In-Flight Actuator Failure Detection and Identification for a Reduced Size UAV Using the Artificial Immune System Approach

Sanchez, Sebastian P.; Perhinschi, Mario G.; Moncayo, Hever; Napolitano, Marcello R.; Davis, Jennifer; Fravolini, Mario Luca

doi:10.2514/6.2009-6266

Cited by 14 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the analysis presented in this paper is based on data generated from flight simulation tests. However, the authors have performed preliminary tests of a similar FDI scheme using actual flight data from a reduced-size unmanned aeroplane (37) , which confirmed the promising capabilities of the proposed approach. The on-line computational effort is reduced allowing for real-time operation without special algorithms or equipment.…”

Section: Identification Performance Of the Hms Strategymentioning

confidence: 69%

Aircraft failure detection and identification over an extended flight envelope using an artificial immune system

Moncayo¹,

Perhinschi²,

Davis

2011

Aeronaut. j.

View full text Add to dashboard Cite

USÂˆˆˆˆ particular, the multi-dimensionality of the parameter space associated with the dynamic response of the aircraft at abnormal conditions exposes the FDI process to specific issues with potential negative impact. Recently, a new concept inspired from the biological immune system was proposed for aerospace systems FDI (19,20) . The Artificial Immune System (AIS)-based fault detection operates in a similar manner to its biological counterpart -according to the principle of self/non-self discrimination -when it distinguishes between entities that belong to the organism (self) and entities that do not (non-self). All appropriate parameters must be identified that are capable of capturing the dynamic signatures of each type of failure considered. Therefore, these parameters characterise/define the 'self' -or normal conditionsand, for that matter, the non-self -or the abnormal conditions. The concept of immunity-based fault detection originates from the idea that an abnormal situation can be declared when a current configuration of 'features' or 'identifiers' matches with a configuration from a pre-determined set -detectors -known NOT to correspond to a normal situation.An integrated set of methodologies for AIS-based detection, identification, and evaluation of a wide variety of aircraft sensor, actuator, propulsion, and structural failures/damages has been developed (21) at West Virginia University (WVU) within NASA's Aviation Safety Program. As part of this effort, the development of an integrated high-performance AIS-based FDI scheme using a hierarchical multi-self strategy is presented in this paper. The scheme is capable of detecting and identifying several categories of sub-system abnormal conditions over an extended area of the flight envelope. The effectiveness of the approach in terms of high detection rate and low number of false alarms for the four categories of failures is tested using data from the WVU motionbased flight simulator. The aircraft model represents a supersonic fighter including model-following direct adaptive control laws based on non-linear dynamic inversion and artificial neural network augmentation (22) .A brief review of the AIS paradigm and its application is presented in Section II. The general framework for the development and testing of the AIS-based FDI scheme is discussed in Section III including aircraft sub-system failure modelling, adaptive control laws, and motion-based flight simulator tests for self definition and performance evaluation. The design of the AIS, including data processing and detector generation and optimisation, is described in Section IV. The design process of the proposed AIS-based FDI scheme is outlined in Section V. Test results, analysis, and evaluation of the FDI scheme performance are presented in Section VI. Finally, some conclusions are summarised in Section VII followed by acknowledgements and a bibliographical list.

show abstract

Section: Identification Performance Of the Hms Strategymentioning

confidence: 69%

Aircraft failure detection and identification over an extended flight envelope using an artificial immune system

Moncayo¹,

Perhinschi²,

Davis

2011

Aeronaut. j.

View full text Add to dashboard Cite

show abstract

“…However, as a new computational paradigm on its own right, the AIS emerged in the mid-1990s. The concept has proven itself as an inviting ground for research in various applications such as anomaly or breakage detection [53][54][55][56], data mining [54,57], computer safety [47,[58][59][60][61][62], pattern recognition [63,64], and adaptive control [24,51,65].…”

Section: Immunity-based Systemsmentioning

confidence: 99%

Immunity-based accommodation of aircraft subsystem failures

Togayev¹

2017

AEAT

Self Cite

View full text Add to dashboard Cite

Immunity-Based Accommodation of Aircraft Subsystem Failures This thesis presents the design, development, and flight-simulation testing of an artificial immune system (AIS) based approach for accommodation of different aircraft subsystem failures. Failure accommodation is considered as part of a complex integrated AIS scheme that contains four major components: failure detection, identification, evaluation, and accommodation. The accommodation part consists of providing compensatory commands to the aircraft under specific abnormal conditions based on previous experience. In this research effort, the possibility of building an AIS allowing the extraction of pilot commands is investigated. The proposed approach is based on structuring the self (nominal conditions) and the non-self (abnormal conditions) within the AIS paradigm, as sets of artificial memory cells (mimicking behavior of T-cells, B-cells, and antibodies) consisting of measurement strings, over pre-defined time windows. Each string is a set of features values at each sample time of the flight including pilot inputs, system states, and other variables. The accommodation algorithm relies on identifying the memory cell that is the most similar to the incoming measurements. Once the best match is found, control commands corresponding to this match will be extracted from the memory and used for control purposes. The proposed methodology is illustrated through simulation of simple maneuvers at nominal flight conditions, different actuators, and sensor failure conditions. Data for development and demonstration have been collected from West Virginia University 6-degreesof-freedom motion-based flight simulator. The aircraft model used for this research represents a supersonic fighter which includes model following adaptive control laws based on non-linear dynamic inversion and artificial neural network augmentation. The simulation results demonstrate the possibility of extracting pilot compensatory commands from the self/non-self structure and the capability of the AIS paradigm to address the problem of accommodating actuator and sensor malfunctions as a part of a comprehensive and integrated framework along with abnormal condition detection, identification, and evaluation. DEDICATION To my mother Gulnara Yezhebayeva and my grandparents,

show abstract

“…In addition, the AIS concept has shown a promising application for fault detection of aerospace systems [30,34,35]. These efforts have been focused primarily on aircraft systems fault detection and identification; however, they only have considered single classes and high magnitudes of failure for limited regions of the flight envelope.…”

Section: Introductionmentioning

confidence: 99%

Comparison of immunity-based schemes for aircraft failure detection and identification

Azzawi

Moncayo

Perhinschi

et al. 2016

Engineering Applications of Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

In this paper, two approaches are proposed and compared for the detection and identification of aircraft subsystem failures based on the artificial immune system paradigm combined with the hierarchical multiself strategy. The first approach relies on the heuristic ranking of lower order self/non-self projections and the generation of selective immunity identifiers through structuring of the non-self. The second approach is based on an information processing algorithm inspired by the functionality of the dendritic cells. The artificial dendritic cell is defined as a computational unit that centralizes, fuses, and interprets information from the multiple selves to produce a unique detection and identification outcome. A hierarchical multi-self strategy is used with both approaches considering 2-dimensional self/non-self projections or subselves. A mathematical formulation of the concepts and detailed implementation algorithms are presented. The proposed methodologies are demonstrated and compared using simulation data for a supersonic fighter from a motion-based flight simulator at nominal conditions, under failures of actuators, malfunction of sensors, and wing damage. In all cases considered, both detection and identification schemes achieve excellent detection and identification rates with practically no false alarms.

show abstract

In-Flight Actuator Failure Detection and Identification for a Reduced Size UAV Using the Artificial Immune System Approach

Cited by 14 publications

References 9 publications

Aircraft failure detection and identification over an extended flight envelope using an artificial immune system

Aircraft failure detection and identification over an extended flight envelope using an artificial immune system

Immunity-based accommodation of aircraft subsystem failures

Comparison of immunity-based schemes for aircraft failure detection and identification

Contact Info

Product

Resources

About