Expert System For Process Planning Research Articles

An expert system for process planning of sheet metal parts produced on compound die for use in stamping industries

Process planning of sheet metal part is an important activity in the design of compound die. Traditional methods of carrying out this task are manual, tedious, time-consuming, error-prone and experience-based. This paper describes the research work involved in the development of an expert system for process planning of sheet metal parts produced on compound die. The proposed system is organized in six modules. For development of system modules, domain knowledge acquired from various sources of knowledge acquisition is refined and then framed in form of ‘IF-Then’ variety of production rules. System modules are coded in AutoLISP language and user interface is created using visual basic (VB). The system is capable to automate various activities of process planning including blank modeling, blank nesting, determining punch force required, selection of clearance between punch and die, identifying sheet metal operations, and determining proper sequence of operations for manufacturing the part. The proposed system can be implemented on a PC having VB and AutoCAD software, therefore its low cost of implementation makes it affordable even for small scale sheet metal industries.

Expert system for process planning of pressure vessel fabrication by deep drawing and ironing

The fiber reinforced composite material is widely used in the multi-industrial field where the weight reduction of the infrastructure is demanded because of their high specific modulus and specific strength. It has two main merits which are to cut down energy by reducing weight and to prevent explosive damage proceeding to the sudden bursting which is generated by the pressure leakage condition. Therefore, pressure vessels using this composite material in comparison with conventional metal vessels can be applied in the field such as defence industry, aerospace industry and rocket motor case where lightweight and the high pressure are demanded. In this paper, for non-linear finite element analysis of E-glass/epoxy filament wound composite pressure vessel receiving an internal pressure, the standard interpretation model is developed by using the ANSYS, general commercial software, which is verified as the accuracy and useful characteristic of the solution based on AutoLISP and ANSYS APDL. Both the preprocessor for doing exclusive analysis of filament wound composite pressure vessel and postprocessor that simplifies result of analysis have been developed to help the design engineers.

Expert System for Process Planning of Non-axisymmetric Forging Products by Using Society of Cooperative Virtual Forming Processes.

In this paper, the authors use the concepts of a 'virtual process'and a 'real process', and use a 'constraint blackboard' for CAPP for non-axisymmetric hot-forging products. A virtual process is a primitive and basic forming process, which may exist only in the mind of a process designer. A real process is a complex process havig virtual processes as its elements. When the designer designs a forging process, he guesses the transitional pre-form shape in each successive virtual process, and finally assembles the virtual processes into one real process. These virtual processes restrict each other in compressing direction or parting line, deformability, and ability of combination and works cooperatively when they are assembled. The authors researched such virtual processes and their constraints, entered them as 'processing cases data' into a database called the 'processing case base', and implemented an expert system for connecting rod products. A 'constraint blackboard' is a common working memory which can be accessed by the procedures described in every processing case. The system starts design from the final shape and works back toward the raw material. It establishes a manufacturing plan at each virtual process. Once a virtual process starts to be designed, some procedures on the processing case are executed and new constraint is written on the constraint blackboard. When the other virtual process is designed, the system examines the process by referring to the constraint blackboard. Thus, the design process of each virtual process is done cooperatively to others. The system continues to assemble virtual processes into one real process until it fails to find a virtual process which is consistent with past fixed virtual processes.

Expert System for Process Planning of Combined Forging Sequence with Using General Purpose FEM Code.

The authors develop the expert system for process planning of combined cold forging sequence. Starting from the final product shape, the expert system designs a temporally pre-form shape and process by using case-based reasoning. Then, the temporally process is evaluated by the deformation analysis with using general purpose FEM code. When the result is not close to the post-form, temporary pre form shape is corrected by rules described on the cases with considering the result of the analysis. After then, corrected shape is analyzed by the FEM code again. The system repeats the above procedure until getting raw material and develops forging process plans. Thanks to this approach, the system designs forging sequences with using combined process, i. e. direct-indirect extrusion having different extrusion-ratio. A combined process requires lower energy and force than the ordinary in general, so the system is advantageous on developing the sequence design including combined process. The authors applied the system on actual forging example, and evaluate with experiment using plasticine. In the case, developed sequence design requires lower peak-manufacturing force than the ordinary sequence design including no combined process and only 62.5 [%] of the energy of the ordinary.

グラインディングセンタによる研削加工の工程設計用エキスパートシステムの開発

グラインディングセンタによる研削加工の工程設計用エキスパートシステムの開発

An expert process planning system for electronics PCB assembly

The electronics manufacturing is one of the most prosperous industries in the world today. With the continuous advancement in electronics components and automatic assembly machines, printed circuit board (PCB) assembly has become more dynamic and complicated. The process planning is usually a complex and time-consuming task yet an important key in accomplishing a fully automated computer integrated manufacturing (CIM) system. The added diversity of electronic products, inefficiency in planning time and inconsistency among manually generated process plans have increased the necessity for developing a computer aided process planning (CAPP) system for electronics assembly. The success of surface mount technology (SMT) and flexible manufacturing concept make the process planning for electronics assembly a more frequent and challenging task than ever before. This paper discusses and presents a prototype Expert Process Planning System for Electronics Assembly (EPPSEA) which utilizes the expert system technique to solve the complicated process planning problem in a PCB assembly system. The structure, generating strategy and application of the system are described.

An experimental expert system for process planning of sheet-metal parts

This paper presents an experimental expert system for process planning of sheet-metal parts. A basic framework for representing the necessary expert knowledge and part geometry information is outlined. The system, which is developed in Turbo Prolog and implemented for the planning of simple bent and punched parts, is described. Directions for further research are also examined.

Neural Networks for Process Planning of Cold Forging

The technique of neural networks is applied to an expert system for process planning of cold forging in order to improve the process generating speed. A three-layer neural network is used and the back-propagation algorithm is employed to train the network. By utilizing the ability of pattern recognition of the neural networks, a system is developed to relate the shapes of rotationally symmetric products with their preforms and forming methods. Average speed of process inference for the products which have similar shapes to the products used in the network training can be improved significantly by using the trained neural network system.

Implementation of a “backwards planning” technique in the automation of process planning

It is essential to automate the process-planning function to achieve true integration of CAD and NC machining for computer-integrated manufacturing. Several planning techniques have been used for this purpose and the popular method called the “bottom-up” approach or “backwards planning” has been successfully used in developing an expert process-planning system called EXCAP. This paper describes the implementation of this approach, providing details and examples of the model-updating module which enables the planning to be executed automatically for turned components.