Browsing by Author "Van den Honert, Andrew Francis"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- ItemAdapting modern portfolio theory for prioritising asset care planning in industry(Southern African Institute for Industrial Engineering, 2014-05) Van den Honert, Andrew Francis; Vlok, Pieter-JanProductivity improvement within any organisation can lead to increased turnover. This study focuses on developing a maintenance productivity improvement model that is based upon an established financial investment portfolio technique known as the Modern Portfolio Theory (MPT). The model can be used as a tool to minimise and diversify the long term risk associated with variances or fluctuations in the increase in productivity in multiple maintenance service centres. This is achieved by optimising the most efficient way of splitting resources, such as time and money, between these multiple service centres, resulting in increased productivity and a more constant maintenance work load. This model is verified through the use of an efficient frontier, resulting in a graphical method to determine the link between the expected increase in productivity and the standard deviation of the increase in productivity. Ultimately this model can be adapted for use in many sectors within an organisation, over and above the application in maintenance prioritisation. This study concludes that the model offers a simple tool to aid decision-making among various combinations of assets within a maintenance context; and this model, adapted from MPT, was successfully validated with the use of an efficient frontier.
- ItemEstimating the continuous risk of accidents occurring in the mining industry in South Africa(SAIIE, 2015) Van den Honert, Andrew Francis; Vlok, Pieter-JanThis study contributes to the on-going efforts to improve occupational safety in the mining industry by creating a model capable of predicting the continuous risk of occupational accidents occurring. Contributing factors were identified and their sensitivity quantified. The approach included using an Artificial Neural Network (ANN) to identify patterns between the input attributes and to predict the continuous risk of accidents occurring. The predictive Artificial Neural Network (ANN) model used in this research was created, trained, and validated in the form of a case study with data from a platinum mine near Rustenburg in South Africa. This resulted in meaningful correlation between the predicted continuous risk and actual accidents.