Intelligent process planning by evolutionary computing with genetic algorithms.

Gecevska, Valentina ; Cus, Franc ; Zuperl, Uros 等

1. INTRODUCTION

The complexity of manufacturing process itself and extended application of computer supported equipment has led toward identifying three main phases in manufacturing integration (Chang, 1990; Jang, 2005): (1) hardware and software integration, (2) application integration and (3) process and people integration. After several years in focusing on CAD/CAM integration, the research has moved toward the third phase, process integration. One of most important links for implementation of integrated manufacturing is process planning, the link between product design (CAD) and production planning and execution (CAM, MES). Process planning (CAPP), as one of the key activities for product design and manufacturing, is developed in many researches. Recent research efforts are devoted to generation and evaluation of alternative process plans and to enlargement of manufacturing knowledge base (Jang, 2005; Sormaz, 1999). Integration with other manufacturing planning functions and the issues of data and knowledge representation and integration framework has also received significant interest.

This paper addresses an issue of generating process information within the integration framework in order to modeling manufacturing systems.

2. MANUFACTURING SYSTEM ACTIVITIES

The product development and manufacture involves several production management activities with a series of individual tasks that are to be completed in order to design and manufacture a product of a required quality. These tasks are usually carried out in a linear sequence, but very often the feedback is necessary from the subsequent task to the previous one. Many of these feedback loops are requests to modify the previous task's solution in order to generate a better solution in the subsequent one. This interlinking is what has become known as concurrent or simultaneous engineering.

This section of paper will provide a model of manufacturing activities and tasks, and identify how these tasks connect high level activities. It is done identified need for integration from the whole cycle of product development and described of manufacturing activities model with extensive set of manufacturing planning tasks.

2.1 Manufacturing activities model

Starting from analyzing set of tasks of process planning and other activities, it is possible to develop the model that shows interactions between process planning and them. The model of these interactions, shown in Figure 1 (Sormaz ,1999), where each activity represents with circle, consists a set of tasks that are to be done in the product development. All of these activities are identified in manufacturing planning literature as activities required during the product development and manufacture. The classification shown in the Fig.1 represents a starting point for the use of this method in each individual factory. There are numerous tasks that require interactions between two or more activities. They are shown within overlapping circles of activities and represent integration links.

[FIGURE 1 OMITTED]

It is important to understand explained activities and interactions shown on the Figure 1 in order to completely utilize engineering knowledge and expertise, activities that need specialists in the domain, suitable for applying concurrent engineering principles. The most important intersections from process planning perspective are: between design and process planning related to part family formation, between process planning and resource management related to manufacturing cell design and between process planning and scheduling related to production control of cells.

2.2 Modeling of manufacturing process

The basic entity of the manufacturing process modeling is a process, understood as an activity, usually planned in advance, with all necessary attributes. All manufacturing planning functions generate various planned tasks or activities. Each of these tasks has numerous attributes that have to be defined before the task can be undertaken. These attributes are usually defined by different manufacturing planning functions.

2.3 Process planning network

The basis of the above-described modeling of manufacturing process is the process planning network. This network is result of process planning that enable manufacturing integration. The process planning network consists of four interconnected layers: feature layer, process layer, tool orientation layer and machine layer. The first layer, feature layer, represents a network of machining features. The next layer is the process layer, which contains process candidate instances for individual features. There is necessary to show alternative machining processes for the same features in order to allow for later selection of the most suitable processes for given conditions. The next layer is tool condition layer that nodes represent sets of cutting process instances performed using tool orientation and machine type. The final layer of process planning network is machine layer. Its nodes set of cutting processes with all constraints of machining conditions to determine cutting data (Gecevska et al., 2006; Milfelner et al., 2005).

2.4 Process planning optimization approach

The present paper proposes optimal determination of the cutting parameters for the machining process addressed as a multi objective programming mathematical model, obtained by using a deterministic method and a genetic algorithm. In this research, is proposed the optimization process for NC machining with: (i) mathematical model for objective function, (ii) mathematical modeling of constraints and (iii) criteria for optimization. Mathematical model for objective function is derived for the purpose in establishment of the interrelation between the machining parameters, based of the object-oriented algorithm for ordering of cutting operation in the process planning. The function of constrains are formulated from: cutting tools characteristics and tool wear, cutting tool life in different machining conditions, quality and accuracy of the machining, properties of tool and workpiece materials, geometry of the machining workpiece, characteristics of the main and idle movements. The machining economics problem consists in determining the process parameters, usually cutting speed, feed rate and dept of cut, in order to optimize an objective function, usually a machining cost or machining time function, or a combination of several objective functions.

2.5 Developed optimization approaches

Proposed deterministic optimization approach (DO), in our research, is created as a numerical program for optimization modeling, based on the numerical algorithm with several modules, organized in 4 blocks.

Block 1 for solving the optimal cutting parameters.

Block 2 as an engine of the numerical program for optimization that contains more elementary original created algorithms and procedures.

Block 3 for optimization of the analyzing machining process based of the complex mathematical model that is the virtual machining process presentation.

Block 4 for offering as an output optimal cutting parameters in matrix (tables) and graphic presentations. The optimization of complete machining process with determination of optimized cutting parameters is possible for each machining operation (and passes) in process planning. In this way, the parameters for machining process, as a machining time, productivity, cost, are determined by total computations of suitable parameter for each machining operation.

The genetic algorithms (GA) optimization approach is developed in our research. There is made the GA program module, based of the elementary pseudo-code for GA, with using the MatLAB program language and C++, called GAMO (Genetic Algorithm for Machining Operation). There are the three fundamental operators involved in the search process of a genetic algorithm: reproduction, crossover and mutation. With these operators the algorithm is given a chance to survive and to produce better strings thereby giving them a chance to have more copies in subsequent generations.

The main evaluation function (1) for GA optimization, which defines the genetic operators and parameters, is done:

[x, endPop, bPop] = ga(bounds, evaFN, params, startPop, termFN, selectFN,...xOverFN, xOverParams, mutFN, mutParams) (1)

3. INTELLIGENT PROCESS MODELLING BY BOTH DEVELOPED APPROACHS

In the research, it is done process planning during modelling of production process for new metal product by using of developed GA and DO optimization tools.

The optimization of complete machining process with determination of optimized cutting parameters is made for each machining operation (and passes), designed in process planning for new product. The parameters for machining process as a machining time, productivity and costs are determined by total computations of suitable parameter for each machining operation. The system is first analyzed by simulations, and then it is verified by experiments on a CNC machining lathe (type Matsuura TN550) and vertical machining centre (type Matsuura MC-760VX). Input data for each operation, in each tool pass, are computed by developed tools.

4. CONCLUSION

This paper has described manufacturing process model as a basis for intelligent information integration and has presented the multi-objective optimization of the machining process as a method applicable in process planning during mechanical product development. Multi-objective optimization is developed by using the deterministic optimization method and genetic algorithms to obtain the optimum cutting speed and feed rate and to predict the cutting forces and cutting tool wear during machining. The experimental results show that the machining process is improved through reduction of machining time if there are used optimized cutting parameters.

5. REFERENCES

Chang, T.(1990). Expert Process Planning for Manufacturing, Pub.Addison-Wesley, New York

Gecevska, V.; Cus, F.; Kuzinovski, M. & Zuperl, U. (2005). Evolutionary Computing with Genetic Algorithm in Manufacturing Systems, Journal of Machine Engineering, Vol.5, No 3/4 (Sept.2006), pp 188-198, ISBN 1642-6568

Jain, A.; Jain, P. & Singh, P. (2005). Deadlock Analysis in FMS in the Presence of Flexible Process Plans, International Journal of Simulation Modelling, Vol.4, No.2 (June 2005), pp 53-66, ISSN 1726-4529

Milfelner, M.; Zuperl, U. & Cus, F. (2005). Optimization of Cutting Parameters in High Speed Milling Process by GA, International Journal of Simulation Modelling, Vol.3,No.4,Dec.2004, pp 158-165, ISSN 1726-4529

Sormaz, D. (1999). Intelligent Manufacturing Based on Generation of Alternative Process Plans, Proceedings of 9th Int. Conference on Flexible Automation and Intelligent Manufacturing, pp 35-49, Nederland, June 1999, Tilburg