J. H. Vandenbrande and A. A. G. Requicha, "Spatial reasoning for the automatic recognition of machinable features in solid models," IEEE Trans. Pattern Anal. Machine Intell., vol. 15, pp. 1--17, Dec. 1993.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....on feature detection itself. Known techniques for feature detection [12] could be incorporated into our algorithms to obtain a practical system. Thus it is important that in defining our features we limit ourselves to simple features which can be detected by known algorithms of acceptable e#ciency [15, 18]. The current state of the art [10] for surface fitting can reliably fit planes, spheres, cylinders, cones and tori and detect fixed radius rolling ball blends between them [5] Many mechanical parts can be described by these surfaces [16] Simple parts constructed from them often exhibit ....

J. H. Vandenbrande, A. A. G. Requicha. Spatial Reasoning for the Automatic Recognition of Machinable Features in Solid Models. IEEE Pattern Analysis and Machine Intelligence, 15:1269--1285, 1993.

....CNC Cutter Path Generation 5.1 Introduction Research in CNC cutter path generation could be broadly classified into two areas. Automatic tool path generation using feature recognition techniques. Generation of CNC tool paths for sculptured surfaces. In feature based techniques [1] 2] [62], full automation is possible only with complete enumeration of all the manufacturing features which is practically impossible. Thus manual input becomes essential at one stage in any feature based technique. In non feature based techniques, most of the work has been done in generating cutter ....

J. H. Vanderbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machining features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269--1285, 1993.

....in the areas of manufacturing process planning and solid modeling, past research efforts have developed a variety of techniques for reasoning about geometric and topological information. Much research has been done in the area of automatic feature recognition from threedimensional solid models [22, 33, 24, 25, 46]. Marefat et al. 24, 27, 26] introduced a novel way of integrating evidence based reasoning with geometry for process and inspection planning. Marefat s recent work [3] has focused on how to more effectively adapt new planning techniques to process planning. Vandenbrande, Han, and Requichia [45, ....

....46] Marefat et al. 24, 27, 26] introduced a novel way of integrating evidence based reasoning with geometry for process and inspection planning. Marefat s recent work [3] has focused on how to more effectively adapt new planning techniques to process planning. Vandenbrande, Han, and Requichia [45, 46, 21, 22] integrated knowledge based systems with solid modeling to identify machining features and perform process planning for machined parts. Some of the author s past work on geometric reasoning for manufacturing feature identification and process planning includes [34, 33, 16] 2.2. Comparisons of ....

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269--1285, December 1993.

....activities; hence, designs must be interpreted in terms of manufacturing features. Automated feature recognition has become the preferred technique for producing feature based representations, having been employed with varying success for a variety of applications including process planning[26, 25], part code generation for group technology and design analysis [17] These feature technologies rely heavily on the geometric and topological manipulation capabilities of solid modeling systems and deal predominantly with form or machining features. ffl Assembly Planning has been approached as ....

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269--1285, December 1993.

.... domain: since it corresponds to basic operations in the process plan, it will let us develop measures of design similarity that are useful for retrieving designs that have similar process plans; Since a number of well known techniques exist for extracting machining features from CAD models [13, 17] (for example, we use the technique described in [12] it is possible to generate the design signatures automatically. Our future work has two basic directions. We intend to extend the theoretical basis and algorithmic work, by developing new definitions of equivalence relations upon design ....

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269--1285, December 1993.

....scheme of [12] and used a novel combination of expert system and hypothesis testing techniques to extract surface features from polyhedral objects. Perhaps the most comprehensive and formal approach to date for recognizing features and handling their interactions has been that of Vandenbrande [30]. It provides a computationally rigorous framework for recognizing a significant class of realistic machining features of interest for process planning via artificial intelligence techniques in combination with queries to a solid modeler. He formalized a set of feature classes and recognition ....

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269, December 1993.

....plans. We describe how primary feature instances can be used to overcome computational difficulties faced by previous work, and present complexity results for the domain of machined parts. 2 Manufacturing Features A number of attempts have been made to define and classify manufacturing features [1, 6, 23, 2]. Although there are differences among these approaches, many of them share important similarities. For example, a machining feature usually corresponds to the volume of material that can be removed by a machining operation. In general, manufacturing features usually have associated with them ....

....representations. Many of the existing approaches to recognizing feature instances address the problem as one in 3 dimensional geometric pattern recognition to be approached with techniques from AI (such as frame based reasoning, graph and plex grammars, expert systems, neural nets etc. [9, 16, 12, 23], pattern matching [15, 20] graph searching [4, 10, 3, 13] or geometric algorithms [11, 5, 18] Feature instances recognized by these systems are grouped into FBRs using the two approaches described in the next two sections. 4.1.1 Generating FBRs Directly In this approach, FBRs are generated ....

[Article contains additional citation context not shown here]

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269, December 1993.

....(in some cases this may include a description in terms of design features) This step requires coming up with a domain specific representation of the design, using manufacturing features appropriate to the domain at hand. Much previous 7 work has been done on design interpretation for machining [18, 17, 4, 15, 24]. A presentation of a generic framework for achieving design understanding for a multiple critiquing environment is beyond the scope of this paper. The other key component of a generic critiquing system, and the focus of the remainer of this paper, is the facility for design rating and ....

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269, December 1993.

....and pockets. Each such feature of the solid model may correspond to some manufacturing procedure or step of the design process. 2. 4 Feature Recognition from Three dimensional Solid Models Much research has been done in the area of automatic feature recognition from three dimensional solid models [7, 14, 11, 12, 18]. Although there are other representation schemes, the most commonly used representations in systems that perform automatic feature recognition are the B Rep and the CSG. This is in part due to the fact that a majority of solid modeling and CAD systems make use of either the B Rep or the CSG in ....

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269--1285, December 1993.

.... ffl since it corresponds to basic operations in the process plan, it will let us develop measures of design similarity that are useful for retrieving designs that have similar process plans; ffl Since a number of well known techniques exist for extracting machining features from CAD models [13, 17] (for example, we use the technique described in [12] it is possible to generate the design signatures automatically. Our future work has two basic directions. ffl We intend to extend the theoretical basis and algorithmic work, by developing new definitions of equivalence relations upon design ....

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269--1285, December 1993.

....approaches: A manufacturing feature library is a set of manufacturing features, each of which represents a class of shapes, such as slots, holes and pockets, which characterize the types of shapes that can be produced with a given manufacturing process. Feature extractors (Joshi and Chang, 1988; Vandenbrande and Requicha, 1993; Jong and Fuchs, 1994; Han and Requicha, 1995) search the part s geometry for instances of features in the library to determine if the part can be produced. This makes it easy to support downstream reasoning, such as setup planning and tool path planning, because the features are well defined ....

Vandenbrande, J. H. and Requicha, A. A. G. (1993). Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269--1285.

....volumes and then employ a mapping process to apply these features to a particular application. Finally, 3) tool centric approaches identify machinable features by reasoning from properties of the manufacturing equipment. Manufacturing feature approaches: Manufacturing feature based techniques [9, 17, 8, 6, 7] are perhaps the most prevalent approaches to feature recognition. The system is provided with a library of feature types and searches the part geometry of instances of these features. However, feature class approaches are not modular. Each feature contains knowledge about a combination of ....

Jan H. Vandenbrande and Aristides A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269--1285, 1993.

.... et al. 1995, Hayes, 1996, Stor and Wright, 1996, Vancza and Markus, 1996] Other research has investigated methods for automatically detecting the presence of these feature classes directly from the solid model of the part [Choi et al. 1984, Joshi and Chang, 1988, Marefat and Kashyap, 1990, Vandenbrande and Requicha, 1993, Gupta et al. 1994, Regli et al. 1994] The feature recognizer searches the part model for geometry matching these feature descriptions. A drawback to these approaches is that feature class libraries are difficult to maintain and extend. While it is possible to apply these techniques to ....

....considered by selecting the sine table, in addition to the vise, as fixturing devices. With the addition of a sine table, MEDIATOR finds two possible ways to make the part, using clamping configurations show in Figure 23. 4. 7 Example 2: Part III Figure 24 shows a more complex part (adapted from [Vandenbrande and Requicha, 1993]) along with the stock from which it is generated. The set of tools include the flat endmill Face Intersections Removal Volume Pf7 Cf1 Pf7 Part Surface Approach Directions 1 2 1 1 2 1 Tool Motion Requirements q left Feature Tool Shape Requirements Fixturing flat endmill Tool ....

[Article contains additional citation context not shown here]

Vandenbrande, J. H. and Requicha, A. A. G. (1993). Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269--1285.

....which operations to do when and in which setups, and how to hold the workpiece during each setup. In one way or another, most recent work on generative process planning (both by manufacturing researchers and AI researchers) has tried to address these difficulties (e.g. Kambhampati et al. 1992; Vandenbrande and Requicha, 1993; Opas and Mantyla, 1994; S. Gupta et al. 1994b; Das et al. 1994; Hayes, 1995; Britanik and Marefat, 1995 ] However, there are also some recent AI efforts at process planning that unfortunately do not seem to address such difficulties at all. We suspect one reason for this is that the ....

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(12):1269, Dec. 1993.

....representations, in order to incorporate them in a feature based CAD system, for instance. This leads to systems which aim at converting 2 D geometric representations to a higher level model by implementing various schemes for automating the recognition of machinable manufacturing features [18, 23]. A number of recent papers on this topic can for instance be found in the Proceedings of the IFIP International Conference on Feature Modeling and Recognition in Advanced CAD CAM Systems 1 . But in both cases, starting from a paper drawing or directly from a set of geometrical 2 D views ....

J. H. Vandenbrande and A. A. G. Requicha. Spatial Reasoning for the Automatic Recognition of Machinable Features in Solid Models. IEEE Transactions on PAMI, 15(12):1269--1285, December 1993.

....problems, yet to be addressed are how to extend the techniques to better handle interacting features and non linear solid models. Many aspects of the feature recognition problem are still open and active areas of research. Among these are: recognizing and representing interacting features [31], incremental recognition of features [18, 13] modeling alternative feature interpretations and completeness [19, 24] reasoning about the manufacturability of features [12] and incorporation of user customizable feature classes. a) part (after machining) b) part (underside view) Figure 2: ....

....on the work of [15] and augmented it with hypothesis testing techniques. In this method, information from the solid model is used to generate hypotheses about the existence of features. These hypotheses are tested to see if they give rise to valid feature instances. Vandenbrande and Requicha [31] were the first to formalize trace based (or hint based) techniques for constructing features from information in a solid model. In the work of Vandenbrande, the traces are used to fill feature frames in a frame based reasoning system. After filling frames with the trace information present in ....

[Article contains additional citation context not shown here]

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269, December 1993.

....can be generated from the set of primary feature instances. Finally, in Section 7, we present our conclusions and describe the benefits that can be achieved by using our formulation. 2 Manufacturing Features A number of attempts have been made to define and classify manufacturing features [1, 7, 11, 24, 2]. Although there are differences among these approaches, many of them share important similarities. For example, a machining feature usually corresponds to the volume of material that can be removed by a machining operation. In general, manufacturing features usually have associated with them ....

....representations. Many of the existing approaches to recognizing feature instances address the problem as one in 3 dimensional geometric pattern recognition to be approached with techniques from AI (such as frame based reasoning, graph and plex grammars, expert systems, neural nets etc. [8, 16, 5, 12, 24], pattern matching [15, 20] graph searching [4, 9, 22, 3, 13] or geometric algorithms [10, 6, 19] Feature instances recognized by these systems are grouped into FBRs using the two approaches described in the next two sections. 4.1.1 Generating FBRs Directly In this approach, FBRs are ....

[Article contains additional citation context not shown here]

J. H. Vandenbrande and A. A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1269, December 1993.

....as design and planning, which involve synthesis, are much less understood. We speculate that the difficulties arise because synthesis algorithms must reason about space, which is notoriously hard to do computationally. Nevertheless, applications such as feature recognition for machining planning [Vandenbrande93, Han97] dimensional inspection planning [Spyridi90, Spyridi94] and robot path planning [Latombe91] are getting close to industrial usability. Most of these application algorithms use extensively the fundamental queries and constructions described above. For example, mass property calculation for CSG ....

....slot feature, which is a more appropriate abstraction for manufacturing process planning than the ribs. Techniques developed by Requicha and his students at the University of Southern California address issues of automatic feature conversion and dependencies between converted and original features [Vandenbrande93, Han97]. In essence, the input (or design) features are converted either manually or automatically into other, application dependent features. The challenge is to capture the results of these conversions in a form that persists when the parameters of the model are changed. Otherwise, all user ....

J. H. Vandenbrande and A. A. G. Requicha, "Spatial reasoning for the automatic recognition of machinable features in solid models", IEEE Trans. Pattern Analysis & Machine Intelligence, Vol. 15, No. 10, pp. 1269-1285, December 1993.

....poorly when features intersect spatially, e.g. when two slots cross, or a hole intersects a pocket. At USC s Programmable Automation Laboratory we have developed two systems that are very powerful in recognizing intersecting features. The first, called OOFF (Object Oriented Feature Finder) 11] [12] [13] introduced the concept of hint based reasoning for feature recognition. In OOFF, the characteristic traces left by a feature in the surface of a part are used to create a hint, or clue, for the existence of the feature. For example, two parallel, opposing faces generate a slot hint. The ....

....to repair V so as to obtain a maximal feature that does not intrude into the part. Repair is not always possible, and therefore some hints are discarded after completion fails. Non intrusion is not sufficient to ensure feature validity. Accessibility (and a few other conditions discussed in [12] [13] must also be guaranteed. We consider 3 axis machining operations, and therefore the cutter and spindle orientations coincide. A machinable surface must have clearance in the direction of the cutter for the tool to approach and for the cutting motions to proceed without collisions. ....

Vandenbrande, J. H., and Requicha, A. A. G., Spatial Reasoning for the Automatic Recognition of Machinable Features in Solid Models, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 15, No. 12, December 1993, pp. 1-17.

....section summarizes the paper and draws conclusions. 2 Modeler Independence Our research was motivated by practical considerations. We have developed a feature recognizer, dubbedOOFF (Object Oriented Feature Finder) which recognizes machining features such as slots or holes from a solid model [7, 8]. OOFF was built upon PADL 2 and communicated extensively with it through PADL 2 s API. OOFF was written in LISP and all of the PADL 2 libraries were loaded into LISP, making them available as though they were LISP functions. This loading process was time consuming and inconvenient for ....

....such as surfaces. However, topological entities such as faces are designated by name vectors which are integer arrays of length 5. The first four elements of the vector designate the particular assembly, solid, face, and edge, respectively. The 5th element is for internal use. For example, [2,4,7,0,0] is the identifier for the 7th face of the 4th solid under the 2nd assembly. Therefore the PADL 2 adaptor is responsible for mapping such heterogeneous names into Tags. PADL 2 and Parasolid provide very different sets of API procedures. For example, an adaptor procedure may be implemented as a ....

Vandenbrande, J. H., and Requicha, A. A. G., Spatial Reasoning for the Automatic Recognition of Machinable Features in Solid Models, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 15, No. 12, December 1993, pp. 1-17.

No context found.

J. H. Vandenbrande and A. A. G. Requicha, "Spatial reasoning for the automatic recognition of machinable features in solid models," IEEE Trans. Pattern Anal. Machine Intell., vol. 15, pp. 1--17, Dec. 1993.

No context found.

J. Vandenbrande and A. Requicha, "Spatial reasoning for the automatic recognition of machinable features in solid models," IEEE Trans. on Pattern Analysis and Machine Intelligence, pp. 1269--1285, December 1993.

No context found.

J. Vandenbrande and A. Requicha, "Spatial reasoning for the automatic recognition of machinable features in solid models," IEEE Trans. on Pattern Analysis and Machine Intelligence, pp. 1269--1285, December 1993.

No context found.

J. H. Vandenbrande and A. G. Requicha. Spatial reasoning for the automatic recognition of machinable features in solid models. IEEE Transactionson on Pattern Analysis and MAchine Intelligence, 15:1269--1285, 1993.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC