A neural network based methodology for machining operations selection in Computer-Aided Process Planning for rotationally symmetrical parts

2006 ◽  
Vol 17 (5) ◽  
pp. 557-569 ◽  
Author(s):  
Sankha Deb ◽  
Kalyan Ghosh ◽  
S. Paul
1996 ◽  
Vol 118 (3) ◽  
pp. 406-414 ◽  
Author(s):  
J. B. Levin ◽  
D. Dutta

Parallel N.C. machines, also referred to as mill-turns, are a new generation of machine tools aimed at increasing machining accuracy and reducing part cycle times. In addition to their capacity to do both milling and turning, these next generation machines tools can perform multiple machining operations simultaneously, involving one or more parts at a time, and can completely finish a part (front and back) in a single setup. Parallel machining raises issues with respect to computer aided process planning which have not been dealt with in the past. In this paper, a prototype CAPP system called PMPS, for parallel machining, is described. First, we briefly highlight the new issues to be dealt with in process planning for parallel machining. Next, the architecture and details of PMPS, a generative CAPP system, is described. Finally, the implementation and results are discussed.


2011 ◽  
Vol 264-265 ◽  
pp. 1551-1556
Author(s):  
Deepak Byotra ◽  
Rajesh Kumar Bhushan

Bulk of power transmitting metal gears of machinery is produced by machining processes from cast, forged or hot rolled blanks. It includes a number of versatile machining operations that use a milling cutter, a multi tooth tool to produce a variety of configurations. The aim of the computer aided process planning (CAPP) is to develop a programme for milling cutting processes. This paper reveals the hybrid approach to computer aided process planning for milling and grinding operations on gear blank, so that the plan can be generated taking into account the availability of machines and the material. The developed computer aided process plan has reduced the set up time and machining time by 40.90 and 30.15 % respectively.


2017 ◽  
Vol 46 (2) ◽  
pp. 97-117 ◽  
Author(s):  
Stylianos Moschonissiotis ◽  
George-Christopher Vosniakos

Programming of computer numerical control (CNC) machining centres using computer aided manufacturing (CAM) software is efficient provided that machining operations and their sequence has been correctly determined by the user. Such decisions, however, are a largely matter of experience. If the user is inexperienced, then Computer Aided Process Planning systems may be employed, but these are usually legacy systems. Thus, normally some prior knowledge has to be induced to the inexperienced user in the form of structured knowledge or rules. After studying a representative number of parts, creating and validating process plans and feeding them to a CAM system some baseline knowledge has been created and structured into rules. Training the user towards applying these rules, or even creation of custom rules is based on part analysis according to a basic reasoning. This is best implemented by advance-organisers of the schematic type regarding part form, process identification, work-holding and setup sequencing, whilst creation of steps or instructions for guiding the process plan generation flow is effected according to the Structure of the Observed Learning Outcome paradigm. The method has been applied to a sizeable audience and preliminary statistical and qualitative evidence on its effectiveness is presented.


Author(s):  
Jordan B. Levin ◽  
Debasish Dutta

Abstract Computer-aided process planning is a critical function in the overall scheme of computer-integrated manufacturing (CIM). Progress in CIM is key to increased productivity. Furthermore, as new CIM systems evolve, the latest advancements from the constituent areas must be incorporated. Toward that end, our ongoing research deals with the development of methodologies to enable the inclusion of a new class of machine tools characterized by their ability to carry out machining operations in parallel. In this paper, we identify and elaborate on the effects of parallelism on computer-aided process planning, which are brought about by these new machine tools.


Author(s):  
Izabela Rojek

AbstractThe central objective of the present author's research is to develop a system supporting the design of a technological process (a computer-aided process planning system) that functions similarly to a human expert in the field in question. The use of neural networks makes the creation of such a system possible. The proposed method uses a system of three blocks of neural networks, and involves the creation of neural networks to be used for the selection of machines, tools, and machining parameters. These networks are built for each process operation separately; that is, a set of neural networks is created for each selection. For the construction of models, different types of neural networks (multilayer networks with error backpropagation, radial basis function, and Kohonen) with different structures were employed, and the networks that made the best selections were identified. A method was also developed for the elimination of defects occurring during the production process. When a defect comes to light, this method suggests changes to the technological process, thus improving the quality of that process. Guidelines for the elimination of defects are produced in the form of decision rules. Such a computer-aided process planning system will be especially useful for process engineers who do not yet have sufficient experience in the design of technological processes, or who have only recently joined a particular manufacturing enterprise and are not fully familiar with its machines and other means of production (tools and instrumentation). It should be emphasized that such a system performs an advisory role, and it is always the process engineer who makes the final decision. The neural network models were tested on real data from an enterprise. A computer-aided process planning system based on rules and neural network models enables the intelligent design of technological processes.


2014 ◽  
Vol 598 ◽  
pp. 591-594 ◽  
Author(s):  
Li Yan Zhang

ISO 14649, known as STEP-NC, is new model of data transfer between CAD/CAM systems and CNC machines. In this paper, the modeling based on machining feature is proposed. The machining feature comes from the manufacturing process considering the restriction of machining technology and machining resource. Then the framework for computer aided process planning is presented, where the algorithms of operation planning is studied. The practical example has been provided and results indicate that machining feature based model can integrate with CAPP and STEP-NC seamlessly.


Sign in / Sign up

Export Citation Format

Share Document