Abstract
The operation and maintenance of modern aircraft multi-sensor data fusion systems generate vast amounts of numerical and symbolic data. Learning useful and non-trivial insights from this data may lead to considerable savings, and detection and reduction of the number of faults, as a result increasing the overall level of aircraft safety. Several machine learning techniques exist to learn from big amounts of data. However, the use of these techniques to infer the desired readable and accurate interval regression tree models from the data obtained during the operation and maintenance of aircraft is extremely challenging. Difficulties that need to be addressed include data warehouse collection and preprocessing, machine learning model readability, setup, evaluation, and maintenance. This article presents the interval gradient prediction tree algorithm (INGPRET), which addresses these issues. As shown by the empirical evaluation of a real aircraft multi-sensor data set, the INGPRET algorithm provides better readability and similar performance in comparison to other machine learning algorithms.
TopIntroduction
Maintenance of aircraft components have always been an important consideration in aviation. Accurate prediction of possible failures will increase the reliability of aircraft components and systems and decrease maintenance of big future failures. The scheduling of maintenance operations help determine the overall maintenance and overhaul costs of aircraft components. Maintenance costs constitute a significant portion of the total operating expenditure of aircraft systems (Kadir, Onur, & Harun, 2020).
According to Fan (2015) there are three main types of maintenance for equipment: corrective maintenance, preventive maintenance, and predictive maintenance. Corrective maintenance helps manage repair actions and unscheduled fault events, such as equipment and machine failures. When aircraft equipment fails while it is in use, it is repaired or replaced. Preventive maintenance can reduce the need for unplanned repair operations. It is implemented by periodic maintenance to avoid equipment failures or machinery breakdowns. Tasks for this type of maintenance are planned to prevent unexpected downtime and breakdown events that would lead to repair operations. Predictive maintenance, as the name suggests, uses some parameters which are measured while the equipment is in operation to guess when failures might happen. It intends to interfere with the system before faults occur and help reduce the number of unexpected failures by providing the maintenance personnel with more reliable scheduling options for preventive maintenance. Assessing system reliability is important to choose the right maintenance strategy.
The operation and maintenance of modern predictive sensor-equipped systems such as aircraft generates vast amounts of numerical and symbolic data streams. According to Tawaikuli et al. (2020) m Multi Sensor Data Fusion oulti sensor data streams collection and preparation is an expensive, resource consuming and complex phase often performed centrally on raw data for a specific application. These data streams are generated by thousands of sensors installed in various components of the aircraft and then sent in real-time to relational databases storages in ground stations. Before being transmitted to the ground, a number of on-board computer systems monitor and analyze the data stream in order to make sure that various systems of the aircraft are operating properly. However, once the data stream is stored in central databases, further data analysis is rarely performed. This paper presents an algorithm that makes use of this data stream in order to develop interval Machine Learning ML regression tree models to predict the need for replacement of various aircraft components before they become non-operational. The end goal is to implement this ML model in a flight monitoring system that will receive the real-time multi-sensor data input from aircraft fleet, analyze it, and output alerts in the form of appropriate replacement rules when there is a need for component maintenance.
Key Terms in this Chapter
Neural Networks Algorithm (NN): Scalable and robust supervised learning prediction algorithm that contains layers of interconnected nodes or perceptrons. These nodes feed the signal produced by a multiple linear regression into an activation function that may be nonlinear and produces a neural net prediction model.
Support Vector Machines Algorithm (SVM): Scalable and robust supervised learning prediction algorithm that maps training examples to points in space so as to maximize the width of the gap between categories. New examples are then mapped into that same space and predicted to belong to a category based on which side of the gap they fall.
Random Decision Trees Forest (RF): An ensemble learning bagging prediction algorithm for classification, regression, and other tasks that operates by constructing a multitude of decision trees. For classification tasks, the output of the random forest is the class selected by most trees. For regression tasks, the mean or average prediction of the individual trees is returned.
Extreme Gradient Boosting Algorithm (XGBOOST): Scalable, distributed, gradient-boosted decision tree machine learning library. It provides parallel tree boosting and is the leading machine learning library for regression, classification, and ranking problems.
Multi-Sensor Data Fusion (MSDF): The process of combining or integrating measured or preprocessed data or information originating from different active or passive sensors or similar sources, to produce a more specific, comprehensive, and unified data set about an event of interest that has been observed.
Interval Gradient Prediction Tree Algorithm (INGPRET): A scalable interval prediction tree algorithm which predicts values of numerical attributes in aggregated temporal data streams. The proposed algorithm differs from existing state-of-the-art regression algorithms in that it accomplishes the splitting of each input continuous feature according to the best mean-variance contributor, and because it removes outliers from the training data.