The perceived benefits of permanent usage monitoring equipment in helicopters include savings in the cost of helicopter maintenance and a favourable impact on safety and fleet management. Unlike indirect fatigue monitoring, direct load monitoring relies on a large number of sensors which requires high operational and maintenance costs. In this paper, a learning network has been developed, and during training sessions allowed to learn how to predict fatigue damage indirectly from flight parameters. Each training example consists of instantaneous fatigue damage induced during a small time step, and flight parameters measured during the time step. The instantaneous damage values are evaluated through a new approach called the progressive damage model. By considering the laws of aerodynamics and dynamics, the network combines the flight parameters in such a way that the resulting features can be mapped into fatigue. About 10.5 flying hours of data were used to train the network. After training, the network was blind tested using flight parameters from 5.8 flying hours. The network was found to predict the fatigue damage of two rotating components indirectly from the flight parameters with accuracy better than the accuracy of a strain gauge system with 5 per cent measurement error.
Development of integrated health and usage monitoring systems (IHUMS) involved the use of personal computer-based math-dynamic models, which in this particular case simulate a range of helicopter rotor system faults and potentially catastrophic failures. Using both theoretical and in-field data, over 120 fault cases have been analysed to identify discriminatory characteristics. This paper reports on the background of the math-dynamic models and the findings of the diagnostic analysis.
Since September 2006, an international Aerospace Industry Steering Committee was assembled at Stanford University. Since February 2009, the committee has been formally working on developing guidelines for validating, qualifying and certifying structural health monitoring systems. Working within the G-11 division of SAE International, the committee has compiled guidelines for civil transport aircraft. Some of these guidelines can be used for military applications. However, military guidelines are needed to address specific military considerations including concept of operations. The military guidelines should also cover the wider spectrum of military aircraft types and should focus on the key elements required for integrating structural health monitoring within military systems. Therefore, a G-11 Aerospace Industry Steering Committee Military Aircraft Working Group was formed to develop such guidelines. This article describes the motivation, rationale, scope, milestones and initial work of the Military Aircraft Working Group. The results of the guidelines will form the future framework for the military community.
Helicopter health and usage management systems (HUMS) generate large amounts of data, which are downloaded to ground-based systems. The data are automatically examined on download for damage indications, which provide the immediate go/no-go response required by the aircraft operations management. This level of reactive fault detection and diagnosis is reasonably well understood and has been demonstrated to improve aircraft availability and airworthiness. To achieve further benefit and maintenance cost savings from HUMS, another level of analysis is required, leading to prognostics and predictive maintenance through intelligent management (IM) of the accumulated HUMS records. In collaboration with the Civil Aviation Authority (CAA), Smiths has developed a suite of IM methods and has successfully applied them to gearbox seeded fault data. Working closely with the UK Ministry of Defence (UK MOD), Smiths has tested these methods on Chinook HUMS data, including an in-flight transmission bearing failure incident described in this article. The result is a high degree of early anomaly detection and a clear view of the deterioration to failure. The objective of the MOD programme has been to apply IM tools to the enormous quantity of HUMS data being gathered, thereby enabling improved analysis capability, increased levels of automation, and more intelligent use of resources. The article presents the results of the work carried out under both the CAA and the MOD programmes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.