8.2 User Friendliness
An aspect easily neglected when working with complex reasoning systems is the user interface. Although the robustness and accuracy of the reasoning algorithms if of vital importance for any decision aid system, user interface is of equal importance in order to establish user con.dence. In the context of HUMS, a somewhat neglected area has been data mining and management. This mainly due to the fact that all the data analysis needs, both for operator and OEM, were not clear when the functional speci.cations for HUMS were developed. Consequently, HUMS software was not equipped with the data
127
analysis tools necessary to satisfy the needs of all clients, and no mechanism were included to share HUMS data with third party tools when necessary.
These shortcomings have been addressed by the data structuring work detailed in the chapter on data migration, and facilitate the use of third party tools to perform more in-depth analysis of HUMS data. This work also addresses the problem of data availability for the OEM researchers and support personnel, as well as reducing client workload associated with data sharing. Further, this study has been a contributer to a project facilitating discrepancy reporting between client and OEM, signi.cantly reducing client workload associated with discrepancy reporting as well as cutting response time for the OEM. This latter point probably being an example to follow for support services dealing with other aspects of the aircraft than HUMS.
8.3 Reliability
The main focus for this study has been on fault detection, which has aimed at increasing system reliability and reducing operator workload. In the ut-most consequence it can be said that traditional threshold based methods are capable of detecting all faults, provided that all thresholds are correctly adjusted. Experience does however show that indicator thresholds are not aways correctly set. This due to the fact that the correct tuning of any threshold changes as a function of outside factors like maintenance interven-tions. In order to cope with this reality, it has been necessary to explore new concepts in order to reach the aim for this study; a reliable fault detection method not in need of any user con.guration.
Using progression analysis as feature extraction for faults not easily de-tectable through traditional means has shown increased detection rate and reduced false alarm rates compared to traditional threshold based methods. Although the test data available is too scarce to generalize, progression anal-ysis shows promise as an alternative to conventional methods. Another ad-vantage of progression analysis is that it does not require any con.guration by the operator. By combining threshold based detection methods where applicable with progression analysis for components not easily monitored by traditional means, it is possible to create an autonomous HUMS. Such a sys-tem has clear safety bene.ts as it is not susceptible to miss-con.guration by the user. This is probably the most interesting aspect of this study, as there are currently no systems of the marked capable of functions autonomously. Together with the increased detection rate demonstrated in the case study, these advances deliver the technology necessary to produce a commercial solution well ahead of the competing systems.
中國(guó)航空網(wǎng) www.k6050.com
航空翻譯 www.aviation.cn
本文鏈接地址：OPTIMIZATION OF FAULT DIAGNOSIS IN HELICOPTER HEALTH AND USA(68)
