Application of Artificial Intelligence Methods of Tool Path Optimization in CNC Machines

Application of Artificial Intelligence Methods of Tool Path Optimization in CNC Machines

Application of Artificial Intelligence Methods of Tool Path Optimization in CNC Machines

S. Bharath

Department of Mechanical Engineering, Student of PRCET

K. Natraj

Department of Mechanical Engineering, Student of PRCET

Abstract: Today, in most of metal machining process, Computer Numerical Control (CNC) machine tools have been very popular due to their efficiencies and repeatability to achieve high accuracy positioning. One of the factors that govern the productivity is the tool path travel during cutting a work piece. It has been proved that determination of optimal cutting parameters can enhance the machining results to reach high efficiency and minimum the machining cost. In various publication and articles, scientist and researchers adapted several Artificial Intelligence (AI) methods or hybrid method for tool path optimization such as Genetic Algorithms (GA), Artificial Neural Network (ANN), Artificial Immune Systems (AIS), Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO). This study presents a review of researches in tool path optimization with different types of AI methods that show the capability of using different types of optimization methods in CNC machining process. Keywords: Artificial intelligence, CNC machines, machining, optimization, tool path

INTRODUCTION

Recently, the advanced of computer system and improvement of semiconductors in various field have lead to the enhancement of machining process especially that involved Computer Numerical Control (CNC) (Li and Frank, 2006). The CNC machining are used mainly in manufacturing areas such as machining parts for automotive tools, jig and mold. The main advantage of CNC machining is catch high machining accuracy with easily programming and repeatability in complicated parts machining (Al-Kindi and Zughaer, 2012; Safaieh et al., 2013).

The conventional ways of selecting the tool path or programming the NC code used data from machining handbooks and the knowledge of programmer for optimal processing (El-Midany et al., 2006; Suh and Lee, 1998). However, the conventional or traditional NC programming when compared to the modern CNC machining has many disadvantages for instance increasing time and cost production and, decreasing accuracy and quality of the workpiece (Liu et al., 2013; Lasemi et al., 2010).

Nowadays, most of the CNC machines tools are programmed automatically using Computer Aided Manufacturing (CAM) software instead of manual program input in order to reduce programming time and to avoid human errors (Mattson and Mattson, 2009; Suneel and Pande, 2000). Therefore, one of the most essential factors in optimizing the machining process is the selection of tool path.

For example, before a machinist performs an optimal cutting process using CNC machine tools, the tool path for tool processing should be determined before the actual tool processing (Zhang et al., 2011; Mayor and Sodemann, 2008). In general, the current way of tool path selection is based on the set of ordinary path such as zig, zig-zag, radial, spiral tool paths etc (López de Lacalle et al., 2007).

The objective of this study is to review of prior works on tool path optimization in CNC machines in order to classify different types of machining process with CNC machine tools. First we describe an overview of optimization methods. In the next section, collection of all previous research in tool path with different types of Artificial Intelligence (AI) optimization methods will be presented to show the ability of various methods in optimizing machining process.

DIFFERENT AI OPTIMIZATION METHOD

Different types of optimization methods in AI have been adapted in many previous researches to find optimum parameters for machining process. In general, AI is a branch of Computer Science (CS) which are developed and emerged in the mid-1950s that deals with the intelligence of machines (Jones, 2008; El-Mounayri et al., 2002). Since then, it had generated numbers of powerful tools that have practical usage especially in engineering in order to solve difficult problems which normally need the secrets of Natural Intelligence (NI). The research in AI is designed for the simulation of NI by making the machines to be intelligent (Zhong, 2008). In the next section we will describe separately of each AI methods used in tool path optimization.

Genetic algorithms: A Genetic Algorithm (GA) adapts the manipulation of a population of potential solutions for optimize problem (Agrawal et al., 2006; Chan et al., 2005). In 1970s, Holland (1992) first proposed the genetic algorithms, GA stand the one of the interesting investigation method in search algorithms (Man et al., 1996). GA has three main operators, crossover, reproduction and mutation. GA method use binary encoded way to coding the process parameters in optimization of machining process. In this method important section is choose appropriate parameters and constraints for the

algorithms to perform efficiently. Until today, the GA has been successfully applied for optimization problem in various fields. For instance, the problem formulation that used Travel Salesman Problem (TSP) can be solved by GA. TSP is a Non-deterministic Polynomial time (NP) -hard problem and one of the most widely studied combinatorial optimization problems (Langevin et al., 1990; Laporte, 1992). It is based on the task to find the shortest possible route for any number of cities and the costs of travelling from any city to any other city (Qudeiri et al., 2006).

Artificial neural network: ANN is a computational model inspired from natural neurons concept. Since the first neural model by McCulloch and Pitts (1943), there have been developed hundreds of diverse models considered as ANNs (McCulloch and Pitts, 1943; Karayel, 2009). Different types of ANN such as feed forward, radial basis function and Kohonen self- organizing neural networks are used to model real neural networks to study the behavior and control in animals and machines (Bose and Liang, 1996; Ghosh et al., 2007). Nowadays, there also are ANNs that are used for engineering purposes, for example pattern recognition, forecasting and data compression (Ghosh et al., 2007; Bose and Liang, 1996; El-Mounayri et al., 2005; Yang and Zhuang, 2010).

Artificial immune systems: AIS are intelligence and adaptive systems inspired by observed immune function, principle and models, which are applied to toward real- world problem solving (Ãœlker et al., 2009; De Castro and Timmis, 2002). Two generations of AIS are currently in use, with the first generation relying on simplified immune models and the second generation applying interdisciplinary collaboration to develop of the immune system and hence produce more complex models (Li et al., 2011). In variety of problem can applied both generation of algorithms, including anomaly detection, dependable systems, pattern recognition, optimization and robotics (Wang et al., 2011).

Ant colony optimization: The ACO is consequences of research based on computational intelligence approaches used for solving combinatorial optimization problems. ACO is stimulated by the foraging behavior of ants and their natural aptitude to find the shortest path from a food source to their nest (Dorigo and Blum, 2005; Blum, 2005; Dorigo et al., 1996; Chandra Mohan and Baskaran, 2012). This characteristic of real ant colonies is exploited in ACO algorithms in recent techniques for approximate optimization. However, ACO one of the youngest meta- heuristics techniques. The number of ACO applications is covered large area such as industrial, multi-objective and bioinformatics problems (Kanan and Faez, 2008; Yang and Zhuang,2010).

Particle swarm optimization: PSO is an optimization technique based on the behavior of a swarm of insects

such as ants, bees or a flock of birds which is originally proposed by Kennedy and Eberhart (1995). In PSO, each potential solution is assigned a randomized rapidity called particles which are flown through hyperspace (Shi et al., 2007). PSO is evolutionary technique similar to GA because both are population based and are equally affective. Many studies have successfully employed PSO and its variants to optimize process parameters of several manufacturing processes such as drilling, welding and turning (Eberhart and Kennedy, 1995; Kanan and Faez, 2008; Kennedy and Eberhart, 1995).

LITERATURE REVIEW ON TOOL PATH OPTIMIZATION

There are quite numbers of literature related to tool path optimization by AI can be found. Most of them used GA, ANN, ACO, AIS and PSO optimization methods. For instance, Chen and Tseng (1996) proposed of using GA for planning of a near-optimum tool path and location of a workpiece. They tried to reduce the processing time required for a robot to complete its work on a workpiece (Chen and Tseng, 1996). In addition, Dereli et al. (2001) used GA to determine the optimal cutting parameters for increasing productivity and competitiveness.

Castelino et al. (2003) presented an algorithm for minimizing the airtime for milling process by optimal connected diverse tool path divisions. They combined the TSP and Sequential Ordering Problem (SOP) for formulation as a generalized with precedence constraints. This algorithm used in an automated process planning system, also can be applied to other parts of path planning optimization (Castelino et al., 2003). Moreover Cus and Balic (2003) proposes a new approaches on GA for solving the optimization problem is both effective and efficient of the cutting parameters in machining operations. Finally this proposed approach will lead to reduction in production cost, production time and improvement of production quality (Cus and Balic, 2003).

For free form surface or sculptured surfaces, Agrawal et al. (2006) presented the minimization of machining time while implementing Iso-scallop machining. The positioning of the primary Master Cutter Path (MCP) was achieved through application of GA.

Qudeiri et al. (2006) attempted to find an efficient solution approach to determine the best sequence of operations for a set of holes that are located in disproportionate locations and diverse levels. Oysu and Bingul (2007) proposed of using GA for different processing techniques in tool path optimization in order to minimize the unproductive air during machining. They adapted GA with pre and post-processing techniques to reduce the tool paths for optimize airtime travel on three axis Cartesian routers during milling of wood materials. Their results show that GA with pre and post-processing techniques gave shorter computation time 33.7% which

was better path solution rather than standard GA. Their study focused on finding the shortest Cutting Tool Travel Path (CTTP) for Hole-Cutting Operations (HCO) with GA and formulated CTTP as a special case of the TSP (Oysu and Bingul, 2007). Also Queiri et al. for find the best sequence of operations to achieves the shortest CTTP used GA (Qudeiri et al., 2007).

In milling machining Palanisamy et al. (2007) used GA optimization technique for find the optimal process parameters. The obtained results indicated that the optimized parameters are capable to reach more efficiently result (Palanisamy et al., 2007). Also Saravanan and Janakirman (2007) used GA for find minimum machining time by optimizing machining parameters such as cutting speed, tool path and feed rate. Moreover for increase production rate and reduce production cost Durán et al. (2007) proposed Non- dominated Sorting GA (NSGA).

In the process parameters optimization of tangential turn-milling machining Savas and Ozay (2008) used GA method. In the result for surface roughness optimization, investigate on diverse process parameters such as depth of cut, workpiece speed, tool speed and feed rate. Oysu and Bingul (2007) also used heuristic algorithms such as Simulated Annealing (SA), GA and hybrid algorithm (hybrid-GASA) which was applied to the tool path optimization problem in order to minimize the airtime during machining. The comparison between their performances was based on shortest path and minimum airtime which shows that the hybrid algorithm gave better results than other heuristic algorithms alone (Oysu and Bingul, 2009).

Liu et al. (2013) presented the optimum path of CNC turret typing system for reducing the changing tools times. They optimized the tool movement routes to make up the deficiency of CNC turret typing machine production efficiency. They used the polynomial model based on asymmetric traveling salesman problem and GA to solve the path optimization problem. The experimental result showed that the GA can decrease the processing time and reduced the air traveling without changing the machines hardware through sensible arrangement of the varying and moving tools path (Liu et al., 2011).

On the other hand, Balic and Korosec (2002) presented ANN approach for prediction of milling tool- path strategy. Their proposed the ANN with sequence appropriation to find the best surface quality of machining surface at the free surface machining. In their case, the primary technological aim was to generate the best possible surface quality of machined surface (Balic and Korosec, 2002). Also Zuperl and Cus (2003) employed the ANN approach to increase the productivity and cost reduction for complex optimization of cutting parameters. Their proposed ANN is able to optimize the cutting parameters in order to find efficient machining process (Zuperl and Cus, 2003).

Moreover Zuperl et al. (2004) for complex

optimization of cutting parameters for turning operation used hybrid optimization ANN and OPTIS routine. The result compare with other algorithms and approaches are found the better perform in term of the objective function values. Since the hybrid optimization can obtain near optimal solution for machining parameter selection of complex machined parts (Zuperl et al., 2004).

In the other research for high speed machining and high resolution manufacturing by Ãœlker E et al. (2009) which utilized new and powerful AI tool called Artificial Immune Systems (AIS) with Non-Uniform Rational B- Spline (NURBS). Their developed tool patches for reducing machining time and increased accuracy for a sculptured surface (Ãœlker et al., 2009). The result of their work demonstrated that the proposed AIS based tool path interval and step-size algorithm for NURBS can reduce the machining time and data while increasing the machining resolution. In minimization surface roughness of milling operation Mahdavinejad et al. (2012) employed AIS. In this study for find optimum parameters focus on different parameters such as cutting speed, depth of cutting and feedrate.

The researches of utilizing ACO also have taken interest from several researchers. For example, in minimize the summation of tool switching time and tool airtime in hole-making operation, Ghaiebi and Solimanpur (2007) used ants algorithm on TSP problems to solve the proposed mathematical model. In cutting optimization for multi pass turning operation Jing and Yingxue (2008) employed modified Machining ACO (MCACO). From the experiment results, it was found optimum process parameters to minimize the production unit cost (Jing and Yingxue, 2008). Meanwhile in optimize the process parameters of turning machining Cus et al. (2009) proposed ACO. In this research, the ACO technique focused on the reduce production cost and increase productivity. This approach used Adaptive Neuro-Fuzzy Inference System (ANFIS) and an ACO method to achieve the optimal parameters (Cus et al., 2009). Similarly, Abbas et al. (2010) aplied the ACO algorithm to find the optimum path planning in CNC drilling machines for large number of holes. The holes were arranged in a rectangular matrix and they used two modifications and basic ACO algorithm to take advantage of the rectangular layout of the holes. Their result shows that their modified ACO algorithms worked efficiently than the basic ACO algorithm in reduction of total tool travel distance (Abbas et al., 2010). Medina-Rodriguez et al. (2012) used Parallel ACO in order to obtain an optimal tool travel path and determine the best sequence of G commands for a set of holes in a printed circuit board. They adapted ACO application as special case of the TSP (Medina- Rodriguez et al., 2012). It confirmed that the combination of algorithm based on Parallel ACO and TSP can be applied to any similar problem, such welding and tapping. Also Wang et al. (2012) focused in tool path

optimization for group of holes drilling. In this research used graph theory of TSP based on ACO and Lin- Kernighan (LK) algorithm. In their result, they improved the precision and efficiency of the drilling process (Wang et al., 2012).

Meanwhile for drilling operation with CNC machines, Onwubolu and Clerc (2004) formulated the drilling operations as a TSP and used PSO to solve it. The technique of their proposed PSO required few control variables. The advantages of their technique are that it is multipurpose, robust and easy to use and hence reduction of production costs (Onwubolu and Clerc, 2004). Zperl et al. (2007) for optimize process parameters in milling machining employed ANN method for predict cutting force in during of machining and used PSO to find optimum process machining such as cutting speed and feed rate. Also Gao et al. (2008) in milling machining proposed PSO method and optimization algorithm for Cutting Parameters Optimization (CPO) to find optimum process parameters.

Junmei and Gaohua (2009) employed PSO method to find optimum process parameters in turning machining. In this study researcher find optimum cutting speed and feed rate which influence with increase machining accuracy and decrease machining time and machining cost (Junmei and Gaohua, 2009). In the optimization process parameters of CNC end milling Prakasvudhisarm et al. (2009) proposed PSO method to optimize characteristics of roughness and its factors which captured by Support Vector Machine (SVM). The result showed corporation between this two methods reached to the high surface quality and increase productivity (Prakasvudhisarn et al., 2009). In multi- pass turning Srinivas et al. (2009) employed PSO for selecting optimum machining parameters. In this research, researcher focus on reduce production cost and machining time (Srinivas et al., 2009). Also in optimize process of multi-pass turning Lee Yi and Ponnambalam used PSO. In the result for minimization unit production cost, PSO method compare with GA and SA methods (Zheng and Ponnambalam, 2010).

Also Hsieh and Chu (2012) proposed an Advanced Particle Swarm Optimization (APSO) and Fully Informed Particle Swarm Optimization (FIPSO) algorithms for a 5- axis milling machine to improve the quality of optimal solutions and search efficiency of the machining process. From the result, they found that FIPSO is most effective in reducing the error due to the capability to determine the next move with a particle utilizes information from all its neighbors rather than just the best one in PSO.

Other resech by Klancnik et al. (2012) in the automatic programming of a CNC milling machining that used PSO shows that the method can achieve a reduction machining costs and increased productivity in machining process. Also for find optimum machining parameters in face milling on aluminum material Raja and Baskar used

PSO. In the result, the predicted roughness using PSO, shows the better result than the actual roughness (Bharathi Raja and Baskar, 2012).

OPTIMIZATION METHODS FOR MACHINING

In this study, based on the literatures that we surveyed, various types of optimization method used by researchers in reduction of cost, tool changing time and tool travel path, minimizing machining time, airtime, computation time and increase productivity and surface roughness as shown in Table 1. GA and PSO optimization methods principally used to improve machining parameters respectively as shown in Fig. 1.

14

Number of researcher

12

10

8

6

4

2

0

GA AIS ANN ACO PSO

Optimization methods

Fig. 1: Number of researcher used different optimization methods

Table 1: Shows which optimization methods used for improve machining factors in previous research Optimization

methods

——————————————————————————————————————————-

Authors, year

Chen and Tseng (1996) Dereli et al. (2001)

Balic and Korosec (2002) Zuperl and Cus (2003) Cus and Balic (2003) Castelino et al. (2003)

Onwubolu and Clerc (2004) Zuperl et al. (2004) Agrawal et al. (2006) Qudeiri et al. (2006)

Oysu and Bingul (2007) Qudeiri et al. (2007)

Ghaiebi and Solimanpur (2007) Palanisamy et al. (2007) Zperl et al. (2007)

Saravanan and Janakiraman (2007) Gao et al. (2008)

Savas and Ozay (2008) Jing and Yingxue (2008) Oysu and Bingul (2009) Junmei and Gaohua (2009)

Factors

GA AIS ANN

ACO PSO

—————————————————————————————————————————————–

	Minimizing machining	Increase	Reduction	Minimizing	Reduction tool travel	Shorter computation	Reduce tool	Increase surface
Authors, year	time	productivity	of cost	airtime	path	time	changing time	quality
Chen and Tseng (1996)
Dereli et al. (2001)
Balic and Korosec (2002) Zuperl and Cus (2003)
Cus and Balic (2003)
Castelino et al. (2003) Onwubolu and Clerc (2004)
Zuperl et al. (2004)
Agrawal et al. (2006)
Qudeiri et al. (2006)
Oysu and Bingul (2007)
Qudeiri et al. (2007)
Ghaiebi and
Solimanpur (2007)
Palanisamy et al. (2007)
Zperl et al. (2007)
Saravanan and
Janakiraman (2007)
Gao et al. (2008)
Savas and Ozay (2008)
Jing and Yingxue (2008)
Oysu and Bingul (2009) Junmei and Gaohua (2009)

Optimization methods

——————————————————————————————————————————-

Authors, year GA AIS ANN ACO PSO Cus et al. (2009)

Ãœlker et al. (2009)

Prakasvudhisarn et al. (2009) Srinivas et al. (2009)

Zheng and Ponnambalam (2010)

Abbas et al. (2010) Liu et al. (2011)

Medina-Rodriguez et al. (2012)

Wang et al. (2012) Hsieh and Chu (2012)

Mahdavinejad et al. (2012) Bharathi Raja and Baskar (2012) Klancnik et al. (2012)

Table 1: Continue
					Factors
					—————————————————————————————— ——————————————————
	Minimizing				Reduction Shorter Reduce tool Increase
	machining	Increase	Reduction	Minimizing	tool travel computation changing surface
Authors, year	time	productivity	of cost	airtime	path time time quality
Cus et al. (2009) Ãœlker et al. (2009)
Prakasvudhisarn
et al. (2009)
Srinivas et al. (2009)
Zheng and Ponnambalam (2010)
Abbas et al. (2010)
Liu et al. (2011)
Medina-Rodriguez
et al. (2012)
Wang et al. (2012)
Hsieh and Chu (2012) Mahdavinejad et al.
(2012)
Bharathi Raja and
Baskar (2012)
Klancnik et al. (2012)

20

18

Number of each factors

16

14

12

10

8

6

4

2

Minimizing machining time

Increase productivity

Reduction of cost

Minimizing airtime

Reduce tool travel path

Shorter computation time

Reduce tool changing time

Increase surface quality

0

Factors

Fig. 2: Number of each factors optimized with researcher

Other method such as ANN was used to increase the productivity, surface quality and reduction of cost. On the other hand, PSO method was adapted to reduce tool travel path, reduction cost and minimizing machining time. ACO method was employed for minimizing machining time and air time, reduction cost production, tool travel path and tool changing time and increase productivity. Also small size of researcher employed AIS method for minimizing machining time and increase surface quality. According to the Fig. 2, in recent years researchers focused on improving four parameters, minimizing machining time, reduction of cost and tool travel path and increase surface

quality on CNC machining for increasing the machining efficiency.

CONCLUSION

This study presented a survey of prior studies on tool path optimization with different types of methods such as ANN, GA, ACO, AIS and PSO. From our review, GA and PSO are largely used to optimize machining efficiency. When compared with other methods GA and PSO was most widely adapted to improve machining process. It can be ascertained from our results, the GA has been successfully applied for many optimization problem in various parameters related to tool path and effective in improving the robustness of feature selection over a range of problems. Meanwhile the ACO method mainly utilized in minimizing machining time, airtime and reduction of tool travel path which targeted to find the shortest path in machining. On the other hand, the ANNs were used to increase productivity, increase surface quality and reduction cost. Other method PSO was mainly employed for the reduction of tool travel path, cost and minimization of machining time. From our review, the most important factor was the machining time because we found that all the AI optimization methods applied in purpose of minimizing it. This is because the machining time is an extremely effective factor in improving

machining process.

For future study we suggest to use hybrid methods to find optimal machining parameters. Hybrids methods include two or more optimization methods in one research to find optimal machining parameters. For instate, use GA and ANN for reduce machining time, cost and computation time and increase productivity, surface

quality together at the same time. In this type of research when compare to the other research used one optimization method the hybrid way appear more optimal result.

REFERENCES

[1] Abbas, A.T., M.F. Aly and K. Hamza, 2010. Optimum drilling path planning for a rectangular matrix of holes using ant colony optimisation. Int. J. Prod. Res., 49(19): 5877-5891.

[2] Agrawal, R.K., D.K. Pratihar and A.R. Choudhury, 2006. Optimization of CNC isoscallop free form surface machining using a genetic algorithm. Int. J. Mach. Tool. Manu., 46(7-8): 811-819.

[3] Al-Kindi, G. and H. Zughaer, 2012. An approach to improved CNC machining using vision-based system. Mater. Manuf. Process., 27(7): 765-774.

[4] Balic, J. and M. Korosec, 2002. Intelligent tool path generation for milling of free surfaces using neural networks. Int. J. Mach. Tool. Manu., 42(10): 1171-1179.

[5] Bharathi Raja, S. and N. Baskar, 2012. Application of particle swarm optimization technique for achieving desired milled surface roughness in minimum machining time. Expert Syst. Appl., 39(5): 5982-5989.

[6] Blum, C., 2005. Ant colony optimization: Introduction and recent trends. Phys. Life Rev., 2(4): 353-373.

[7] Bose, N.K. and P. Liang, 1996. Neural Network Fundamentals with Graphs, Algorithms and Applications. McGraw-Hill, Inc., Hightstown, NJ, USA, ISBN: 0-07-006618-3.

[8] Castelino, K., R. D'Souza and P.K. Wright, 2003. Toolpath optimization for minimizing airtime during machining. J. Manuf. Syst., 22(3): 173-180.

[9] Chan, F.T.S., T.C. Wong and L.Y. Chan, 2005. A genetic algorithm-based approach to machine assignment problem. Int. J. Prod. Res., 43(12): 2451-2472.

[10] Chandra Mohan, B.C. and R. Baskaran, 2012. A survey: Ant colony optimization based recent research and implementation on several engineering domain. Expert Syst. Appl., 39(4): 4618- 4627.

[11] Chen, C.J. and C.S. Tseng, 1996. The path and location planning of workpieces by genetic algorithms. J. Intell. Manuf., 7(1): 69-76.

[12] Cus, F. and J. Balic, 2003. Optimization of cutting process by GA approach. Robot. Cim-Int. Manuf., 19(1-2): 113-121.

[13] Cus, F., J. Balic and U. Zuperl, 2009. Hybrid ANFIS- ants system based optimisation of turning parameters. J. Achiev. Mater Manuf. Eng., 36: 79-86.

[14] De Castro, L.N. and J. Timmis, 2002. Artificial Immune Systems: A New Computational Intelligence Approach. Springer-Verlag, London.

[15] Dereli, T, I.H. Filiz and A. Baykasoglu, 2001. Optimizing cutting parameters in process planning of prismatic parts by using genetic algorithms. Int. J. Prod. Res., 39(15): 3303-3328.

[16] Dorigo, M. and C. Blum, 2005. Ant colony optimization theory: A survey. Theor. Comput. Sci., 344(2-3): 243-278.

[17] Dorigo, M., V. Maniezzo and A. Colorni, 1996. Ant system: Optimization by a colony of cooperating agents. IEEE T. Syst. Man Cyb. B, 26(1): 29-41.

[18] Durán, O., R. Barrientos and L. Consalter, 2007. Multi objective optimization in machining operations. In: Melin, P.,

O. Castillo, E. Ramírez, J. Kacprzyk and

[19] W. Pedrycz (Eds.), Analysis and Design of Intelligent Systems using Soft Computing Techniques. Advances in Soft Computing, Springer Berlin, Heidelberg, 41: 455-462.

[20] Eberhart, R. and J. Kennedy, 1995. A new optimizer using particle swarm theory. Proceedings of the 6th International Symposium on Micro Machine and Human Science (MHS '95), pp: 39-43.

[21] El-Midany, T.T., A. Elkeran and H. Tawfik, 2006. Optimal CNC plunger selection and toolpoint generation for roughing sculptured surfaces cavity. J. Manuf. Sci. E-T. ASME, 128(4): 1025-1029.

[22] El-Mounayri, H., H. Kishawy and V. Tandon, 2002. Optimized CNC end-milling: A practical approach. Int. J. Comp. Integ. M., 15(5): 453-470.

[23] El-Mounayri, H., H. Kishawy and J. Briceno, 2005. Optimization of CNC ball end milling: A neural network-based model. J. Mater. Process. Tech., 166(1): 50-62.

[24] Gao, D., Z.J. Yuan, Y.X. Yao, C.Q. Liu and J.G. Li, 2008.

Cutting parameters optimization by using Particle Swarm Optimization (PSO). Appl. Mech. Mater., 10: 879-883.

[25] Ghaiebi, H. and M. Solimanpur, 2007. An ant algorithm for optimization of hole-making operations. Comput. Ind. Eng., 52(2): 308-319.

[26] Ghosh, N., Y.B. Ravi, A. Patra, S. Mukhopadhyay,

[27] S. Paul, A.R. Mohanty and A.B. Chattopadhyay, 2007. Estimation of tool wear during CNC milling using neural network-based sensor fusion. Mech. Syst. Signal Pr., 21(1): 466-479.

[28] Holland, J.H., 1992. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence. MIT Press, Cambridge, MA.

[29] Hsieh, H.T. and C.H. Chu, 2012. Improving optimization of tool path planning in 5-axis flank milling using advanced PSO algorithms. Robot. Cim-Int. Manuf., 29(3): 3-11.

[30] Jing, W. and Y. Yingxue, 2008. A modified ant colony system for the selection of machining parameters. Proceeding of 7th International Conference on Grid and Cooperative Computing (GCC '08), pp: 89-93.

[31] Jones, M.T., 2008. Artificial Intelligence: A Systems Approach: A Systems Approach. Jones and Bartlett Learning.Junmei, X. and L. Gaohua, 2009. Cutting parameter optimization based on particle swarm optimization. Proceeding of 2nd International Conference on Intelligent Computation Technology and Automation (ICICTA '09), pp: 255-258.

[32] Kanan, H.R. and K. Faez, 2008. An improved feature selection method based on Ant Colony Optimization (ACO) evaluated on face recognition system. Appl. Math. Comput., 205(2): 716-725.

[33] Karayel, D., 2009. Prediction and control of surface roughness in CNC lathe using artificial neural network. J. Mater. Process. Tech., 209(7): 3125-3137.

[34] Kennedy, J. and R. Eberhart, 1995. Particle swarm optimization. Proceeding of IEEE International Conference on Neural Networks, 4: 1942-1948.

[35] Klancnik, S., M. Brezocnik, J. Balic and I. Karabegovic, 2012. Programming of CNC

milling machines using particle swarm optimization. Mater. Manuf. Process., 28(7): 811-815.

[36] Langevin, A., F. Soumis and J. Desrosiers, 1990. Classification of travelling salesman problem formulations. Oper. Res. Lett., 9(2): 127-132.

[37] Laporte, G., 1992. The traveling salesman problem: An overview of exact and approximate algorithms. Eur. J. Oper. Res., 59(2): 231-247.

[38] Lasemi, A., D. Xue and P. Gu, 2010. Recent development in CNC machining of freeform surfaces: A state-of-the-art review. Comput. Aided Design, 42(7): 641-654.

[39] Li, Y. and M.C. Frank, 2006. Machinability analysis for 3-axis flat end milling. J. Manuf. Sci. Eng., 128(2): 454-464.

[40] Li, Z., Y. Zhang and H.Z. Tan, 2011. IA-AIS: An improved adaptive artificial immune system applied to complex optimization problems. Appl. Soft Comput., 11(8): 4692-4700.

[41] Liu, C., Y. Li, W. Wang and W. Shen, 2013. A feature- based

method for NC machining time estimation. Robot. Cim-Int. Manuf., 29(4): 8-14.

[42] Liu, M., X.L. Ding, Y.F. Yan and X. Ci, 2011. Study on optimal path changing tools in CNC turret typing machine based on genetic algorithm. Comput. Comput. Technol. Agric, IV, 347: 345-354.

[43] López de Lacalle, L.N., A. Lamikiz, J.A. Sánchez and

[44] M.A. Salgado, 2007. Toolpath selection based on the minimum deflection cutting forces in the programming of complex surfaces milling. Int. J. Mach. Tool. Manu., 47(2): 388-400.

[45] Mahdavinejad, R., N. Khani and M. Fakhrabadi, 2012. Optimization of milling parameters using artificial neural network and artificial immune system. J. Mech. Sci. Technol., 26(12): 4097-4104.

[46] Man, K.F., K.S. Tang and S. Kwong, 1996. Genetic algorithms: Concepts and applications [in engineering design]. IEEE T. Ind. Electron., 43(5): 519-534.

[47] Mattson, M.W. and M. Mattson, 2009. CNC Programming: Principles and Applications. Delmar, Cengage Learning, Clifton Park, New York.

[48] Mayor, J.R. and A.A. Sodemann, 2008. Intelligent tool- path segmentation for improved stability and reduced machining time in micromilling. J. Manuf. Sci. E-T. ASME, 130(3): 31121-34500.

[49] McCulloch, W. and W. Pitts, 1943. A logical calculus of the ideas immanent in nervous activity. B. Math. Biophys., 5(4): 115-133.

[50] Medina-Rodriguez, N., O. Montiel-Ross, R. Sepulveda and O. Castillo, 2012. Tool path optimization for computer numerical control machines based on parallel ACO. Eng. Lett., 20: 101- 108.

[51] Onwubolu, G.C. and M. Clerc, 2004. Optimal path for automated drilling operations by a new heuristic approach using particle swarm optimization. Int. J. Prod. Res., 42(3): 473-491.

[52] Oysu, C. and Z. Bingul, 2007. Tool path optimization using genetic algorithms. Proceeding of Conference on Genetic and Evolutionary Methods. Las Vegas, USA, pp: 120-126.

[53] Oysu, C. and Z. Bingul, 2009. Application of heuristic and hybrid-GASA algorithms to tool-path optimization problem for minimizing airtime during machining. Eng. Appl. Artif. Intel., 22(3): 389-396.

[54] Palanisamy, P., I. Rajendran and S. Shanmugasundaram, 2007. Optimization of machining parameters using genetic algorithm and experimental validation for end-milling operations. Int. J. Adv. Manuf. Tech., 32(7-8): 644-655.

[55] Prakasvudhisarn, C., S.

Kunnapapdeelert and

[56] P. Yenradee, 2009. Optimal cutting condition determination for desired surface roughness in end milling. Int. J. Adv. Manuf. Tech., 41(5-6): 440-451.

[57] Qudeiri, J.E.A., H. Yamamoto and R. Ramli, 2007. Optimization of operation sequence in CNC machine tools using genetic algorithm. J. Adv. Mech. Design Syst. Manuf., 1: 272-282.

[58] Qudeiri, J.E.A., A.M. Raid, M.A. Jamali and

[59] H. Yamamoto, 2006. Optimization hole-cutting operations

sequence in CNC machine tools using GA. Proceeding of International Conference on Service Systems and Service Management, pp: 501-506.

[60] Safaieh, M., A. Nassehi and S.T. Newman, 2013. A novel methodology for cross-technology interoperability in CNC machining. Robot. Cim- Int. Manuf., 29(3): 79-87.

[61] Saravanan, R. and V. Janakiraman, 2007. Study on reduction of machining time in CNC turning centre by genetic algorithm. Proceeding of IEEE International Conference on Computational Intelligence and Multimedia Applications, pp: 481-486.

[62] Savas, V. and C. Ozay, 2008. The optimization of the surface roughness in the process of tangential turn- milling using genetic

algorithm. Int. J. Adv. Manuf. Tech., 37(3-4): 335-340.

[63] Shi, X.H., Y.C. Liang, H.P. Lee, C. Lu and Q.X. Wang, 2007.

Particle swarm optimization-based algorithms for TSP and generalized TSP. Inform. Process. Lett., 103(5): 169-176.

[64] Srinivas, J., R. Giri and S.H. Yang, 2009. Optimization of multi- pass turning using particle swarm intelligence. Int. J. Adv. Manuf. Tech., 40(1-2): 56-66.

[65] Suh, S.H. and J.J. Lee, 1998. Five-axis part machining with three-axis CNC machine and indexing table. J. Manuf. Sci. Eng., 120(1): 120-128.

[66] Suneel, T.S. and S.S. Pande, 2000. Intelligent tool path correction for improving profile accuracy in CNC turning. Int. J. Prod. Res., 38(14): 3181-3202.

[67] Ülker, E., M. Emin Turanalp and H. Selçuk Halkaci, 2009. An artificial immune system approach to CNC tool path generation. J. Intell. Manuf., 20(1): 67-77.

[68] Wang, X.L., J.H. Cheng, Z.J. Yin and M.J. Guo, 2011. A new approach of obtaining reservoir operation rules: Artificial immune recognition system. Expert Syst. Appl., 38(9): 11701- 11707.

[69] Wang, S.G., Y.J. Wang, G.X. Wu and Y.L. Fu, 2012.

[70] Application of intelligence fusion algorithm in path optimization problem. Appl. Mech. Mater., 151: 632-636.

[71] Yang, J. and Y. Zhuang, 2010. An improved ant colony optimization algorithm for solving a complex combinatorial optimization problem. Appl. Soft Comput., 10(2): 653-660.

[72] Zhang, Y., X. Xu and Y. Liu, 2011. Numerical control machining simulation: A comprehensive survey. Int. J. Comp. Integ. M., 24(7): 593-609.

[73] Zheng, L.Y. and S.G. Ponnambalam, 2010. Optimization of multipass turning operations using particle swarm optimization. Proceeding of 7th International Symposium on Mechatronics and its Applications (ISMA, 2010), pp: 1-6.

[74] Zhong, Y., 2008. Structuralism? functionalism? behaviorism? or mechanism? looking for a better approach to AI. Int. J. Intell. Comput. Cyb., 1(3): 325-336.

[75] Zuperl, U. and F. Cus, 2003. Optimization of cutting conditions during cutting by using neural networks. Robot. Cim-Int. Manuf., 19(1-2): 189-199.

[76] Zuperl, U., F. Cus, B. Mursec and T. Ploj, 2004. A hybrid analytical-neural network approach to the determination of optimal cutting conditions.

[77] J. Mater. Process. Tech., 157-158: 82-90.

[78] Zperl, U., F. Cs and V. Gecevska, 2007. Optimization of the characteristic parameters in milling using the PSO evolution technique. J. Mech. Eng., 53(6): 354-368.