University of Oulu

System for measuring steel scrap volume using depth imaging

Saved in:
Author: Veijola, Tommi1
Organizations: 1University of Oulu, Faculty of Information Technology and Electrical Engineering, Department of Information Processing Science, Information Processing Science
Format: ebook
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 2.6 MB)
Pages: 48
Persistent link:
Language: English
Published: Oulu : T. Veijola, 2023
Publish Date: 2023-05-12
Thesis type: Master's thesis
Tutor: Seppänen, Pertti
Reviewer: Seppänen, Pertti
Kelanti, Markus


Sustainability and green values are major themes in the world today. Companies across all fields are constantly implementing new technologies to reduce emissions and to limit the magnitude of global warming. The steel industry in general is one of the major producers of carbon dioxide emissions.

The objective of this thesis was to develop a system to measure the volume of scrap metal being charged to an electric arc furnace. Obtaining the scrap volume would help the furnace operators in timing the charging of scrap baskets, thus avoiding the adverse effects resulting from early and late charging. The intention is to increase the energy efficiency of the process.

The theory section of the thesis provides a short overview of the electric arc furnace process and a more detailed description of the charging process. Depth imaging technologies are then explored from a theoretical standpoint to provide the background for the selection and usage of imaging hardware.

In this thesis, design science research methodology was utilized to develop the scrap volume measurement system, which consists of imaging hardware and developed software. The actual contribution of this thesis is the algorithm to extract the height of the scrap surface level from a 3-dimensional image of scrap baskets. The development process was iteratively carried out in a steel factory.

The system performance was evaluated in a real-world scenario. It was established that the system was able to capture 3-dimensional data from scrap baskets and determine the scrap surface level height according to the algorithm. However, for some cases the image capturing did not perform as expected. These failure cases were a result of either steel dust obstructing the scene or the inability of the camera to capture data from unreflective material.

Further research prospects were identified during conducting of the thesis. The failure cases could be addressed either programmatically, with new hardware technology, or a combination of both. Also, research could be conducted on the usage of the information provided by the system in actual charging events with the goal of optimizing charging timing.

see all

Copyright information: © Tommi Veijola, 2023. Except otherwise noted, the reuse of this document is authorised under a Creative Commons Attribution 4.0 International (CC-BY 4.0) licence ( This means that reuse is allowed provided appropriate credit is given and any changes are indicated. For any use or reproduction of elements that are not owned by the author(s), permission may need to be directly from the respective right holders.