set of mathematical and structural optimization benchmark problems with discrete and continuous variables. Numerical results indicate that the new algorithm is competitive with other well-stablished metaheuristic algorithms.

Interactive search algorithm: A new hybrid metaheuristic optimization algorithm

In this paper, a new hybrid optimization algorithm, called “Interactive Search Algorithm (ISA)” is proposed for the solution of the optimization problems. This algorithm modifies and combines affirmative features of two developed metaheuristic methods called Integrated Particle Swarm Optimization (iPSO) and Teaching and Learning Based Optimization (TLBO). ISA consists of two separate paradigms: (i) Tracking and (ii) Interacting. Tracking paradigm utilizes the information stored in the current agent’s memory and two other important agents, the weighted and best agents, to guide the colony. On the other hand, interacting paradigm provides a pairwise interaction between agents to share their knowledge with each other. Each agent based on its tendency factor employs one of these two paradigms in each cycle of ISA to explore the search space. Additionally, rather than conventional penalty approach, ISA utilizes the improved fly-back approach to handle problem constraints. The search capability of the proposed method is tested on the number benchmark mathematical functions and constrained mechanical design problems as the real-world examples. Consequently, the achieved numerical results demonstrate that the proposed method is competitive with other well-established metaheuristic methods.

Applications of TLBO algorithm on various manufacturing processes: AReview

Different manufacturing processesoptimized by the Teaching and learning based optimization (TLBO) algorithm are presented in this review paper. The main focus of this review paperis on the optimization of the various manufacturing process that has been optimized by TLBO algorithm. The machining processes that have been considered in this work are viz. End milling, Face Milling, Drilling, Turning, Grinding, Electric Discharge Machining, Abrasive Jet Machining, Ultrasonic Machining, Electrochemical Machining, Laser Beam Machining, Micro Machining, and other different hybrid and advanced versions of machining process. The review work on manufacturing process, on such a large scale was not performed earlier by considering different processes at a time on TLBO algorithm, and hence, this review work may be prepare for the future information at one place for the subsequent researchers, in order to determine their way of research on TLBO algorithm.

A geometric image segmentation method based on a bi-convex, fuzzy, variational principle with teaching-learning optimization

This paper proposes an efficient, bi-convex, fuzzy, variational (BFV) method with teaching and learning based optimization (TLBO) for geometric image segmentation. Firstly, we adopt a bi-convex, object function to process a geometric image. Then, we introduce TLBO to maximally optimize the length-p enalty item, which will be changed under the teaching phase and the learner phase of the TLBO. This makes the length penalty item closer to the target boundary. Therefore, the length-penalty item can be automatically adjusted according to the fitness function, namely the evaluation standards of the image quality. At last, we combine the length-penalty item with the numerical remedy mechanism to achieve better results. Compared with existing methods, simulations show that our method is more effective.

TLBO optimized sliding mode controller for multi-area multi-source nonlinear interconnected AGC system

Abstract This paper represents design of output feedback sliding mode controller (SMC) for multi area multi-source interconnected power system. After designing output feedback SMC, teaching and learning based optimization (TLBO) technique is utilized to optimize feedback gain and switching vector of the controller. The superiority of the proposed approach is shown by comparing the result with output feedback tuned SMC with differential evolution and particle swarm optimization and state feedback SMC tuned with genetic algorithm for a two area thermal interconnected power system. Further, the proposed approach is extended to multi-area multi-source non linear automatic generation control (AGC) system with/without HVDC link. First area consists up thermal, hydro and gas; second area consists up thermal, hydro and nuclear as generating unit. Additionally, the superiority of proposed approach is shown by sensitivity analysis, which is carried out with wide changes in system parameters.