Wyniki wyszukiwania - BazTech

1

The use of combined quality management instruments to analyze the causes of non-conformities in the castings of the cover of the rail vehicle bearing housing

Czerwińska Karolina, Piwowarczyk Adam

Production Engineering Archives

|

2022

|

Vol. 28, Iss. 3

289--294

EN

The most critical activities influencing the success of each company are continuous improvement of the quality of manufactured products and monitoring of the production process. Skillful use of available technologies and quality management tools allows for eliminating casting non-conformities and preventing their repetition in the future. The research aimed to analyze the types of defects occurring in castings, the location of their most frequent occurrence areas, and to identify the causes of defects in castings of bearing housings used in rail vehicles. The benefits of a combination of quality management tools for diagnosing material discontinuities in the analyzed castings are presented in this article.

2

Comparison of selected shading correction methods

Gądek-Moszczak Aneta, Wojnar Leszek, Piwowarczyk Adam

System Safety : Human - Technical Facility - Environment

|

2019

|

Vol. 1, nr 1

819--826

EN

Shade effect is a defect of the images very often invisible for human vision perception but may cause difficulties in proper image processing and object detection especially if the aim of the task is to proceed detection and quantitative analysis of the objects. There are several methods in image processing systems or presented in the literature, however some of them introduce unexpected changes in the images, what may interfere the final quantitative analysis. In order to solve this problem, authors proposed a new method for shade correction, which is based on simulation of the image background based on analytical methods which return pixel values representing smooth grey level changes. Comparison of the effects of correction by applying standard methods and the method proposed are presented.

3

Machine learning versus human-developed algorithms in image analysis of microstructures

Piwowarczyk Adam, Wojnar Leszek

Quality Production Improvement - QPI

|

2019

|

Vol. 1, Iss. 1

412--416

EN

Automatic image analysis is nowadays a standard method in quality control of metallic materials, especially in grain size, graphite shape and non-metallic content evaluation. Automatically prepared solutions, based on machine learning, constitute an effective and sufficiently precise tool for classification. Human-developed algorithms, on the other hand, require much more experience in preparation, but allow better control of factors affecting the final result. Both attempts were described and compared.