1. A model of tool wear monitoring system for turningAco Antić, Goran Šimunović, Tomislav Šarić, Mijodrag Milošević, Mirko Ficko, 2013, original scientific article Abstract: Acquiring high-quality and timely information on the tool wear condition in real time, presents a necessary prerequisite for identification of tool wear degree, which significantly improves the stability and quality of the machining process. Defined in this paper is a model of tool wear monitoring system with special emphasis on the module for acquisition and processing of vibration acceleration signal by applying discrete wavelet transformations (DWT) in signal decomposition. The paper presents a model of the developed fuzzy system for tool wear classification. The system comprises three modules: module for data acquisition and processing, module for tool wear classification, and module for decision-making. The selected method for feature extraction is presented within the module for data classification and processing. The selected model for the fuzzy classifier and classification in experimental laboratory conditions is shown within data classification and clustering. The proposed model has been tested in longitudinal and transversal machining operations.
Keywords: artificial intelligence, tool wear monitoring, feature extraction
Published in DKUM: 10.07.2015; Views: 1506; Downloads: 138
 Full text (1,87 MB)
This document has many files! More... |
2. Fast convex layers algorithm for near-duplicate image detectionSmiljan Šinjur, Damjan Zazula, Borut Žalik, 2012, original scientific article Abstract: This paper builds on a novel, fast algorithm for generating the convex layers on grid points with linear time complexity. Convex layers are extracted from the binary image. The obtained convex hulls are characterized by the number oftheir vertices and used as representative image features. A computational geometric approach to near-duplicate image detection stems from these features. Similarity of feature vectors of given images is assessed by correlation coefficient. This way, all images with closely related structure and contents can be retrieved from large databases of images quickly and efficiently. The algorithm can be used in various applications such as video surveillance, image and video duplication search, or image alignment. Our approach is rather robust up to moderate signal-to-noise ratios, tolerates lossy image compression, and copes with translated, rotated and scaled image contents.
Keywords: near duplicate image detection, feature extraction, geometric features, convex layers, similarity measure
Published in DKUM: 10.07.2015; Views: 1321; Downloads: 72
 Link to full text |
3. Feature extraction from CAD model for milling strategy predictionJože Balič, Simon Klančnik, Simon Brezovnik, 2008, original scientific article Abstract: In this paper we present a procedure of feature determination from a CAD model. From the model we extract information, which has the greatest influence on the technological parameters of treatment and then transform this information into appropriate input data for different intelligent processing strategy prediction systems (for example artificial neural network). With formally complex CAD models, different processing strategies are required on a single workpiece. For this reason we use segmentation as described in this paper, to partition the surface of the CAD model into regions, so that we treat each region as an independent model and determine its features.
Keywords: CAD-CAM systems, milling strategies, feature extraction, CAD models, segmentation
Published in DKUM: 31.05.2012; Views: 2161; Downloads: 42
Link to full text |
