We all use different machines and appliances in our everyday life. From the coffee machine to start our day better, the elevator to go to the office to an airplane to travel to our dream location during holidays. These systems can fail. Some failures are just an inconvenience, while others could mean life or death.
As technologies are evolving, we have become more dependent on the machines that we are surrounded by. When purchasing any type of machine one of the most important things is its reliability, and with reliability, we are also thinking about future maintenance costs.
When the stakes are high, we perform regular maintenance on our systems. For example, cars are serviced once every few months, and aircrafts are serviced daily.
With technology moving forward, maintenance methods are also becoming more sophisticated.
The maintenance methods are as follows:
Reactive – If something is not broken, don’t fix it. This approach is best for cases where equipment failure is rare, easy-to-fix and with limited impact – for example changing a lightbulb in a warehouse
Planned – maintenance (or preventive maintenance) uses routine maintenance to diagnose equipment for failure. It works and it is widely employed – but it’s costly and doesn’t capture asset-specific conditions
Predictive – maintenance leverages data from an individual asset to predict failure. This way, repairs can be done when needed (and avoided when not). It offers the best upside, but at the cost of complexity.
Predictive maintenance has been around for ages; when a technician inspects an asset and makes a change to avoid future failure, that’s predictive maintenance. With technology improving, we are able to collect more information from systems, analyze it, and then later take maintenance actions based on it.
To understand the details, let’s think of a bus transportation company. If a bus breaks down during a trip, the company needs to deal with many unhappy customers, send and most probably pay for a replacement. Both the bus and driver will be out of service while in repair if there is no replacement vehicle in the company. The cost of failure is much higher than its apparent cost.
One way to deal with this problem is to be pessimistic and replace fallible components well before failures. For example, regular maintenance operations, such as changing engine oil or replacing tires, handle this. Although regular maintenance is better than failures, we end up doing the maintenance before it’s needed. Hence, it is not an optimal solution. For example, changing the oil of a vehicle for every 3000 miles might not use the oil effectively. If we can predict failures better, the bus can go a few hundred miles without the oil being replaced.
The goal of predictive maintenance is to forecast and prevent asset failure. Predictive maintenance provides early warnings and detects the anomalies and failure patterns. Warnings can trigger the efficient maintenance of analyzed components. This can lead to large cost savings, higher predictability, and increased availability of the systems.
In the next series of blogs, we will cover this subject in more details. While waiting, you can think about how your system can be optimized and think of the right partner – with experience in your industry and with software development, our team could be the best option for predictive maintenance implementation for your system!