Intelligent strain sensing on a smart composite wing using extrinsic fabry-perot interferometric sensors and neural networks

Abstract

Abrtracr ~ Strain prediction at various locations on a smart composite wing can provide useful information on its aerodynamic condition. The smart wing consisted of a glasslepoxy composite beam with three Extrinsic Fahry-Perot Interferometric (EFPI) sensors mounted at three different locations near the wing root. Strain acting on the three sensors at different air speeds and angles-of-attack were experimentally ohtained in a closed circuit wind tunnel under normal conditions of operation. A function mapping fhe angle of attack and air speed to the strains on the three sensors was simulated using feed-forward neural networks trained using hack-propagation training algorithm. This mapping provides a method to predicl stall condilion by comparing the strain available in real time and the predicted strain by the trained neural network. I INTRODUCT~ONAdvanced composite materials are being used in substantial amounts for the developmeni and construction of advanced aerospace structures [ I ] that provides the structures with clear advantages of long life, high strength-to-weight ratio, and flexible design. A built-in Health Monitoring System (HMS) can monitor structural condition, and react to any changes in environment, resulting in a smart structure 12-31. Research in HMS development for efficient smart structures has improved capability in data interpretation or control functions [3-61. The choice of an optical sensor system, an important component of a HMS, has proven to he an effective choice owing to the number of advantages over non-optical sensors including little perturbation to the host structure, immunity to electromagnetic interference and the ability to form multiplexed networks for complex measurements [2].Advances in fiber optic sensing technology are reducing the weight, required power, and the cost. Fiber optic sensor based HMS have been used for monitoring structural integrity [7-81, vibration control [9], and damage assessment using modal analysis [IO].Artificial Neural Networks (ANN) are being used extensively as an efficient processing system due to their capabilities in pattern recognition, classification and function approximation [4-6, 10-1 11. The integration of optical sensor system and ANNs has enhanced the applications of fiherreinforced composite components into aerospace systems.Research has been carried out on the development of a smart helicopter rotor model using neural networks [IZ]. Neural networks are being extensively used in many aerospace applications including auto-pilots, flight path simulations, control systems, component simulations and fault detection Prediction of aerodynamic parameters under varying load conditions on an aircraft wing would provide useful information on the working condition of the wing. One such parameter is the strain levels acting at various points on the wing. The mathematical modeling of strain levels using known parameters such as angle-of-attack and wind speed is highly complex and not feasible. Complication factors are unpredictable wing stall, cond...

Demodulation of extrinsic Fabry-Pe´rot interferometric sensors for vibration testing using neural networks

“…Host materials include concrete, 29 metals, and composites, 27,30 and applications include the associated civil, aerospace, and automotive structures. [20][21][22][31][32][33] In particular, EFPI strain sensors have high dynamic and static sensitivity, a low physical profile, [12][13][14] and good compatibility with fiberglass reinforced plastic ͑FRP͒ composites. 30,34 However, EFPI suffers from nonlinearity, requiring extra processing.…”

“…[6][7][8]12 Strain sensing techniques are shown to be capable of characterizing impact-induced damage, warning of impending weakness in structural integrity, and assessing performance of composite structures. [20][21][22] For modal testing of structures, fiber optic sensors and ANNs have been combined to locate and classify damage from changes in resonant frequencies. 23 A Fourier series neural network ͑FSNN͒ has been employed in obtaining modal frequencies from the fiber optic sensor output.…”

New compliant strain gauges for self-sensing dynamic deformation of flapping wings on miniature air vehicles

“…Flapping wing MAVs have light, flexible wings that deform during flight, enhancing aerodynamic performance [5,6]. To monitor wing deformation, strain sensors can be placed on the wing surface [7]. A piezoelectric film has recently been mounted onto the frame of a flapping wing to serve as a sensing skin to measure wing deformation [8].…”