Dia Al Azzawi

Artificial Dendritic Cell Mechanism for Aircraft Immunity-Based Failure Detection and Identification

Biological dendritic cells perform a complex activation/suppression role in the generation, direction, and control of antibodies. Their action relies on balancing information regarding the external antigen type, amount, and virulence, as well as the state and resources of the host organism. In this paper, an information processing algorithm inspired by the functionality of the dendritic cells is proposed to enhance aircraft subsystem abnormal condition detection and identification within the artificial immune system paradigm. A hierarchical multi-self-strategy is used to produce multiple failure detection and identification outcomes at each sample time over a time window. The artificial dendritic cell is defined as a computational unit that centralizes, fuses, and interprets this information to decide upon a unique detection and identification outcome with reduced false alarms and a low number of incorrect identifications. A mathematical formulation of the concept and a detailed implementation algorithm a...

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

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.

Bio-Inspired Approach for Aircraft Health Assessment and Flight Envelope Estimation

Based on the artificial immune system paradigm and a hierarchical multi-self strategy, a set of algorithms for aircraft sub-systems failure detection, identification, evaluation and flight envelope estimation have been developed and implemented. Data from a six degrees-of-freedom flight simulator were used to define a large set of 2-dimensional self/non-self projections as well as for the generation of antibodies and identifiers designated for health assessment of an aircraft under upset conditions. The methodology presented in this paper classifies and quantifies the type and severity of a broad number of aircraft actuators, sensors, engine and structural component failures. In addition, the impact of these upset conditions on the flight envelope is estimated using nominal test data. Based on immune negative and positive selection mechanisms, a heuristic selection of sub-selves and the formulation of a mapping-based algorithm capable of selectively capturing the dynamic fingerprint of upset conditions is implemented. The performance of the approach is assessed in terms of detection and identification rates, false alarms, and correct prediction of flight envelope reduction with respect to specific states.Copyright

Integrated Immunity-Based Framework for Aircraft Abnormal Conditions Management

This paper presents the development of a biologically inspired generalized conceptual framework for the detection, identification, evaluation, and accommodation of aircraft subsystem abnormal conditions. The artificial immune system paradigm in conjunction with other artificial intelligence techniques, analytical tools, and heuristics are used in an attempt to provide a comprehensive solution to the problem of safely operating aircraft under abnormal flight conditions. The main concepts and foundations are established, and methodologies and algorithms for implementation are outlined. The approach addresses directly the complexity and multidimensionality of aircraft dynamic response in the context of abnormal conditions and is expected to facilitate the design of onboard augmentation systems to increase aircraft survivability, improve operation safety, and optimize performance at both normal and abnormal/upset conditions. Results obtained with an example implementation are presented to illustrate the poten...

Development of Immunity Based Adaptive Control Laws for Aircraft Fault Tolerance

This paper presents the development and testing of a novel fault tolerant adaptive control system based on a bio-inspired immunity-based mechanism applied to an aircraft fighter model. The proposed baseline control laws use a non-linear dynamic inversion and model reference adaptive control on the inner loops of the aircraft dynamics. In this new approach, the baseline controllers are augmented with an artificial immune system mechanism that relies on a direct compensation inspired primarily by the biological immune system response. The effectiveness of the approach is demonstrated through a full 6 degrees-of-freedom aircraft model interfaced with a Flight gear environment. The performance of the proposed control laws are investigated under a novel set of performance metrics, which quantify the level of input activity from the pilot and from the control surfaces in order to ensure the stability and performance of the aircraft under different actuator and structural failures. Optimization of the parameters of the artificial immunity system is performed using a genetic algorithm. The results show that the optimized fault tolerant adaptive control laws improve significantly the failure rejection using minimum pilot input and control surfaces activity under upset flight conditions.Copyright

Immunity-based aircraft actuator failure evaluation

Purpose This paper aims to present the development of prediction models for aircraft actuator failure impact on flight envelope within the artificial immune system (AIS) paradigm. Design/methodology/approach Simplified algorithms are developed for estimating ranges of flight envelope-relevant variables using an AIS in conjunction with the hierarchical multi-self strategy. The AIS is a new computational paradigm mimicking mechanisms of its biological counterpart for health management of complex systems. The hierarchical multi-self strategy consists of building the AIS as a collection of low-dimensional projections replacing the hyperspace of the self to avoid numerical and conceptual issues related to the high dimensionality of the problem. Findings The proposed methodology demonstrates the capability of the AIS to not only detect and identify abnormal conditions (ACs) of the aircraft subsystem but also evaluate their impact and consequences. Research limitations/implications The prediction of altered ranges of relevant variables at post-failure conditions requires failure-specific algorithms to correlate with the characteristics and dimensionality of self-projections. Future investigations are expected to expand the types of subsystems that are affected and the nature of the ACs targeted. Practical implications It is expected that the proposed methodology will facilitate the design of on-board augmentation systems to increase aircraft survivability and improve operation safety. Originality/value The AIS paradigm is extended to AC evaluation as part of an integrated and comprehensive health management process system, also including AC detection, identification and accommodation.

Pilot-in-the-Loop Evaluation of a Bio-Inspired Adaptive Fault Tolerant Control System in a Motion Based Flight Simulator

This paper presents the development and testing of a novel fault tolerant adaptive bioinspired control system applied to a supersonic fighter aircraft. The control configuration uses an immunity-based feedback mechanism to augment a baseline controller consisting of model reference and dynamic inversion approach. The capabilities of the proposed system, addressing different upset conditions, are compared with different control configurations and tested on a motion based simulation environment with a pilot in the loop. One configuration includes the baseline controller augmented with artificial neural networks, whereas an alternative configuration uses the baseline controller augmented with both, neural networks and artificial immune system itself. A set of novel performance metrics were defined to quantify the input activity from the pilot and from the control surfaces in order to investigate the effectiveness and handling characteristics of the different configurations under failure conditions. Optimization of the immune controller parameters was performed for the most relevant failures of the system using a genetic algorithm approach. The results show that the inclusion of the immunity-based mechanism within the control laws scheme improve the tracking performance in terms of pilot input and control surfaces activity under a variety of abnormal flight conditions

Immunity-Based Abnormal Condition Accommodation of Aircraft Sub-system Failures

This paper describes the design, development, and flight-simulation testing of an artificial immune-system-based approach for accommodation of different aircraft sub-system failures/damages. The accommodation of abnormal flight conditions is regarded as part of a complex integrated artificial immune system scheme, which consists of four major components: detection, identification, evaluation, and accommodation. The accommodation part consists of providing compensatory commands under upset conditions for specific maneuvers.The approach is based on building an artificial memory, which represents the self (nominal conditions) and the non-self (abnormal conditions) within the artificial immune system paradigm. Self and non-self are structured as a set of memory cells 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 is based on the cell in the memory that is the most similar to the in-coming measurement. 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 and under locked actuator.The results demonstrate the possibility of extracting pilot compensatory commands from the self/non-self structure and capability of the artificial-immune-system-based scheme to accommodate an actuator malfunction, maintain control, and complete the task.Copyright