Digital avionic solutions enable advanced flight control systems to be available also on smaller aircraft. One of the safety-critical segments is the air data system. Innovative architectures allow the use of synthetic sensors that can introduce significant technological and safety advances. The application to aerodynamic angles seems the most promising towards certified applications. In this area, the best procedures concerning the design of synthetic sensors are still an open question within the field. An example is given by the MIDAS project funded in the frame of Clean Sky 2. This paper proposes two data-driven methods that allow to improve performance over the entire flight envelope with particular attention to steady state flight conditions. The training set obtained is considerably undersized with consequent reduction of computational costs. These methods are validated with a real case and they will be used as part of the MIDAS life cycle. The first method, called Data-Driven Identification and Generation of Quasi-Steady States (DIGS), is based on the (i) identification of the lift curve of the aircraft; (ii) augmentation of the training set with artificial flight data points. DIGS’s main aim is to reduce the issue of unbalanced training set. The second method, called Similar Flight Test Data Pruning (SFDP), deals with data reduction based on the isolation of quasi-unique points. Results give an evidence of the validity of the methods for the MIDAS project that can be easily adopted for generic synthetic sensor design for flight control system applications.
The application of virtual sensor is widely discussed in literature as a cost effective solution compared to classical physical architectures. RAMS (Reliability, Availability, Maintainability and Safety) performance of the entire avionic system seem to be greatly improved using analytical redundancy. However, commercial applications are still uncommon. A complete analysis of the behavior of these models must be conducted before implementing them as an effective alternative for aircraft sensors. In this paper, a virtual sensor based on neural network called Smart-ADAHRS (Smart Air Data, Attitude and Heading Reference System) is analyzed through simulation. The model simulates realistic input signals of typical inertial and air data MEMS (Micro Electro-Mechanical Systems) sensors. A procedure to define the background noise model is applied and two different cases are shown. The first considers only the sensor noise whereas the latter uses the same procedure with the operative flight noise. Flight tests have been conducted to measure the disturbances on the inertial and air data sensors. Comparison of the Power Spectral Density function is carried out between operative and background noise. A model for GNSS (Global Navigation Satellite System) receiver, complete with constellation simulator and atmospheric delay evaluation, is also implemented. Eventually, a simple multi-sensor data fusion technique is modeled. Results show a good robustness of the Smart-ADAHRS to the sensor faults and a marginal sensitivity to the temperature-related faults. Solution for this kind of degradation is indicated at the end of the paper. Influences of noise on input signals is also discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.