Genetic equation for the cutting force in ball-end milling

https://doi.org/10.1016/j.jmatprotec.2005.02.147Get rights and content

Abstract

The paper presents the development of the genetic equation for the cutting force for ball-end milling process. The development of the equation combines different methods and technologies like evolutionary methods, manufacturing technology, measuring and control technology and intelligent process technology with the adequate hardware and software support. Ball-end milling is a very common machining process in modern manufacturing processes. The cutting forces play the important role for the selection of the optimal cutting parameters in ball-end milling. In many cases the cutting forces in ball-end milling are calculated by equation from the analytical cutting force model. In the paper the genetic equation for the cutting forces in ball-end milling is developed with the use of the measured cutting forces and genetic programming. The experiments were made with the system for the cutting force monitoring in ball-end milling process. The obtained results show that the developed genetic equation fits very well with the experimental data.

The developed genetic equation can be used for the cutting force estimation and optimization of cutting parameters. The integration of the proposed method will lead to the reduction in production costs and production time, flexibility in machining parameter selection, and improvement of product quality.

Introduction

The paper presents the development of the genetic equation of machining process, which is shown in detail on the process of machining of steels with ball-end milling. The milling process has become a very important and useful procedure for the manufacture of 3D surfaces of different shapes. Due to the widespread use of highly automated machine tools in the industry, manufacturing requires reliable monitoring and optimization models and methods.

The cutting forces that are developed during the milling process, can directly or indirectly estimate process parameters such as tool wear, tool life, surface finish, etc. The capability of modeling cutting forces therefore provides an analytical basis for machining process planning, machine tool design, cutter geometry optimization, and on-line monitoring/control. A large amount of work has been carried out on force modeling.

The modeling of cutting forces is often made difficult by the complexity of the tool/workpiece geometry and cutting configuration. Analytical cutting force is difficult due to the large number of interrelated machining parameters. The large number of interrelated parameters that influence the cutting forces (cutting speed, feed, depth of cut, cutter geometry, tool wear, physical and chemical characteristics of the machined part, etc.) makes it extremely difficult to develop a proper model.

Researchers [1], [2], [3], [4] have been trying to develop mathematical models that would predict the cutting forces based on the geometry and physical characteristics of the process. However, due to its complexity, the milling process still represents a challenge to the modeling and simulation research effort.

The main objective of this work is to develop an intelligent model for cutting forces in ball-end milling process. By exploring the advantages of the artificial intelligence methods, the genetic equation is developed. The genetic equation is developed for use as a direct modeling method, to predict cutting forces for the ball-end milling operations. Prediction of cutting forces in ball-end milling is often needed in order to establish automation or optimization of the machining processes.

The developed genetic equation will be applied into the manufacturing process for the determination of optimal cutting parameters with a few number of experiments and maximum cutting power on tool machine.

Section snippets

Ball-end milling

Ball-end milling is a very common machining process especially in the automobile, aerospace, die and mold industries [5]. It is used for machining the freely shaped surfaces such as dies, moulds, turbines, propellers, and for the aircraft structural elements. Due to various reasons, such as structural, optimization or aesthetic points of view, nowadays, most of the industrial part geometries are becoming more and more complicated. The recent advance in CAD/CAM systems and CNC machining centers

Cutting force model

Products with 3D sculptured surfaces are widely used in the modern tool, die and turbine industries. These complex-shaped premium products are usually machined using the ball-end milling process. The objective of this work is to develop an accurate and practical cutting force model (equation) for ball-end milling in the three-axis finishing machining of 3D sculptured surfaces. This requires the model to be able to characterize the cutting mechanics of nonhorizontal and cross-feed cutter

Genetic programming (GP)

The genetic algorithm (GA) is a model of machine learning, which derives its behaviour from a metaphor of the processes of evolution in nature [8]. This is done by the creation within a machine of a population of individuals represented by chromosomes, in essence a set of character strings that are analogous to the base-4 chromosomes that we see in our own DNA. The individuals in the population then go through a process of evolution.

We should note that evolution (in nature or anywhere else) is

Experimental setup

The experiments were made with the system for the cutting force monitoring (Fx, Fy in Fz) in ball-end milling process. The system for monitoring consists of (Fig. 4):

  • tool machine (CNC milling machine MORI SEIKI FRONTIER-M),

  • tool (solid ball-end milling cutter type R216.44-10030-040-AL10G, tool material GC 1010),

  • clamping device,

  • workpiece (material: Ck45, Ck45 (XM), 16MnCr5 in 16MnCr5 (XM)),

  • piezoelectric dynamometer (KISTLER 9259A),

  • amplifier (KISTLER 5001),

  • A/D interface board (PC-MIO-16E-4.),

Genetic equation for cutting force in ball-end milling

For the determination of the relationship between cutting forces and cutting parameters in ball-end milling we developed the genetic equation with genetic programming.

For the determination of the genetic equation in ball-end milling with the milling cutter type R216.44-10030-040-AL10G and workpiece material Ck45 was selected 45 experimental data. The maximal cutting forces were monitored with different cutting conditions (radial depth RD = 0.2–0.6 mm, axial depth AD = 0.2–0.6 mm, feeding fz = 0.08–0.12 

Conclusion

The paper presents the development of the genetic equation in ball-end milling. The results obtained from the proposed genetic programming approach prove its effectiveness. The implication of the encouraging results obtained from the present approach is that such approach can be integrated on-line, with an intelligent manufacturing system for automated process planning. Since the genetic programming-based approach can obtain near-optimal solution, it can be used for machining parameter

References (8)

  • M. Yang et al.

    Int. J. Mach. Tools Manuf.

    (1991)
  • P. Lee et al.

    Int. J. Mach. Tools Manuf.

    (1996)
  • M. Milfelner et al.

    Robot. Comput. Integr. Manuf.

    (2003)
  • I. Lazoglu

    Int. J. Mach. Tools Manuf.

    (2003)
There are more references available in the full text version of this article.

Cited by (32)

  • Design of robust energy consumption model for manufacturing process considering uncertainties

    2018, Journal of Cleaner Production
    Citation Excerpt :

    Göloğlu and Arslan, (2009) used GP for surface roughness prediction in zigzag milling process and compared the GP models with ANN models in terms of accuracy. Milfelner et al. (2005) applied GP in cutting force modeling of milling process and achieved an approximately accuracy of 96.5%. In context of energy conservation, Garg et al. (2015) proposed an energy consumption modeling approach based on GP.

  • Stepwise approach for the evolution of generalized genetic programming model in prediction of surface finish of the turning process

    2014, Advances in Engineering Software
    Citation Excerpt :

    Researchers have carried out additional set of experiments to test the empirical models, but it involves high labour costs and results in increase in overall cost of the product [31,32]. The applications for the explicit formulation of the performance of machining process using evolutionary approach GP have been on the rise [33–38]. The main advantage of GP over the regression analysis and other statistical modelling techniques is that it has the ability to generate mathematical equations without assuming any prior form of the existing relationships.

  • Performance evaluation of microbial fuel cell by artificial intelligence methods

    2014, Expert Systems with Applications
    Citation Excerpt :

    Based on the input, the soft computing method can then be able to generate meaningful solutions for complicated problems (Castelli, Vanneschi, & Silva 2013; Garg, Rachmawati & Tai, 2013a; Garg, Tai, Lee, & Savalani, 2013b; Nazari, 2012; Peteiro-Barral, Guijarro-Berdiñas, Pérez-Sánchez, & Fontenla-Romero, 2013). Additionally, among the various soft computing methods described above, GP offers the advantage of a fast and cost-effective explicit formulation of a mathematical model based on multiple variables without any pre-definition of non-linear structure of the model (Al-Sahaf, Song, Neshatian, & Zhang, 2012; Giot, & Rosenberger, 2012; Kala, 2012; Kovacic & Brezocnik, 2003; Mabu, Hirasawa, Obayashi, & Kuremoto 2013; Mabu, Tjahjadi, & Hirasawa, 2012; Milfelner, Kopac, Cus, & Zuperl, 2005; Tsakonas, 2013; Tsakonas & Gabrys, 2012). The analytical model hence obtained can then be used by fuel cell developers to optimize the performance of their fuel cell based on specific operating conditions.

  • Genetic equation for the prediction of tool-chip contact length in orthogonal cutting

    2013, Engineering Applications of Artificial Intelligence
    Citation Excerpt :

    In engineering, especially manufacturing engineering, GP is frequently applied to model various processes and conditions. Some applications of GP have been reported in prediction of surface roughness (Brezocnik et al., 2004); nonlinear system modeling (Metenidis et al., 2004); investigation of the cutting force (Milfelner et al., 2005) and machine scheduling problems (Dimopoulos and Zalzala, 2001). It is noteworthy that this paper is the first research in which GP modeling method is used in the field of manufacturing engineering to predict the length of tool–chip contact in the turning process.

View all citing articles on Scopus
View full text