Fusion and decision making techniques for structural prognostic health management

Azzam, H.; Beaven, F.; Hebden, T.; Gill, Laurence; Wallace, Manolis

doi:10.1109/aero.2005.1559683

Cited by 8 publications

(10 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All these potential sources of error should be understood and taken account of in the design and in the formulation of design accuracy requirements; there is no mileage in setting unachievable accuracy requirements. Azzam (8,9) refers to this process as establishing 'truth margins'.…”

Section: Feature Extraction Methodsmentioning

confidence: 97%

“…Reed and Cole (17) and Reed (18) reported the development of an ANN-based parametric fatigue monitor for the wing and tailplane of a military trainer aircraft. With the exception of the work reported by Azzam and his associates (8,9,10) and Reed and Cole (17,18) the majority of the methods used were developed to predict discrete loading actions or manoeuvres rather than to predict the usage of the aircraft throughout its operational envelope.Within the following sections, the architecture of the ANN core of the structural health and usage neural network (SHAUNN) is explained. Thereafter, a generic process for developing a SHAUNN system is outlined.…”

mentioning

confidence: 99%

“…Azzam et al (8,9) described the use of a mathematical network to predict loads. Azzam et al (9) and Wallace et al (10) described co-operative work programmes involving Smiths Aerospace, the UK Ministry of Defence and BAE Systems and reported, among other successes, excellent correlation between measured and predicted strains at a number of structural locations for the Tornado combat aircraft, over a large number of test flights. Azzam (8) also described the development of methods to predict damage in helicopter components and the prediction of high frequency events, such as buffet loading on the fin of a fixed-wing aircraft.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Development of a parametric-based indirect aircraft structural usage monitoring system using artificial neural networks

Reed¹

2007

Aeronaut. j.

View full text Add to dashboard Cite

development of cost-effective indirect monitoring system because many of the relationships between parameters and strains are often non-linear and difficult to identify with more traditional regression techniques.Researchers in the aeronautical arena have published work using ANNs and similar mathematical techniques to identify loading actions, or to supplement sparse flight test data. Azzam et al (8,9) described the use of a mathematical network to predict loads. Azzam et al (9) and Wallace et al (10) described co-operative work programmes involving Smiths Aerospace, the UK Ministry of Defence and BAE Systems and reported, among other successes, excellent correlation between measured and predicted strains at a number of structural locations for the Tornado combat aircraft, over a large number of test flights. Azzam (8) also described the development of methods to predict damage in helicopter components and the prediction of high frequency events, such as buffet loading on the fin of a fixed-wing aircraft. Jacobs and Perez (11) used a hybrid cascade ANN to augment sparse buffet data by predicting the power spectral densities of surface pressures on a fighter aircraft vertical tail, from parametric data. Kim and Marciniak (12) reported the use of a back-propagation ANN to predict strains in the empennage of a Cessna 172P general aviation aircraft during discrete manoeuvres. Hill et al (13) described the use of a back-propagation ANN to synthesise strain and fatigue damage in several Lynx helicopter components. Furthermore, Manry and co-authors (14) applied ANNs to flight load synthesis, using Bell helicopter data. Levinski (15) used ANN technology to synthesise loads on the vertical tail of a F/A-18 aircraft, using wind tunnel pressure data. Wang (16) used a recurrent ANN to predict loads during discrete manoeuvres for a fighter aircraft. Reed and Cole (17) and Reed (18) reported the development of an ANN-based parametric fatigue monitor for the wing and tailplane of a military trainer aircraft. With the exception of the work reported by Azzam and his associates (8,9,10) and Reed and Cole (17,18) the majority of the methods used were developed to predict discrete loading actions or manoeuvres rather than to predict the usage of the aircraft throughout its operational envelope.Within the following sections, the architecture of the ANN core of the structural health and usage neural network (SHAUNN) is explained. Thereafter, a generic process for developing a SHAUNN system is outlined. Also, results from case-study demonstrator programmes are reported. Finally, conclusions are drawn and recommendations for further work are made. It is noteworthy that software development methods and practices are not discussed within this paper; a range of comprehensive standards and guidance, appropriate to the safety criticality of the software, already exists and is familiar to software developers.

show abstract

Section: Feature Extraction Methodsmentioning

confidence: 97%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Development of a parametric-based indirect aircraft structural usage monitoring system using artificial neural networks

Reed¹

2007

Aeronaut. j.

View full text Add to dashboard Cite

show abstract

“…In order to address these objectives, legacy data were used to configure, optimise and test a suite of FUMS TM tools [5] to [9]. The Smiths FUMS TM tools included data quality algorithms, MNs that fuse flight data into prognostic information, dynamic event models, UIs, signal processing tools, AI tools and force life management software that have enabled an efficient application of these tools on large datasets.…”

Section: The Fums Tm Olm Techniquesmentioning

confidence: 99%

“…At this stage, the preliminary collaborative work concentrated on the following: investigation of existing AE signal processing and feature extraction techniques; investigation of the effect of AE sensor locations on noise to signal ratio; investigation of methods to characterise damages from extracted AE features; and investigation of methods to derive invariant AE features. The results of the preliminary collaborative work indicated the feasibility of developing automatic AI processes that could address the challenges facing AE technologies [4] and [5].…”

Section: Damage Detectionmentioning

confidence: 99%

FUMS Technologies for Advanced Structural PHM

Azzam

Beaven

Smith

et al. 2007

2007 IEEE Aerospace Conference

View full text Add to dashboard Cite

Over the past seven years, Smiths and BAE SYSTEMS have launched collaborative work to evolve a certifiable practical Structural Prognostic Health Management (SPHM) system. The collaborative work has built on BAE SYSTEMS' vast advanced technology experience and on Smiths' unique experience that has produced intelligent Fleet and Usage Management Software (FUMS TM ) including fusion, prognostic and decision support algorithms combining model-based and Artificial Intelligence (AI) techniques. This paper describes the recent advances and optimisation of the Smiths algorithms for damage detection and Operational Load Monitoring (OLM). A combination of FUMS TM signal processing and AI techniques have been applied to acoustic emission sensor data to locate and classify damage of different types in composite and metallic structures. The FUMS TM damage detection software has been embedded in real-time hardware to support ground tests. Techniques have been implemented to enable adequate calibration of OLM algorithms using data from flight tests. The techniques should address concerns raised about the accuracy of algorithms trained to synthesise strains throughout the entire flight envelope from data recorded close to the edge of the flight envelope. Working with the UK MOD, Smiths has continued the evaluation of FUMS TM software that allows aircraft design authorities and military operators to build their force life management applications without the need for software rewriting. 1,2

show abstract

Artificial Neural Networks

Reed

2008

Encyclopedia of Structural Health Monitoring

View full text Add to dashboard Cite

Artificial neural networks (ANNs) are able to learn from experience, generalize from examples, and identify underlying information from within noisy data. These characteristics, and the explosion in ANN techniques over the past 15 or 20 years, have led to an ever‐increasing role for ANNs within structural health monitoring (SHM) systems. Within this article, the development of ANNs and the basic principles behind their functionality, training, and deployment are described. Emphasis is placed upon the multilayer perceptron (MLP), as the workhorse of ANN methods; however, other techniques, including radial basis functions (RBF) and self‐organizing feature maps (SOFMs), are also detailed. Examples of the use of ANNs within SHM systems are presented and reference has been made to a wide range of texts throughout this article.

show abstract

Fusion and decision making techniques for structural prognostic health management

Cited by 8 publications

References 2 publications

Development of a parametric-based indirect aircraft structural usage monitoring system using artificial neural networks

Development of a parametric-based indirect aircraft structural usage monitoring system using artificial neural networks

FUMS Technologies for Advanced Structural PHM

Artificial Neural Networks

Contact Info

Product

Resources

About