| Full text | |
| Author(s): |
Pordeus Gomes, Joao Paulo
[1]
;
Rodrigues, Leonardo Ramos
[2]
;
Leao, Bruno P.
[3]
;
Harrop Galvao, Roberto Kawakami
[4]
;
Yoneyama, Takashi
[4]
Total Authors: 5
|
| Affiliation: | [1] Univ Fed Ceara, Dept Comp Sci, BR-60455760 Fortaleza, Ceara - Brazil
[2] Inst Aeronaut & Espaco, Elect Div, BR-12228904 Sao Jose Dos Campos - Brazil
[3] GE Global Res, Brazil Technol Ctr, Rio De Janeiro - Brazil
[4] Inst Tecnol Aeronaut, Dept Elect Engn, BR-12228900 Sao Jose Dos Campos - Brazil
Total Affiliations: 4
|
| Document type: | Journal article |
| Source: | IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING; v. 15, n. 1, p. 214-224, JAN 2018. |
| Web of Science Citations: | 1 |
| Abstract | |
This paper presents a failure prognostics methodology based on degradation messages using a particle filter framework. In the proposed method, the degradation messages are interpreted as quantized measurements. The use of degradation messages reduces the need for data communication bandwidth, since they only need to be transmitted or stored when some predefined threshold is crossed. In contrast, the direct monitoring of degradation-related measurements requires frequent updates, usually at a fixed sampling rate. This characteristic is fundamental on failure prognostics applications in real aircraft due to the high infrastructure costs associated with data transmission. A case study using field data recorded from commercial aircraft is presented to illustrate the proposed methodology. The problem under consideration consists of estimating the time remaining until the fluid level reaches unacceptably low values in the hydraulic system. Two quantization steps are considered in the evaluation. Predictions employing direct measurements of fluid level are also performed to establish a comparative performance baseline. The results show that it is possible to choose a quantization step that allows a reduction in the transmission costs without significant loss of prognostics performance. Note to Practitioners-Failure prediction is a topic of great interest in various industry sectors. Predicting these events is challenging not only because of the advanced techniques involved in signal processing but also the availability of these signals with proper quality. Specifically in the aeronautical industry, the availability of signals for failure prediction may rely on in-flight data transmission systems. The usage of such systems can lead to prohibitive costs when transmitting large quantities of data. As a consequence, most commercial aircraft monitoring systems can only send a small set of failure messages indicating that the systems are failed or, in some cases, that they achieved an intermediate degradation level. This paper proposes an adaptation of a state-of-the-art failure prognostics algorithm (particle filter) that uses intermediate degradation messages to predict failure instants. The method is tested with real commercial aircraft data and the impact of the number of intermediate degradation levels is analyzed. (AU) | |
| FAPESP's process: | 11/17610-0 - Monitoring and control of dynamic systems subject to faults |
| Grantee: | Roberto Kawakami Harrop Galvão |
| Support Opportunities: | Research Projects - Thematic Grants |