Why is effective asset management so important?
The rapidly changing and volatile global economy is putting enormous pressure on organisations to control or preferably reduce their operating costs. This is resulting in a period of uncertainty with a range of new and complex factors having to be considered. For example:
- Ageing infrastructure and assets, more demanding operating conditions and higher throughputs
- Stricter regulatory requirements and much higher penalties for not meeting them
- The public’s increasing awareness of and care for the environment
- Increasing global demand for water and other natural resources
- Shifting economic and political power balances
- Investors’ attitudes to risk and how it can be controlled or preferably reduced.
Traditional reactive asset management policies do not meet these demands nearly well enough and so (more) proactive asset management policies based on predictive analytics are required. These policies result in optimised asset management by lowering asset maintenance costs, increasing asset lifetimes and therefore lower capital replacement costs, and improved customer service by, for example, fewer and shorter service interruptions, and fewer flooding and pollution incidents.
Unfortunately, some organisations do not have accurate or up-to-date information on how their assets are performing. This lack of knowledge manifests itself in many ways, including poor asset performance and higher than expected costs. Poor asset performance as measured by, for example, long periods of unscheduled downtime, low throughput and poor product quality has an adverse effect on the financial and operational performance of organisations.
How predictive analytics can improve asset performance
We live in a world in which the amount of data being collected and stored is ever increasing, and the rate at which this is happening is itself increasing. All this data provides very rich foundations for applying predictive analytics and other modelling techniques such as dynamic simulation for optimising asset management. This will in turn lead to improved financial and operational performance of organisations.
This abundance of data must not be confused with the different and separate subject of data quality – data quality and data quantity do not go hand-in-hand: more data does not necessarily mean better quality data.
A range of data can be used in predictive analytics models, including the static data for each asset from the asset register, the dynamic data for each intervention from the maintenance history database, external factors, for example land use, weather and seasonality, and internal factors, for example workforce.
Implementing a new predictive asset management system is a major undertaking that needs careful and detailed planning (a subject outside the scope of this article). Two common obstacles that may be encountered when implementing such a system are fear of the unknown and a reluctance to change. These feelings can be overcome by implementing a carefully designed change management programme to ensure that the people affected gain an appreciation and understanding of why the changes are necessary so that they accept that they are for the good of the whole organisation.
Asset management questions that predictive analytics can answer
Predictive analytics can be used to answer a range of asset management questions, including:
- Which factors contribute to asset failure?
- How do different values of a factor, for example different manufacturers, affect the risk of asset failure as the assets age?
- How does the risk of failure of each asset change as the asset ages and how does the risk change as it undergoes maintenance?
- Which assets have the greatest risk of imminent failure and so need immediate proactive maintenance?
- How do repeated asset failures affect the times to subsequent failures, and subsequent maintenance costs and replacement costs?
- How can organisations’ asset management policies be optimised at the strategic level by using a range of data including failure data, cost data and the organisations’ attitude to risk?
Predictive analytics, business intelligence and asset management
Predictive analytics can be used to build accurate models that help explain asset failure, and the models can then be used to predict the state of the assets at specified future times. This analytical approach is in contrast to business intelligence where summary reports about what happened in the past are presented. By their very nature, these reports provide little or no insight into the causes of asset failure and therefore how the risk of asset failure can be reduced. By analogy, business intelligence involves looking back through the rear view mirror to see the past whereas predictive analytics is about looking ahead so that future risks to asset performance can be overcome before they occur.
Predictive analytics goes much further than business intelligence by enabling organisations to design and implement new asset management policies that minimise the risk of future asset failure.
Predictive analytics has a big and important part to play in improving asset performance and thereby improving the performance of organisations. This is largely due to the huge increase in the amount of available data and the development of technology that can use all this data. However, the amount of data does not detract from the imperative of understanding the data fully and making sure they are fit for purpose before they are used to develop and then apply predictive analytics models. On the contrary, it can be argued that the sheer quantity of data increases the importance of assessing their quality and understanding them fully before starting the predictive analytics. So, only when the data, and current systems and processes are fully understood, and the business objectives clearly defined can predictive analytics be applied successfully to improve asset performance.
This post was originally published at www.pamanalytics.com/asset_management.html.