We describe the Intelligent Autopilot System (IAS), a fully autonomous autopilot capable of piloting large jets such as airliners by learning from experienced human pilots using Artificial Neural Networks. The IAS is capable of autonomously executing the required piloting tasks and handling the different flight phases to fly an aircraft from one airport to another including takeoff, climb, cruise, navigate, descent, approach, and land in simulation. In addition, the IAS is capable of autonomously landing large jets in the presence of extreme weather conditions including severe crosswind, gust, wind shear, and turbulence. The IAS is a potential solution to the limitations and robustness problems of modern autopilots such as the inability to execute complete flights, the inability to handle extreme weather conditions especially during approach and landing where the aircraft’s speed is relatively low, and the uncertainty factor is high, and the pilots shortage problem compared to the increasing aircraft demand. In this paper, we present the work done by collaborating with the aviation industry to provide training data for the IAS to learn from. The training data is used by Artificial Neural Networks to generate control models automatically. The control models imitate the skills of the human pilot when executing all the piloting tasks required to pilot an aircraft between two airports. In addition, we introduce new ANNs trained to control the aircraft’s elevators, elevators’ trim, throttle, flaps, and new ailerons and rudder ANNs to counter the effects of extreme weather conditions and land safely. Experiments show that small datasets containing single demonstrations are sufficient to train the IAS and achieve excellent performance by using clearly separable and traceable neural network modules which eliminate the black-box problem of large Artificial Intelligence methods such as Deep Learning. In addition, experiments show that the IAS can handle landing in extreme weather conditions beyond the capabilities of modern autopilots and even experienced human pilots. The proposed IAS is a novel approach towards achieving full control autonomy of large jets using ANN models that match the skills and abilities of experienced human pilots and beyond.
In this paper we develop a controller reduction procedure for linear parameter-varying (LPV) systems. The method uses synthesis Riccati inequalities for the normalized robust stabilization problem as a basis for the approximation. The technique provides a priori error bounds which are used to obtain closed-loop stability conditions and performance degradation level. We also generalize the relative model reduction method to LPV systems and give an energy interpretation to the controller reduction procedure. To illustrate the method, a reduced order controller is synthesized and tested on a nonlinear missile model. 相似文献
Hand gestures that are performed by one or two hands can be categorized according to their applications into different categories including conversational, controlling, manipulative and communicative gestures. Generally, hand gesture recognition aims to identify specific human gestures and use them to convey information. The process of hand gesture recognition composes mainly of four stages: hand gesture images collection, gesture image preprocessing using some techniques including edge detection, filtering and normalization, capture the main characteristics of the gesture images and the evaluation (or classification) stage where the image is classified to its corresponding gesture class. There are many methods that have been used in the classification stage of hand gesture recognition such as Artificial Neural Networks, template matching, Hidden Markov Models and Dynamic Time Warping. This exploratory survey aims to provide a progress report on hand posture and gesture recognition technology. 相似文献
Purpose: To investigate the efficacy of Ivoclean as a ceramic cleansing agent, by assessing shear bond strength of pre-etched lithium disilicate (LD) ceramic to resin cement.Materials and Methods: Seventy LD discs (10 × 10 × 4 mm) were fabricated and etched using 5% hydrofluoric acid (HF) for 20 s. Ten specimens were not exposed to saliva and silicone disclosing medium (negative control). The other 60 specimens, divided into six groups (n = 10), were exposed to saliva for 20 s and silicone disclosing medium for 3 min. Following contamination, 10 specimens were not cleansed (positive control). The remaining five groups were exposed to one of the five different cleansing agents: 96% isopropanol, 37% phosphoric acid-30 s, 5% HF acid- 20 s, 5% HF acid- 120 s, and Ivoclean paste-20 s. All specimens were treated with primer and bonded to a self-curing resin cement. Before shear bond strength testing, all specimens were thermocycled (3000 cycles; 5–55°).Results: Contamination of pre-etched LD ceramic specimens significantly reduced the shear bond strength values from 22.39 ± 0.38 MPa (negative control) to 6.54 ± 0.90 MPa (positive control) (p < 0.05). Cleansing of contaminated ceramic specimens with 5% HF acid [20 s (19.28 ± 1.06 MPa) and 120 s (20.04 ± 1.09 MPa)] and Ivoclean (18.30 ± 0.97) provided significantly higher bond strength values than other cleansing methods with 37% phosphoric acid and 96% isopropanol (p < 0.05).Conclusion: Ivoclean and 5% HF acid were found to be effective in cleansing of LD ceramic surface by demonstrating maximum increase in shear bond strength values as compared to contaminated LD ceramics. 相似文献
This paper presents an original Switched Observer (SO) for reduced-sensor control of a grid-connected Packed U Cells (PUC) multilevel inverter. The proposed SO performance is evaluated using a single-phase 7-level PUC inverter connected to the grid through filtering inductor. Based on the actual grid current, the proposed SO estimates accurately the PUC capacitor voltage, which is fed to the Model Predictive Control (MPC) algorithm while making use of a hybrid model considering both discrete and continuous variables. For real-time application, necessary conditions are given to guarantee the practical stability of the proposed SO under system parameters and input voltage variations according to the selected switching pattern. Theoretical analysis and simulation investigations are conducted to prove that the proposed SO-MPC scheme is stable in closed-loop for all system configurations and has good performances even during various disturbances (load change, parameters mismatch, and input voltage variation). 相似文献
Using combined Raman spectroscopy, atomic force microscopy and optical microscopy, this paper suggests that breakaway oxidation of Zircaloy is caused by the change of circumferential stress sign from compressive to tensile, which triggers catastrophic cracks to propagate from the oxide free surface toward the oxide–metal interface. The stress sign changes at a critical oxide thickness, which depends on the circumferential stress at the interface. This biaxial interfacial stress is promoted by a lattice expansion stress that accompanies the tetragonal to monoclinic crystal phase transition. In contrast with current research in the literature, this allotropic transformation is suggested to be beneficial, not detrimental, because it contributes to retard the thresholds for the change of circumferential stress sign, and thus breakaway oxidation. The tetragonal phase was revealed to localize at the interface and adopt the shape of prismatic isosceles triangles detected at early stages of oxidation. These growth morphologies are consistent with a cationic oxidation mechanism. Upon phase transition, the monoclinic variant quickly dominates the oxide scale above the interfacial regions and forces the overall oxidation to proceed by an anionic diffusion mechanism. The results of Raman spectroscopy compared well with those of atomic force microscopy. 相似文献