The manufacturing environment is characterized by rapid change, originating new challenges and problems to the production and operation manager in the industry. In response to the need for fast and flexible manufacturing, increasing attention is being given to integration of computing technologies with the manufacturing systems leading to the development of fast and flexible manufacturing systems aided with high performance vision capabilities. This paper presents an inspection and recognition system for manufacturing applications in difficult industrial environments. In such difficult environments, where objects to be recognized can be dirty and illumination conditions cannot be sufficiently controlled, the required accuracy and rigidity of the system are critical features. The purpose of the real-time system is to inspect and recognize air-conditioning objects for avoiding deficiency in the manufactured process and erroneous identifications due to a large variety of size and kinds of objects. The proposed system is composed by five USB cameras (640times480 pixel resolution, 30 Hz frame rates and 8 mm lenses) plug into a conventional computer (Pentium IV 3 GHz). The edged images are features which are relatively robust against illumination changes, so the system can work well in difficult environments mentioned. Experimental results on inspection and recognition of a large variety of air-conditioning objects are provided to show the performance of the system in a difficult environment.
An image acquisition and processing system to measure the width and inspect the quality of the stainless steel strip in a production line is presented in this paper. It is based on the real-time processing of the images acquired by a twin linear camera system. Image processing algorithms to detect defects and anomalies in the edges have been implemented. The core of the image processing is submitted to the GPU of the graphic card to reduce the total processing time. A system like this has been proved and installed in a stainless steel production line for quality control purposes.
We present a procedure for the calibration of an instrument for noncontact thickness measurement of stainless steel sheets, based on a pair of triangulation laser sensors. Firstly, we carry out a general review of the architecture of this kind of instrument and of the problems associated with noncontact measurement based on commercial laser sensors in an industrial production environment. Secondly, we introduce a method for the calibration and characterization of this instrument based on the piecewise linear approximation of the isoline curves obtained in the calibration process (isoline bilinear look-up tables). We follow with a description of the searching and calculation of thickness in these types of tables.
In this paper we present an image processing algorithm to detect and measure the amount of residual oxide remaining on the surface of stainless steel coils for quality control in a production line. This algorithm processes in real time the images taken by the acquisition system which we have designed for this purpose and which has been installed in the finish line of a stainless steel production factory. We present here a more robust and reliable algorithm than the initial one, which has been adapted to deal with non-ideal conditions such as non-perfect homogeneous lighting, different surface finish, water marks, etc., which usually occur in practice.
The argon-oxygen decarburization (AOD) is the refining process of stainless steel to get its final chemical composition through several stages where tons of materials are added and oxygen and inert gas are blown. We present in this paper the design of an empirical model of this process to predict critical values of the decarburization process in order to automate it and enhance the production performance of the AOD. We show that it is possible to build an empirical model, simpler than analytical parameterized models, based on Multilinear Regression or Neural Network Perceptron to predict the amount of oxygen to be blown and the temperature to be reached.
A real time system to measure without contact the length of stainless steel sheets in a production line is presented in this paper. The items are measured in real time as they are cut in the production line and are moved forward by a conveyor passing down a differential laser sensor device which measures and integrates its perpendicular speed. One challenge of the system is to deal with different length and speed maintaining the accuracy. Also installation, calibration and supervision procedures have been established. In addition the designed system must be robust enough to be installed in the hard industrial environment of the iron and steel works. The presented system has been designed and installed for quality control purpose in a stainless steel factory.