AI takes to the skies: The four practical applications of AI in aviation maintenance

by | Apr 24, 2024 | Innovation, MRO IT

AI is answering some of the most difficult questions in aviation.

I pose here four questions and show how AI is transforming aviation maintenance in four key areas:

  1. Maintenance Scheduling & Supply Chain Optimization
  2. Error Detection & Reclassification
  3. Automated Failure, Troubleshooting, & Repair Identification
  4. Predictive Maintenance & Anomaly Detection


I think maintenance can be a little more efficient, don’t you? Maintenance Scheduling & Supply Chain Optimization

An application of AI that has many use cases is optimization, which includes maintenance scheduling optimization.

An optimization engine that can schedule maintenance at the best possible time at the best possible location has the potential to greatly reduce maintenance costs and improve maintenance yield fleet wide. At the same time, optimizing the order that are performed in, and how personnel are assigned to tasks can result in more efficient maintenance—reducing costs, improving turnaround time, getting the aircraft back in the air sooner—thereby generating more revenue.


Are you sure that’s correct? Error Detection & Reclassification

Another use of AI is to identify errors made in entering data, or to reclassify data after the fact to ensure accuracy of data and improve the overall quality of the dataset. A common problem across the airline industry is the misclassification of the failed ATA system when raising a fault. These misclassifications can impact the data quality in the system.

IFS Customer Southwest Airlines has rolled out a solution to use AI to identify misclassified faults and improve the overall quality of their data. This is an excellent application of LLMs that learn to identify patterns in the text entered by the technicians to classify faults more accurately. Using AI to identify potential errors and surface those potential errors to a person helps to make the whole process vastly more efficient while maintaining authorized human oversight.


Let’s try this again—Automated Failure, Troubleshooting, and Repair Identification

When a fault is raised, a technician is often required to spend a considerable amount of time researching the correct source of a fault, what troubleshooting steps to take and what repairs to apply.

The logical extension of fault classification is to take the same kind of LLM model which will suggest potential sources of the failure, and recommend troubleshooting activities or even make repair suggestions. Suggestions would be based on previous success rates.

By providing first time fix rate percentages to the technician, they may choose options that save time by resolving the issue quicker, meaning the aircraft may be able to get back in the air sooner, or even prevent recurrences in the future. Avoiding or reducing has real value, according to Airlines for America, in 2023, delays have a direct cost of $101.18 for every minute a flight is delayed.


Now what will happen? Predictive Maintenance & Anomaly Detection

The concept of predictive maintenance is nothing new. However, what is new is the application of newer types of AI, namely Anomaly Detection and Pattern Recognition. Predictive maintenance uses time-series data—which is gathered over long periods of time recoded at fixed known points along the way, i.e., discrete data points in time.

Live feeds of sensor data changed that with IoT, allowing current data to be considered—but that huge amount of data is difficult to interpret, requiring highly trained data scientists. Then Machine Learning (ML) came into the picture. Using ML means that data scientists are now focussed on creating the current learning model for the AI, rather than developing the algorithm themselves.

Unsupervised learning models are lowering the barrier to entry for the use of AI in predictive maintenance applications. “Unsupervised” learning models for AI means that you can plug the AI into a set of data and it can figure out its own algorithm. This reduces the time and cost of implementing a solution, and also has the power to remove bias from the process, particularly when dealing with large amounts of unlabeled data like multiple terabytes of data points generated from a modern aircraft .

Anomaly Detection means that you can plug the AI into the sensor data to figure out what “normal” looks like, it then warns you whenever a deviation from “normal” occurs. Coupled with Pattern Recognition, the AI can learn to detect patterns in the sensor data that indicate certain events are about to occur—providing an early warning system that can warn what is about to happen with extremely accurate results.


AI is here to stay

By using AI to streamline tasks, to provide decision support to the human, to pare down the noise of information—while keeping the human in the loop, still requiring them to be the ultimate decision maker—cutting edge companies have the ability to make huge strides in terms of efficiency and accuracy.

These improvements can represent real value to airlines & air operators and ultimately, their customers.


Article by Rob Mather, Vice President, Aerospace and Defense Industries at IFS


Discover more from Aerospace Tech Review

Subscribe now to keep reading and get access to the full archive.

Continue reading