Advanced Analysis Methods for Military Aviation Reliability Data Bases
Navy SBIR 2008.1 - Topic N08-038 NAVAIR - Mrs. Janet McGovern - [email protected] Opens: December 10, 2007 - Closes: January 9, 2008 N08-038 TITLE: Advanced Analysis Methods for Military Aviation Reliability Data Bases TECHNOLOGY AREAS: Air Platform, Information Systems, Materials/Processes ACQUISITION PROGRAM: PMA 265, Super Hornet, Hornet and Growler The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), which controls the export and import of defense-related material and services. Offerors must disclose any proposed use of foreign nationals, their country of origin, and what tasks each would accomplish in the statement of work in accordance with section 3.5.b.(7) of the solicitation. OBJECTIVE: Develop and demonstrate a suite of innovate computational tools for reliability data base analysis. This novel toolset would automatically generate timely and actionable intelligence for maintainers, fleet support engineers and design engineers improving propulsion safety, affordability, and readiness of military gas turbine engines. DESCRIPTION: The F414 Maintenance Data Warehouse (MDW) contains a wealth of data on engine and component reliability and maintenance activities. The data warehouse contains detailed maintenance records for all F414 engines and their serialized modules and components. Such data starts with propulsion system metrics (engine flight hours, cycles and customized life usage indicators) through organizational level engine and line replaceable unit (LRU) removals with reasons for removal and commentary. The data follows the engines, modules and components through maintenance at intermediate level and the depot, including shop findings and changes in component serial number and engine configuration. This affords the opportunity to track removal causes and shop findings to the module and component level, automatically tracking root causes and component reliability against propulsion system, module and component usage. An added complexity of the F414 MDW is the high levels of lifetime data censoring due to scheduled removals and the staggered introduction of F-18 aircraft into service. Several layers of competing risk (scheduled engine inspections and removals, opportunistic module removals at the inspection level, and opportunistic component replacement and refurbishment at the depot) compounded by the modular maintenance strategy complicate any analysis, particularly given the evolving and non-uniform engine configuration. Extracting representative latent reliability characteristics requires case based reasoning and analysis tailored to the context of individual failures. The tremendous volume of this data limits most investigations to basic metrics and reactive analysis on a case by case basis. Advanced data mining and statistical analysis techniques are needed to provide in-depth studies to flag trends and anomalies, enabling proactive maintenance, engineering investigations and design modifications. However, the workload to implement such tools in the complex, multi-faceted F414 MDW is prohibitive and the artificial intelligence tools to automate this process have proven unsuccessful. Additionally, multiple data bases (engine, weapons replaceable assembly (WRA), module and components) must be interrogated to adequately characterize system reliability. Analysis to date indicates that novel non-parametric and parametric analysis models will be needed, particularly to validate the multi-variate component life usage indicators [LUI] employed in scheduling engine removals. Machine aided update of the failure modes, effects and criticality analysis (FMECA) and a representative reliability model for the F414 engine is one anticipated product of the proposed toolset. Another added benefit of such tools would reduce component improvement costs (CIP) by providing better targeted configuration change. PHASE I: Determine the feasibility of developing a suite of tools that automatically generates timely and actionable intelligence from maintenance and reliability data warehouses. Identify preliminary deliverable specifications and conduct initial trials of promising analytical methods to show the feasibility of the proposed approaches. PHASE II: Demonstrate the automated data mining and analysis tools developed in Phase I in the MDW information technology environment. The utility of the tools developed is to be demonstrated through trials conducted with the participation of working level GE and US Navy personnel responsible for the management of F414 reliability and maintenance processes. PHASE III: Full implementation of an integrated F414 automated usage and reliability analysis tool box in the MDW environment through to qualification and release for routine use by maintenance personnel and maintenance, reliability and design engineering. Transition the toolset to other USN platforms as appropriate. PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: There is expected to be extensive cross fertilization of the advanced analysis tools, as commercial aircraft operators and service providers are building similar maintenance and reliability data warehouses. REFERENCES: 2. Millar, Richard C., 2007, Application of Reliability Data Base Analysis Tools, to be published in the proceedings of SAE AeroTech, September 2007. KEYWORDS: Reliability; Analysis; Propulsion; Engine; Module, Component TPOC: (301)757-0517
|