Hendrik J. Groenewald

Using Technology Transfer to Advance Automatic Lemmatisation for Setswana

South African languages (and indigenous African languages in general) lag behind other languages in terms of the availability of linguistic resources. Efforts to improve or fast-track the development of linguistic resources are required to bridge this ever-increasing gap. In this paper we emphasize the advantages of technology transfer between two languages to advance an existing linguistic technology/resource. The advantages of technology transfer are illustrated by showing how an existing lemmatiser for Setswana can be improved by applying a methodology that was first used in the development of a lemmatiser for Afrikaans.

Business case for industrial DSM maintenance

The performance of industrial DSM projects often deteriorates without proper maintenance. Underperforming DSM projects waste money and increase the demand for electricity from Eskom. A solution to this problem is dedicated maintenance on industrial DSM projects. This ensures maximum performance and maximum electricity cost savings. In this paper, the business case for industrial DSM maintenance is presented. Results show that the benefits significantly outweigh the cost of DSM maintenance.

Educating Lia: The Development of a Linguistically Accurate Memory-Based Lemmatiser for Afrikaans

This paper describes the development of a memory-based lemmatiser for Afrikaans called Lia. The paper commences with a brief overview of Afrikaans lemmatisation and it is indicated that lemmatisation is seen as a simplified process of morphological analysis within the context of this paper. This overview is followed by an introduction to memory-based learning — the machine learning technique that is used in the development of the Afrikaans lemmatiser. The deployment of Lia is then discussed with specific emphasis on the format of the training and testing data that is used. The Afrikaans lemmatiser is then evaluated and it is indicated that Lia achieves a linguistic accuracy figure of over 90%. The paper concludes with some ideas on future work that can be done to improve the linguistic accuracy of the Afrikaans lemmatiser.

Improving mine compressed air network efficiency through demand and supply control

The platinum price has decreased nearly 42% since 2010, forcing platinum mines to reduce expenses in order to remain profitable. Electricity consumption is a large capital expenditure for the mining sector and efforts should thus be made to reduce energy consumption while maintaining production. Compressed air networks were identified as a large energy consuming section in the mining industry. Inefficiencies in these networks were thus investigated, with focus given to the compressors, the pipelines transferring compressed air and the compressed air consumers. A strategy was then developed in order to ensure that the compressed air consumers will not receive insufficient pressure or flow. This strategy also includes a reduction in energy consumption of the compressed air network. Finally this strategy was tested on a mine and savings were calculated. These savings include daily energy savings of 18.9 MWh which result in annual cost savings of R15.7 million.

Re-evaluation of a DSM project baseline model for improved project impact reporting

Several challenges exist for the successful implementation of demand side management (DSM) projects in the industrial sector. Due to the large financial impact of these projects, the process of determining and reporting project-specific impact is crucial to the ultimate success of the project. Numerous DSM projects have been implemented worldwide, including South Africa. The success of these projects, and the success of the Energy Services Company (ESCO) industry, have ultimately been due to the large energy savings that DSM projects have delivered. Currently there are detailed measurement and verification (M&V) frameworks and guidelines that are well developed and widely implemented. The ESCO industry relies on these well-proven, standardised methodologies to ensure accountability and sustainability of DSM projects. A DSM project on a mine cooling system was identified as a case study to highlight the effect of baseline model selection on the perceived and reported savings. It was found that a conservative estimate of an additional unclaimed saving for a specific project on a surface mine cooling system amounted to R247 000, with a total unclaimed energy saving of 610 MWh, over the six-month period from March to August 2016. This highlighted the need for a post-project reassessment of the pre-project implementation accepted baseline model.

Maintenance procedure for improved sustainability of DSM pump load shifting projects

Mine dewatering systems are energy intensive and present ample opportunity for the implementation of electricity cost saving measures. One such electricity cost saving measure is the implementation of load shifting projects to shift pumping load from the peak periods to the off-peak periods of the Eskom Megaflex tariff structure. However, past experience has shown that the electricity cost savings generated by a pump load shifting project can deteriorate without proper maintenance. The major causes of the deterioration were therefore investigated with the aim of developing a maintenance procedure. The maintenance procedure consists of four sections: data loss prevention, mechanical failure prevention, control & instrumentation maintenance and control parameter optimisation. The developed maintenance procedure was implemented on the dewatering systems of South African gold mines. Results indicate that the application of the maintenance procedure resulted in both increased electricity cost savings and sustained performance.