How to reduce baggage handling system OPEX with data analytics

By Per Engelbrechtsen

Data analytics has become an essential component of all business operations and baggage handling systems are no different. A data-driven approach to baggage handling systems has huge potential for operational expenditure (OPEX) savings by providing greater visibility into the operations.

The importance of data analytics to baggage handling systems

The gathering and storing of large amounts of information – often referred to as big data – for analysis can happen at any point throughout the baggage handling system. Real-time analytics of that data is then able to support decision making across organisational units:

• Maintenance level: Data can be sourced from the equipment and read in real time through sensors and devices and processed for the purposes of predictive maintenance, reducing cost and increasing efficiency.
• Operational level: Decision science is to improve the operation by use of data driven recommendations for operational decisions – or even letting the system carry out decisions automatically.
• Management level: Dashboards can be customised and reports built on real-time data that management can rely on to forecast and plan, based on the historical data in combination with passenger forecasts (for example, are we able to cope with the summer peak this year, based on last year’s statistics and this summer’s forecast? – or how should we plan the staffing?).

Through data analytics, airports can gain meaningful insights into their baggage handling operations which will enable them to optimise their performance and processes.

How can data analytics help reduce baggage handling OPEX?

But how do data analytics enable the optimisation of the baggage handling system process? Well, there are a number of ways analyses of data can help reduce baggage handling OPEX.

Operations

Here are three examples of how to use data analytics to drive down OPEX:

• Data analytics can improve the use of bag storage systems (EBS) – in one case, the analysis of data from the EBS delivered an 80 percent reduction of recirculations, while optimising the slot release time;
• The up-time and flow of Hold Baggage Screening (HBS) is constantly monitored on dashboards to continually improve and ensure optimal use of the area; and
• The handling of arrival baggage can be optimised by analysing the first bag and last bag times to help improve the baggage handling efficiency for arrival passengers.

Reduce maintenance costs

Data analytics can also provide predictive maintenance for unplanned repairs which are needed when a system failure triggers an alarm. It’s possible to minimise these reactive repairs through the use of data analytics which can improve maintenance planning. For example, maintenance operators can practise predictive maintenance based on data and real-time performance, instead of maintenance based on routines or schedules. Parts of a baggage handling system may go through a performance dip of five percent that no-one would be able to identify from just observing the equipment or the output. With predictive data analytics, no one will have to: data is keeping them informed.

Data-driven maintenance can optimise maintenance efforts as the system will only require inspection when the data precisely indicates it does. This is because data analytics has enabled airport maintenance staff to move from a calendar – or metre – based approach to identifying elements and components due for an inspection through the use of predictive maintenance. Data analytics, then, enables airport baggage operation teams to predict, react and prevent maintenance needs before a unit fails. Data provides an easy overview of active issues within different elements and types of units and predictively points to the specific parts of the BHS that need to be inspected.

Read more: “5 ways to reduce costs and improve operational efficiency in baggage handling”.

Revealing trends

Data analytics can reveal trends that can be useful and valuable for fine-tuning operations. They can provide insight, for example, on why bags are mis-sorted. They can also inform operators to both predict and prevent bottlenecks. Through data analytics, poor operational or planning habits can become transparent. So, while operators won’t necessarily see the patterns in their daily operations, data analytics can identify trends over the course of a year. Even slight performance improvements will make a significant difference in costs.

Provide real-time management

Data analytics can help with operational forecasting, such as preparing for peaks and providing an overview of maintenance. It enables management to structure the entire BHS operation around data-based insights that wouldn’t otherwise be recognised. By comparing data from previous baggage handling “production days” and forecasting future productions, management can learn from previous experience to improve future operations and settle on the best use of resources. Management will be able to forecast every aspect of their operations, such as baggage volumes, peak season volumes and maintenance needs. Data analytics gives management a unique opportunity to plan for the future and optimise its operations and maintenance resources on the basis of these real-time and transparent insights.

In the future, airport BHS management will need to become better at learning from experience and planning future baggage handling production. But in order to do this, it requires a detailed and accurate assessment of past and future production.

Thankfully, this is exactly what data analytics provides.

Download the whitepaper “The ultimate Baggage Handling System pulling airports into the future.”

How machine learning adds to analytics and OPEX reduction potential

Businesses are increasingly using machine learning technologies to take data analytics to another level. In baggage handling systems, too, machine learning has the potential to play a big role in reducing OPEX costs. Often, traditional data analytics can be static and limited when addressing fast-changing and unstructured data. There may be a need, for example, to identify correlations between dozens of sensor inputs and external factors that quickly produce millions of data.

By learning from the data and identifying patterns, machine learning enables the system to make decisions with minimal human intervention. It can be used to support operators in making faster and better decisions. Machine learning still requires human input and the cognitive abilities they provide. But machine learning, which is an AI-based category, can lead to decision science and machine-based – instead of human-based – suggestions to solving problems (before they occur). The system has the experience (machine learning) that makes it “wise” enough to be the “adaptive cruise control” to the BHS control team and management, to draw a parallel with the automotive world.

Conclusion

Just a fraction of the vast amounts of data collected at airports is currently being used to contribute to the overall strategic and operational decision-making process. Yet, data collected from a baggage handling system has much to reveal about a system’s performance, condition and efficiency. Data analytics can provide useful insights which can transfer data into a valuable asset airports can then utilise to optimise their baggage handling systems.