APIRA

All over the world, aircraft are flying far beyond their designed life expectancy. The safety and reliability of aircraft fleet inventory management is therefore especially critical. PredictionProbe has created a comprehensive condition-based aircraft post-inspection reliability analysis capability in a truly efficient and effective engineering computational tool. APIRA is an object-oriented, flexible, scalable, and customizable tool. PredictionProbe, created APIRA in connection with the U.S. Air Force (USAF) as aircraft structural risk and reliability is a vital and growing element of the USAF Aircraft Structural Integrity Program (ASIP).

Condition-Based Aircraft Repair

Predictive Structural Reliabillity Analysis

APIRA has the capability and flexibility to correctly model the physics of the variety of possible post-inspection structural repair options within the object-oriented modeling environment of PPI’s proprietary general-purpose, commercial-off-the-shelf (COTS) software, SPISE.

PPI’s technical approach revolves around construction of the condition tree (Condition Tree). The Condition Tree is a graphical representation of all the possible conditions between the time the aircraft is placed into service and until the time it is retired. The Application Software Development capability of SPISEâ was used to develop the APIRA Software that includes 367 modules and 99 workflows linking the modules. The main features of APIRA include:

  • Two user-friendly Graphical User Interface (GUI) including:
    • APIRA Dynamic GUI for preparing input, executing APIRA and retrieving results; and
    • SPISE GUI for modifying and/or adding new modules and workflows of APIRA, adding new modules or workflows, and more.
  • Ability to define an unlimited number of inspections, repairs conditions, and non-repair conditions, PODs and their related input variables that includes the following three pre-configured inspection types, repair conditions, non-repair conditions, and PODs:
    • Three inspection types including D_level, I_level, and O_level;
    • Three repair conditions including Oversized Hole, Doubler, and Replacement for each inspection type;
    • Two non-repair conditions including No Indication (i.e., no crack found) and Initial Condition (i.e., starting condition at flight time = 0); and
    • Six PODs including three for D_level, I_level, and O_level with Doubler Repair and three for D_level, I_level, and O_level with Oversized Hole, Replacement, and non-repair conditions (e.g., No Indication and Initial Condition).
  • Ability to predict inspection time based upon an acceptable level of single flight probability of failure (SFPOF).
  • Ability to: a) store the project’s input and output data inside three databases (Master Databases) with user selected platform (e.g., SQLite), b) provide access to all pre- and post-processor raw data files, c) to easily import and/or export such data as needed, and provide input variable traceability.
  • Ability to assign:
    • Specific repair and non-repair conditions to each inspection;
    • Specific POD for every repair in each inspection type; and
    • Different time intervals to scheduled inspections.
  • Bayesian EIDS based on whether or not cracks were found at: the inspection of a single aircraft in multiple locations (multiple details); and/or b) multiple inspections of multiple aircrafts with different flight hours, at the same time or at different time.Condition Tree Updating capability based on inspection results.
  • Ability to predict the number of repair types per fleet at: a) each inspection times and b) over time up to and including current inspection.
  • Ability to predict: a) number of cracks in a fleet at each inspection; and b) number of aircrafts per fleet with cracks at each inspection time.
  • Ability to abort the software execution during the analysis and resume it later, from the closest previous inspection time to where it was aborted earlier, at a future time.
  • Ability to control the number and time of the analyses to be performed between two consecutive inspections.
  • Dynamic Logic Engine for defining analyses logics, condition tree, various variables, workflows and condition-based decision making & analysis.
  • Automatic backtracking & analysis criteria modification in response to errors, and error identification in GUI.

The DMAP™ Module of SPISE provides numerous probabilistic methods to generate the desired data such as cumulative probability of failure (POF); SFPOF; POF as a function of crack size, POF(a); Crack Size Distribution (CSD), Found CSD, and No Indication CSD, etc.

APIRA provides the Probability of Failure (POF(a)) at each condition. Additionally, for each condition and for the total summed across all conditions (Overall), APIRA provides: a) Aircraft SFPOF and POF; b) Single Detail SFPOF and POF; and c) Single Detail CSD, Found CSD, and No Indication CSD, based on a user specified CSD percentile, as a function of time and at each inspection.

Although the focus of APIRA has been for use in USAF applications, the technology developed here will have significant technical leverage and value which can be applied to other branches of the Department of Defense’s (DoD) Armed-Forces, Federal Aviation Administration (FAA), National Aeronautics and Space Administration (NASA), aerospace, airline industries, and so on. APIRA Software will decrease the threat of cumulative effects of structural repairs to the structural integrity of aircraft fleets and will ensure the safety and reliability of such fleets—with considerable cost savings and cost avoidance benefits to both industry and the government.

Learn More

Connect with us for a demonstration on how Predictive Technology can take the stress and strain out of your most rigorous business dilemmas.