AI-MSET™ for Commercial and Defense Aviation Landing Gear

---

Landing gear challenges can be addressed using TNP’s mature and well-proven AI-MSET™ to predict when mission-critical and safety-relevant mechanical, electromechanical, hydraulic, and servo-motor subsystems comprising landing gear assets are developing incipient defect modes. This enables small issues to be proactively remediated between flights—well before serious asset anomalies turn into costly and sometimes dangerous equipment failures.

TNP’s AI-MSET™ provides real-time surveillance of all physical transducers, including voltages, currents, RPMs for rotating elements, pressures for hydraulic components, vibration prognostics from uni-axis and tri-axis accelerometers, and all available ambient environmental parameters. In addition to real-time surveillance of all sensors associated with landing gear assets, AI-MSET™ brings significant advantages to offline inspections (between flights) using high-frequency non-destructive testing (NDT) techniques for avionics landing gear assets, including pixelated 2D IR thermal imagery.

Solution to Landing Gear Prognostic Challenges via TNP’s Mature and Well-Proven AI-MSET™

TNP can predict when mission-critical and safety-relevant mechanical, electromechanical, hydraulic, and servo-motor subsystems comprising landing gear assets are developing incipient defect modes, allowing small issues to be proactively remediated between flights—well before serious asset anomalies turn into costly and sometimes dangerous equipment failures.

TNP’s third-generation Multivariate State Estimation Technique, AI-MSET™, provides real-time surveillance of all physical transducers, including voltages, currents, RPMs for rotating elements, pressures for hydraulic components, vibration prognostics from uni-axis and tri-axis accelerometers, and all available ambient environmental parameters. In addition to real-time surveillance of all sensors associated with landing gear assets, TNP’s APR brings significant advantages to offline inspections (performed between flights) using high-frequency non-destructive testing (NDT) techniques for avionics landing gear assets, including pixelated 2D IR thermal imagery. These capabilities are enabled by separately patented TNP techniques for enhanced defect identification with ultra-low false- and missed-alarm probabilities.

Commercial Aviation Benefits from TNP’s Solution Framework

• AI-MSET™ is a third-generation disruptive technology that enables continuous system telemetry of complex engineering assets and advanced AI pattern-recognition techniques. These capabilities enable prognostic health management (PHM), disturbance prediction, system diagnostics, and incipient fault characterization in an integrated package known as Electronic Prognostics (EP).
• EP provides continuous real-time information on the operational status of components, sensors, programmable logic controllers (PLCs), interconnects, and integrated line-replaceable units (LRUs) for commercial and defense landing gear subsystems.
• A separate EP function, sensor operability validation, continuously validates the health of all existing sensors, identifies defective sensors, and replaces them with highly precise “virtual” sensors based on analytical estimates. Meanwhile, APR’s predictive and prescriptive maintenance capabilities proactively detect and identify incipient component degradation so that small developing mechanical, electromechanical, or thermal-hydraulic anomalies can be remediated during scheduled preventive maintenance windows—well before evolving into serious anomalies during mission-critical take-off and landing operations where safety margins may be compromised.

Bottom Line

These benefits translate to improved Reliability, Availability, and Serviceability (RAS) of mission-critical systems, enhanced operational risk mitigation, increased safety margins, and significantly lower Operations and Maintenance (O&M) costs for carriers.

AI-MSET™: Disruptive Technology Background

TNP’s motivation for developing advanced real-time prognostic machine-learning algorithms is to achieve high reliability, availability, and proactive serviceability (RAS) for mission-critical and safety-critical infrastructures.

Definitions

• AI-MSET™: AI-enabled Multivariate State Estimation Technique
• SPRT: Sequential Probability Ratio Test

AI-MSET and SPRT are industry-leading prognostic algorithms. These AI algorithms predict, in real time, what each process metric should be based on learned correlations among process variables from subsystems with dozens of sensors, large-scale assets with thousands of sensors, or fleets involving millions of sensors. AI-MSET™ prognostic innovations integrate advanced pattern-recognition methodologies with SPRT, which offers independently configurable false- and missed-alarm probabilities (FAPs/MAPs). This combination achieves high sensitivity for proactive detection of subtle anomalies in noisy process variables while maintaining ultra-low false- and missed-alarm rates.

TNP’s Prognostic Algorithmic Innovations Combine Two Powerful Pattern-Recognition Techniques

Sequential Probability Ratio Test (SPRT)is an advanced pattern-recognition technique offering high-sensitivity, high-reliability surveillance of sensor and equipment operability. Researchers have demonstrated in refereed journals and international symposia that SPRT provides the earliest mathematically possible annunciation of subtle faults in noisy process variables. This capability is critical for landing gear health monitoring, enabling ultra-low and separately specifiable false-alarm and missed-alarm probabilities (Type I and Type II errors).

Across commercial and defense aviation, false alarms are extremely costly because they remove revenue-generating and mission-critical assets from service unnecessarily, while missed alarms can be catastrophic. AI-MSET™, combined with SPRT, continuously disambiguates between sensor anomalies and actual asset anomalies.

AI-MSET™: Online Model-Based Fault Detection and Identification

AI-MSET predicts, in real time, what each process metric should be based on learned correlations among all process variables. It incorporates SPRT to monitor residuals between actual observations and AI-MSET™ predictions.

TNP has significantly advanced the state of the art beyond original MSET-1 and now offers the next generation of predictive health and prognostics, known as AI-MSET™. It integrates multiple intelligent data preprocessing (IDP) pattern-recognition and autonomous training, tuning, and optimization algorithms, eliminating the need for aviation carriers to employ PhD-level data scientists to deploy and operate landing gear prognostic analytics.

TNP has developed a dense portfolio of patented innovations that leverage AI-MSET as a core algorithm, integrated with advanced preprocessing and post-processing techniques. These innovations make TNP’s solutions robust to low-resolution sensors, data-acquisition bandwidth limitations, missing values in time-series data, intermittent spurious anomalies, and signal asynchrony in large-scale IoT applications. AI-MSET™ achieves higher sensitivity and superior false-alarm avoidance than alternative AI/ML approaches, including neural networks (NNs), support vector machines (SVMs), and kernel regression.

Traditional Threshold-Based Surveillance Is Inadequate for IoT Prognostic Applications

Traditional threshold-based prognostic approaches may use machine learning to distill important metrics distinguishing “normal” from “anomalous” behavior. However, these metrics are ultimately compared against fixed thresholds:

• Threshold limit tests suffer from a “see-saw” trade-off between false alarms and missed alarms.
• Tightening thresholds to detect early problems increases false-alarm rates.
• Relaxing thresholds to reduce false alarms allows severe degradation or failure to occur before alerts are generated.

TNP Disruptive Technology as Applied to Landing Gear Assets

U.S. FAA “Grand Challenge”

Predicting failure in mission-critical landing gear systems is difficult. Performance and availability of electronic, interconnect, mechanical, electromechanical, and thermal-hydraulic components may degrade due to intensive use, environmental extremes, aging, or cyclic stress. Conventional PHM methods do not adequately account for these factors, leading to reduced readiness and remaining useful life (RUL). Traditional threshold-based PHM approaches fail to provide early enough detection to support truly predictive or condition-based maintenance.

Discussion

Effective PHM solutions for mission-critical assets require comprehensive methodologies that proactively detect and isolate failure mechanisms, minimize Type I and Type II errors, and estimate RUL in real time. TNP’s mature AI-MSET™-based Electronic Prognostics (EP) extends PHM capabilities to electronic systems where thermal events most often originate, including embedded command-and-control (C&C) computing elements, ASICs, PLCs, actuators, and interconnecting networks.

No competing ML algorithms can proactively detect the incipience of thermal dissipation mechanisms in embedded C&C elements for safety-critical aviation assets. AI-MSET™ includes over four dozen patented innovations for electronic component health assessment, performance tolerance estimation, and quantitative RUL determination.

Summary

TNP’s modular, pluggable software provides:

• Real-time signal validation for landing gear electronic prognostics
• Fault isolation to the component level with persistent logging for enhanced      root-cause analysis (RCA), reducing false alarms and maintenance labor      costs
• Incipient fault annunciation to identify intermittent faults
• Quantitative RUL estimation with confidence factors to support informed maintenance decisions
• Analytical signal replacement enabling continued operation with failed or degraded sensors
• Automated sensor calibration monitoring for on-condition maintenance

TNP’s signal validation and sensor operability validation algorithms are already approved for safety-critical applications, including U.S. Nuclear Regulatory Commission (NRC) approval for use in commercial nuclear reactors.