Raw material optimization and CO₂ sensitivity-predictive analytics in cement manufacturing: a case study at Union Bridge Plant, Heidelberg Materials, Maryland
| dc.contributor.author | Boakye, Kwaku, author | |
| dc.contributor.author | Simske, Steve, advisor | |
| dc.contributor.author | Bradley, Tom, committee member | |
| dc.contributor.author | Troxell, Wade, committee member | |
| dc.contributor.author | Goemans, Chris, committee member | |
| dc.date.accessioned | 2024-05-27T10:32:48Z | |
| dc.date.available | 2024-05-27T10:32:48Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | Cement has been in use by humans throughout history, and its manufacturing process has undergone many changes. The high increase in economic growth around the world and the demand for rapid infrastructure development due to population growth are the underlying reasons for the globally high cement demand. Cement is produced by grinding clinker together with a mixture of ground gypsum. The clinker is produced using a rotary kiln which burns a mixture of limestone, clay, magnesium, silica, and iron with desired atomic percentages through the calcination process. The quarry serves as the main source of raw material for the rotary kiln in cement production. Over the years cement manufacturing has hurt environmental, social, and political aspects of society. This negative impact includes the overuse of raw material which is obtained by mining resulting in disturbed landmass, overproduction of rock waste material, and the emission of CO2 resulting from the calcination of limestone in the pyro process. The study looks at three cement manufacturing systems and uses different methodologies to achieve results that can be implemented in the cement industry. These three systems were (1) the quarry (2) the preheat tower and (3) the kiln. Ensuring the consistency of material feed chemistry, with the quarry playing a pivotal role, is essential for optimizing the performance of a rotary kiln. The optimization of the raw material also allows limited use of raw materials for cement manufacturing, cutting down waste. The study employed a six-step methodology, incorporating a modified 3D mining software modeling tool, a database computer loop prediction tool, and other resources to enhance mining sequencing, optimize raw material utilization, and ensure a consistent chemistry mix for the kiln. By using overburden as a raw material in the mix, the quarry nearly universally reduced the environmental impact of squandering unwanted material in the quarry. This has a significant environmental impact since it requires less space to manage the overburdened waste generated during mining. In addition, raw material usage was optimized for clinker production, causing a reduction of 4% in sand usage as raw material, a reduction in raw material purchase cost, a reduction of the variability of kiln feed chemistry, and the production of high-quality clinker. The standard deviation of kiln feed LSF experienced a 45 percent improvement, leading to a 65 percent reduction in the variability of kiln feed. The study also uses machine learning methods to model different stages of the calcination process in cement and to improve knowledge of the generation of CO2 during cement manufacturing. Calcination plays a crucial role in assessing clinker quality, energy requirements, and CO2 emissions within a cement-producing facility. However, due to the complexity of the calcination process, accurately predicting CO2 emissions has historically been challenging. The objective of this study is to establish a direct relationship between CO2 generation during the raw material manufacturing process and various process factors. In this paper, six machine-learning techniques are explored to analyze two output variables: (1) the apparent degree of oxidation, and (2) the apparent degree of calcination. Sensitivity analysis of CO2 molecular composition (on a dry basis) utilizes over 6000 historical manufacturing health data points as input variables, and the findings are utilized to train the algorithms. The Root Mean Squared Error (RMSE) of various regression models was examined, and the models were then run to ascertain which independent variables in cement manufacturing had the largest impact on the dependent variables. To establish which independent variable had the biggest impact on CO2 emissions, the significance of the other factors was also assessed. | |
| dc.format.medium | born digital | |
| dc.format.medium | doctoral dissertations | |
| dc.identifier | Boakye_colostate_0053A_18229.pdf | |
| dc.identifier.uri | https://hdl.handle.net/10217/238478 | |
| dc.language | English | |
| dc.language.iso | eng | |
| dc.publisher | Colorado State University. Libraries | |
| dc.relation.ispartof | 2020- | |
| dc.rights | Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright. | |
| dc.subject | cement | |
| dc.subject | machine learning | |
| dc.subject | sustainability | |
| dc.subject | CO2 emission | |
| dc.subject | AI | |
| dc.subject | raw material optimization | |
| dc.title | Raw material optimization and CO₂ sensitivity-predictive analytics in cement manufacturing: a case study at Union Bridge Plant, Heidelberg Materials, Maryland | |
| dc.type | Text | |
| dcterms.rights.dpla | This Item is protected by copyright and/or related rights (https://rightsstatements.org/vocab/InC/1.0/). You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s). | |
| thesis.degree.discipline | Systems Engineering | |
| thesis.degree.grantor | Colorado State University | |
| thesis.degree.level | Doctoral | |
| thesis.degree.name | Doctor of Philosophy (Ph.D.) |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Boakye_colostate_0053A_18229.pdf
- Size:
- 4.54 MB
- Format:
- Adobe Portable Document Format