The intent of this effort is to successfully train a corrosion algorithm that accurately assesses cumulative exposure state as an input to a condition based maintenance plus (CBM+) algorithm to more efficiently define maintenance (Mx) requirements. The approach is to use only readily accessible data as inputs to the algorithms, potentially eliminating the long-term need for on-board sensors. The technical objective of this proposed project is to develop and validate matrices of environmental indicators and a cumulative exposure state to predict the likelihood of corrosion in the form of a corrosion algorithm where the resulting data ultimately feed condition data into CBM+ algorithms offering corrosion predictive prognostics, as well as greater, expanded asset health monitoring (by tail/asset number).

Technology Description

Corrosion monitoring systems will be used to characterize asset environments and will be placed on racks, ground support equipment (GSE), and aircraft at several USAF locations. Coupons of various substrates will be placed on racks and selected GSE to support validation of visual corrosion to sensor data. Environmental data from each selected DoD Base location will be captured and analyzed from the National Oceanic and Atmospheric Administration (NOAA) and outputs from each base weather station. The environmental data captured from the sensor will be compared to the data downloaded from NOAA to ensure accuracy of the sensor. Sensor and environmental data will be collected and analyzed over a statistically-significant period of time to develop a matrix of environmental indicators. On-board sensors will provide insight and data for capturing the environmental effects of altitude changes and Mx operations (including washes and rinses) on aircraft. Tail specific flight patterns will be developed for each aircraft by working with each program office. The matrix will support the development of a corrosion algorithm to correlate the cumulative exposure state to the potential for corrosion. This algorithm will be continuously validated against the sensor and environmental data and revised accordingly to enhance outputs and predictive accuracy. The sensors, environmental data, witness panels, and the subsequent cumulative exposure state will in essence cross-check each other to ensure high-confidence in corrosion prediction. The algorithm to describe cumulative exposure state will then be cross-checked with Mx actions and asset location history to develop a CBM+ predictive algorithm to affect aircraft Mx in terms of wash events and inspections, minimizing the need for corrective Mx by promoting CBM+. “Maintenance upon evidence of need” is the guiding principle of CBM+. This effort is necessary to advance the state of environmental exposure characterization, and thereby provide decision-makers with the ability to make sound decisions without the unknowns that lead to the current (overly conservative and wasteful) time-based decisions and calendar-based wash cycles.


The elimination of unscheduled Mx activities will reduce hazardous material usage and waste disposal, thereby lowering wastewater treatment issues. It will curb operator exposure to carcinogenic materials such as hexavalent chromium and save related costs. This concept will affect every GSE and aircraft asset in the USAF and potentially DoD inventory. The proposed novel approach removes the need to install sensor(s) on every aircraft while still providing the capability to individually track assets for potential corrosion. By employing an integrated and predictive approach that integrates corrosion and CBM+ principles, the DoD will realize great environmental benefits through the reduction of unnecessary Mx operations. The approach to integrate monitoring systems output with environmental conditions to develop a cumulative exposure state into CBM+ algorithms will provide reliable information to improve corrosion prediction capabilities and simultaneously address environmental impacts and Mx costs.