Ivo Paixao de Medeiros

Use of PHM Information and System Architecture for Optimized Aircraft Maintenance Planning

Remaining useful life (RUL) estimations obtained from a prognostics and health monitoring (PHM) system can be used to plan in advance for the repair of components before a failure occurs. However, when system architecture is not taken into account, the use of PHM information may lead the operator to rush to replace a component that would not affect immediately the operation of the system under consideration. This paper presents a methodology for decision support in maintenance planning with application in aeronautical systems. The proposed methodology combines system architecture information and RUL estimations for all components in the system under study, allowing the estimation of an overall system-level RUL (S-RUL). The S-RUL information can be used to support maintenance decisions regarding the replacement of multiple components. For this purpose, the decision problem can be cast into an optimization framework involving the minimization of the component replacement cost under a safety constraint. Two case studies are used to illustrate the S-RUL concept, as well as the proposed optimization methodology.

Comparative case study of life usage and data-driven prognostics techniques using aircraft fault messages

Abstract Prognostics are a key activity in repair and maintenance operations. A recent approach to condition-based maintenance is the data-driven approach. This approach has been mostly based on past failure time measures, and sensed measurements of component degradation to derive estimates of the remaining useful life of equipment. An alternative source of data, rarely used in these models, is the stream of automatic messages derived from diagnostics systems, which consist of fault codes indicating abnormal events or deviations from optimal operation. Despite the richness and concise nature of these messages, their difficult interpretation poses significant challenges to its use in prognostics. This paper aims to show that data-driven prognostics based on this type of messages can be better suited to maintenance than time-based approaches. We illustrate this comparison with an industrial case study involving the removal times of a bleed valve from the aircraft air management system. Our experimental results reveal a significant accuracy improvement over the contrasting time-based models. We also establish the contribution to this improvement of the data-driven methods and message-related predictors.

Proton Exchange Membrane Fuel Cells (PEMFC) impedance estimation using regression analysis

This paper describes the application of the PHM concept to assess the State of Health (SoH) of a Proton Exchange Membrane Fuel Cell (PEMFC) as part of the IEEE PHM 2014 Data Challenge. Two regression approaches are used as health monitoring algorithms to estimate the impedance of the PEMFC. One was a linear regression and the other was a higher order polynomial regression combined with other function found on the literature. The linear regression presented the best results compared to the other method.

PHM-based Multi-UAV task assignment

This paper is relating to the application of Integrated Vehicle Health Management (IVHM) concepts based on Prognostics and Health Monitoring (PHM) techniques to Multi-UAV systems. Considering UAV as a mission critical system, it is expected and required to accomplish its operational objectives with minimal unscheduled interruptions. So that, it does make sense for UAV to take advantage of those techniques as enablers for the readiness of multi-UAV. The main goal of this paper is to apply information from a PHM system to support decision making through an IVHM framework. PHM system information, in this case, comprises UAV remaining useful life (RUL) estimations. UAV RUL is computed by means of a fault tree analysis that it is fed by a distribution function from a probability density function relating time and failure probability for each UAV critical components. The IVHM framework, in this case, it is the task assignment based on UAV health condition (RUL information) using the Receding Horizon Task Assignment (RHTA) algorithm. The study case was developed considering a team of electrical small UAVs and pitch control system was chosen as the critical system.

Forecasting fault events for predictive maintenance using data-driven techniques and ARMA modeling

Abstract Presently, time-based airline maintenance scheduling does not take fault predictions into account, but happens at fixed time-intervals. This may result in unnecessary maintenance interventions and also in situations where components are not taken out of service despite exceeding their designed risk of failure. To address this issue we propose a framework that can predict when a component/system will be at risk of failure in the future, and therefore, advise when maintenance actions should be taken. In order to facilitate such prediction, we employ an auto-regressive moving average (ARMA) model along with data-driven techniques, and compare the performance of multiple data-driven techniques. The ARMA model adds a new feature that is used within the data-driven model to give the final prediction. The novelty of our work is the integration of the ARMA methodology with data-driven techniques to predict fault events. This study reports on a real industrial case of unscheduled removals of a critical valve of the aircraft engine. Our results suggest that the support vector regression model can outperform the life usage model on the evaluation measures of sample standard deviation, median error, median absolute error, and percentage error. The generalized linear model provides an effective approach for predictive maintenance with comparable results to the baseline. The remaining data-driven models have a lower overall performance.

Data-driven aircraft estimated time of arrival prediction

Predicting an aircrafts Estimated Time of Arrival (ETA) while enroute can be a challenging endeavor. The great number of factors that can affect a flights punctuality range from things well under the pilots control, such as flight level and cruise airspeed, all the way to environmental circumstances that are generally very hard to predict, such as weather phenomena and airport congestion. Therefore, aircraft ETA predictions tend to rely heavily on aircraft performance models, along with either parametric or physics-based trajectory models, being only sometimes enhanced by simplistic statistical considerations, such as the average winds encountered in a flight path during a certain period of the year. This work presents a method for enhancing aircraft ETA predictions by applying machine learning techniques, taking into account general information about the flight as well as weather and air traffic. A good amount of effort is put into feature generation and selection, and subsequently a model is built from representative flight, weather and air traffic data, allowing for an increase in prediction accuracy. Some of the challenges that arise from the nature of the data are discussed, such as the fact that weather information is naturally fragmented into a great number of variables, which makes it difficult to extract value from it without a very large number of samples covering all possible scenarios. The results show that it is possible to enhance the ETA predictions obtained from traditional methods by correcting them with a model that takes into account the statistical relationships observed between flight, air traffic and weather information.

Aircraft on-condition reliability assessment based on data-intensive analytics

The implementation of condition-based maintenance continues to face several challenges especially in the aeronautics field. While it is true that time-based maintenance dominates the industry today, it is believed that condition monitoring could yield promising results with a better compromise on cost over effectiveness in the long run. The aim of condition-based monitoring in aeronautics is, based on the available system data (e.g., flight, event and maintenance data), to evaluate the current health state of an aircraft component and to estimate its remaining useful life. Several approaches have been studied in condition-based maintenance with the most promising being data-driven modeling. This paper proposes a comparison of a set of data-driven modeling techniques to perform prognostics on a critical component of the jet engine bleed system. The novelty of our work is twofold. First, we perform this comparative study on a real case study of a critical valve of the aircraft bleed system. Fielded data from different data sources are used in the models. To our knowledge, this is the first case study that merges data from the computer central maintenance system (fault messages), maintenance data, and flight data on a prognostics system. Second, a variety of data-driven techniques are compared from neural nets to regression support machines. The models are compared using the standard metrics of absolute, mean, and squared errors. A regressive accuracy curve is also used to compare the models along different prediction window sizes. The results show the best model comprised information from all data sources. The data that most contributed to the performance improvement was the maintenance, flight and fault data, in this order. This result comes to reinforce the notion that it is more difficult to extract quantitative information from fault events than flight data with data-driven regressive methods.

Maintenance cost optimization for multiple components using a condition based method

Since maintenance planning directly affect the availability and the lifecycle cost of components and systems, it has become a topic of great interest among researchers and industry practitioners in recent years. Preventive maintenance techniques can be adopted in order to determine a convenient maintenance schedule, reducing the number of unexpected failure events. The implementation of a preventive maintenance approach may also provide other benefits such as increase in equipment availability, reduction in maintenance costs and increase in equipment lifetime. In this scenario, the application of PHM (Prognostics and Health Monitoring) techniques can be thought as a powerful tool to support the implementation of a CBM (Condition Based Maintenance) approach. The problem of CBM optimization can be formulated as finding the optimum maintenance schedule for a set of components so that the average maintenance cost per unit of time is minimized. In this paper, a maintenance cost optimization method for multiple components is presented. The proposed method uses information on the health condition of each component and takes into account the economic benefits of repairing multiple components at the same time instead of scheduling maintenance interventions for different components in different time instants, based on individual optimization recommendations. A numerical example is presented to illustrate the application of the proposed method.

Integrated task assignment and maintenance recommendation based on system architecture and PHM information for UAVs

PHM (Prognostics and Health Monitoring) can be defined as the capability of assessing the health condition, forecasting impending failures and the expected RUL (Remaining Useful Life) of a component based on a set of measurements collected from systems. Additionally, an important concept that could stem from PHM is IVHM (Integrate Vehicle Health Management); that is the unified capability of integrating PHM within a framework of available resources and operational demand. Therefore, this work aims to integrate task assignment and maintenance recommendation, both based on PHM information, for UAVs (Unmanned Aerial Vehicle) Swarm. Task assignment is the problem of assigning a vehicle to a task. This paper uses a PHM-based task assignment solution; this solution takes into account mission time, task priority and vehicles health condition. Maintenance recommendation is the operation of defining which component should receive maintenance action, using an algorithm that takes into account PHM information, system architecture and safety margins. Both task assignment and maintenance recomendations take advantage of a combination of PHM information and system architecture to compute the UAVs health condition, referred as S-RUL (System Level Remaining Useful Life). The S-RUL provides information related to the time when the whole system will stop working. In the case study, a simplified pitch control system is used to illustrate the application of the proposed method to UAVs Swarm.

Investigation of Entropy Nets Induced by Oblique Decision Trees for Target Detection in Ocean SAR

An artificial neural network whose topology is informed by an Oblique Decision Tree is applied to target detection in maritime Synthetic Aperture Radar. The number of neurons in the first layer is the same as the number of decision tree nodes and the number of nodes in the second hidden layer is the same as the number of leaf nodes. The neural network output are the class labels. Our approach differs from other efforts in the literature in that the Oblique Decision Tree and the Fisher´s Linear Discriminant are used as a decision criterion. Classifier testing and validation were achieved, applying these algorithms to radar images. Initial results are practical with satisfactory training time; generalization capability and a speedy architecture definition.