Vision-Based Online Process Control in Manufacturing Applications

Abstract

Listen

Translate article

Applications such as layered manufacturing, or in general, solid free-form fabrication, pose a major challenge on online process control. For these parts to be functional, it is imperative that their mechanical and structural properties are strictly kept within respective tolerances. To that end, no internal or external defects, especially voids, can be tolerated. Since these parts are made layer by layer, it is necessary to inspect top surface and boundary of each layer before the next layer is deposited. Two issues are of major concern here: 1) inspection must be nondestructive, that is, layer surface and boundary must not be touched by the inspecting instruments and 2) the time window for inspection and any corrective measures should not exceed the maximum time limits necessary for two adjacent layers to properly bind together. Here, we present a closed-loop online process control model, where the process feedbacks are obtained from a 3-D imaging system, and where the process dynamics model takes into account the correlation and dependency between adjacent layers. To ensure that the feedback is performed within the tolerable time windows, our 3-D image processing parametric model takes advantage of physical characteristic of layer surface, and uses Gaussian function as a shape descriptor of image units. We obtain 2-D profiles from representative signature(s), and then sweep along road path defined in the CAD model. The idea of reconstructing representative signature comprises some accuracy, but compared with classical shape-from-shading method, the proposed approach is computationally more efficient. The 3-D quality measures (such as volume or depth of voids) are then fed to process dynamics model, which computes the necessary compensation on the deposition flow rate for the next layer. We examine three process dynamics models to And out that a fuzzy model which takes into account correlation between adjacent layers and includes locally linear submodels for underfills and overfills is the most appropriate.