Health And Usage Monitoring System Research Articles

Preliminary Nose Landing Gear Digital Twin for Damage Detection

An increase in aircraft availability and readiness is one of the most desired characteristics of aircraft fleets. Unforeseen failures cause additional expenses and are particularly critical when thinking about combat jets and Unmanned Aerial Vehicles (UAVs). For instance, these systems are used under extreme conditions, and there can be situations where standard maintenance procedures are impractical or unfeasible. Thus, it is important to develop a Health and Usage Monitoring System (HUMS) that relies on diagnostic and prognostic algorithms to minimise maintenance downtime, improve safety and availability, and reduce maintenance costs. In particular, within the realm of aircraft structures, landing gear emerges as one of the most intricate systems, comprising several elements, such as actuators, shock absorbers, and structural components. Therefore, this work aims to develop a preliminary digital twin of a nose landing gear and implement diagnostic algorithms within the framework of the Health and Usage Monitoring System (HUMS). In this context, a digital twin can be used to build a database of signals acquired under healthy and faulty conditions on which damage detection algorithms can be implemented and tested. In particular, two algorithms have been implemented: the first is based on the Root-Mean-Square Error (RMSE), while the second relies on the Mahalanobis distance (MD). The algorithms were tested for three nose landing gear subsystems, namely, the steering system, the retraction/extraction system, and the oleo-pneumatic shock absorber. A comparison is made between the two algorithms using the ROC curve and accuracy, assuming equal weight for missed detections and false alarms. The algorithm that uses the Mahalanobis distance demonstrated superior performance, with a lower false alarm rate and higher accuracy compared to the other algorithm.

Anomaly Detection on Time Series with Wasserstein GAN applied to PHM

Modern vehicles are more and more connected. For instance, in the aerospace industry, newer aircraft are already equipped with data concentrators and enough wireless connectivity to transmit sensor data collected during the whole flight to the ground, usually when the airplane is at the gate. Moreover, platforms that were not designed with such capability can be retrofitted to install devices that enable wireless data collection,as is done on Airbus A320 family. For military and heavy helicopters, HUMS (Health and Usage Monitoring System) also allows the collection of sensor data. Finally, satellites send continuously to the ground sensor data, called telemetries. Most of the time, fortunately, the platforms behave normally, faults and failures are thus rare. In order to go beyond corrective or preventive maintenance, and anticipate future faults and failures, we have to look for any drift, any change, in systems’ behavior, in data that is normal almost all the time. Moreover, collected sensor data is time series data. The problem is then anomaly detection or novelty detection in time series data. Among machine learning techniques that can be used to analyze data, Deep Learning, especially Convolutional Neural Networks, is very popular since it has surpassed human capacities for image classification and object detection. In this field, Generative Adversarial Networks are a technique to generate data similar to a potentially high dimension original dataset. In our case, generate new data could be useful to enrich the learning dataset with generated abnormal data to make it less unbalanced. Yet we are more interested in the potential of such techniques to perform anomaly detection for high dimensional data, comparing newly observed data with data that could have been generated from a distribution built from normal examples.

Structural monitoring of RPAS MILANO in the flight test phase

The RPAS (Remote Piloted Air System) MILANO is the largest unmanned aerial system developed by INTA that aims to become a research platform capable of carrying out in-flight tests with many scientific payload, thus complementing the Air Research Platforms (PAIs) of INTA. At the structural level, the RPAS MILANO is made in its entirety in carbon / epoxy composite material that is cured out of the autoclave. Its design has been followed by the airworthiness regulations applicable to the aircraft type (STANAG-4671). In the month of December 2018, the RPAS MILANO flight test phase began and it’s Health and Usage Monitoring System (HUMS) is being used to collect data before, after and during flights, providing very useful information when evaluating and analyzing the state of the structure and the possible appearance of structural overloads not foreseen during the mission. Information about special events, such as forced landing or burst loading, can be provided to maintenance operators after each flight. The simulation model and its predictions have been validated in a real structure of the rear fuselage of the MILANO and in which real damage of larger sizes is introduced by eliminating rivets progressively. In our study, three different damage detection algorithms are used, based on a damage index, PCA and Artificial Neural Networks (ANN).

Aero-Engine Health Monitoring with Real Flight Data Using Whale Optimization Algorithm Based Artificial Neural Network Technique

Health monitoring of an aero-engine assumes importance in the light of primary requirements of flight safety and reliability. This paper proposes a novel, simple method for monitoring aircraft engine health using Whale Optimization Algorithm based Artificial Neural Network (WOANN) technique, for analyzing the data downloaded from the health and usage monitoring system (HUMS) of a military aircraft. The actual engine data recorded during 47 different flights of eight different engines (of the same type) have been considered in this work. Thirteen engine parameters have been used to determine and monitor the health of the engine. The efficiency of the WOANN technique for engine health monitoring, is compared with that of three other common machine learning algorithms: Probabilistic based Neural Network (PNN), K-Nearest Neighbour (KNN), and Back propagation based Artificial Neural Network (BPANN). The results show that WOANN algorithm classifies and predicts engine health far more accurately as compared to PNN, KNN and BPANN. The values obtained for the metrics of Accuracy, Error, False Positive Rate, F1 score, Mathews Correlation Coefficient, Specificity, Kappa coefficient are found to be the best for WOANN algorithm. The WOANN achieved overall prediction accuracy of 95%, thus presenting itself as a very useful tool for day-to-day monitoring of aircraft engine health using the data downloaded from the aircraft’s HUMS.

In-Flight Strain Monitoring of Aircraft Tail Boom Structure Using a Fiber Bragg Grating Sensor Based Health and Usage Monitoring System

With the increased use of composite materials in aircraft structures, continuous and thorough monitoring of structural conditions is highly required for the assurance of safety and reliability. In this study, as part of the fiber Bragg grating (FBG) sensor-based aircraft health and usage monitoring system (HUMS) development research, in-flight strain monitoring of an aircraft tail boom structure using the FBG sensor-based aircraft HUMS was investigated. The FBG sensor-based aircraft HUMS was implemented to the tail boom structure of an ultralight propeller composite aircraft. Flight tests of the testbed aircraft were performed, and in-flight strain variations of the tail boom structure were measured using the implemented system. For in-flight strain variation data-based verification through comparative analysis with flight parameters, the in-flight strain variations of the tail boom structure were analyzed with the flight parameters for various flight conditions. As a result, the HUMS operated as expected during the actual flights, and the acquired in-flight strain variations corresponded adequately in relation to the loading conditions during flight, such as bending loads due to the use of control surfaces and ground impacts during landing procedures.

Vehicular Sensor Network and Data Analytics for a Health and Usage Management System.

Automated collection of on-vehicle sensor data allows the development of artificial intelligence (AI) techniques for vehicular systems’ diagnostic and prognostic processes to better assess the state-of-health, predict faults and evaluate residual life of ground vehicle systems. One of the vital subsystems, in terms of safety and mission criticality, is the power train, (comprising the engine, transmission, and final drives), which provides the driving torque required for vehicle acceleration. In this paper, a novel health and usage monitoring system (HUMS) architecture is presented, together with dedicated diagnosis/prognosis algorithms that utilize data gathered from a sensor network embedded in an armoured personnel carrier (APC) vehicle. To model the drivetrain, a virtual dynamometer is introduced, which estimates the engine torque output for successive comparison with the measured torque values taken from the engine control unit. This virtual dynamometer is also used in conjunction with other sensed variables to determine the maximum torque output of the engine, which is considered to be the primary indicator of engine health. Regression analysis is performed to capture the effect of certain variables such as engine hours, oil temperature, and coolant temperature on the degradation of maximum engine torque. Degradations in the final drives system were identified using a comparison of the temperature trends between the left-hand and right-hand final drives. This research lays foundations for the development of real-time diagnosis and prognosis functions for an integrated vehicle health management (IVHM) system suitable for safety critical manned and unmanned vehicle applications.

Distributed Fiber Optic for Structural Health Monitoring System Based on Auto-Correlation of the First-Order Derivative of Strain

The high sensitivity of composite materials to in service accidental damage and manufacturing imperfections can often lead to oversized components design and expensive maintenance approaches. The possibility to trust on a reliable onboard structural health and usage monitoring system (HUMS), able to real-time detect damage, comparable or even smaller than the one currently assumed for design and certification, could improve, generally speaking, structural strength and simplify the maintenance philosophy. This paper resumes the results achieved by a methodology developed at the Adaptive Structures Division of CIRA, based on auto-correlation of strain map provided by distributed fiber optic on a set of 17 aeronautical stiffened carbon fiber reinforced plastic (CFRP) panels. Sensors and data processing are properly down-selected and the health monitoring system designed according to the specific goal. In this case, the bonding line integrity at skin-stringer interface is the committed target, and the capability of debonding detection after low energy impact is herein discussed. Then, probability of detection (PoD), being one of the most crucial topics in the aircraft industry for system reliability estimation, is also presented on the base of collected data, as preliminary result on the way of the procedure assessment.

Using frequency domain analysis techniques for diagnosis of planetary bearing defect in a CH-46E helicopter aft gearbox

Abstract Condition monitoring for helicopters has always been one of the most critical technologies to guarantee the integrity of the rotorcrafts, enhance operational and personnel safety, and reduce the overall maintenance costs. Over the past decades, health and usage monitoring system (HUMS) has been developed and implemented in helicopters to monitor the health status for the main gearbox (MGB) and other key components of the transmission system, improving condition-based maintenance for helicopters. However, many studies have indicated that current HUMS has a limited sensitivity to MGB planetary bearing defects. To enhance HUMS' performance, this paper presents an approach based on frequency domain analysis techniques to diagnose planetary bearing defects using real helicopter data collected from a CH-46E helicopter aft MGB. Vibration data was processed using signal processing techniques including self-adaptive noise cancellation (SANC), discrete-random separation (DRS), cepstrum editing, kurtogram, envelope analysis and iterative envelope cancellation. Processing results conclude that frequency domain analysis techniques can provide distinct and intuitive indications of the seeded defects at both the inner race and the outer race of the faulty planetary bearing.

Health and Usage Monitoring System (HUMS) Strategy to enhance the Maintainability & Flight Safety in a Flight Control Electromechanical Actuator (EMA)

Concerning flight control actuation systems, the current state of the art is the fly-by-wire control of servo actuators hydraulically operated. In the last decades several research programs have been dedicated to analyze the replacement of these equipments with the implementation of Electro-Hydrostatic Actuators (EHA) or Electro-Mechanical Actuators (EMA), pursuing the challenge to get More Electrical Aircraft (MEA).This paper focuses on the HUMS strategy proposed to provide diagnosis and prognosis of the EMA as one way to enhance Flight Safety and Maintainability for its use in Primary Flight Controls.Considerations related to Flight Safety are analyzed, specially linked to the main problem associated to the EMA, the critical effects derived from the mechanical jamming of some parts of the EMA, and the advantages of the HUMS implementation to anticipate and mitigate these consequences.

Aircraft health and usage monitoring system for in-flight strain measurement of a wing structure

This paper presents an aircraft health and usage monitoring system (HUMS) using fiber Bragg grating (FBG) sensors. This study aims to implement and evaluate the HUMS for in-flight strain monitoring of aircraft structures. An optical-fiber-based HUMS was developed and applied to an ultralight aircraft that has a rectangular wing shape with a strut-braced configuration. FBG sensor arrays were embedded into the wing structure during the manufacturing process for effective sensor implementation. Ground and flight tests were conducted to verify the integrity and availability of the installed FBG sensors and HUMS devices. A total of 74 flight tests were conducted using the HUMS implemented testbed aircraft, considering various maneuvers and abnormal conditions. The flight test results revealed that the FBG-based HUMS was successfully implemented on the testbed aircraft and operated normally under the actual flight test environments as well as providing reliable in-flight strain data from the FBG sensors over a long period of time.

Diagnostic methods and tools for condition-based maintenance of aircraft drives

The helicopter ground-airborne health and usage monitoring system (HUMS) presented in the paper illustrates the basic methods of determining the technical condition of aircraft drives by a set of signals received in operation. These algorithms can be realized using the kinematic scheme of a rotor unit with information about the number of teeth in gears, the number of splines in spline connections, the design parameters of the bearings as well as the presence of synchronization signals that are recorded in parallel with vibration signals. The presented methodology for the estimation of vibration parameters of multi-shaft units takes into account the fluctuation of specific frequencies in the real operating conditions of the gearbox. Hardware requirements are formed on the basis of vibration models of gears and gearboxes. The operating frequency envelope of vibration sensors is to include specific frequencies of all gears, spline connections and rolling bearings. The dynamic range is determined based on the vibration activity of the gearbox and units in the places where the sensors are installed. The requirements to the equipment of data accumulation and pretreatment are presented and validated. A method of balancing helicopter classical and coaxial rotors is presented. The method is based on the analysis of the effect of varying the values of the adjustment parameters of rotor blades (balance weight, assembly swash plate, tab angle) on the values of amplitudes of vibration harmonic components. The main goals of the support center concerning the technical condition of helicopter drives and its cooperation with the operator are stated.

The use of pseudo-inverse methods in reconstructing loads on a missile structure

A missile during air carriage is subjected to high vibratory forces. These forces consequently impose high levels of stress on the attachment points to the aircraft. A repetitive application of stress causes fatigue. However, since the vibratory forces cannot be measured directly at the interface, an inverse method utilising missile accelerometer data has been used to determine the forces. This paper presents two frequency domain techniques of reconstructing loads. Both techniques utilise the Moore-Penrose pseudo-inverse method, although the second procedure incorporating a normal modes analysis is perhaps better suited for embedding within a health and usage monitoring system (HUMS). Both techniques enable discrete dynamic loads, which are applied to a finite element model in the time domain, to be successfully reconstructed. Consequently, by identifying forces on a missile structure successfully, the presented techniques enable a better structural integrity assessment to be undertaken.

PCA algorithm for detection, localisation and evolution of damages in gearbox bearings

A fundamental aspect when dealing with rolling element bearings, which often represent a key component in rotating machineries, consists in correctly identifying a degraded behaviour of a bearing with a reasonable level of confidence. This is one of the main requirements a health and usage monitoring system (HUMS) should have. This paper introduces a monitoring technique for the diagnosis of bearing faults based on Principal Component Analysis (PCA). This method overcomes the problem of acquiring data under different environmental conditions (hardly biasing the data) and allows accurate damage recognition, also assuring a rather low number of False Alarms (FA). In addition, a novel criterion is proposed in order to isolate the area in which the faulty bearing stands. Another useful feature of this PCA-based method concerns the capability to observe an increasing trend in the evolution of bearing degradation. The described technique is tested on an industrial rig (designed by Avio S.p.A.), consisting of a full size aeroengine gearbox. Healthy and variously damaged bearings, such as with an inner or rolling element fault, are set up and vibration signals are collected and processed in order to properly detect a fault. Finally, data collected from a test rig assembled by the Dynamics & Identification Research Group (DIRG) are used to demonstrate that the proposed method is able to correctly detect and to classify different levels of the same type of fault and also to localise it.

Acceleration-Based Remaining Life Prognostics for Terrain-Loaded Components on an Army Ground Vehicle System

Use of a health and usage monitoring system (HUMS) is one method the Department of Defense is investigating to meet conflicting cost and performance goals for Army wheeled vehicles. One area where a HUMS would be of great benefit is monitoring critical components vulnerable to terrain-induced fatigue. While strain is typically the desired input to a fatigue model, acceleration sensors are less susceptible to damage from the military ground vehicle environment and provide more reliable data over long periods of usage. The feasibility of using vibratory inputs from an accelerometer to make component fatigue predictions for a military wheeled vehicle system is explored in this study, and the use of limited subsets of data for algorithm training are evaluated. An example component is used to demonstrate that the proposed HUMS algorithms are appropriate and provide suitably accurate fatigue predictions.

Multi-functional fibre Bragg grating sensors for fatigue crack detection in metallic structures

This paper investigates the use of multi-functional fibre Bragg grating (FBG) sensors for structural health and usage monitoring. It is shown how FBG sensors can be used simultaneously for both a strain-sensing-based load-monitoring system and a Lamb-wave-based damage-detection system. Structural health and usage monitoring has gained considerable interest in engineering technologies. Especially for the aircraft industry where damage can lead to catastrophic and expensive failures and the vehicles involved undergo regular cost intensive inspections, a health and usage monitoring system (HUMS) has one of the highest payoffs. Although different approaches for an HUMS can be found in the literature, a system based on the fusion of load monitoring and damage detection could provide highest potential for implementation in future aircrafts. For this paper, initial tests have been carried out to demonstrate the dual load and damage monitoring on a simple aluminium plate. A fatigue test was carried out to study the crack propagation of the plate. FBG sensors were used to record the load history of the test. For the fatigue analysis, the crack growth was observed using a conventional method and the Lamb-wave analysis. Piezoceramic transducers and the same FBG sensors that already monitored the load history were applied to record the Lamb-wave signals. A novel damage index that correlates the sensor signals with the crack length is introduced. Subsequently, the results obtained for both transducers are given and their performance is compared. Final remarks on this initial test of a dual load and damage-monitoring system based on FBG sensors conclude the paper.

Flight deck indication of health monitoring data—a critique

In September 1995 there was an incident involving an AS332L Super Puma helicopter over the North Sea. This followed the onset of high vibration due to the fatigue failure of a tail rotor blade retaining hinge. This was the first major vibration incident involving a helicopter fitted with a health and usage monitoring system (HUMS). The UK Air Accidents Investigation Branch made a number of recommendations. One was that the UK Civil Aviation Authority (CAA) should develop the concept of providing a flight deck display of health monitoring information to the flight crew. The CAA asked the Helicopter Health Monitoring Advisory G roup (HHM AG) (an industry body that advises the CAA) to consider the issue. This paper will examine the findings of the H HMAG working group and discuss the practicality of such systems in an operational environment.