The virtual landing pad: facilitating rotary-wing landing operations in degraded visual environments

The safety of rotary-wing operations is significantly affected by the local weather conditions, especially during key phases of flight including hover and landing. Despite the operational flexibility of rotary-wing craft, such craft accounts for a significantly greater proportion of accidents than their fixed-wing counterparts. A key period of risk when operating rotary-wing aircraft is during operations that occur in degraded visual environments, for example as a result of thick fog. During such conditions, pilots’ workload significantly increases and their situation awareness can be greatly impeded. The current study examines the extent to which providing information to pilots via the use of a head-up display (HUD) influenced perceived workload and situation awareness, when operating in both clear and degraded visual environments. Results suggest that whilst the HUD did not benefit pilots during clear conditions, workload was reduced when operating in degraded visual conditions. Overall results demonstrate that access to the HUD reduces the difficulties associated with flying in degraded visual environments.     

The Feasibility of Using an Adaptive Technique in Flight Simulator Training

This study explores the feasibility of using an adaptive technique in flight simulator training to improve piloting skills. An operational flight simulator is used to simulate a jet fighter aircraft. Eighteen non-jet-experienced pilots are assigned to two groups for the purpose of receiving equivalent amounts of practice in the task of maintaining a constant altitude program during simulated air turbulence. One group is trained using an adaptive technique and the other is trained under conditions more representative of conventional training. The hypothesis is that an adaptive technique is feasible if adaptively trained pilots are more proficient than conventionally trained pilots when transferred to a flight simulation representative of an aircraft in turbulent air. Resulting data support the hypothesis.     

Reachability Analysis of Landing Sites for Forced Landing of a UAS

This paper details a method to ascertain the reachability of known emergency landing sites for any fixed wing aircraft in a forced landing situation. With a knowledge of the aircraft’s state and parameters, as well as a known wind profile, the area of maximum glide range can be calculated using aircraft equations of motion for gliding flight. A landing descent circuit technique used by human pilots carrying out forced landings called high key low key is employed to account for the extra glide distance required for an approach and landing. By combining maximum glide range analysis with the descent circuit, all the reachable landing sites can be determined. X-Plane flight simulator is used to demonstrate and validate the techniques presented.     

An ANNs-based system for the diagnosis and treatment of diseases

The review of a prototype Medical Decision Making System based on a robust configuration of Artificial Neural Networks (ANNs) is the topic of this article. It is designed to cover a whole category of human diseases, as can be proved by the already adapted systems that covered Pulmonogical and Haematological Cases. Moreover, an inside view is provided on one of the most crucial topics: ANNs' learning procedure.     

Hate to interrupt you,but… analyzing turn-arounds from a cockpit perspective

This study aimed to analyze aircraft ground operation processes from a human factors perspective with special emphases on the occurrence and influence of interruptions on pilots’ workload. Interruptions have been shown to increase workload and error probability as well as to contribute to fatal accidents in various fields. Countermeasures have been initiated especially in high-risk environments such as those involving medical issues. In aviation, more explicitly during turn-around processes, interruptions might occur frequently and impair flight safety. One hundred and sixty fully certified pilots working for a European airline were observed during their turn-around while performing real operations. Pilots’ interruptions were documented and classified in order to predict subjectively perceived workload by use of multiple linear regression analysis. External factors such as weather conditions, technical problems, and time pressure were considered as covariates. On average, a pilot experienced about eight interruptions during a turn-around. Overall workload estimates showed a level comparable to that of manual flying in a simulator. Interruptions from colleagues or from outside the cockpit were found to predict pilots’ workload; however, further external factors such as poor weather conditions impacted workload even more strongly. We suggest two approaches based on our results to handling the high rate of interruptions. We first recommend procedural changes to diminish the interruption rate; second, we recommend comprehensive, line-oriented flight training for airline and ground staff to raise awareness about the negative influence of interruptions.     

Computational intelligence techniques for modeling of dynamic adsorption of organic pollutants on activated carbon

Neural Computing and Applications - The objective of this work is to compare the efficiency of three computational intelligence techniques: Artificial Neural Networks (ANNs), Support Vector...     

Pilot performance, strategy, and workload while executing approaches at steep angles and with lower landing minima

OBJECTIVE: We examined the willingness and ability of general aviation pilots to execute steep approaches in low-visibility conditions into nontowered airports. BACKGROUND: Executing steep approaches in poor weather is required for a proposed Small Aircraft Transportation System (SATS) that consists of small aircraft flying direct routes to a network of regional airports. METHOD: Across two experiments, 17 pilots rated for Instrument Flight Rules at George Mason University or Virginia Tech flew a Cessna 172R simulator into Blacksburg, Virginia. Pilots were familiarized with the simulator and asked to fly approaches with either a 200- or 400-foot ceiling (at approach angles of 3 degrees, 5 degrees, and 7 degrees in the first experiment, 3 degrees and 6 degrees in the second). Pilots rated subjective workload and the simulator recorded flight parameters for each set of approaches. RESULTS: Approaches with a 5 degree approach angle produced safe landings with minimal deviations from normal descent control configurations and were rated as having a moderate level of workload. Approaches with 6 degree and 7 degree approach angles produced safe landings but high workload ratings. Pilots reduced power to control the speed of descent and flew the aircraft slightly above the glide path to gain time to control the landing. CONCLUSION: Although the 6 degree and 7 degree approaches may not be practical for routine approaches, they may be achievable in the event of an emergency. APPLICATION: Further work using other aircraft flying under a wider variety of conditions is needed before implementing SATS-type flights into airports intended to supplant or complement commercial operations in larger airports.     

Application of generalised neural network for aircraft landing control system

 It is observed that landing performance is the most typical phase of an aircraft performance. During landing operation the stability and controllability are the major considerations. To achieve a safe landing, an aircraft has to be controlled in such a way that its wheels touch the ground comfortably and gently within the paved surface of the runway. The conventional control theory found very successful in solving well defined problems, which are described precisely with definite and clearly mentioned boundaries. In real life systems the boundaries can't be defined clearly and conventional controller does not give satisfactory results. Whenever, an aircraft deviates from its glide path (gliding angle) during landing operation, it will affect the landing field, landing area as well as touch down point on the runway. To control correct gliding angle (glide path) of an aircraft while landing, various traditional controllers like PID controller or state space controller as well as maneuvering of pilots are used, but due to the presence of non-linearities of actuators and pilots these controllers do not give satisfactory results. Since artificial neural network can be used as an intelligent control technique and are able to control the correct gliding angle i.e. correct gliding path of an aircraft while landing through learning which can easily accommodate the aforesaid non-linearities. The existing neural network has various drawbacks such as large training time, large number of neurons and hidden layers required to deal with complex problems. To overcome these drawbacks and develop a non-linear controller for aircraft landing system a generalized neural network has been developed.     

Distributed memory systems for simulating artificial neural networks

In executing tasks involving intelligent information processing, the human brain performs better than the digital computer. The human brain derives its power from a large number [O(10¹¹)] of neurons which are interconnected by a dense interconnection network [O(10⁵) connections per neuron]. Artificial neural network (ANN) paradigms adopt the structure of the brain to try to emulate the intelligent information processing methods of the brain. ANN techniques are being employed to solve problems in areas such as pattern recognition, and robotic processing. Simulation of ANNs involves implementation of large number of neurons and a massive interconnection network. In this paper, we discuss various simulation models of ANNs and their implementation on distributed memory systems. Our investigations reveal that communication-efficient networks of distributed memory systems perform better than other topologies in implementing ANNs.     

Differences in situation assessments and prospective diagnoses of simulated weather radar returns amongst experienced pilots

Weather radar systems are an important tool in commercial aviation to safeguard the safety and security of aircraft. However, the utility of weather radar systems lies in the accuracy and the reliability of the interpretations of the displays. The primary aim of this study was to determine whether experienced pilots could be clustered based on their assessments of the turbulence associated with simulated weather radar displays and whether these groups corresponded to differences in experience-related metrics. Sixty one participants completed a series of on-line scenarios in which they were asked to rate the level of turbulence associated with 11 simulated weather radar displays. They were also asked to indicate their confidence in being able to continue the flight for 80 nautical miles in the absence of an alteration in track or altitude. A cluster analysis reliably differentiated two groups of participants and these groups corresponded to differences in the capacity to discriminate between weather radar scenarios. The results also reveal both a lack of reliability in experienced pilots' interpretations of weather radar displays and difficulties associated with classifications of expertise on the basis of experienced-related metrics. At an empirical level, the outcomes have implications for assessments of expertise in domains in which ideal performance is difficult to establish. From an industry perspective, the results reveal important differences in the interpretation of weather radar displays amongst experienced, qualified pilots. This suggests a need for both more effective weather radar design, complemented by more reliable and comprehensive training that focuses on the accurate interpretation of different types of weather radar returns.     

Mapping of artificial neural networks onto message passing systems

Various Artificial Neural Networks (ANNs) have been proposed in recent years to mimic the human brain in solving problems involving human-like intelligence. Efficient mapping of ANNs comprising of large number of neurons onto various distributed MIMD architectures is discussed in this paper. The massive interconnection among neurons demands a communication efficient architecture. Issues related to the suitability of MIMD architectures for simulating neural networks are discussed. Performance analysis of ring, torus, binary tree, hypercube, and extended hypercube for simulating artificial neural networks is presented. Our studies reveal that the performance of the extended hypercube is better than those of ring, torus, binary tree, and hypercube topologies.     

遗传算法优化BP网络初始权重用于入侵检测

基于遗传算法的全局搜索和BP网络局部精确搜索的特性,将遗传算法与BP算法有机结合,先采用遗传算法优化BP网络初始权重,完成网络的训练过程,并将此方法运用于入侵检测中。实验证明,运用此方法有利于提高网络的收敛性,可在一定程度上提高入侵检测系统的准确率。     

Adaptive autopilots for tankers

Two adaptive autopilots for ships are designed. The autopilots are based on velocity scheduling, a self-tuning regulator for steady state course keeping, a high gain turning regulator with variable structure and a Kalman filter. Methods for design of the autopilots are discussed. Results from simulations and full-scale experiments with three different tankers are presented. The autopilots are shown to work excellently under different load, speed, and weather conditions.     

基于小波重构的控制图并发异常模式识别研究

对于统计质量控制过程中的复杂过程而言,多种异常的并发现象比较普遍,而常规的基于规则的方法以及人工神经网络（ANNs）技术均针对单一异常模式的识别,难以完成对并发异常模式的识别任务。提出一种混合方法,将小波分析与ANNs相结合,通过小波分解重构将并发异常模式分解为基本的异常模式组合,无须用并发异常样本训练ANNs,实现对并发异常模式的有效识别。     

Examining the Effects of Conformal Terrain Features in Advanced Head‐Up Displays on Flight Performance and Pilot Situation Awareness

Synthetic vision systems (SVS) render terrain features for pilots through cockpit displays using a GPS database and three‐dimensional graphical models. Enhanced vision systems (EVS) present infrared imagery of terrain using a forward‐looking sensor in the nose of an aircraft. The ultimate goal of SVS and EVS technologies is to support pilots in achieving safety under low‐visibility and night conditions comparable to clear, day conditions. This study assessed pilot performance and situation awareness (SA) effects of SVS and EVS imagery in an advanced head‐up display (HUD) during a simulated landing approach under instrument meteorological conditions. Videos of the landing with various HUD configurations were presented to eight pilots with a superimposed tracking task. The independent variables included four HUD feature configurations (baseline [no terrain imagery], SVS, EVS, and a combination of SVS and EVS), two visibility conditions, and four legs of the flight. Results indicated that SVS increased overall SA but degraded flight path control performance because of visual confusion with other display features. EVS increased flight path control accuracy but decreased system (aircraft) awareness because of visual distractions. The combination of SVS and EVS generated offsetting effects. Display configurations did not affect pilot spatial awareness. Flight performance was not different among phases of the approach, but levels and types of pilot SA did vary from leg to leg. These results are applicable to development of adaptive HUD features to support pilot performance. They support the use of multidimensional measures of SA for insight on pilot information processing with advanced aviation displays. © 2012 Wiley Periodicals, Inc.     

Flying personal planes: modeling the airport choices of general aviation pilots using stated preference methodology

This study employed stated preference (SP) models to determine why general aviation pilots choose to base and operate their aircraft at some airports and not others. Thirteen decision variables identified in pilot focus groups and in the general aviation literature were incorporated into a series of hypothetical choice tasks or scenarios. The scenarios were offered within a fractional factorial design to establish orthogonality and to preclude dominance in any combination of variables. Data from 113 pilots were analyzed for individual differences across pilots using conditional logit regression with and without controls. The results demonstrate that some airport attributes (e.g., full-range hospitality services, paved parallel taxiway, and specific types of runway lighting and landing aids) increase pilot utility. Heavy airport congestion and airport landing fees, on the other hand, decrease pilot utility. The importance of SP methodology as a vehicle for modeling choice behavior and as an input into the planning and prioritization process is discussed. Actual or potential applications include the development of structured decision-making instruments in the behavioral sciences and in human service programs.     

Design and flight testing of a digital optimal control general aviation autopilot

This paper presents the designs of proportional-integral-filter (PIF) autopilots for a General Aviation (NAVION) aircraft. The PIF autopilots use modern control theory to determine heading select and altitude select and hold autopilot modes. The PIF control law uses typical General Aviation sensors for state feedback; command error integration for command tracking; digital complimentary filtering and analog prefiltering for sensor noise suppression; a control filter for computation delay accommodation; and the incremental form to eliminate trim values in implementation. Theoretical developments for the control law are described which combine the sampled-data regulator with command generator tracking for use as a digital flight control system. The digital PIF autopilots are evaluated using closed-loop eigenvalues, plots of gain and phase vs frequency and plots of simulations. Successful flight test results for the PIF autopilots are presented for different turbulence conditions and quadratic weights.     

Intelligent automatic landing system using time delay neural network controller

This paper presents an intelligent automatic landing system that uses a time delay neural network controller and a linearized inverse aircraft model to improve the performance of conventional automatic landing systems. The automatic landing system of an airplane is enabled only under limited conditions. If severe wind disturbances are encountered, the pilot must handle the aircraft due to the limits of the automatic landing system. In this study, a learning-through-time process is used in the controller training. Simulation results show that the neural network controller can act as an experienced pilot and guide the aircraft to a safe landing in severe wind disturbance environments without using the gain scheduling technique.     

Development of a bespoke human factors taxonomy for gliding accident analysis and its revelations about highly inexperienced UK glider pilots

Low-hours solo glider pilots have a high risk of accidents compared to more experienced pilots. Numerous taxonomies for causal accident analysis have been produced for powered aviation but none of these is suitable for gliding, so a new taxonomy was required. A human factors taxonomy specifically for glider operations was developed and used to analyse all UK gliding accidents from 2002 to 2006 for their overall causes as well as factors specific to low hours pilots. Fifty-nine categories of pilot-related accident causation emerged, which were formed into progressively larger categories until four overall human factors groups were arrived at: ‘judgement’; ‘handling’; ‘strategy’; ‘attention’. ‘Handling’ accounted for a significantly higher proportion of injuries than other categories. Inexperienced pilots had considerably more accidents in all categories except ‘strategy’. Approach control (path judgement, airbrake and speed handling) as well as landing flare misjudgement were chiefly responsible for the high accident rate in early solo glider pilots.     

BP网络及遗传算法在河道流量预报中的应用

基于遗传算法的全局搜索和BP网络局部精确搜索的特性,采用遗传算法对BP网络模型进行优化,并将此模型应用于北江流域的坪石-犁市河道的预报流量中.实验结果表明,该算法在提高BP网络的收敛速度和预测精度上是行之有效的,为流量预报提供了一种新的方法.