Figure 2 - uploaded by Goran Petrović
Content may be subject to copyright.
Source publication
This paper describes the meta-heuristic improved harmony search algorithm (IHSA) and analyzes the performance of IHSA in solving unconstrained function minimization problems. The most important challenge to this algorithm is setting the parameters for various optimization problems. Performance of IHSA is quite sensitive to initial settings. Using T...
Context in source publication
Citations
... Using expression (22), the Ch-C condition from constraint (6) can be transformed into expression (23) [16]. ...
... However, this paper does not consider the selection of optimal parameters for the given problem but uses the recommended parameters. The parameters of the IHSA used to solve the VRPSD are [22]: harmony memory size -HMS = 10; harmony memory consideration rate -HMCR = 0.95; pitch adjustment rate -PARmin = 0.1; PARmax = 0.85; bandwidthbwmin = 0.001; bwmax = 0.8; number of improvizations -NI = 1e3. ...
... Res. (171) [24][25][26][27][28][29][30][31][32][33][34][35][36][37][38]2006. ...
امروزه الگوریتم‌های فراابتکاری نقش بسیار مهمی، در حل مسائل بهینه‌سازی دارند. این الگوریتم‌ها پارامترهای اولیه‌یی دارند که تنظیم بهینه‌ی آنها نقش مؤثری در کیفیت جواب‌های به دست آمده دارد. در بیشتر روش‌های موجود، پارامترهای تنظیم در تمام مراحل، به‌صورت ثابت در نظر گرفته شده است، اگرچه بهتر است پارامترهای تنظیم با توجه به شرایط مختلف مسئله در طول مراحل بهینه‌سازی تغییرات لازم را داشته باشند. در این مقاله ما روشی را براساس طراحی آزمایشات تاگوچی، برای الگوریتم فراابتکاری هارمونی سرچ پیشنهاد داده‌ایم که پارامترهای اولیه را به‌صورت پویا تنظیم می‌کند و در بسیاری از الگوریتم‌های فراابتکاری قابل اجراست. کارایی روش تنظیم پارامتر تاگوچی پویا در حل چهار مسئله‌ی بهینه‌سازی تخصیص قابلیت اطمینانٓـ اجزای مازاد بررسی شده که نتایج به دست آمده مؤید استواری این روش نسبت به روش کلاسیک تنظیم پارامتر تاگوچی است.
... A. Taboada et al., 2008;Zoulfaghari, Hamadani, & Ardakan, 2015), and MOPSO (Chambari, Rahmati, & Najafi, 2012) to solve these problems. In addition, , (Landa-Torres, Gil-Lopez, Salcedo-Sanz, Ser, & Portilla-Figueras, 2012;Marković, Madić, & Petrović, 2012;Rahmati, Hajipour, & Niaki, 2013;Ricart, Hüttemann, Lima, & Barán, 2011) have applied MOHS to solve a wide range of multi-objective RAP problems. It should be noted that the most distinctive characteristic of multi-objective problems is independent objectives (Deb, 2001). ...
... (Santos Coelho & de Andrade Bernert, 2009) introduced a modified HS approach combined with an operator of differential evolution, a paradigm of evolutionary computation, to solve RAP optimization problems. More recently, several researchers have studied the multi-objective version of the HS 5 algorithm to solve different problems such as traffic and mobility , facility location (Rahmati et al., 2013), health-care facility location (Landa-Torres et al., 2012), and refuse collection vehicles (Marković et al., 2012). (Ricart et al., 2011) have proposed two HS methods for solving multi-objective optimization problems using the Zitzler-Deb-Thiele functions as a test-bed which performed well against the NSGA-II method. ...
In this paper, we study a series-parallel multi-objective multi-state redundancy allocation problem (MSRAP) with known performance levels and corresponding state probabilities. The problem is comprised of multiple subsystems in series and each subsystem is comprised of multiple components in parallel. The system components have a range of performance level from complete working to complete failure. The subsystems contain homogenous redundant components and the component prices come under an all-unit discount policy if a unique brand (type) is chosen for purchasing all subsystem components. Each component is characterized by its cost, weight and availability. The goals are to find the optimal combination of the components in each subsystem that maximizes system availability and minimizes the total cost under a weight constraint. We propose a multi-objective harmony search (MOHS) algorithm, a non-dominated sorting genetic algorithm (NSGA-II), and a multi-objective genetic algorithm (MOGA) to solve this problem. In addition, the Taguchi method is utilized to tune the parameters in each algorithm. We use a number of numerical examples to demonstrate the applicability and exhibit the efficacy of the three algorithms. The results show that the MOHS outperforms the NSGA-II and MOGA with respect to all of the considered metrics.
... The following IHSA parameters were used: HMS = 50, HMCR = 0.9, PAR = 0.35, number of improvisations = 5.000. As discussed in [19], Taguchi experimental design method was applied to assist in determining the IHSA parameter values. The obtained optimization results are given in Table 3. ...
This study presents an approach by coupling artificial neural network (ANN) and improved harmony search algorithm (IHSA) to determine the optimum cutting parameter settings for minimizing surface roughness when turning of polyamide material. An ANN model surface roughness was developed in terms of cutting speed, feed rate, depth of cut, and tool nose radius using the data from the turning experiment conducted according to Taguchi's L 27 orthogonal array. The optimal cutting parameter settings were determined by applying the IHSA to the developed ANN surface roughness model. The results show that the proposed optimization approach can be efficiently used for optimization of cutting parameter settings when turning polyamides. Although determining ANN and IHSA parameters is quite complex and problem dependent, it can be simplified by using Taguchi's experimental design as in this study.
