Engine Health Monitoring Research Articles

An Optical Fiber Measurement System for Blade Tip Clearance of Engine

The benefits of reducing the tip clearance have been receiving many scholars’ attention all the time, which bring turbine efficiency increasing, emissions reduction, payloads increasing, and mission range abilities extension. In order to gain the blade tip clearance dynamically, a prototype optical fiber measurement system was built and tested based on the rotor test rig. The optical fiber tip clearance measurement system consists of the reflective intensity-modulated optical fiber bundle (sensor), main signal processing unit, high-speed data acquisition card, and a computer. The static performance and dynamic performance experiments were conducted to verify the performance of the system we designed. In addition, the results show that the accuracy of the system is 25 μm or better; the stability of the measurement system was evaluated in room temperature. The clearance measurement range is about 5 mm, and sensitivity of the sensor is 0.0733/mm. Furthermore, the typical tip clearance dynamic measurement experiment results show that the system has good dynamic response characteristics as well. The system will provide a new tool for engine health monitoring or fast active tip clearance control.

Conceptual Study on Integration of Engine Health Monitoring (EHM) System with Integrated Vehicle Health Monitoring (IVHM) System

AbstractAn approach to upgrade existing control system and lean architecture principle is presented to optimize the system along with reduction of weight by understanding the physical system design, Engine Health Monitoring (EHM) system and data study from Integrated Vehicle Health Monitoring (IVHM) system (Aaseng n.d.). This paper brings out the integration of EHM sufficiency with IVHM system. Research effort to describe the hardware, software, algorithms and engine parameters required to monitor various events capturing, health and life management issues with IVHM. Here basic functionality will be performance monitoring, vibration monitoring, event monitoring (including stall, surge, over speed, flameout, over temperature, oil parameter and life monitoring) anti ice system with IVHM requirement of mission completion, safety and data protection.A systematic SE approach and methodology with need and requirement is generated using DOORS software (INCOSE 2011). Full requirement capture with engine designer and aircraft designer (Harinarayana, Developing light combat aircraft: foresight as the guiding principle 2004) for integrating with IVHM (Philip A. Scandura October 30, 2005)has been studied and brought out to model the concept using Rhapsody software. Here various operational scenarios has been attempted to make the functional model. Functional model has been tested for various operational issues and a final configuration has been proposed to the designer (Jaw, Van and Mink 7 – 10 May 2007). This study has brought out a perspective work model for a designer and as a result of this the final product will be tested for integrating the EHM with IVHM

Improved Engine Health Monitoring Using Full Flight Data and Companion Engine Information

Improved Engine Health Monitoring Using Full Flight Data and Companion Engine Information

An improved extended Kalman filter with inequality constraints for gas turbine engine health monitoring

Various Kalman filter approaches have been proposed for the state estimation of gas turbine engines, among which Linear Kalman Filter (LKF) is the most common one. Kalman filters achieve state estimation provided that there are more available measurement sensors than state parameters to be estimated. However, it is hard to hold this assumption in gas turbine engine health monitoring applications, and an underdetermined estimation problem rises up.The aim of this contribution is to present a nonlinear underdetermined state estimation method on the basis of Extended Kalman Filter (EKF); and to evaluate the performance of this methodology, the comparisons of three nonlinear estimators, i.e. basic EKF, underdetermined EKF and resultant EKF are conducted to gas turbine engine health state estimation. The underdetermined EKF is developed from the previous linear achievements using the transformation matrix, and it produces the least estimation errors in the nonlinear framework. Moreover, the prior state information represented by inequality constraints is introduced to create the resultant EKF, and the estimates of state variables are tuned to truncated Probability Density Function (PDF). Results from the application to a turbojet engine health monitoring in the flight envelope show that the proposed methodology yields a significant improvement in terms of underdetermined estimation accuracy and robustness.

A High Temperature Frequency Signal Conditioning Unit for Aeronautical Rotating Systems

This paper covers the development and testing of a high temperature signal conditioning unit capable of sensing wide dynamic range signals from rotating sensors. The unit includes a current peak detector block, a digital pulse generator, ESD (electrostatic discharge) protection and generates an output current proportional to the peak value of the applied input signal. The digital data from the unit can be directly utilized by the FADEC (Full Authority Digital Electronic Control) system or the EHMS (Engine Health Monitoring System) on an aeroengine. The mixed signal unit presented in this paper was designed and fabricated on 1 $\mu\text{m}$ silicon-on-insulator (SOI) CMOS (complementary metal oxide semiconductor) technology and has been shown to function up to 235 $^{\circ}$ Celsius with very high linearity of the output signal. This is the highest operating temperature of an integrated signal conditioning unit developed for a civil aircraft. The mixed signal unit was mounted on a high temperature hybrid module and helps reducing the weight of the aeroengine by several kilograms.

Guest editorial: special issue on predictive analytics using machine learning

Predictive analytics is concerned with the prediction of future trends and outcomes. The approaches used to conduct predictive analytics can be classified into machine learning techniques and regression techniques. Machine learning techniques have become increasingly popular in conducting predictive analytics due to their outstanding performance in handling large-scale datasets with uniform characteristics and noisy data. Innovative predictive models have been applied successfully in several domains such as health care, cyber security, education, credit card fraud detection, social media, cloud computing, software measurement, quality and defect prediction, cost and effort estimation and software reuse. The main focus of this special issue is on the current state of practice of machine learning techniques to address various predictive problems. A total of 14 papers are included in this special issue. A summary of the papers appears below. In ‘‘Dynamic neural networks for gas turbine engine degradation prediction, health monitoring and prognosis’’ by Kiakojoori and Khorasani, the problem of health monitoring and prognosis of aircraft gas turbine engines using intelligent-based methodologies are investigated to support enhancement of flight safety and performance. Two different neural network-based architectures, namely the nonlinear autoregressive neural network with exogenous input (NARX) and the Elman neural network, are proposed and developed for predicting the health condition of the engine. Various degradations may occur in a given engine resulting in changes in the performance of its components. Two main degradation factors, namely the compressor fouling and the turbine erosion, are modeled and considered in this work. The proposed dynamic neural networks are first developed and applied to capture the degradation dynamics in the aircraft jet engine. The health condition of the engine is then predicted subject to occurrence of these deteriorations. Multiple scenarios are considered and extensive simulations are conducted corresponding to both dynamic neural network approaches. For each degradation scenario, several neural networks are trained and their performance in predicting the turbine exhaust temperature for multi-flights ahead is evaluated. The most suitable neural network for this prediction is then selected by using a normalized Bayesian information criterion model selection. Simulation results presented demonstrate and illustrate the effective performance of the proposed dynamic neural network-based prediction and prognosis strategies. In ‘‘A hybrid grid-GA-based LSSVR learning paradigm for crude oil price forecasting’’, Yu et al. propose a hybrid learning paradigm integrating least squares support vector regression (LSSVR) with a hybrid optimization searching approach for the parameters selection in the LSSVR in order to effectively model crude oil spot price with inherently high complexity. The grid method is first applied to determine the proper boundaries of the parameters in the LSSVR. Then, the genetic algorithm is implemented to & Ali Bou Nassif anassif@sharjah.ac.ae

Vibration-based detection of axial-flow compressor unstable operation

Computer-aided and experimental research of a axial stage stability loss is presented. Informative criteria of the pre-surge compressor state is formulated. It is proved that the harmonic of a rotating stall is unstable, standing out sharply against noise; thus it can serve as a rotating stall indicator and a surge precursor. It was proved that vibration from the mounted on casing sensor can be applicable for rotating stall detection. An algorithm is proposed that detects the compressor pre-surge state by vibrations of the compressor casing. The algorithm is easy to be implemented in engine control and health monitoring systems

Inductive sensors for blade tip-timing in gas turbines

Abstract The paper reviews features and applications of the upgraded inductive sensor for BTT, which is able to operate in contact with exhaust gases of temperature even as high as 1200 K. The new design includes metal-ceramic housing ensuring proper heat transfer, magnetic circuit containing set of permanent magnets with various magnetic field values and Curie temperatures, completely redesigned windings and current/voltage converter used instead of an electromotive force amplifier. Its principle of operation is based on electro-dynamical interaction and therefore it may be referred as a passive eddy-current sensor. The sensor technique has been demonstrated on four stages of a surplus military turbofan including the high pressure turbine as part of the engine health monitoring system. We present signal samples and review methods used for online processing of time-of-arrival signals when only a limited number of sensors is available.

Fault detection and isolation of gas turbine engines using a bank of neural networks

The main goal of this paper is to design and develop a fault detection and isolation (FDI) scheme for aircraft gas turbine engines by using neural networks. Towards this end, first for the fault detection task two types of dynamic neural networks are used and compared to learn the engine dynamics. Specially, the dynamic neural model (DNM) and the time delay neural network (TDNN) are utilized. For both architectures a bank of neural networks is trained separately to capture the dynamic relationships among the engine measurable variables. The results show that certain engine parameters have better detection capabilities as compared to the others. Finally, the fault isolation task is accomplished by using a multilayer perception (MLP) network functioning as a pattern classifier applied to the residual signals that are generated by the two dynamic neural networks used for the purpose of the fault detection task. The simulation results do indeed substantiate and verify that our proposed FDI scheme represents a promising tool for aircraft engine diagnostics and health monitoring.

Early Detection of Combustion Instability from Hi-speed Flame Images via Deep Learning and Symbolic Time Series Analysis


 
 
 Combustion instability, characterized by self-sustained, large-amplitude pressure oscillations and periodic shedding of coherent vortex structures at varied spatial scales, has many detrimental effects on flight-propulsion dynamics and structural integrity of gas turbine engines. Hence, its early detection is one of the important tasks in engine health monitoring and prognostics. This paper proposes a dynamic data-driven approach, where a large volume of sequential hi-speed (greyscale) images is used to analyze the temporal evolution of coherent structures in combustion chamber for early detection of combustion instability at various operating conditions. The proposed hierarchical approach involves extracting low-dimensional semantic features from images using Deep Neural Networks followed by capturing the temporal evolution of the extracted features using Symbolic Time Series Analysis (STSA). Extensive experimental data have been collected in a swirl-stabilized dump combustor at various operating conditions for validation of the proposed approach. Intermediate layer visualization of deep learning reveals that meaningful shape-features from the flame images are extracted, which enables the temporal modeling layer to enhance the class separability between stable and unstable regions. At the same time, the semantic nature of intermediate features enables expert-guided data exploration that can lead to better understanding of the underlying physics. To the best of the authors knowledge, this paper presents one of the early applications of the recently reported Deep Learning tools in the area of prognostics and health management (PHM).
 
 

Dynamic neural networks for gas turbine engine degradation prediction, health monitoring and prognosis

In this paper, the problem of health monitoring and prognosis of aircraft gas turbine engines is considered by using computationally intelligent methodologies. Two different dynamic neural networks, namely the nonlinear autoregressive with exogenous input neural networks and the Elman neural networks, are developed and designed for this purpose. The proposed dynamic neural networks are designed to capture the dynamics of two main degradations in the gas turbine engine, namely the compressor fouling and the turbine erosion. The health status and condition of the engine in terms of the turbine output temperature (TT) are then predicted subject to occurrence of these deteriorations. Various scenarios consisting of fouling and erosion separately as well as combined are considered. For each scenario, several neural networks are trained and their performance in predicting multiple flights ahead TTs is evaluated. Finally, the most suitable neural networks for achieving the best prediction are selected by using the normalized Bayesian information criterion model selection. Simulation results presented demonstrate and illustrate the effective performance of our proposed neural network-based prediction and prognosis strategies.

Sequential pattern mining applied to aeroengine condition monitoring with uncertain health data

Numerical algorithms that can assess Engine Health Monitoring (EHM) data in aeroengines are influenced by the high level of uncertainty inherent to gas path measurements and engine-to-engine variability. Among them, fuzzy rule-based techniques have been successfully used due to their robustness towards noisy signals and their capability to learn human-readable rules from data. These techniques are useful in detecting the presence of certain types of abnormal events or general engine deterioration, through the identification of specific combinations of EHM signals associated with these specific cases. However, there are also other types of engine events that manifest themselves as an ordered sequence of otherwise normal combinations of the EHM signals. These combinations are dismissed when considered in isolation as the current existing techniques cannot assess them. In this paper it is proposed to use sequence mining techniques in order to obtain fuzzy rules from uncertain EHM data which can in turn be used to identify the cases where an engine event is determined as a sequence of otherwise normal combinations of EHM signals. The results are subsequently tested on a representative sample of aeroengine data.

Smart, In Situ, Wide Range Pressure Sensor for Advanced Engine Controls

Air Force Research Laboratory (AFRL) is pursuing development of advanced, distributed, intelligent, adaptive engine controls and engine health monitoring systems. The goals this pursuit are enhancing engine performance, safety, affordability, operability, and reliability while reducing obsolescence risk. The development of smart, high-bandwidth, high-temperature-operable, wide-range, pressure/temperature multi-sensors, which addresses these goals, is discussed. The resulting sensors and packaging can be manufactured at low cost and operate in corrosive environments, while measuring temperatures up to 2,552 °F (1,400 °C) with simultaneous pressure measurements up to 1,000 psi (68 atm). Such a sensor suite provides unprecedented monitoring of propulsion, energy generation, and industrial systems. The multi-sensor approach reduces control system weight and wiring complexity, design time, and cost, while increasing accuracy and fault tolerance. In situ pressure sensors reduce size and weight while eliminating failures associated with hypo-tube fouling. High-bandwidth sensors support advanced compressor and combustor control schemes that facilitate higher thrust, reduced fuel consumption and reduced emissions. Smart sensors are a key enabling technology for distributed engine control which is an important architectural paradigm shift to achieve increased flexibility, scalability, fault tolerance and performance while reducing weight, lifecycle costs and obsolescence risk. Current efforts include combining the sensor technology with other high-temperature electronics to produce smart sensors for distributed engine controls, capacitive transducer elements with increased dynamic bandwidth, and advanced high-temperature sensor packaging technologies. Test results demonstrating technology readiness level (TRL) 6 are reported herein.

Review on Advanced Health Monitoring Methods for Aero Gas Turbines using Model Based Methods and Artificial Intelligent Methods

The aviation gas turbine is composed of many expensive and highly precise parts and operated in high pressure and temperature gas. When breakdown or performance deterioration occurs due to the hostile environment and component degradation, it severely influences the aircraft operation. Recently to minimize this problem the third generation of predictive maintenance known as condition based maintenance has been developed. This method not only monitors the engine condition and diagnoses the engine faults but also gives proper maintenance advice. Therefore it can maximize the availability and minimize the maintenance cost. The advanced gas turbine health monitoring method is classified into model based diagnosis (such as observers, parity equations, parameter estimation and Gas Path Analysis (GPA)) and soft computing diagnosis (such as expert system, fuzzy logic, Neural Networks (NNs) and Genetic Algorithms (GA)). The overview shows an introduction, advantages, and disadvantages of each advanced engine health monitoring method. In addition, some practical gas turbine health monitoring application examples using the GPA methods and the artificial intelligent methods including fuzzy logic, NNs and GA developed by the author are presented.

Multiple-Model Sensor and Components Fault Diagnosis in Gas Turbine Engines Using Autoassociative Neural Networks

In this paper the problem of fault diagnosis in an aircraft jet engine is investigated by using an intelligent-based methodology. The proposed fault detection and isolation (FDI) scheme is based on the multiple model approach and utilizes autoassociative neural networks (AANNs). This methodology consists of a bank of AANNs and provides a novel integrated solution to the problem of both sensor and component fault detection and isolation even though possibly both engine and sensor faults may occur concurrently. Moreover, the proposed algorithm can be used for sensor data validation and correction as the first step for health monitoring of jet engines. We have also presented a comparison between our proposed approach and another commonly used neural network scheme known as dynamic neural networks to demonstrate the advantages and capabilities of our approach. Various simulations are carried out to demonstrate the performance capabilities of our proposed fault detection and isolation scheme.

Design and Assembly of High Temperature Distributed Aero-engine Control System Demonstrator

This paper covers the development of a distributed high temperature electronics demonstrator for integration with sensor elements to provide digital outputs that can be used by the FADEC (Full Authority Digital Electronic Control) system or the EHMS (Engine Health Monitoring System) on an aircraft engine. This distributed electronics demonstrator eliminates the need for the FADEC or EHMS to process the sensor signal, which will assist in making the overall system more accurate and efficient in processing only digital signals. This will offer weight savings in cables, harnesses and connector pin reduction. The design concept was to take the output from several on-engine sensors, carry out the signal conditioning, multiplexing, analogue to digital conversion and data transmission through a serial data bus. The unit has to meet the environmental requirements of DO-160 with the need to operate at 200°C, with short term operation at temperatures up to 250°C. The work undertaken has been to design an ASIC based on 1.0μm Silicon on Insulator (SOI) device technology incorporating sensor signal conditioning electronics for sensors including resistance temperature probes, strain gauges, thermocouples, torque and frequency inputs. The ASIC contains analogue multiplexers, temperature stable voltage band-gap reference and bias circuits, ADC, BIST, core logic, DIN inputs and two parallel ARINC 429 serial databuses. The ASIC was tested and showed to be functional up to a maximum temperature of 275°C. The ASIC has been integrated with other high temperature components including voltage regulators, a crystal oscillator, precision resistors, silicon capacitors within a hermetic hybrid package. The hybrid circuit has been assembled within a stainless steel enclosure with high temperature connectors. The high temperature electronics demonstrator has been shown to operate from −40°C to +250°C. This work has been carried out under the EU Clean Sky HIGHTECS project with the Project being led by Turbomeca (Fr) and carried out by GE Aviation Systems (UK), GE Research – Munich (D) and Oxford University (UK).

Trends in Automotive Packaging

The long-term trend in automobiles has been increasing electronics content over time. This trend is expected to continue and drives diverse functional, form factor, and reliability requirements. These requirements, in turn, are leading to changes in the package types selected and the performance specifications of the packages used for automotive electronics. Several examples will be given. This abstract covers the development of a distributed high temperature electronics demonstrator for integration with sensor elements to provide digital outputs that can be used by the FADEC (Full Authority Digital Electronic Control) system or the EHMS (Engine Health Monitoring System) on an aircraft engine. This distributed electronics demonstrator eliminates the need for the FADEC or EHMS to process the sensor signal, which will assist in making the overall system more accurate and efficient in processing only digital signals. This will offer weight savings in cables, harnesses and connector pin reduction. The design concept was to take the output from several on-engine sensors, carry out the signal conditioning, multiplexing, analogue to digital conversion and data transmission through a serial data bus. The unit has to meet the environmental requirements of DO-160 with the need to operate at 200°C, with short term operation at temperatures up to 250°C. The work undertaken has been to design an ASIC based on 1.0 μm Silicon on Insulator (SOI) device technology incorporating sensor signal conditioning electronics for sensors including resistance temperature probes, strain gauges, thermocouples, torque and frequency inputs. The ASIC contains analogue multiplexers, temperature stable voltage band-gap reference and bias circuits, ADC, BIST, core logic, DIN inputs and two parallel ARINC 429 serial databuses. The ASIC was tested and showed to be functional up to a maximum temperature of 275°C. The ASIC has been integrated with other high temperature components including voltage regulators, a crystal oscillator, precision resistors, silicon capacitors within a hermetic hybrid package. The hybrid circuit has been assembled within a stainless steel enclosure with high temperature connectors. The high temperature electronics demonstrator has been demonstrated operating from −40°C to +250°C. This work has been carried out under the EU Clean Sky HIGHTECS project with the Project being led by Turbomeca (Fr) and carried out by GE Aviation Systems (UK), GE Research – Munich (D) and Oxford University (UK).

An integrated framework for online diagnostic and prognostic health monitoring using a multistate deterioration process

Efficient asset management is of paramount importance, particularly for systems with costly downtime and failure. As in energy and capital-intensive industries, the economic loss of downtime and failure is huge, the need for a low-cost and integrated health monitoring system has increased significantly over the years. Timely detection of faults and failures through an efficient prognostics and health management (PHM) framework can lead to appropriate maintenance actions to be scheduled proactively to avoid catastrophic failures and minimize the overall maintenance cost of the systems. This paper aims at practical challenges of online diagnostics and prognostics of mechanical systems under unobservable degradation. First, the elements of a multistate degradation structure are reviewed and then a model selection framework is introduced. Important dynamic performance measures are introduced, which can be used for online diagnostics and prognostics. The effectiveness of the result of this paper is demonstrated with a case study on the health monitoring of turbofan engines.

Blade Tip Clearance Sensors for Use in Engine Health Monitoring Applications

Blade Tip Clearance Sensors for Use in Engine Health Monitoring Applications

Active Condition Monitoring of a Marine Gas Turbine through Rotor Shaft Vibration Analysis

While preventive and predictive maintenance have played their part in engine health monitoring, the problem of downtime maintenance has truly reached a serious level. Also, most companies have found out that their maintenance costs can be cut drastically by establishing a proactive line of defence. Most imminent faults in gas turbines often result from the vibration of the rotor shaft of the engine. Some of these faults that could lead to catastrophy include misalignment, imbalance, cracks and eccentricity. These defects are equally likely to lead to unscheduled downtime resulting to large economic losses. It is on this backdrop that the rotor shaft of a marine gas turbine system was isolated and used for condition monitoring to enunciate methods to reduce downtime. The need to study vibration which is one of the biggest threats to rotating equipment has become much required now than ever before. This project thus presents a case to monitor the condition of the gas turbine through its thermodynamic and rotor shaft vibration analyses. Selected measurements from an industrial gas turbine to detect changes in operating conditions of the plant were of immense help in setting the proactive measures for the plant. Simulation and analysis were achieved using high level java computer programming language and data collected from a gas turbine plant. The work shows that vibration reduces the active load of the engine. Thus, proactive maintenance monitoring programs should be employed in gas turbine usage to avoid the effects of vibration.