A decision support framework for implementing condition-based maintenance programs

What is it about?

Condition-based maintenance (CBM) and predictive maintenance (PdM) techniques help determine the condition of in-service equipment in order to predict when maintenance should be performed. There exist several technologies such as vibration analysis and oil analysis for conducting CBM. These technologies are expensive to purchase and implement. According to the standards for Prognostics and Health Management (PHM), a return on investment (ROI) analysis should be conducted prior to the implementation of the system. We introduce a methodology to industrial practitioners that helps them choose the best level of implementation. For example, if a construction company wants to implement an oil analysis program, at what level they should do it? Do they need to purchase all the expensive oil analysis equipment or just a portion of them? How advanced should be the information system they are going to purchase? The methodology uses computer simulation and statistical experiments to see which factors play the most significant role in reducing cost and what level is optimal for each factor.

Featured Image

Why is it important?

New emerging technologies and concepts such as Industrial Internet of Things (IIoT) are making predictive technologies so much easier to implement in manufacturing and service industries. Companies are moving from reactive organizations (in which equipment are fixed after they are broken) to proactive (in which the health of equipment is monitored and is under control). Because there are many technologies and many options out there that can be implemented, companies need decision support systems for deciding on what technology to implement. The standards for Prognostics and Health Management (PHM) advise companies that a return on investment (ROI) analysis should be conducted prior to the implementation of these systems. And this research is a decision support system in this regard.

Perspectives