1,721,123 research outputs found
Deep learning-supported machine vision-based hybrid system combining inhomogeneous 2D and 3D data for the identification of surface defects
Full text linkMachine vision systems for automatic defect detection commonly adopt 2D image-based systems or 3D laser triangulation systems. 2D and 3D systems present opposite advantages and disadvantages depending on the typology and position of defects to be detected. When the variety of defects is large, none of them performs defect detection accurately. To overcome this limitation, this paper illustrates a hybrid Deep Learning-supported system where the 2D- and 3D-generated data are juxtaposed and analyzed contextually. Anomaly scores are subsequently determined to distinguish suitable and uncompliant parts. The implementation of the hybrid system allowed the identification of defective parts in an aluminium die-cast component with an accuracy concerning true positives of over 95% by comparing the system outputs with human defect detection. The inspection time was reduced by approximately 20% if compared, once again, with the same activities performed by humans. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group
Superhydrophobic surfaces for polymers with micro and sub-micro scale structure via Two-Photon Polymerization
No full textAn approach to improve accuracy and productivity of industrial CMM measurements at high scanning speed
No full textA reference artefact to evaluate the metrological performance in the quantification of raising surface defects on manufactured surfaces
No full text
Preface
No full textThe rapid progress of nanotechnologies poses significant challenges in manufacturing and characterization. Scanning Probe Microscopy (SPM) techniques have significantly contributed to such development, allowing characterization of a number of properties at the microscale and nanoscale. Having been invented for the morphological investigation of surfaces, SPM has represented the basis for the development of techniques where the tip is used for probing physical properties and the SPM position control system is used for imaging such properties on the samples surface, simultaneously to their topography. The combination of scanning probe microscopy, and in particular of Atomic Force Microscopy (AFM) with ultrasound techniques, led to the development of acoustic AFM (A-AFM) and acoustic SPM (A-SPM) opening up to a number of measuring techniques which allow surface mechanical properties imaging. In A-AFM, piezoelectric transducers are used to set the sample surface or the AFM cantilever into vibration at ultrasonic frequencies that are well above the cutoff frequency of the electronics, so that the oscillations are not compensated by the feedback. As a consequence such oscillation does not influence the standard topographical reconstruction, and on the other hand, the ac component of the deflection signal is not suppressed and thus can be subsequently analyzed. The particular way in which ultrasonics and SPM are combined is different for each specific technique and allows collection of different information. Readers working in different fields of nanotechnology, material science, and biology will find in this book a comprehensive overview of such A-SPM techniques, presented by evidencing similarities and peculiarities. We proudly say that the most widely recognized scientists and researchers have contributed to the 17 chapters of the present volume, discussing acoustic SPM techniques both from the theoretical and from the practical points of view. The volume is divided into three parts
- …
