Intelligently helping the human planner in industrial process planning

The function of a process planning system is to determine the methods by which a product is to be manufactured economically and competitively. In a modern manufacturing environment, a process planning system consists of highly trained people and complex software. The plans prepared by a process planning system are not always executed as planned. It is useful if the system can discover why plans fail, when they do fail. In order to learn why plans fail, the system must analyse a number of plans, both successful and unsuccessful, to find patterns in the failures of plans. This type of analysis is difficult for people, who are much better at analysing single events than multiple events.The aim of the project described here is to design and implement a computer program which will help human planners in a process planning system to understand why plans fail. To achieve this aim, a program called IMAFO (Intelligent MAnufacturing FOreman) has been developed. IMAFO uses decision tree induction to analyse examples of both successful and unsuccessful plans.The difficulties presented by this application are discussed and solutions are presented. Problems addressed include finding an appropriate set of attributes for describing the plans, using data efficiently, consolidating input from distinct sources, and presenting decision trees in an understandable form. Potential applications and directions for future research are considered.

Download Full-text

Customization of a Micro Process Planning System for an Actual Machine Tool Based on Updating a Machining Database and Generating a Database Oriented Planning Algorithm

ASME/ISCIE 2012 International Symposium on Flexible Automation ◽

10.1115/isfa2012-7202 ◽

2012 ◽

Cited By ~ 1

Author(s):

Shinji Igari ◽

Fumiki Tanaka ◽

Masahiko Onosato

Keyword(s):

Decision Tree ◽

Machine Tool ◽

Process Planning ◽

Cutting Tools ◽

Regression Tree ◽

Planning System ◽

Regression Equations ◽

Process Planning System ◽

Planning Algorithm ◽

Tree Method

To generate optimal machining information, an automatically customizable micro process planning system that reflects the change of properties of an actual machine tool is proposed. The system consists of an updatable machining database and a database oriented micro process planning algorithm. A machining database is updated based on analyzing NC data that are adaptively generated for an actual machine tool by skilled process planners. From the updated machining database, a database oriented micro process planning algorithm is generated by a decision tree and a regression tree. Machining strategy and cutting tools are determined using IF-THEN rules that are generated from the database by decision tree method. Cutting conditions were determined from a feasible regression equation. Regression equations and selection rules of these equations were generated from the database by regression tree method. The example of micro process planning using the generated algorithm is also shown.

Download Full-text

OPPS-PRI 2.0: an open and optimized process planning system for prismatic parts to improve the performance of SMEs in the machining industry

International Journal of Production Research ◽

10.1080/0020754042000298548 ◽

2005 ◽

Vol 43 (5) ◽

pp. 1039-1087 ◽

Cited By ~ 5

Author(s):

T. Derelİ * ◽

A. Baykasoğlu

Keyword(s):

Process Planning ◽

Planning System ◽

Prismatic Parts ◽

Process Planning System

Download Full-text

Applications of Software Engineering to Manufacturing Process Planning

Journal of Computing and Information Science in Engineering ◽

10.1115/1.2960488 ◽

2008 ◽

Vol 8 (3) ◽

Cited By ~ 2

Author(s):

V. Sundararajan ◽

Paul K. Wright

Keyword(s):

Software Development ◽

Process Planning ◽

Tool Path ◽

Numerical Control ◽

Planning System ◽

Cnc Milling ◽

Design Development ◽

Tool Selection ◽

Process Planning System ◽

New Algorithms

Agile methods of software development promote the use of flexible architectures that can be rapidly refactored and rebuilt as necessary for the project. In the mechanical engineering domain, software tends to be very complex and requires the integration of several modules that result from the efforts of large numbers of programmers over several years. Such software needs to be extensible, modular, and adaptable so that a variety of algorithms can be quickly tested and deployed. This paper presents an application of the unified process (UP) to the development of a research process planning system called CyberCut. UP is used to (1) analyze and critique early versions of CyberCut and (2) to guide current and future developments of the CyberCut system. CyberCut is an integrated process planning system that converts user designs to instructions for a computer numerical control (CNC) milling machine. The conversion process involves algorithms to perform tasks such as feature extraction, fixture planning, tool selection, and tool-path planning. The UP-driven approach to the development of CyberCut involves two phases. The inception phase outlines a clear but incomplete description of the user needs. The elaboration phase involves iterative design, development, and testing using short cycles. The software makes substantial use of design patterns to promote clean and well-defined separation between and within components to enable independent development and testing. The overall development of the software tool took about two months with five programmers. It was later possible to easily integrate or substitute new algorithms into the system so that programming resources were more productively used to develop new algorithms. The experience with UP shows that methodologies such as UP are important for engineering software development where research goals, technology, algorithms, and implementations show dramatic and frequent changes.

Download Full-text