Learn how to increase prediction accuracy in Condition-Based Maintenance (CBM) and Condition-Based Data (CBD)
The second in a series of exclusive presentations by James “Hoffy” Hofmeister.
Improve the accuracy of your maintenance prediction information with this unique approach to prognostics.
Algorithm-based Prognostic Health Monitoring (PHM) done the Ridgetop Group way, can improve the maintenance cycles on your applications from critical Aerospace systems, Lithium Ion battery systems, to Railroad car bearings.
Sign up here and you will receive instructions to join the event.
June 10, 2020 10am (GMT-7)
NightHawk™ was developed to solve the problem of “No Fault Found” (NFF) instances in electronic subsystems in aircraft. NFFs occur when a performance problem exists, but conventional testing does not find or indicate a problem. Initially developed, tested and validated on the Air Force VDATS system, NightHawk™ was subsequently implemented into various Automated Test Equipment (ATE) clusters. NightHawk functionality can be ported to the Navy’s eCASS platform to provide additional tools to improve test coverage of key electronic subsystems in Naval Aircraft to provide modern test and logging data analytic tools to handle aging aircraft problems and prolong the sustainability of the fleet.
NightHawk can significantly reduce the Mean-Time-to-Repair (MTTR) – up to 60% – by pinpointing the specific electronic circuit boards that are defective, but still pass the legacy TPS tests. NightHawk can benefit both the military (NAVAIR, Air Force, Army Aviation) as well as commercial aircraft fleet operators such as FedEx World Services and other commercial airlines.
NightHawk Enhancements to Conventional Automated Test Equipment Shortcomings
Test program sets (TPSs) currently used to test and debug electronic problems on aircraft are largely developed by OEMs that support acceptance requirements of their subsystems decades earlier. With operation of the aircraft over decades in harsh environments, encompassing shock, vibration, lightning strikes and temperature extremes, the components in the subsystems can drift from their original values. These variations can cause “soft faults” that go undetected by the original TPS, so NightHawk was developed to root-out these difficult-to-detect performance anomalies using advanced anomaly detection.
These analysis capabilities rely on time and frequency-domain test software for thorough analysis of aging avionics and weapon systems that have been subjected to harsh environments, failures caused by parameter drift, and component degradation, all of which can result in elusive, intermittent ‘soft faults’ that negatively impact the mission objective and increase lifecycle maintenance costs.
According to Doug Goodman, CEO of Ridgetop, “We are very fortunate to have such a World-Renowned Researcher and key contributor having the background and depth of knowledge in our field of advanced diagnostics and prognostics. His technical leadership has helped Ridgetop expand its integrated vehicle health management (IVHM) tools to new government and commercial markets.” Szidar was instrumental in developing special algorithms to support detection of “No Fault Found”, or NFF conditions on critical aircraft systems.
Dr Szidarovszky is presently working in the determination of “effective age” of electronic modules that may include a combination of new, old or aged components. Effective age plays a major role in the determination of State-of-Health (SoH) and Remaining Useful Life (RUL) that can support Condition Based Maintenance (CBM+) programs on complex systems such as aircraft, autos and industrial equipment. His paper, “A New Method to Estimate Expected Number of Failures for Allocating Spare Parts and Labor”, will be presented at IEEE Autotestcon September 14, 2017 in Schaumburg, Illinois.
At Ridgetop, Dr. Szidarovszky was instrumental in the development of the NightHawk™ algorithm library that is being applied to reducing “No Fault Found” (NFF) instances. NightHawk has been successfully applied on a variety of ATE platforms including the Air Force’s VDATS tester, and custom ATE clusters used for other purposes.
Lately, Szidar has been focusing on developing new advanced algorithms and mathematically rigorous methods of handling subsystem assets with different aging or degradation profiles. This is a common situation found in aircraft, where subsystems are removed and replaced as wear and aging affect their performance.