Chidi Umeano, Principal Consultant at Codub Consulting Ltd, says that with more focus on Predictive Maintenance strategies, which is a key aspect of Asset Management, Big Data has a major role to play.
In a nutshell, the ‘Big Data’ concept is about trying to predict the future. Data has always existed and the issue I think is about ‘meaningful’ data. Yes there is an increase in the data generated today and the possibilities are huge. However, the methods of analysing these huge data lag way behind. It is important to note that it is the systems and tools that are used to analyse and understand such vast amounts of data that could be disrupting the huge potentials in the way we practice Asset Management. Nevertheless there are good opportunities like the ability to make insightful planning, fore-casting and predictions as regards asset behavior and production patterns, which should increase return on investment (ROI) e.g. predicting and avoiding asset down time. Equally, matching data samples around different asset operating parameters and the resulting production output can give us insight into how different operating levels affect the asset and its components. Such information allows for a truly optimised operation as an asset is run to the most efficient production rate, whilst ensuring that equipment and components life-cycles are at maximum capacity.
Failure to produce relevant data for decision making is a major drawback due to the lack of very intelligent analytic tools. Equally, there is a cost implication when it comes to introducing additional sensors to capture the required data. The opportunities depend solely on the proper application of big data. This means the ability to understand what data sample is needed, how to analyse and interpret these data and of course the flawless application of the findings. Without factoring each of these functions, big data may be just too much to handle. Analysed Big Data: So rather than ‘Big Data’, we should think of ‘Analysed Big Data’
One needs to balance the effort (cost or otherwise) required in sifting and analysing big data in order to predict an asset failure with the cost of the asset failure. This I feel is where the focus should be as the practice of Asset Management is about realising value from assets.