Development of model identification methodology based on form recognition for Computer-Aided Process Planning
Journal of Advanced Mechanical Design, Systems, and Manufacturing
Computer-Aided Process Planning (CAPP) systems have become essential in manufacturing environments to integrate the information between CAD and CAM systems, and to automatically generate the NC code from the CAD model. Though the future of these systems seems to belong to the use of Artificial Intelligence to create knowledge-based algorithms which emulate human decisions, the CAPP systems based on feature recognition and model matching, which use databases of previously known mechanical
... nts to generate new process plans, are also a very interesting option due to their accuracy and smaller development costs. Many researchers have proposed different kind of feature recognition algorithms before. However, these algorithms are usually application-dependent and require external codes to identify the features of wireframe models. This paper proposes a new methodology for shape recognition and model matching stages which improves the accuracy of the recognition tasks, uses solid models instead of wireframe models and can be successfully applied to any kind of part. The methodology is based on an original coding system that links the geometric information extracted from the CAD model with the features of the part by means of an identification sequence which is detailed in the text. Also, a score system has been created for the model matching stage. The obtained results show that the system presents high accuracy in shape recognition, feature identification and model matching tasks, even when the analyzed part is similar to the ones in the database. In addition, quantitative geometric data is also extracted from the CAD model on behalf of future steps of the CAPP system, such as the NC code generation stage. In contrast to other systems, this methodology can be easily applied to the industry since it makes use of the CAD model only. manufacturing processes. CAPP systems have also been developed as a link between Computer-Aided Design (CAD), Computer-Aided Manufacturing (CAM) and Material Requirement Planning (MRP) (Ciruana et al., 2006) . In an integrated manufacturing environment, CAPP systems allow the designers to manage the flow of information between CAD, CAM, MRP and Numerical Control (NC) programs. This paper focuses in the first stages of CAPP systems which analyze the CAD model of the part and select, from a previously known database, the most similar one. The process plan of the new part can be created automatically based on the process plans of the database's parts. Because of that, this research proposes a new methodology in order to work directly with the CAD model and, consequently, simplify the shape recognition process while improving its accuracy. To do so, the developed system has been divided in three stages (shape recognition, component identification and database-based model matching), and has been laid out as a sequential flow in which the output of a stage is the input for the next one. The proposed methodology works in a solid model environment, avoiding unclear wireframe models of the part and allowing the system to be applied in current industry. As this methodology has been programmed in VBScript using the SolidWorks API interface, only SolidWorks is required (except, of course, Microsoft Excel or similar to view the output files). This can be achieved by means of an original coding system that generates an identification sequence. This sequence links the information of the part, extracted directly from the CAD model, with the features and components that make it up. Therefore, no external application-dependent codes are required to recognize the features of the analyzed part. Besides, the development of a score system that, among others, makes use of these identification sequences, improves substantially the accuracy in model matching tasks. The paper has been divided as follows: first, a review of some existing shape recognition and model matching methods is presented in Section 2; the proposed methodology is explained in detail in Section 3 (including a practical application), which in turn has been divided in three sub-sections, one for each stage of the methodology; finally, Section 4 outlines some of the most important conclusions, and states the advantages of this methodology when compared with other existing shape recognition and model matching methods.