Emanuele Zappa, Rui Liu
In a wide range of monitoring applications, vision systems are nowadays applied. The main advantages of vision-based monitoring include the possibility to: i) measure a wide region of the target, obtaining a dense measurement, ii) obtain a 3D estimation of shape, displacements and strain field, iii) measure with a completely contactless technique, therefore avoiding loading effect and wear of measuring components and target. Digital Image Correlation (DIC) is an image processing technique that allows measuring the displacement and strain fields of target, as well as the 3D shape of the...
TC10 Workshop on Technical Diagnostics 2016
· TC10
· 2016
· Download
Liangliang Cheng, Giorgio Busca, Alfredo Cigada
Modal analysis is commonly considered as an effective tool to obtain the inherent characteristics of structures including natural frequency, modal damping and mode shapes, which are significant indicators for monitoring the health status of engineering structures. In this paper, distributed fiber optics, as dense measurement transducer has been applied into acquiring huge amount of strain data along the beam surface. Thanks to the dense spatial resolution, CMIF (Complex Mode Indicator Function) is used to identify strain modal parameters like natural frequency and modal damping. Strain mode...
TC10 Workshop on Technical Diagnostics 2016
· TC10
· 2016
· Download
Vladimir Chmelko, Martin Garan
In most of cases the structural condition monitoring allows to receive significant states or values in a real operation of that structure, such as: - change in value of safety coefficient by reason of arising overload or non-standard operation mode during service - vibrations increasing by reason of change in toughness of the structure - increasing of fatigue damage accumulation in a critical point or section by reason of change in variable stress amplitudes In this paper, there is presented the extended concept of compensation for elimination of unwanted offset change that can appear during...
TC10 Workshop on Technical Diagnostics 2016
· TC10
· 2016
· Download
Alberto Lavatelli, Emanuele Zappa
This paper addresses the problem of motion blur when 3D vibration monitoring is performed by means of vision based measurement methods. Starting from an original analytic model developed previously by the authors, the paper discusses the effects of acquisition parameters on the final measurement accuracy. Consequently the paper proposes an experimental method in order to asses the presented theoretical framework as well as the accuracy of a generic vision based vibration monitoring system.
TC10 Workshop on Technical Diagnostics 2016
· TC10
· 2016
· Download
Marc Seimert, Clemens Guehmann
The paper presents a vibration based diagnostic system to detect cracks in balls of hybrid ball bearings. The diagnostic system based on a Bayesian Classifier. It is shown that it is able to separate healthy bearings from damaged balls and races. The system is tested with measurement data from a bearing test bench in different operating points of the bearing.
TC10 Workshop on Technical Diagnostics 2016
· TC10
· 2016
· Download
Dorel Aiordachioaie, Theodor D. Popescu
The objective of the paper is to introduce an experimental model (VIBROMOD) designed for solving change detection and diagnosis problems in various fields of applications, mainly vibration engineering. The hardware structure contains two basic levels: one for fast computations and alarms, which processes data in a matter of hours, and, an upper level, for large-scale monitoring and statistical computation of moments, over a time span of days and months. The algorithms running on VIBROMOD are coming from a specialized toolbox, which contains classical methods, based on statistical signal...
TC10 Workshop on Technical Diagnostics 2016
· TC10
· 2016
· Download
Diego Scaccabarozzi, Bortolino Saggin, Luca Cornolti, Marco Tarabini, Hermes Giberti
The tuning of Injection Stretch Blow Molding (ISBM) process for PET bottles is crucial to lower the production costs, reduce the environmental impact and assure a sufficient quality of the final product. Among the parameters defining PET bottles quality, the thickness is of primary importance for the appearance and mechanical resistance of the final product. Up to date, tuning of the process is demanded to the operator skills through a trial and error process, iterated until the wanted configuration is achieved. Moreover, the process is not controllable because the PET bottles...
TC10 Workshop on Technical Diagnostics 2016
· TC10
· 2016
· Download
Konstantin Trambitckii, Katharina Anding, Galina Polte, Daniel Garten, Victor Musalimov, Petr Kuritcyn
Quality assessment is an important step in production processes of metal parts. This step is required in order to check whether surface quality meets the requirements. Progress in the field of computing technologies and computer vision gives the possibility of surface quality assessment using industrial cameras and image processing methods. Authors of different papers proposed various texture feature algorithms which are suitable for different fields of images processing. In this research 27 texture features were calculated for surface images taken in the different lighting conditions....
TC10 Workshop on Technical Diagnostics 2016
· TC10
· 2016
· Download
Zsolt János Viharos, Jenö Csanaki, János Nacsa, Márton Edelényi, Csaba Péntek, Krisztián Balázs Kis, Ádám Fodor, János Csempesz
The paper introduces a methodology to define production trend classes and also the results to serve with trend prognosis in a given manufacturing situation. The prognosis is valid for one, selected production measure (e.g. a quality dimension of one product, like diameters, angles, surface roughness, pressure, basis position, etc.) but the applied model takes into account the past values of many other, related production data collected typically on the shop-floor, too. Consequently, it is useful in batch or (customized) mass production environments. The proposed solution is applicable to...
TC10 Workshop on Technical Diagnostics 2016
· TC10
· 2016
· Download
Piotr Bilski
The paper presents the application of Self- Organizing Maps (SOM) to the ambiguity groups detection in the analog system. This type of neural network is able to find dependencies in data, indicating groups of similar examples in the data set used for training the classifier or the regression machine. Various configurations of the network were implemented and compared. The ability to detect ambiguity groups was verified on the model of the induction machine. Results show the efficiency of the approach, able to identify examples difficult to distinguish by the fault detection and location...
TC10 Workshop on Technical Diagnostics 2016
· TC10
· 2016
· Download