João Paulo Pordeus Gomes
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
João Paulo Pordeus Gomes has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Roberto Kawakami Harrop Galvão
Instituto Tecnológico de Aeronáutica
7 shared publications - Takashi Yoneyama
Aeronautics Institute of Technology, Brazil
6 shared publications - Wlamir Olivares Loesch Vianna
Embraer S.A., São José dos Campos, São Paulo, 12227-901, Brazil
3 shared publications - Leonardo Ramos Rodrigues
Embraer S.A., São José dos Campos, São Paulo, 12227-901, Brazil
2 shared publications - Bruno C. Ferreira
EMBRAER – Empresa Brasileira de Aeronáutica, S.J. dos Campos, SP, 12227901,Brazil
1 shared publication - Bruno P. Leao
EMBRAER, São Jose dos Campos, São Paulo, 12227-901, Brazil
1 shared publication
Latest Publications
- Open Access
- 14 October 2013
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 5 (1)
Estimation of APU Failure Parameters Employing Linear Regression and Neural Networks
This study is concerned with the building of an appropriate model to estimate failure parameters of an Auxiliary Power Unit (APU). Linear and nonlinear models were used in order to evaluate which model is more suitable for this application. Data for model building and testing were obtained by simulating a nonlinear dynamic model of APU in Matlab/Simulink for various operating conditions to which it may be subjected to and with different levels of failure parameter degradation. Linear models were obtained by least-squares regression, whereas nonlinear models were obtained by training neural networks. The results obtained with these two models were compared. As a result, the neural network models were found to provide a better estimate of the APU failure parameters.
- 14 October 2013
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 5 (1)
Open AccessEstimation of APU Failure Parameters Employing Linear Regression and Neural Networks
This study is concerned with the building of an appropriate model to estimate failure parameters of an Auxiliary Power Unit (APU). Linear and nonlinear models were used in order to evaluate which model is more suitable for this application. Data for model building and testing were obtained by simulating a nonlinear dynamic model of APU in Matlab/Simulink for various operating conditions to which it may be subjected to and with different levels of failure parameter degradation. Linear models were obtained by least-squares regression, whereas nonlinear models were obtained by training neural networks. The results obtained with these two models were compared. As a result, the neural network models were found to provide a better estimate of the APU failure parameters.
- Open Access
- 14 October 2013
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 5 (1)
System Level RUL Estimation for Multiple-Component Systems
Aircraft are highly valuable assets and large budgets are spent in predictive maintenance programs in order to maximize fleet availability. The application of PHM (Prognostics and Health Monitoring) technologies can be a powerful decision support tool to help maintenance planners. The estimated RUL (Remaining Useful Life) for each monitored component, obtained from a 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 replace a component that would not immediately affect the availability of the system under consideration. In this paper, a methodology that combines fault tree information and individual components RUL estimations into a system level RUL (S-RUL) estimation is applied in a real life case study. The results showed that the methodology could have been successfully used in order to anticipate the failure of an aircraft ECS (Environmental Control System) and prevent an AOG (Aircraft on Ground) event from happening.
- 14 October 2013
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 5 (1)
Open AccessSystem Level RUL Estimation for Multiple-Component Systems
Aircraft are highly valuable assets and large budgets are spent in predictive maintenance programs in order to maximize fleet availability. The application of PHM (Prognostics and Health Monitoring) technologies can be a powerful decision support tool to help maintenance planners. The estimated RUL (Remaining Useful Life) for each monitored component, obtained from a 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 replace a component that would not immediately affect the availability of the system under consideration. In this paper, a methodology that combines fault tree information and individual components RUL estimations into a system level RUL (S-RUL) estimation is applied in a real life case study. The results showed that the methodology could have been successfully used in order to anticipate the failure of an aircraft ECS (Environmental Control System) and prevent an AOG (Aircraft on Ground) event from happening.
- Open Access
- 23 September 2012
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 4 (1)
Health Monitoring of a Power Supply Using Multivariate Regression
Due to the increasing use of electronics in critical aircraft control systems, it has become more and more important in the aerospace industry to understand how the degradation process of electronic devices occurs. Power supplies are devices of special interest since their internal components such as diodes, capacitors, MOSFETs (Metal Oxide Semiconductor Field Effect Transistor) and IGBTs (Insulated Gate Bipolar Transistors) operate under continuous stress conditions and often present elevated failure rates. The aim of this work is to present a methodology for detecting the gradual health degradation of a COTS (Commercial off-the-shelf) power supply. An accelerated aging process for power MOSFETs was conducted. During this experiment, power MOSFETs were subjected to thermal overstress in order to increase die- junction temperature above rated value through large current from drain to source. Multivariate regression analysis was applied to the raw data collected during the tests in order to assess the power supply health status.
- 23 September 2012
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 4 (1)
Open AccessHealth Monitoring of a Power Supply Using Multivariate Regression
Due to the increasing use of electronics in critical aircraft control systems, it has become more and more important in the aerospace industry to understand how the degradation process of electronic devices occurs. Power supplies are devices of special interest since their internal components such as diodes, capacitors, MOSFETs (Metal Oxide Semiconductor Field Effect Transistor) and IGBTs (Insulated Gate Bipolar Transistors) operate under continuous stress conditions and often present elevated failure rates. The aim of this work is to present a methodology for detecting the gradual health degradation of a COTS (Commercial off-the-shelf) power supply. An accelerated aging process for power MOSFETs was conducted. During this experiment, power MOSFETs were subjected to thermal overstress in order to increase die- junction temperature above rated value through large current from drain to source. Multivariate regression analysis was applied to the raw data collected during the tests in order to assess the power supply health status.
- Open Access
- 23 September 2012
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 4 (1)
Failure Prognostics of a Hydraulic Pump Using Kalman Filter
Hydraulic systems are an important power source in modern aircraft. Most aircraft employ hydraulic power for flight control systems and landing gears actuation. Pumps are a critical component in hydraulic system and monitoring the health of such components may provide economic and operational benefits to aircraft operators. This work describes the use of Kalman Filter techniques for the estimation of remaining useful life of aircraft hydraulic pumps. An empirical model of degradation evolution is employed for this purpose. Low sampling rate measurements of the hydraulic pressure of the aircraft hydraulic systems are the only measurements employed. In order to illustrate and validate the method, two time series of actual run to failure data are analyzed. Results provide evidence that the method can be successfully employed for actual aircraft hydraulic pump failure prognosis.
- 23 September 2012
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 4 (1)
Open AccessFailure Prognostics of a Hydraulic Pump Using Kalman Filter
Hydraulic systems are an important power source in modern aircraft. Most aircraft employ hydraulic power for flight control systems and landing gears actuation. Pumps are a critical component in hydraulic system and monitoring the health of such components may provide economic and operational benefits to aircraft operators. This work describes the use of Kalman Filter techniques for the estimation of remaining useful life of aircraft hydraulic pumps. An empirical model of degradation evolution is employed for this purpose. Low sampling rate measurements of the hydraulic pressure of the aircraft hydraulic systems are the only measurements employed. In order to illustrate and validate the method, two time series of actual run to failure data are analyzed. Results provide evidence that the method can be successfully employed for actual aircraft hydraulic pump failure prognosis.
- Open Access
- 25 September 2011
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 3 (1)
Health Monitoring of an Auxiliary Power Unit Using a Classification Tree
The objective of this work is to present a method to monitor the health of Auxiliary Power Units (APU) using a Dynamic Computational Model, Gas Path Analysis and Classification and Regression Trees (CART). The main data used to train the CART consists of measurements of the exhaust gas temperature, the bleed pressure and the fuel flow. The proposed method was tested using actual APU data collected from a prototype aircraft. The method succeeded in classifying several relevant fault conditions. The few misclassification errors were found to be due to the insufficiency of the information content of the measurement data.
- 25 September 2011
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 3 (1)
Open AccessHealth Monitoring of an Auxiliary Power Unit Using a Classification Tree
The objective of this work is to present a method to monitor the health of Auxiliary Power Units (APU) using a Dynamic Computational Model, Gas Path Analysis and Classification and Regression Trees (CART). The main data used to train the CART consists of measurements of the exhaust gas temperature, the bleed pressure and the fuel flow. The proposed method was tested using actual APU data collected from a prototype aircraft. The method succeeded in classifying several relevant fault conditions. The few misclassification errors were found to be due to the insufficiency of the information content of the measurement data.
- Open Access
- 25 September 2011
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 3 (1)
Fault Detection in Non Gaussian Problems Using Statistical Analysis and Variable Selection
This work concers the problem of fault detection using data-driven methods without the assumption of gaussianity. The main idea is extend the Runger's U2 statistical distance measures to the case where the monitored variables are not gaussian. The proposed extension is based on Gaussian Mixture Models and Parzen windows classifiers to estimate the required conditional probability distributions. The proposed methodology was applied to an APU dynamic model and showed better results when compared to classical fault detection techniques using Multivariate Statistical Process control with Hotelling’s T metrics
- 25 September 2011
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 3 (1)
Open AccessFault Detection in Non Gaussian Problems Using Statistical Analysis and Variable Selection
This work concers the problem of fault detection using data-driven methods without the assumption of gaussianity. The main idea is extend the Runger's U2 statistical distance measures to the case where the monitored variables are not gaussian. The proposed extension is based on Gaussian Mixture Models and Parzen windows classifiers to estimate the required conditional probability distributions. The proposed methodology was applied to an APU dynamic model and showed better results when compared to classical fault detection techniques using Multivariate Statistical Process control with Hotelling’s T metrics
- Open Access
- 10 October 2010
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 2 (1)
Health Monitoring of a Pneumatic Valve Using a PIT Based Technique
This paper is concerned with the development of a health monitoring system for a pneumatic valve employed in pressure regulation systems. The proposed method is based on the statistical analysis of deviations of the controlled pressure signal from a baseline behavior. For this purpose, the Probability Integral Transform is employed to calculate an index of dissimilarity between the distributions of monitored and baseline data. The proposed method was applied to field records of 15 units, which were monitored during eight months. In the case of failed units, the degradation index showed an increasing trend prior to the failure occurrence. It is worth noting that the failure level was similar in all cases, which is an important characteristic for the future development of prognostic solutions. In addition, no false alarms were observed for the healthy units. The results found in the case study are realistic and fit within practical requirements to support maintenance decision
- 10 October 2010
- Published by PHM Society in Annual Conference of the PHM Society
- Vol. 2 (1)
Open AccessHealth Monitoring of a Pneumatic Valve Using a PIT Based Technique
This paper is concerned with the development of a health monitoring system for a pneumatic valve employed in pressure regulation systems. The proposed method is based on the statistical analysis of deviations of the controlled pressure signal from a baseline behavior. For this purpose, the Probability Integral Transform is employed to calculate an index of dissimilarity between the distributions of monitored and baseline data. The proposed method was applied to field records of 15 units, which were monitored during eight months. In the case of failed units, the degradation index showed an increasing trend prior to the failure occurrence. It is worth noting that the failure level was similar in all cases, which is an important characteristic for the future development of prognostic solutions. In addition, no false alarms were observed for the healthy units. The results found in the case study are realistic and fit within practical requirements to support maintenance decision