Predictability is about anticipating scenarios, and it’s different from receiving a simple warning that something is wrong. For example, when a car’s fuel light flashes it’s telling you that you’re almost out of fuel. Predictability is your car informing you that you have 30 kilometres worth of fuel left in the tank, allowing you to make an informed decision about when to stop at the petrol station.
Here at Vanderlande, we take predictive solutions a step further and use them for the condition-based maintenance of BHS, and to optimise the entire baggage process. The aim is to use data to detect trends and foresee problems in advance to allow airports to plan their maintenance around anticipated issues. This will ensure the BHS works as efficiently as possible.
How do predictive solutions work?
For our solutions to work in practice, we must first know what to look for, such as high temperatures, vibrations, misalignment or other glitches in the system.
If we continually monitor processes and store the results, we will see trends develop that can point to potential problems. For example, we may notice that the temperature of a conveyor belt is higher than usual. A week later this change may cause a delay. We now understand that if the same temperature is recorded, we can expect a similar outcome within a specific time frame.
The first step for predictive solutions is gathering data. For predictive maintenance, this means attaching sensors to equipment to measure values, or obtaining values from the equipment itself. Within this data, trends and deviations can be found and presented to process engineers and maintenance teams using dashboards. With this information they can take action to prevent unplanned downtime.
Optimising the baggage process
Our Baggage 4.0 vision does not just address equipment – it’s also about optimising the baggage handling process. Using data backed by advanced analytics will help airports to predict baggage flow and make the entire operation more efficient. It will also help to deal with bottlenecks and minimise recirculation.
For example, a predictive process can prevent mishandling of bags by tracking its previous journey through the BHS. Recently recorded data will show where a problem occurred, allowing changes to be made to ensure it doesn’t happen again. An example of this could be rerouting bags in a different way.
In the end, greater predictability in the behaviour and reliability of equipment and processes will give airports more confidence in their baggage handling operations. And of course, fewer unexpected problems means less service disruption and – in the end – happier passengers.
Please check back soon for our final blog when we will examine how advanced technologies, such as robotics and artificial intelligence, can help us realise our ambitions for Baggage 4.0.
For an introduction to our Baggage 4.0 vision, please read the first blog in our series.