As a part of the series Leveraging Analytics in Transportation to Create Business Value, we are excited to talk about Unscheduled Maintenance. Within this post we will touch upon the benefits of Analyics on Unscheduled Maintenance, the different Analytic approaches, and a few real life examples that occur.
Unscheduled maintenance is reactive in nature and is carried out after failure occurs. Lower incidences of unscheduled maintenance are a reflection of product reliability and effectiveness of planned maintenance. This also implies that there is a tradeoff between the scheduled and unscheduled maintenance. Analytics helps drive the right balance in this regard. Reduction in field failures saves costs while reducing down time associated with unscheduled maintenance. Proper management of unscheduled maintenance helps improve customer satisfaction.
Since failures experienced by a system depend upon many variables such as design, reliability, operating condition and age of the asset, unscheduled maintenance events are stochastic in nature, along with associated repair scope and costs. Therefore, there are many opportunities to apply Analytics in the area of unscheduled maintenance. Analytics techniques such as recurrent event models are very useful in determining expected field failures. Also, many of the data mining techniques including decision trees are useful in identifying the factors that contribute to field failures.
Please also see the reliability section for other Analytics approaches that are used to determine failure rates of components and optimal replacement intervals. Analytics can help determine best course of actions given an unscheduled maintenance event. Analytics can also help with understanding the repair lifecycle for a given asset model and age, or a maintenance profile by model and age. Given that information one can estimate the probabilities of collateral repairs given a field failure, there by arriving at a predicted repair scope for the event.
Also, the logistics from the location of the field failure to the repair shop where it can be attended to can play a major role in the total costs, especially if there are multiple repair providers with different cost structures. The transportation costs need to be factored into this decision as well.
Real Life Examples
Unscheduled maintenance in rail industry is referred to as bad-orders. When a railcar is bad-ordered the owner is responsible for providing instructions as to where the railcar should be routed for repairs. There are many factors to consider in this case: such as what is the reported failure, what other collateral repairs need to be performed, if there are any scheduled maintenance events planned for the asset in the near future that should be attended to during the same visit, which shops can handle the type of the railcar with the commodity it is carrying, what are the transportation costs, etc. The repair costs may also vary by the provider. It is not as simple as sending it to the closest shop that has the capacity to take it.
Many of the large truck owners have their own repair shops, shops at customer facilities and network of other repair shops where they may or may not have negotiated rates. Attending to a repair at a 3rd party repair shop compared to one’s own shop may result in significant additional costs. There are other trade-offs such as attending to a repair at a shop on urgent basis by paying overtime to technicians vs. sending the repair to a 3rd party vs. delaying the repair by taking into account the loss of in-service revenue.
In the airline industry an unscheduled maintenance event may or may not be attended immediately depending on the criticality of the failure considering safety and the passenger impact. For example a broken coffee maker or a broken bathroom door may be considered a critical failure due to the passenger impact when there is no apparent safety implication. Critical failures that need to be attended prior to the next takeoff can severely disrupt the schedule and have a significant down the line impact in terms of pilots, crew and the ground resources. In such cases, Analytics are also used to determine the best way to recover the schedule with minimal impact to passengers and staff.
We hope to provide relevant insights and a fresh perspective on how analytics can make a profound impact on asset-intensive organizations. So stay tuned for our next post on Predictive Management.