This thesis project was carried out by two students on behalf of SMA Mineral AB, which owns the lime plant in Rättvik, where there was need to establish a sampling method for the local quick lime product. The aim was to ensure a maximum concentration of impurities in the product—primarily carbon and sulphur. The mean value of sulphur found in the input material varied over time. Consequently, a suitable statistical method was needed to ensure product quality for the prospective customer as they required that the sulphur content of the proposed product never exceed 500 ppm.The aim was, on the one hand, to process and compile the sampling results in accordance with a suitable statistical method which enabled reasonable conclusions about the product quality and, on the other hand, to answer three key queries that SMA Mineral AB posed:• to investigate whether the product’s sulphur content was affected during conveyance through the lime plant;• to investigate whether sampling at various time intervals may have been a factor which affected the product’s sulphur content;• to investigate whether there was, or were, any particular times of day at which the sulphur content always maintained the correct level.A number of phases were required to find answers to these questions. The planning phase was initiated by a visit to Rättvik, with the purpose of gaining an overall picture of how work at the plant was conducted as well as which guidelines and regulations were in effect. After this visit, a project plan was drawn up in order to serve as support for further work.The sampling campaign took place during the period of 13–16 April 2015 and analysis of the collected material was carried out the following week at the company’s laboratory in Persberg, Sweden. However, the results from the sampling campaign did not provide sufficient basis for answering the company’s questions, which is why data from SMA Mineral AB’s own data collection was used. Data collected during the sampling campaign proved to follow normal distribution. Subsequently, the statistical analysis of variance method, ANOVA, was applied in order to investigate whether the sulphur content changed with respect to the time interval and the sampling site. The test results demonstrated p-values under 0.005, which meant that neither the sampling site nor the sampling time intervals had an effect on the product’s sulphur content. The company’s question, whether there were daily time intervals of acceptable sulphur content in the product, was answered with the assistance of the company’s own data collection, which demonstrated that it did not follow normal distribution. For that reason, the bootstrap method was used to create confidence intervals for the different points in time. The result showed that there were no points in time during which acceptable material was produced. One reason for this is the occurrence of a set of deviating values that were observed to have a sulphur content that exceeded 1,000 ppm. This report presents recommendations for various measures independently of any opinions SMA Mineral AB may have concerning the source of these values and whether they can possibly be avoided. / <p>Validerat; 20160612 (global_studentproject_submitter)</p>
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:ltu-59100 |
| Date | January 2016 |
| Creators | Makhmour, Salim, Thunström, Robert |
| Source Sets | DiVA Archive at Upsalla University |
| Language | Swedish |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0023 seconds