03-01-2013, 12:56 PM
Feature-Based Reverse Engineering of Mechanical Parts
1Feature-Based Reverse.pdf (Size: 545.07 KB / Downloads: 115)
Abstract
Reverse engineering of mechanical parts requires extraction of information about an instance of
a particular part sufficient to replicate the part using appropriate manufacturing techniques. This
is important in a wide variety of situations, since functional CAD models are often unavailable
or unusable for parts which must be duplicated or modified. Computer vision techniques applied
to 3–D data acquired using non-contact, three-dimensional position digitizers have the potential
for significantly aiding the process. Serious challenges must be overcome, however, if sufficient
accuracy is to be obtained and if models produced from sensed data are truly useful for manufacturing
operations. This paper describes a prototype of a reverse engineering system which uses
manufacturing features as geometric primitives. This approach has two advantages over current
practice. The resulting models can be directly imported into feature-based CAD systems without
loss of the semantics and topological information inherent in feature-based representations.
In addition, the feature-based approach facilitates methods capable of producing highly accurate
models, even when the original 3–D sensor data has substantial errors.
INTRODUCTION
CAD models are often unavailable or unusable for parts which must be duplicated or modified. This is a particular
problem for long life cycle systems for which spare part inventories have been exhausted and original
suppliers are unable or unwilling to provide custom manufacturing runs of spare parts at affordable prices and
in a timely manner. For many parts, eitherCAD systems were not used in the original design or the documentation
on the original design is otherwise inadequate or unavailable. For a variety of reasons, CAD models,
even when they exist, may not be sufficient to support modification or manufacturing using modern methods.
Finally, shop floor changes to the original design may mean that the originalCAD model no longer accurately
reflects the geometry of the part. Reverse engineering techniques can be used to create CAD models of a part
based on sensed data acquired using three-dimensional position digitization techniques. Part-to-CAD reverse
engineering allows up to date NC fabrication plus easier modification of the design than would otherwise be
possible. Successful instances include everything from sporting goods to aircraft parts.
FEATURE-BASED REVERSE ENGINEERING
Sensor-based reverse engineering of mechanical parts must yield complete and accurate object models appropriate
for computer-aided manufacturing. Current commercial practice, which represents geometry in
terms of scan lines or meshes of scan points, is inflexible and requires careful coordination between scanning
patterns, tool selection, and tool paths. Parametric model fitting techniques proposed to date do not use
geometric primitives that are natural to most manufacturing operations. Methods for extracting manufacturing
features from lower-level geometric representations are intended to work with existingCAD models, not
imperfect sensed data.
Improvements can be made by specializing the recovery of object models to the manufacturing environment.
Most machined parts are made using a relatively small number of manufacturing operations, each of
a constrained form (Figure 1). Reverse engineering can be done using a form of parametric model fitting,
where the primitives correspond to these features. This avoids inconsistencies between actual object shape
and what the models are capable of representing, while leading in a natural and obvious way to representations
usable in feature-based CAD/CAM systems. The approach we describe here is interactive, which
improves performance and allows for human entry of information that cannot be acquired from sensed data
alone.
To demonstrate the effectiveness of feature-based reverse engineering, we have created a prototype system
called REFAB (Reverse Engineering – FeAture-Based). REFAB allows a user to interactively define
a model composed of mechanical features from a set of 3–D surface points. The user specifies the types of
manufacturing features present and the approximate location of each feature in the object. REFAB deals
with the determination of precise, quantitative parameterization of each feature. The final output is a fully
specified model usable by the Alpha 1 CAD/CAM system. Though we have not yet done so, it would be relatively
easy to produce models suitable for other CAD packages supporting manufacturing features, such as
Pro/ENGINEERTM. The ability to create feature-based models in a more generic form awaits futher progress
on standardization efforts such as PDES/STEP.
SEGMENTATION, FITTING, AND REFINEMENT
In REFAB, the first step in reverse engineering a machined part is to define the stock from which the part is to
be cut. Currently, we support only block stock and determine the dimensions using a straightforward bounding
box computation on the position data. Extensions to standard stock sizes and other stock shapes would
be straightforward. The remaining features require a more careful fit to the position data. Three interrelated
problems must be solved in order to accurately model a particular manufacturing feature: determination of
feature type, segmentation of relevant 3–D points, and model fitting. The user specifies the feature type and
approximate location using REFAB’s control panel. Thus, no automatic feature recognition is required. The
segmentation and fitting operations proceed automatically, using an iterative refinement process.
The accuracy of model fitting depends on the constraints that are used as part of the approximation process.
When fitting surface patches to 3–D points, these constraints are expressed in terms of the functional
form of the patches (i.e., planar, cylindrical, conic, etc.) or in terms of some measure of smoothness as for
splines. An inappropriate choice of constraints or an incorrect partitioning of the original points prior to fitting
individual surface patches can lead to models that are inaccurate representations of the underlying shape.
REFAB avoids most difficulties associated with data partitioning by using a robust, top-down segmentation
technique. Two classes of constraints are used in the model fitting process. The first exploits the 2