09-11-2012, 11:40 AM
Methodology of analysis of casting defects
casting defect.doc (Size: 45.5 KB / Downloads: 39)
Abstract
Purpose: The goal of this publication is to present the methodology of the automatic supervision and control
of the technological process of manufacturing the elements from aluminium alloys and of the methodology of
the automatic quality assessment of these elements basing on analysis of images obtained with the X-ray defect
detection, employing the artificial intelligence tools. The methodologies developed will make identification and
classification of defects possible and the appropriate process control will make it possible to reduce them and
to eliminate them - at least in part.
Design/methodology/approach: The methodology is presented in the paper, making it possible to determine the
types and classes of defects developed during casting the elements from aluminium alloys, making use photos
obtained with the flaw detection method with the X-ray radiation. It is very important to prepare the neural
network data in the appropriate way, including their standardization, carrying out the proper image analysis and
correct selection and calculation of the geometrical coefficients of flaws in the X-ray images. The computer
software was developed for this task.
Introduction
To meet the customer requirements car manufacturers need to develop new technologies related to safety and comfort of travel. As a result the car weight and dimensions are increasing. At the same time the fuel consumption and exhaust emission are increasing too. Thanks to light materials such as aluminum alloys, car manufactures may aim to reduce their weight. These alloys have become popular in automotive industry owing to their low weight and some casting and mechanical qualities [1,2]. The
casting defects occurring during the technological process may be identified by various research methods including microscopy and defectoscopic methods such as X-ray method. The technological progress in material engineering causes the continuous need to develop product testing methods providing comprehensive quality evaluation. In material engineering it is the images obtained by various methods that have become the source of information
about materials. The type of image being the subject of analysis depends on the selected registration method. Metallographic structures of images are obtained by light and electron scanning microscopy. These images are the source of information on material structure, ongoing processes and its properties. Images obtained by defectoscopic methods such X-ray and ultrasound methods provide information on material defects occurring at
various stages of technological processes [3,4,5].
Experimental procedure
This paper presents both the general assumptions for the
application of selected methods of artificial intelligence and the statistical study of classification of defects by X-ray methods in aluminium alloy castings.
The purpose of the applied methodology was to identify the
casting defects [11] that occurred during the casting process (fig.1, fig. 2).
The research was carried on the images of automotive engine elements obtained by the X-ray defectoscopy. To specify the casting quality, the methods of analysis of image defects registered in castings by X-ray methods were applied. To enable the correlation between the morphology of defects registered in research, the scale of X-ray images presenting various sections of automotive engine elements were unified.
Conclusion
The developed computer system, in which the neural networks as well as the method of automatic image analysis were used, can ensure the automatic identification and classification of defects in Al-Si alloy casting, EN AC-AlSi7Cu3Mg type. It has become the way to support and automate the decision to eliminate the castings
below the quality requirements thus reassuring the repetitiveness and objectivism of the results of the evaluation of the metallurgical value of these alloys. The correctly specified number of products enables such technological process control that the number of
castings defects can be reduced by means of the proper correction of the process. Controlling the technological process on the basis of the computer generated information focused on the product quality,can enable the optimisation of this process and so the reduction of defective castings and in the result the reduction of expenses and environmental pollution.