The diagnostic monitoring of the acoustic emission from a laboratory ball mill
| dc.contributor.advisor | Aldrich, C. | en_ZA |
| dc.contributor.advisor | Weber, O. M. | en_ZA |
| dc.contributor.author | Theron, Douglas Arnoldus | en_ZA |
| dc.contributor.other | Stellenbosch University. Faculty of Engineering. Dept. of Process Engineering. | |
| dc.date.accessioned | 2012-08-27T11:34:31Z | |
| dc.date.available | 2012-08-27T11:34:31Z | |
| dc.date.issued | 1999-12 | |
| dc.description | Thesis (M.Ing.) -- University of Stellenbosch, 1999. | |
| dc.description.abstract | ENGLISH ABSTRACT: The harsh interior environment of mills makes on-line monitoring of these grinding systems difficult. Not only are conventional contact sensors expensive, but the nature of the grinding process makes their application impractical. Unfortunately few accurate quantitative measures are in place in industry to describe or assist in the operation and diagnosis of ball mills. In the South African context operators learn to control the mill based on a priori knowledge of the system gathered from years of process experience. It is common knowledge in industry that these operators associate the sound emission from the system with certain process conditions, and adjust the mill set points to obtain optimal grinding conditions. Unfortunately the high turnover of manpower in the mining industry has led to a drain of knowledge from many operations, leading to a loss of valuable control information. In this work the acoustic emission from a ball mill was studied making use of a laboratory ball mill, acoustic microphones and a personal computer, equipped with a sound card. The mill signal was recorded for a series of batch experiments. These consisted of single parameter experiments where single parameters such as percentage filling, mill speed, percentage water and percentage charge mass were varied, while keeping all other parameters constant. A second series of experiments were conducted with two platinum ore types, namely UG2 and Merensky, to study the influence of changing particle size on the acoustic emission from the mill. The acoustic signal was transformed into the frequency domain from the time domain by using Welch's averaged periodogram method. Hereby the power spectral density function for each acoustic sample was obtained and used as the basis for further data analysis. The structure of the data was investigated with a Sammon map obtained from the power spectral density data. This method confirmed that specific conditions in the mill each had a unique fingerprint which enabled differentiation of the acoustic information. Feature vectors were obtained by principal component analysis of the power spectrum density function extracted from the original mill signal. These feature vectors were used for the modelling of different data sets. Linear regression was applied to the Single parameter experiments yielding modelling results with r² values above 0.95. With the platinum- ore data both linear regression and feed forward neural networks were used for modelling. However, the linear regression model was unable to predict the ore particle size from the acoustic data. The non-linear neural network models achieved accurate particle size predictions for both ore types on both known and unknown validation data sets. r² values greater than 0.93 for the test data and 0.97 for the training data were obtained. | |
| dc.description.abstract | AFRIKAANSE OPSOMMING: Monitering van balmeule in die Suid-Afrikaanse industrie word deur operateurs behartig. Dit is algemeen bekend dat ervare operateurs die klank wat tydens maling vrygestel word met sekere prosestoestande en produkgroottes kan assosieer. Die hoe tempo waarteen operateurs tans paste verwissel, het egter gelei tot die verlies van spesifieke kennis wat met bedryf van meule verband hou. Pogings om konvensionele sensors vir monitering te gebruik het hoofsaaklik gefaal as gevolg van die aggresiewe omgewing van maling en vergruising wat normale meetmetodes belemmer. In hierdie werkstuk word die akoestiese sein wat tydens maling vrygestel word deur middel van 'n persoonlike rekenaar, toegerus met klankkaart en akoestiese mikrofone, en'n laboratorium balmeul ondersoek. Akoestiese emissies tydens maling is vir 'n aantal kart enkellading-eksperimente ondersoek. Tydens hierdie lopies is enkel-parameter lopies uitgevoer waar die effek van persentasie meulvulling, meulspoed, pulpdigtheid en meulbelading op die akoestiese sein ondersoek is. 'n Tweede stel eksperimente is uitgevoer am die effek van verandererende partikelgrootte op die akoestiese sein te ondersoek. Hiervoor is twee verskillende platinumerts-tipes wat in die nywerheid bekend is vir hul verskil in klank tydens maling, nl. UG2 en Merensky, gebruik. Die akoestiese sein is vanuit die tyddomein getransformeer na die frekwensie-domein deur van Welch se gemiddelde periodogram-metode gebruik te maak. Die spektrale digtheidsfunksie van elke akoestiese monster is bepaal en gebruik as die basis vir verdere analise. Die struktuur van die datastel is deur 'n topologiese Sammon netwerk voorgestel. Hierdie voorstelling het duidelik bevestig dat spesifieke toestande in die meul 'n unieke vingerafdruk, met onderskeibare klasse na gelang van die bedryfs- en prosestoestande van die meul, laat wat slegs gebaseer kan word op die akoestiese inligting wat uit die proses vrygestel word. Kenmerksvektore is deur hoofkomponentanalise vanuit die spektrale digtheidsfunksie van die oorspronklike akoestiese sein bepaal. Die kenmerksvektore is vir verdere modelering gebruik. Lineeke regressie is op die enkelladingsdata toegepas met akkurate voorstellingsresultate vir die enkelprameter lopies. Beide lineere regressie en'n neurale netwerk is op die platinumertse toegepas am die partikelgrootte vanaf die akoestiese sein te modeleer. Die partikelgrootte vir beide Merensky en UG2 ertse is akkuraat deur die neurale netwerk vir beide die bekende, sowel as die toetsdatastelle voorspel, terwyl die lineere regressiemetode nie akkurate voorspellings kon maak nie. Die slotsom is dus dat die akoestiese inligting wat van 'n balmeul vrygestel word, gebruik kan word vir onder andere diagnostiese analise, modelering en uiteindelik oak meer akkurate beheer van die balmeulstelsel waar tradisionele metodes oneffektief was. | |
| dc.description.version | Master | |
| dc.format.extent | 139 pages : ill. | |
| dc.identifier.uri | http://hdl.handle.net/10019.1/51462 | |
| dc.language.iso | en_ZA | en_ZA |
| dc.publisher | Stellenbosch : Stellenbosch University | |
| dc.rights.holder | Stellenbosch University | |
| dc.subject | Ball mills -- Grinding media | en_ZA |
| dc.subject | Ore-dressing plants | en_ZA |
| dc.subject | Dissertations -- Chemical engineering | en_ZA |
| dc.title | The diagnostic monitoring of the acoustic emission from a laboratory ball mill | en_ZA |
| dc.type | Thesis | en_ZA |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- theron_diagnostic_1999.pdf
- Size:
- 15.54 MB
- Format:
- Adobe Portable Document Format
- Description: