CHAPTER 1 INTRODUCTION 1.

1General Introduction: It has been recognized that conditions during cutting such as feed rate, cutting speed and depth of cut should be selected to optimize the economics of machining operations as assessed by the productivity and total manufacturing cost per component or some other criteria. The selection of efficient machining parameters such as machining speed, feed rate and depth of cut has a direct impact and production economies in the metal cutting processes. Dimensional accuracy is significantly affected by tool wear. Therefore to improve dimensional accuracy one or more tool adjustments may be desirable before a tool is replaced. Taylor showed that an optimum or economic cutting speed exists which will increase the maximum material removal rate. Manufacturing industries have long depended on the skill and the experience of the shop floor machine tool operators for optimum selection of cutting conditions and tools, considerable efforts are still in progress on the use of handbook based conservative cutting conditions and tool selection at the process planning level. The need for selecting and implementing optimal machining conditions and the most suitable cutting tool has been felt over the last few decades. Despite Taylors early work on establishing optimum cutting speeds in single pass turning s process has been slow so all the process has to be optimized. Further more for realistic solutions the many constraints met in practice such as low power temperature, force limits and component surface roughness must be overcome. The non availability of the required technological performance equation is a major obstacle to implement the optimal cutting conditions in practice. Extensive testing is required to establish empirical performance equations for each tool coating and work material combination for a given machining operation. This can be quite expensive when wide spectrums of machining operations are considered. Machining parameters selection has been investigated extensively for a single pass turning operation. However if a large amount of material has been removed it may not be feasible to remove the material in a single pass owing to force and power restrictions and surface finish requirements. Such cases multi pass cutting is more economical than single pass

turning. This gives rise to the multi pass problem which involves not only for selection of machining parameters but also for economical number of passes. Lack of an efficient optimization tool early work in this direction was limited to small problems with mostly two or three passes and a few variables and constraints. The major efforts of earlier works were concentrated on optimization of a single objective function. Various multi-objective optimization approaches have been proposed in recent years for optimizing machining parameters. One major drawback of interactive approaches to machining process optimization is that interactions with manufacturers are necessary for almost every different part. In an open job-shop production system, the lot size of manufactured items is usually small and product mix is usually diverse. Furthermore, in the dynamic global economy, the time-varying market value makes labour and material costs fluctuate. The diversity of product mix and the uncertainty of market value make interactive approaches to machining process planning inefficient owing to the extensive and frequent interactions with manufacturers for planning machining process.

1.2 Machining parameters in turning process: In metal cutting, there are many factors related to process planning for machining operations. These factors can be classified as 1. Type of machining operations (turning, facing, milling, etc.), 2. Parameters of machine tools (rigidity, horsepower, etc.), 3. Parameters of cutting tools (material, geometry, etc.), 4. Parameters of cutting conditions (cutting speed, feed rate , depth of cut, etc.), 5. Characteristics of work pieces (material, geometry, etc.). Among these factors cutting parameters (speed, feed rate, and depth of cut) are evidently dominating ones in a machining operation. 1. CUTTING SPEED: The cutting speed of a tool is the speed at which the metal is removed by the tool from the work material. In a lathe it is the peripheral speed of the work part in m/min.

2. FEED: The feed of the cutting tool in lathe work is the distance, the tool advances for each revolution of the work piece in mm/rev. 3. DEPTH OF CUT: The depth of cut is the perpendicular distance measured from the machined surface to the uncut surface of work piece in mm.

For a given machining operation, determination of the optimum cutting conditions involves a conflict between maximizing the metal removal rate and minimizing the tool wear. By increasing the feed rate or spindle speed, the metal removal rate and hence the production rate can be increased; but this results in excessive tool wear, frequent tool changes and increased production costs. Therefore, there is an optimum set of spindle speed, feed rate and depth of cut which balances these conflicts. The machining process optimization is to determine the most advantageous cutting condition. That is, to determine optimal machine parameters such as s (spindle speed), f (feed rate), and d (depth) to optimize specified objectives such as cutting quality and material removal rate.

CHAPTER 3 PROBLEM DESCRIPTION

To find the optimum machining parameters in order to get the minimum surface roughness and maximum material removal rate. Single objective, multi objective Genetic algorithm and response surface methodology are used to do this and the results are compared. We have taken 15 samples of milling operation in finishing cut and 15 samples of milling operation in roughing cut and the values of the speed, feed and depth of cut and their respective surface roughness and material removal rate. We put these values into a neural network and trained with a network and it is exported to the work space of matlab. Then this is used in the genetic algorithm and the network functions like an equation. In the response surface methodology the linear and second order polynomials were fitted to the experimental data for obtaining regression equatioins. 2.1Objective Function:

The full development of machining process planning is based on optimization of the economic criteria subject to technical and managerial constraints. The economic criteria are the objectives of machining operations in terms of quality and material removal rate. The objectives considered in this paper are surface roughness to be minimized and material removal rate to be maximized for both roughing case and finishing case.

1. Surface Roughness: Surface Roughness is termed as the cutting quality. Surface Roughness Ra is measured using a portable Mitutoyo Surftest Profilometer with a roughness cut-off of 0.8mm.

2. Material Removal Rate: Material Removal Rate is defined as the amount of material to be removed per each operation. Material Removal Rate is expressed in terms of feed rate, the depth of cut and tool diameter. MRR = FdD

Where F, d and D are respectively the feed rate, the depth of cut and tool diameter.

CHAPTER 3 GENETIC ALGORITHM 3.1 Introduction Genetic Algorithms are a family of computational models inspired by evolution. These algorithms encode a potential solution to a specific problem on a simple chromosome-like data structure and apply recombination operators to these structures as to preserve critical information. Genetic algorithms are often viewed as function optimizer, although the range of problems to which genetic algorithms have been applied are quite broad. An implementation of genetic algorithm begins with a population of (typically random) chromosomes. One then evaluates these structures and allocated reproductive opportunities in such a way that these chromosomes which represent a better solution to the target problem are given more chances to `reproduce' than those chromosomes which are poorer solutions. The 'goodness' of a solution is typically defined with respect to the current population.

3.2 Natural Selection In nature, the individual that has better survival traits will survive for a longer period of time. This in turn provides it a better chance to produce offspring with its genetic material. Therefore, after a long period of time, the entire population will consist of lots of genes from the superior individuals and less from the inferior individuals. In a sense, the fittest survived and the unfit died out. This force of nature is called natural selection.

3.3 Simulated Evolution To simulate the process of natural selection in a computer, we need to define the following: A representation of an individual. At each point during the search process we maintain a "generation" of "individuals." Each individual is a data structure representing the "genetic structure" of a possible solution or hypothesis. Like a chromosome, the genetic structure of an individual is described using a fixed, finite alphabet. In GAs, the alphabet 0, 1 is usually used. 3.4 Basic Principle The major steps involved are the generation of a population of solutions, finding the objective function and fitness function and the application of Genetic operators. They are described in detail in the following subsection.

/*Algorithm GA */ Formulate initial population Randomly initialize population

Repeat Evaluate objective function Find fitness function Apply genetic operators Reproduction Crossover Mutation Until stopping criteria