Non Conventional Approaches for Optimizing Of Cutting Parameters in Machining Process: A Review Azlan Mohd Zain
Habibollah Haron
Safian Sharif
Department of Modeling & Industrial Computing, Faculty of Computer Science & Information System, Universiti Teknologi Malaysia, Johor, Malaysia
Department of Modeling & Industrial Computing, Faculty of Computer Science & Information System, Universiti Teknologi Malaysia, Johor, Malaysia
Department of Manufacturing & Industrial Engineering, Faculty of Mechanical Engineering, Universiti Teknologi Malaysia, Johor, Malaysia
[email protected]
[email protected]
[email protected]
ABSTRACT As any cutting process problem in machining may have some unique characteristics, it may be difficult to select a suitable optimization technique that provide acceptable and improved cutting conditions. This paper discusses the non-conventional optimization approaches for optimizing the cutting parameters in various machining processes such as turning, drilling and milling operations. Based on the review; the advantages, limitations and applications of each technique that is classified as a nonconventional approach is described. The current review shows that each approach has its own features that work well and may not applicable in certain optimization problems. The features of the various optimization approaches and their application potentials are concluded in relation to the different type of machining processes.
Keywords non-conventional techniques, optimization, cutting parameters, machining operations.
1. INTRODUCTION Machining refers to cutting processes that are based on the removal of material from an originally rough-shaped workpiece. The cutting processes are dependent on the workpiece parameters (such as material type, crystallography, temperature, and predeformation), cutting tool parameters (such as tool design geometry, and material), and cutting parameters (such as speed, depth of cut, feed rate and cooling media). Optimization techniques was adopted in machining to handle and solve the types of parameters optimization problems. Several optimization techniques that can be classified as conventional and nonconventional approaches have been introduced to optimize the cutting parameters. Recently, the non-conventional approaches had been accepted as a popular technique used to solve the problem for cutting processes. With reference to the published literatures, there are several techniques that can be classified as non-conventional approaches such as Genetic Algorithm (GA), Simulated Annealing (SA), Tabu Search (TS), Ant Colony Algorithm (ACO), and Particle Swarm Optimization (PSO) [1,2,3]. R. Siva Sankar et al. [1] stated that non-conventional optimization approaches consist of a
variety of methods including optimization paradigms that are based on evolution mechanisms such as biological genetics and natural selection. These methods use the fitness information instead of the functional derivatives making them more robust and effective. Indarjit Mukherjee and Pradip Kumar [2] stated that non-conventional approaches based on extrinsic model or objective function developed which are only an approximation and attempt to provide near-optimal cutting conditions. Aman Aggarwal and Hari Singh [3] stated that non-conventional approaches are applied usefully in industrial applications for optimal selection of process variables in the area of machining. In this paper, discussion was focused on the advantages, limitations and applications of some techniques that are classified as non-conventional approaches focusing on optimizing of cutting parameters in various machining processes.
2. NON CONVENTIONAL APPROACHES FOR CUTTING PROCESS Today, the increasing number of sophisticated machine tools used in modern industry shows the need for precise and fast evaluation of many influential production parameters [4]. In a traditional machining processes, cutting parameters are usually selected from handbooks or experiences of the machine operators, and these selected parameters are usually conservative so as to avoid cutting failure. Even if the cutting parameters are optimized off-line by an optimization algorithm, they cannot be adjusted accordingly due to the tool wear, heat generation and other disturbances [5]. To ensure the quality of the machined parts, to reduce the cutting costs and to increase the cutting efficiency, it is necessary to optimize and control the cutting parameters on-line when the machine tools are in used. The cutting parameters must be adjusted in real-time so as to satisfy some optimal cutting criteria. There are many processes in machining including sawing, reaming, tapping, planning, broaching, boring and threading. But, the two most widely used in machining are milling and turning operations. Non-conventional approaches, based on the principles of its features, will be used and recommended for the optimization of cutting conditions in machining processes. The cutting conditions can be optimized within the constraints set by using the non-conventional approaches. Advantages, limitations and
application for different machining processes of five non conventional techniques are discussed in the following section.
Table 1: Applications of GA in optimizing the cutting parameters Author
Proces s
Remark
P.Palanisam y et al, 2007 [11]
Milling
GA has been used to machine mild steel work piece under optimal parameters of feed, cutting speed and depth of cut for a constant material removal rate in an end-milling process
M.S. Shunmugam et al, 2000 [12]
Milling
GA yields production cost values less for the face-milling process
Krimpenis and Vosniakos, 2002 [13]
Milling
GA able to achieve optimal machining time and maximum material removal for sculptured surface CNC milling process
Franci Cus and Joze Balic, 2003 [14]
Milling
Integration of the GA with an intelligent manufacturing system will lead to reduction in production cost, reduction in production time, flexibility in machining parameter selection, and improvement of product quality
F. Cus et al, 2006 [15]
Milling
GA was used for solving the machining processes problem with ball-end milling
M. Kovacic, et al, 2004 [16]
Milling
GA approach is used for cutting force prediction in milling process
N. Baskar, et al, 2005 [17]
Milling
GA is used to determine optimum machining based on maximum profit in milling process
Z.G. Wang et al, 2005 [18]
Milling
GA combined with SA is used to optimize the cutting parameters for multi-pass milling process
R. Saravanan et al, 2001 [19]
Turnin g
GA can be used to solve any type of machining optimization problem by including any number of variables in turning process
Ramo’n Quiza Sardin’as et al [20]
Turnin g
GA technique able to optimize the cutting parameters in turning processes: cutting depth, feed and speed in a multi-objective optimization problem
Onwubolu and Kumalo, 2001 [21]
Turnin g
Propose a local search GA-based technique in multi-pass process
Chowdhury et al, 2002
Turnin
GA outperform goal programming technique in terms of unit production
2.1 GA Optimization GA technique was firstly invented by John Holland in 1975. It is a very powerful optimization algorithm, which works by emulating the natural process of evolution as a means of progressing toward the optimum [6]. The algorithm starts with an initial set of random configurations, called the population. Each individual in the population is a string of symbols, usually a binary bit string representing a solution to the optimization problem. Each iteration called a generation, the individuals in the current population are evaluated using some measure of fitness. Based on this fitness value, some individuals are selected from the population two at a time as parents. The fitter individuals have a higher probability of being selected. A number of genetic operators is applied to the parents to generate new individuals called offspring, by combining the features of both parents. The three genetic operators commonly used are crossover, mutation and inversion, which are derived by analogy from the biological process of evolution. The offspring are next evaluated and a new generation is formed by selecting some of the parents and offspring, once again on similar basis [7]. There are some advantages of GA optimization technique. Indarjit Mukherjee and Pradip Kumar [2] stated that GA: (i) is preferred when near-optimal conditions instead of exact optimal solution are cost effective and acceptable for implementation by the manufacturers, and (ii) it is a derivative-free approach for nearoptimal points search direction, and may be applied to discrete or continuous response function. Monalas D.A. et al [8]: (i) the capability of GAs to handle objective functions of any complexity with both discrete (e.g., integer) and continuous variables successful. Franci Cus and Joze Balic [9]: (i) simple complementing of the model by new input parameters without modifying the existing model structure, (ii) automatic searching for the non-linear connection between the inputs and outputs and (iii) fast and simple optimizing. There are some limitations of GA optimization technique. Indarjit Mukherjee and Pradip Kumar [2] stated that GA: (i) convergence of the GA is not always assured, (ii) no universal rule exists for appropriate choice of algorithm parameters, such as as population size, number of generation to be evaluated, crossover probability, mutation probability, and string length, (iii) GA may require a significant exucation time to attain near-optimal solutions, and convergence speed of the algorithm may be slow and (iv) the repeatability of results obtained by GA with same initial decision variable setting conditions is not guaranteed. Franci Cus and Joze Balic [9]: (i) time-consuming of training parameters, (ii) experience is necessary for conceiving of the algorithm and (iii) repeatability of training is not assured. Z.G. Wang et al [10]: (i) the successful application of GA depends on the population size or the diversity of individual solutions in the search space, and (ii) if GA cannot hold its diversity well before the global optimum is reached, it may prematurely converge to a local optimum. Examples of applications of GA-based technique in cutting process for parameter optimization problem have been reported by various researchers. Table 1 shows the applications of GAbased technique for different machining processes.
[22]
g
time at all the solution points in a single-pass turning process
Wang et al, 2002 [23]
Turnin g
GA was applied for near-optimal cutting conditions for two and three pass turning process having multiples objectives
R. Saravanan et al, 2005 [24]
Turnin g
GA is used on optimizing the machining parameters for turning cylindrical stocks into continuous finished profiles
Z. Khan L B. et al, 1997 [25]
Turnin g
GA combined with SA is used to develop numerous nonlinear and non-convex machining models with the objective of determining optimal cutting conditions in turning process
S. Satishkumar et al, 2006 [26]
Turnin g
The use GA techniques for optimizing the depth of cut in multipass process
As shown in Table 1, GA technique is often used for the milling and turning processes. It handles various types of problems for cutting optimization such as to yield production cost, to optimize machining time, to maximize material removal rate, to improve product quality, to predict cutting force, to minimize profit rate, and to optimize the cutting conditions (feed, speed and depth of cut) during machining.
2.2 SA Optimization SA, originally proposed by Kirkpatrick et al. [27], is a random search technique that is able to escape local optima using a probability function. Based on iterative improvement, the SA algorithm is a heuristic method with the basic idea of generating random displacement from any feasible solution. This process accepts not only the generated solutions, which improve the objective function but also those which do not improve it with the probability function; a parameter depending on the objective function. This algorithm has two important features: perturbation scheme for generating a new solution and an annealing schedule that includes an initial and solution [28]. There are some advantages of SA optimization technique. Kirkpatrick et al [27]: (i) the SA algorithm does not need the calculation of the gradient descent that is required for most traditional optimization algorithms, which means that the SA algorithm can be applied to all kinds of objective and constraint functions, (ii) the SA algorithm with probabilistic hill-climbing characteristics can find the global minimum efficiently, instead of the objective function being trapped in a local minimum, with surrounding barriers, and (iii) the SA search is independent of the initial conditions. Z. Khan et al [25]: (i) the Simulated Annealing algorithm is very easy to program, typically it takes only a few hundred lines of computer code, and (ii) implementation of a new problem often only takes very little modifications of the existing code. Y. S. Tarng et al [29]: (i) SA algorithm does not need to calculate the gradient descent that is required for most traditional optimization algorithms, this means that the SA algorithm can be applied to all kinds of objective and constraint functions, (ii) SA
algorithm can find the global minimum more efficiently instead of trapping in a local minimum where the objective function has surrounding barriers, and (iii) SA search is independent of initial conditions. Z.G. Wang et al [18]: (i) SA is a general-purpose stochastic optimization method that has proven to be quite effective in finding the global optima for many different NP-hard combinatorial problems. Sanghamitra et al [30]: (i) SA techniques consistently outperform classical methods like gradient descent search when the search space is large, complex and multimodal. There are some limitations of implementation of SA optimization technique. Z. Khan et al [25]: (i) the amount of computational effort required by the Simulated Annealing algorithm is very large for convergence to a near-optimum solution, and (ii) may vary depending on the nature and size of the optimization problem. Rahul Swarnkar and M.K. Tiwari [28]: (i) It needs more iteration to find the best solution, (ii) possibility to return to some recently visited solution, (iiii) leads to more iteration and longer computational time, and (iv). the rate of improvement of the solution is very slow. Examples of applications of SA-based technique in cutting process for parameter optimization problem have been reported by various authors as shown in Table 2. Table 2: Applications of SA in optimizing the cutting parameters Author
Proces s
Remark
B.Y. Lee et al, 1998 [31]
Drilling
SA with a performance applied to the developed when searching for the process parameters in process
Z.G. Wang et al, 2005 [18]
Milling
SA combined with GA is used to optimize the cutting parameters for multi-pass milling process
H. Juan et al, 2003 [32]
Milling
SA method is applied to the polynomial network for determining optimal cutting parameters of production cost in HSM for SKD61 tool steels in milling process
R. Saravanan et al, 2005 [24]
Turnin g
SA is used on optimizing the machining parameters for turning cylindrical stocks into continuous finished profiles
Z. Khan L B. et al, 1997 [25]
Turnin g
SA combined with GA is used to develop numerous nonlinear and non-convex machining models with the objective of determining optimal cutting conditions in turning process
index is network optimal drilling
As shown in Table 2, SA technique is often used for turning process. It is used by researchers to handle the problem such as to optimize production cost, and to optimize cutting conditions in machining process.
2.3 TS Optimization
2.4 ACO Optimization
A TS technique proposed by Glover is a determined search technique, which is able to escape local optima by using a list of prohibited neighboring solutions known as the tabu list [33]. In addition to escaping local optima, using the tabu list, revisiting the recent neighbors recorded in the list can be avoided and the computational time is saved. TS is an improvement by-iteration process that begins with an initial feasible solution and searches for a better solution among a large pool of neighborhood. TS has two other features that make it more sophisticated: aspiration and diversification. Aspiration is a checking condition for the acceptance of a solution. It allows search to override the tabu status of a solution. This feature provides backtracking to recent solutions if they can lead to a new path to a better solution. Further it restricts the search from being trapped into a solution surrounded by tabu neighbors. Diversification is often used to explore some sub domains that may not be reached otherwise. It is carried out by redirecting the search path or restricting the search from a different initial solution [28].
Similar to PSO, ant-colony optimization (ACO) algorithms evolve not in their genetics but in their social behavior. ACO was developed by Dorigo et al. [35] based on the fact that ants are able to find the shortest route between their nest and a source of food. This is done using pheromone trails, which ants deposit whenever they travel, as a form of indirect communication. When ants leave their nest to search for a food source, they randomly rotate around an obstacle, and initially the pheromone deposits will be the same for the right and left directions. When the ants in the shorter direction find a food source, they carry the food and start returning back, following their pheromone trails, and still depositing more pheromone. An ant will most likely choose the shortest path when returning back to the nest with food as this path will have the most deposited pheromone. For the same reason, new ants that later starts out from the nest to find food will also choose the shortest path. Over time, this positive feedback (autocatalytic) process prompts all ants to choose the shorter path [36].
There are some advantages of TS optimization technique. Glover F [33]: (i) a tabu search based heuristic is regarded as a higherlevel heuristic for solving optimization problems, and (ii) it has the capability of overcoming the problem of being trapped in a local optimum, as one is encountered during the search, built into its design. Rahul Swarnkar and M.K. Tiwari [28]: (i) a shortterm memory of recently visited solutions, to escape local optima.
There are some advantages of ACO optimization technique. K. Vijayakumar et al [37]: (i) ACO algorithm can obtain a nearoptimal solution in an extremely large solution space within a reasonable computation time, and (ii) ACO is made an effective global optimization procedure by introducing a bi-level search procedure, termed a local and global search. Adil Baykasoglu et al [38]: (i) it is based on the behavior of natural ants that succeed in finding the shortest paths from their nest to food sources by communicating via a collective memory that consists of pheromone trails, and (ii) due to ant’s weak global perception of its environment, an ant moves essentially at random when no pheromone is available.
Limitations of TS are given by authors. Rahul Swarnkar and M.K. Tiwari [28]: (i) it has a deterministic nature and cannot avoid cycling. Examples of applications of TS-based technique in machining processes for parameter optimization problem have been reported by some researchers shown in Table 3. Table 3: Applications of TS in optimizing the cutting parameters
There are some disadvantages of ACO optimization technique. Adil Baykasoglu et al [38]: (i) it tends to follow a path with a high pheromone level when many ants move in a common area, which leads to an autocatalytic process, and (ii) the ant does not choose its direction based on the level of pheromone exclusively, but also takes the proximity of the nest and of the food source, respectively, into account; this is allows the discovery of new and potentially shorter paths.
Author
Proces s
Remark
Farhad Kolahan and Ming Liang, 2000 [34]
Drilling
TS is used to minimize the total processing cost for hole-making in drilling process
Examples of applications of ACO-based technique in machining processes for parameters optimization problem have been reported by some researchers shown in Table 4.
N. Baskar et al. 2005 [17]
Milling
TS is used to determine optimum machining based on maximum profit in milling process
Table 4: Applications of ACO in optimizing the
R. Saravanan et al, 2005 [24]
Turnin g
TS is used on optimizing the machining parameters for turning cylindrical stocks into continuous finished profiles
As shown in Table 3, TS technique is less used by researchers to solve the optimization problem for machining process. It is used for the machining optimization problems such as to minimize the total processing cost and to maximize the profit rate in machining processes.
cutting processes Author
Proces s
Remark
N. Baskar et al, 2005 [17]
Milling
ACO is used to determine optimum machining based on maximum profit in milling process
R. Saravanan et al, 2005 [24]
Turnin g
ACO is used on optimizing the machining parameters for turning cylindrical stocks into continuous finished profiles
K. Vijayakumar
Turnin g
ACO is used to propose a new optimization technique for solving
multi-pass problems
et al, 2003 [37]
turning
optimization
Yi-Chi Wang, 2007 [39]
Turnin g
Demonstrates that the optimal solution using ACO as found by K. Vijayakumar et al, 2003 is not valid
S. Satishkumar et al, 2006 [26]
Turnin g
The use ACO techniques for optimizing the depth of cut in multipass turning
There are some disadvantages of PSO optimization technique. Bilal Alatas et al [44] stated that PSO: (i) different numbers of iterations may also be required to reach the same optimal values. Suganthan PN [48]: (i) sometimes it has a slow fine-tuning ability of the solution quality. Examples of applications of PSO-based technique in the optimization of cutting parameters during machining have been reported by various authors as listed in Table 5.
Table 5: Applications of PSO in optimizing the cutting parameters
As shown in Table 4, ACO technique is often used in solving turning operation problems. It can be used to maximize profit rate, and to optimize cutting conditions in machining processes.
2.5 PSO Optimization PSO is a relatively new technique, first presented in 1995 by R.C. Eberhart and J. Kenerdy [40] for optimization of continuous nonlinear functions. Jim Kennedy [41] discovered the method through simulation of a simplified social model, the graceful but unpredictable choreography of a bird flock. PSO is a very simple concept, and paradigms are implemented in a few lines of the computer code. It requires only primitive mathematical operators, so is computationally inexpensive in terms of both memory requirements and speed. These characteristics are of immense value to the application situation at hand. PSO has been recognized as an evolutionary computation technique [42] and has features of both genetic algorithms (GA) and evolution strategies [43]. It is similar to a GA in that the system is initialized with a population of random solutions. However, unlike GA, each population individual is also assigned a randomized velocity, in effect, flying them through the solution hyperspace. As is obvious, it is possible to simultaneously search for an optimum solution in multiple dimensions. Also, since each particle keeps track of its coordinates in hyperspace which are associated with the best fitness it has achieved so far, as well as the overall best value obtained by any member of the population. There are some advantages of PSO optimization technique. Bilal Alatas et al [44] stated that PSO: (i) a simple stochastic search method and requires little memory, (ii) it has also fast converging characteristics and more global searching ability at the beginning of the run and a local searching near the end of the run, and (iii) can solve discontinuous, multimodal, and non-convex problems. Yinggan Tang and Xinping Guan [45]: (i) it has been proved to be a powerful tool for solving system optimization problem, especially with non-smooth objective function, (ii) PSO does not need the derivative information about the objective function, (iii) PSO adopts velocity position model other than complex genetic operators, (iv) PSO can be easily implemented and converges quickly, and (v) PSO is very suitable to deal with most of real engineering application problems. R.E. Perez and K. Behdinan [46]: (i) it easiness of implementation makes it more attractive as it does not required specific domain knowledge information, internal transformation of variables or other manipulations to handle constraints and (ii) it is a population- based algorithm, so it can be efficiently parallelized to reduce the total computational effort.
Author
Proces s
Remark
Jialin Zhou et al, 2006 [48]
Boring
The implementation of PSO for the self learning of the neural networks to perform diameter error prediction in a boring machining
V. Tandon et al, 2002 [49]
Milling
PSO technique coupled with ANN, is proposed and implemented to efficiently and robustly optimize multiple machining parameters simultaneously for the case of milling
H. ElMounayri et al, 2005 [50]
Milling
PSO algorithm is used to optimize feed, and axial and radial depths of cut for CNC ball end milling
N. Baskar., et al. 2005 [17]
Milling
PSO is used to determine optimum machining based on maximum profit in milling process
R. Saravanan et al, 2005 [24]
Turnin g
PSO is used on optimizing the machining parameters for turning cylindrical stocks into continuous finished profiles
As shown in Table 5, PSO technique is often used by researchers to solve the optimization problem for milling process. It is often used to predict diameter error, to maximize profit rate, and to optimize cutting conditions in machining processes.
3. CONCLUSION This paper has discussed five optimization techniques that are classified as a non-conventional technique during machining which are GA, SA, TS, ACO and PSO. Advantages, limitations and application examples of each technique have been discussed in relation to the main machining processes such as turning, drilling and milling. From the review, it can be concluded that all the non-conventional approaches were suitable and had the potential to be applied for cutting parameters optimization problems during machining. Based on the review, it was found that GA is widely used by most researchers. It may be due to the fact that GA was amongst the earliest technique introduced and familiar by most researchers. Additional, the GA technique can be integrated with others non-
conventional approaches to produce a new technique such as the parallel genetic simulated annealing (PGSA) implemented by Z.G. Wang et al [18]. It is a integration of GA and SA techniques used to optimize the cutting parameters for multi-pass milling process. Further review on the applications of GA technique indicates that the GA technique is used for the various optimization objectives which include minimizing production cost, machining time, material removal rate, improving product quality and profit margin. It was also found that the GA technique could be effectively applied for different types of machining approaches such as single-pass, two-pass, three-pass and multiple-pass for turning and milling operations.
4.0 REFERENCES [1] R. Siva Sankar, P. Asokan, R. Saravanan, S. Kumanan, G. Prabhaharan (2007) Selection of machining parameters for constrained machining problem using evolutionary computation. International Journal Advanced Manufacturing Technology 32:892–901. [2] Indrajit Mukherjee, Pradip Kumar Ray (2006) A review of optimization techniques in metal cutting processes. Computer & Industrial Engineering 50:15-34. [3] Aman Aggarwal, Hari Singh (2005) Optimization of machining techniques- A retrospective and literature review. Sadhana Journal (India) 30:699-711. [4] Joze Balic, Boris Abersek (1997) Model of an integrated intelligent design and manufacturing system. Journal of Intelligent Manufacturing 8:263-270. [5] F. Cus, M. Milfelner, J. Balic (2006) An intelligent system for monitoring and optimization of ball-end milling process. Journal of Materials Processing Technology 175: 90–97. [6] Srinivas, M. and Patnaik Lam, M. (1994) Genetic algorithms: a survey. IEEE Computer Journal 18:17-26. [7] Jian Dong and Sreedharan Vijayant (1997) Manufacturing feature determination and extraction-Part I: Optimal volume segmentation. Computer-Aided Design 29:427-440. [8] Manolas D. A., Gialamas T. P., Frangopoulos C. A, Tsahalis D. T (1996) A genetic algorithm for operation optimization of an industrial cogeneration system. Computers Chem. Engineering 20:1107-1112. [9] Franci Cus, Joze Balic (2003) Optimization of cutting process by GA approach. Robotic and Computer Integrated Manufacturing 19:113-121. [10] Z.G. Wang, Y.S. Wong, M. Rahman (2005) Development of a parallel optimization method based on genetic simulated annealing algorithm. Parallel Computing 31:839-857. [11] P. Palanisamy, I. Rajendra, S. Shanmugasundram (2007) Optimization of machining parameters using genetic algorithm and experimental validation for end-milling operations. International Journal Advanced Manufacturing Technology 32:664-655. [12] M.S. Shunmugam, S.V. Bhaskara Reddy, T.T. Narendran (2000) Selection of optimal conditions in multi-pass facemilling using a genetic algorithm. International Journal of Machine Tools & Manufacture 40:401–414.
[13] Krimpenis, A., Vosniakos, G.C (2002) Optimization of multiple tool NC rough machining of a hemisphere as a genetic algorithm paradigm application. International Journal of Advanced Manufacturing Technology 20:727–734. [14] Cus, F., Balic, J. (2003) Optimization of cutting process by GA approach. Robotics and Computer Integrated Manufacturing 19:113–121. [15] F. Cus, M. Milfelner, J. Balic (2006) An intelligent system for monitoring and optimization of ball-end milling process. Journal of Materials Processing Technology 175: 90–97. [16] M. Kovacic, J. Balic, M. Brezocnik (2004) Evolutionary approach for cutting forces prediction in milling. Journal of Materials Processing Technology 155–156:1647–1652. [17] N. Baskar, P. Asokan, R. Saravanan, G. Prabhaharan (2005) Optimization of machining parameters for milling operations using non-conventional methods. International Journal Advanced Manufacturing Technology 25:1078–1088. [18] Z.G. Wang, M. Rahman, Y.S. Wong, J. Sun (2005) Optimization of multi-pass milling using parallel genetic algorithm and parallel genetic simulated annealing. International Journal of Machine Tools & Manufacture 45:1726–1734. [19] R. Saravanan, P. Asokan, M. Sachithanandam (2001) Comparative analysis of conventional and non-conventional optimisation techniques for CNC turning process. International Journal of Advanced Manufacturing Technology 17: 471-476. [20] Ramo’n Quiza Sardin’as, Marcelino Rivas Santana, Eleno Alfonso Brindis (2006) Genetic algorithm-based multiobjective optimization of cutting parameters in turning processes. Engineering Applications of Artificial Intelligence 19:127–133. [21] Onwubolu, G. C., Kumalo, T. (2001) Optimization of multipass turning operation with genetic algorithm. International Journal of Production Research 39(16): 3727–3745. [22] Chowdhury, K., Pratihar, D. K., Pal, D. K (2002) Multiobjective optimization in turning—using GA algorithm. Journal of the Institute of Engineers (India) 82:37–44. [23] Wang, X., Da, Z. J., Balaji, A. K., & Jawahir, I. S., Performance-based optimal selection of cutting conditions and cutting tools in multi-pass turning operations using genetic algorithms. International Journal of Production Research, (2002): 40(9): 2053–2065. [24] R. Saravanan, R. Siva Sankar, P. Asokan, K. Vijayakumar, G. Prabhaharan (2005) Optimization of cutting conditions during continuous finished profile machining using nontraditional techniques. International Journal Advanced Manufacturing Technology 26:30–40. [25] Z. Khan L B., Prasad, T. Singh (1997) Machining condition optimization by genetic algorithms and simulated annealing. Computers Operations Research 24(7):647-657. [26] S. Satishkumar, P. Asokan, S. Kumanan (2006) Optimization of depth of cut in multi-pass turning using nontraditional optimization techniques. International Journal Advanced Manufacturing Technology 29:230–238.
[27] Kirkpatrick F, Gelatte CD, Vecchi MP (1983) Optimization by simulated annealing. Science 220:671–780.
International Journal of Management Science (Omega) 34:385 – 396.
[28] Rahul Swarnkar, M.K. Tiwari (2004) Modeling machine loading problem of FMSs and its solution methodology using a hybrid tabu search and simulated annealing-based heuristic approach. Robotics and Computer-Integrated Manufacturing 20:199–209.
[39] Yi-Chi Wang (2007) A note on ‘optimization of multi-pass turning operations using ant colony system’. International Journal of Machine Tools & Manufacture 47:2057–2059.
[29] Y. S. Tarng, S. C. Ma, L. K. Chung (1995) Determination of optimal cutting parameters in wire electrical discharge machining. International Journal of Machine Tools & Manufacture 35(12):1693-170. [30] Sanghamitra Bandyopadhyay, Sankar K. Pal, C.A. Murthy (1998) Simulated annealing based pattern classification. Journal of Information Sciences 109: 165-184. [31] B.Y. Lee, H.S. Liu, Y.S. Tarng (1998) Modeling and optimization of drilling process. Journal of Materials Processing Technology 74:149–157. [32] H. Juan, S.F. Yu, B.Y. Lee 2003) The optimal cuttingparameter selection of production cost in HSM for SKD61 tool steels. International Journal of Machine Tools & Manufacture 43:679–686. [33] Glover F. (1990) Tabu search: a tutorial. Interfaces, 20(4):74–94. [34] Farhad Kolahan, Ming Liang (2000) Optimization of holemaking operations: a tabu-search approach. International Journal of Machine Tools & Manufacture 40:1735–1753. [35] Dorigo M, Maniezzo V, Colorni (1996) A Ant system: optimization by a colony of cooperating agents. IEEE Trans Syst Man Cybern, 26(1):29–41.
[40] R.C. Eberhart, J. Kennedy (1995) A new optimizer using particle swarm theory. Proceedings of the Sixth International symposium on Micro Machine and Human Science 39–43. [41] J. Kennedy (1998) The behavior of particles. Proceedings of the 7th ICEC 581–589. [42] P.J. Angeline (1998) Evolutionary optimization versus particle swarm optimization: philosophy and performance differences. Proceedings of the 7th ICEC 601–610. [43] R.C. Eberhart, Y. Shi (1998) Comparison between genetic algorithms and particle swarm optimization. Proceedings of the 7th ICEC 611–616. [44] Bilal Alatas, Erhan Akin, A. Bedri Ozer (2007) Article in Press: Chaos embedded particle swarm optimization algorithms. Chaos, Solutions and Fractals. [45] Yinggan Tang, Xinping Guan (2007) Article in Press: Parameter estimation for time-delay chaotic system by particle swarm optimization. Chaos, Solitons and Fractals. [46] R.E. Perez, K. Behdinan, (2007) Particle swarm approach for structural design optimization. Computers and Structures 85:1579–1588. [47] Suganthan PN (1999) Particle swarm optimizer with neighborhood operator. Proceedings of the 1999 congress of evolutionary computation IEEE Press 3:1958–62
[36] Dorigo M, Gambardella LM. (1997) Ant colonies for the traveling salesman problem. Biosystems Elsevier Science 43(2):73–81.
[48] Jialin Zhou, Zhengcheng Duan, Yong Li, Jianchun Deng, Daoyuan Yu (2006) PSO-based neural network optimization and its utilization in a boring machine. Journal of Materials Processing Technology 178:19–23.
[37] K. Vijayakumar, G. Prabhaharan, P. Asokan, R. Saravanan (2003) Optimization of multi-pass turning operations using ant colony System. International Journal of Machine Tools & Manufacture 43:1633–1639.
[49] V. Tandon, H. El-Mounayri, H. Kishawy (2002) NC end milling optimization using evolutionary computation. International Journal of Machine Tools & Manufacture 42:595–605
[38] Adil Baykasoglu, Turkay Dereli, Ibrahim Sabuncu (2006) An ant colony algorithm for solving budget constrained and unconstrained dynamic facility layout problems. The
[50] H. El-Mounayri, H. Kishawy, J. Briceno (2005) Optimization of CNC ball end milling: a neural networkbased model. Journal of Materials Processing Technology 166:50–62.
