Automated surface inspection is an important task in many manufacturing industries and often requires machine learning driven solutions. Supervised approaches, however, can be challenging, since it is often difficult to obtain large amounts of labeled training data. In this work, we instead perform one-class unsupervised learning on fault-free samples by training a deep convolutional neural network to complete images whose center regions are cut out. Since the network is trained exclusively on fault-free data, it completes the image patches with a fault-free version of the missing image region. The pixel-wise reconstruction error within the cut out region is an anomaly image which can be used for anomaly detection. Results on surface images of decorated plastic parts demonstrate that this approach is suitable for detection of visible anomalies and moreover surpasses all other tested methods.

Computational fluid dynamics (CFD) simulation is an important tool as it enables engineers to study different design options without a time-consuming experimental workload. However, the prediction accuracy of any CFD simulation depends upon the set boundary conditions and upon the applied rheological constitutive equation. In the present study the viscoelastic nature of an unfilled gum acrylonitrile butadiene rubber (NBR) is considered by applying the integral and time-dependent Kaye–Bernstein–Kearsley–Zapas (K-BKZ) rheological model. First, exhaustive testing is carried out in the linear viscoelastic (LVE) and non-LVE deformation range including small amplitude oscillatory shear (SAOS) as well as high pressure capillary rheometer (HPCR) tests. Next, three abrupt capillary dies and one tapered orifice die are modeled in Ansys POLYFLOW. The pressure prediction accuracy of the K-BKZ/Wagner model was found to be excellent and insensitive to the applied normal force in SAOS testing as well as to the relation of first and second normal stress differences, provided that damping parameters are fitted to steady-state rheological data. Moreover, the crucial importance of viscoelastic modeling is proven for rubber materials, as two generalized Newtonian fluid (GNF) flow models severely underestimate measured pressure data, especially in contraction flow-dominated geometries.

No abstract

No abstract

This paper proposes a new machine vision method to test the quality of a semi-transparent automotive illuminant component. Difference images of Frangi filtered surface images are used to enhance defect-like image structures. In order to distinguish allowed structures from defective structures, morphological features are extracted and used for a nearest-neighbor-based anomaly score. In this way, it could be demonstrated that a segmentation of occurring defects is possible on transparent illuminant parts. The method turned out to be fast and accurate and is therefore also suited for in-production testing.