1.

Basic Shape Representation of feature extraction::

The advanced b-rep shape representation ABSR is used as the functional unit for the feature extraction process. The ABSR consists of a set of representation items. This set contains an entity of the type manifold solid b-rep. the manifold solid b-rep entity or its subtype namely b-rep with voids contains the complete definition of the geometry and topology of the solid in the b-rep format. The manifold solid b-rep is a finite arc wise connected volume, bounded by one or more surfaces, each of which is a connected, oriented, finite, closed manifold. There are no restrictions on the number of holes or voids within the volume. It contains an outer closed shell which defines the outer extent of the solid. It the solid contains any voids, they are defined using b-rep with void, with the void formed by a set of oriented closed shells. Void shells are contained completely within the outer shell. The closed shell, which is a type of connected face set, is a set of arc wise connected surfaces known as faces. The working unit in an ABSR is a subtype of face called advanced face.

LITERATURE REVIEW:
Two volumetric features are defined as interacting features if their boundaries intersect, so that they share a non-empty, common volume. More than two volumetric features are called interacting features if every one of them interacts with at least another one and all of them form a connected volume. We classify feature interactions into six categories according to three types of topology variations caused by feature interaction: merging of faces, loss of concave edges, and splitting of faces. Merged faces are those that are shared by more than one feature. To completely cover all combinations of the above three conditions would require eight types of feature interactions. However, two combinations are impossible because both split face and lost concave edge cannot be true simultaneously; this reduces the possible types to six, as shown in Figure 2.4 and Table 2.2. It should be noted that there is no direct correspondence between our six interaction classes and the two interaction types identified by Joshi and Chang. (Gao and Shah, 1998)

The main objective of the project is 1. To recognize and extract the prismatic interacting features along with isolated features. 2. The geometry and topological information of the feature is first extracted from STEP file. 3. The coding is done in object oriented programming method C++ to extract information which uses STEP file as input file for the extraction of geometric and topological information. 4. Further, the segregation of views and recognition of features on all the views is done on 3D parts models by using Region Technique and Object Rotation Technique.

5. WORK PLAN:
1. To recognize and extract the prismatic interacting features along with isolated features. a. Selecting the features which are to be extracted: The interacting of prismatic features together with isolated ones is studied. The features can be rectangular boss, through pocket, blind pocket and the combinations between those features.

Fig.1 Selected features

Fig.2 Combinations of selected features to study

b. Modeling the features by using Pro-e software: The features are first modeled in pro-engineering software. c. STEP file: The geometric and topological information is extracted from STEP neutral file format. STEP is an unambiguous computer-interpretable representation of product data, which offers the facility of an efficient exchange between design, engineering and manufacturing systems and uses EXPRESS to specify the product information to be represented that enables precision and consistency of representation and facilitates implementation. STEP file consists of two parts: the head file and data segment. The head file includes administration and attribute information such as author, date and so on, which begins with the

key word "HEADER". The data segment is the principal part of STEP file, which includes a lot of instantiated objects of entities types defined by EXPRESS. The data structure of STEP file is treelike which is composed of level of entity, face, edge and point. d. The coding is done in object oriented programming method C++ to extract information which uses STEP file as input file for the extraction of geometric and topological information.

The field of feature recognition and feature-based design has been considerably researched. In feature recognition, the solid model for the part is first created and then the manufacturing features are identified or extracted from this model. On the other hand, in the design by feature approach, there is a database of manufacturing or other type (depending on interest for feature extraction) of features (e.g., holes, slots, grooves, etc)., which the designer can use to synthesize the part design. Other information such as manufacturing tolerances, datum information, surface attributes and material specifications can be specified by the designer. This section presents the review of some research work that has been done in terms of extraction of form features from CAD information models. There is also a review of some of the STEP-based feature extraction methods that have been developed recently. Out of all methods the solid modeling techniques are studied more. The CSG includes the volumetric representation, in which the parameterized primitive solid entities are operated by Boolean operation. Transformations are then applied for realizing the solid. Unlike the CSG, in B-REP the solid is represented in hierarchal order. The 3D is represented in terms of 2D primitives; the 2D is represented in terms of 1D primitives. The feature recognition from solid representation include the Graph Based Approach, Convex hull Decomposition method, Cell decomposition method, Hint based methods, Volume decomposition and re-composition method and Hybrid methods. The convex hull decomposition technique decomposes a volume by subtracting it from its convex hull Woo and repeating the process for all the resulting volumes.

developed this type of algorithm, in which a volume is decomposed into alternating sum of volumes(ASV) and the features are extracted from it. The algorithm however has a problem of non-convergence resulting in erroneous volumes of features. Kim developed a product shape recognition algorithm using convex decomposition, and extending the original ASV to avoid non-convergence. The algorithm called alternating sum of volumes partitioning (ASVP) can be applied to polyhedral solids. ASVP decomposition is a hierarchical decomposition of the boundary faces of the given solid. The ASVP is converted into a form feature decomposition (FFD), wherein all the components represent meaningful high level shape entities. However, this technique can only be applied to polyhedral solids. Pariente and Kim have integrated an incremental update form feature recognizer with the earlier system. The system can update the ASVP structure if any changes are made to the design. Ferreira and Hinduja have also described a feature recognition technique that is applied to 2.5D components created from a boundary representation (B-Rep) solid modeler. The method involves determination of the convex hull for the components faces. The approach works on a face-by-face basis and so it is not capable to dealing with complex features involving interactions between faces. The system can also determine possible directions of approach for the cutter and machining depths.