Browse Topic: Injuries
Rotorcraft continue to experience higher fatal accident rates compared to fixed-wing aircraft, primarily due to low altitude flight operations and reduced situational awareness in complex environments. A critical factor is the limited availability of accurate, up-to-date information on helipads and surrounding obstacles - such as trees, poles, and buildings - that pose significant risks during takeoff and landing. Existing resources, including the Federal Aviation Administration's heliport registry, are often outdated and incomplete, particularly for private or state-operated sites, and fail to report nearby obstacles. This lack of up-to-date data is largely due to privacy restrictions at certain locations and the high cost associated with comprehensive obstacle surveys. To address this challenge, we develop a deep learning (DL) framework that automatically detects helipads and nearby obstacles from high-resolution satellite imagery. Our approach combines Mask R-CNN for precise pixel-level helipad segmentation with Grounding DINO, a zero-shot vision-language model that identifies obstacles using flexible text prompts (e.g., "Pole", "Tree") without task-specific training. This text-guided, scalable detection method adapts to diverse and evolving operational settings. We validate our framework across helipads in the United States, and demonstrate strong performance in both helipad localization and obstacle detection. In addition, we build a web-based application that automates image processing, updates incorrect heliport coordinates, and provides obstacle reports. This work aims to enhance aviation safety, modernize infrastructure records, and deliver scalable tools to the aviation and machine learning communities.
Dynamic rollovers represent a major hazard for helicopters during near-ground operations, often resulting in significant aircraft damage and passenger injuries. To improve safety in operations, recent studies have focused on developing a Helicopter Flight Data Monitoring framework to provide data-driven insights on operational safety. This work contributes to that effort by proposing an approach to identify precursors to dynamic rollovers. According to NTSB reports, approximately 60% of such incidents occur during in-flight phases like hover, hover-taxi, or landing. To capture the complex non-linear dynamics of helicopters, physics-based simulations were conducted to estimate a first hitting time metric, defined as the time until blade-ground contact, across a wide range of initial conditions for an inflight initial state of the helicopter. Eight parameters were identified as driving the first hitting time, and a probabilistic model was created to predict the distribution of that metric for different values of those parameters. Based on the predicted distributions, a risk-based metric was derived to robustly assess the risk of dynamic rollover and identify safer operational boundaries.
Prior to 1950, use of the helicopter for evacuation was extremely limited, as military top brass often considered it a worthless contraption; thus, rescue was uncertain at best for downed pilots and wounded soldiers stranded behind enemy lines. However, this all changed in Korea, where twelve U.S. Army helicopters from three detachments, working in tandem with seven, newly created Mobile Army Surgical Hospital (MASH) units, would fundamentally change the Army's medical-evacuation doctrine forever. Using several models of the Bell H-13, the Hiller H-23, and the Sikorsky H-5 and H-19, this small band of courageous pilots pushed themselves and their aircraft to their limits, transporting 21,212 critically wounded soldiers for life-saving surgery to various MASH units, cutting the fatality rate from World War II in half. Adopting the 3rd Air Rescue Squadron's motto, "That Others May Live," these pilots and their helicopters were affectionately known to the wounded as "Angels of Mercy."
ABSTRACT For many rotorcraft platforms, incorrect timing of the autorotation flare and deceleration maneuvers may result in significant aircraft damage and injury to the crew, or worse. There is a clear need for new pilot cueing and control augmentation technologies that lead to a higher probability of a successful autorotation landing. This paper describes a recent effort to develop two different Tau (time-to-contact)-based autorotation controllers that can be used to drive visual aids to help guide a pilot to apply the required control inputs to complete a safe autorotative landing. Such controllers may also be useful for fully autonomous autorotation landing for unmanned vehicles.
ABSTRACT
ABSTRACT
Rotorcrafts are generally subject to a higher fatal accident rate than other segments of aviation, including commercial and general aviation. The safety improvement for rotorcrafts would directly improve the efficiency of air traffic control, since rotorcrafts operate primarily within low-level airspace; an area that is becoming increasingly complex with new entrants, such as unmanned aircraft systems and urban air mobility. The recent impact of artificial intelligence and deep learning algorithms on various aspects of our lives has led to the investigation of the application of these algorithms in the aviation domain; as it may offer a prime opportunity to enhance safety within the aviation community. In this research, we explore the efficacy, reliability, and, more importantly, the explainability of modern deep learning algorithms. We use machine learning models to predict the attitude (pitch and yaw) of rotorcrafts using video data recorded with ordinary cameras. The cameras were mounted inside the helicopter cockpit and recorded outside view through windshield continually during the flight. We train four different architectures of convolutional neural networks (CNNs), i.e., VGG16, VGG19, ResNet50, and Xception. The models achieved 90%, 91%, 88%, and 88%, respectively, average attitude prediction accuracy on the test video dataset. Furthermore, we use gradient class activation maps (grad-CAM) to ascertain the features and regions of the image that influenced the model to make a specific prediction. We show that CNNs learn to focus on similar features as human operators (pilots), i.e., the natural horizon curve. Our findings demonstrate the feasibility of using deep learning models for attitude prediction from f light videos recorded using ordinary inexpensive cameras. The proposed video analytics framework provides a cost-effective means to supplement traditional Flight Data Recorders (FDR); a technology that is often beyond the financial reach of most general aviation rotorcraft operators.
As the premier agency for promoting and insuring aviation safety, the Federal Aviation Administration (FAA) continues to promote and highlight the importance of participating in aviation Flight Data Monitoring (FDM) programs to improve flight safety and operational efficiency. Indeed, recorder safety is one of the agency's top 10 most wanted list of safety improvements in 2017-2018. The FAA, National Transportation Safety Board (NTSB), and the United States Helicopter Safety Team (USHST) are strong proponents of recorder use. These organizations and other industry partners are working together to implement a helicopter safety enhancement that promotes the use of flight data recorders as a mechanism to reduce the helicopter fatal accident rate. However, despite these best efforts to reduce the fatal accident rate with this lifesaving technology, barriers to implementation exist. These include initial costs of flight data recorders which can range from 9,000 - 50,000, on average. These costs can be significant for small operators and they combine to prohibit the widespread adoption of FDM by the rotorcraft community. Thus, rotorcraft, in general, typically have a lower participation rate in FDM programs than other forms of aviation (i.e. commercial fixed-wing or part 121 airline operations). On the other hand, even small helicopter operators often have access to or the financial means to purchase one or more off-the-shelf video cameras, which can be mounted inside the cockpit. These cameras offer an alternative to traditional flight data recorders as well as a means to augment them with supplementary data not always available depending on the type of Flight Data Recorder (FDR) installed in the helicopter. On board video data offers several possibilities for improving safety including flight replay, as well as the ability to extract information from the external scene such as readings of instrument panel gauges. As part of our research approach, we analyzed video data from cameras recording the instrument panel and compared these values against ground truth data from the flight data recorder. These values formed the training dataset for our video analytic framework. To analyze this information, we first cropped the gauge of interest (i.e. airspeed indicator, tachometer, engine oil temperature/pressure) in each frame of every video. The gauge image, extracted from all videos, were subsequently fed to train a deep Convolutional Neural Network (CNN) using the FDR measurements as ground truth. We trained Resnet50 CNN models for airspeed, engine oil temperature/pressure, and tachometer gauges. These models obtained 78%, 89%, 89%, and 88% validation accuracy on airspeed, engine oil temperature/pressure, and tachometer gauges, respectively. To further demonstrate the feasibility, we used the trained models to retrieve airspeed and engine oil values from the complete flight profile. We observed that the our models predicted trajectories for gauges closely follow the actual sensory values recorded by FDR. Such solution results in an effective flight data analysis tool as well as improved safety and operational efficiency of rotorcraft. These results demonstrate the feasibility of an inexpensive cockpit camera solution that would facilitate participation in FDM programs even for legacy helicopters that may otherwise require significant installation work.
Safety features introduced in recent rotorcraft designs have not made their way into the bulk of the rotorcraft flying fleets around the world in spite many of them have been firstly introduced many years ago in newly certified platforms. The longevity of the current rotorcraft population has proved to be exceeding all the expectations and forecast that were made when these features were introduced. However the flat trend in accident rates and fatalities verified in these years especially in some sectors is urging the regulators and many other stakeholders to take action. Hence the need to define a method able to establish rational priorities to push the new safety features into the market, by using quantitative and qualitative criteria.
At 1414 hours on 11 September 1970 John W. C. "Pee Wee" Judge lost control of a Wallis WA-117 autogyro and plunged to his death in front of the viewing stand at the Society of British Aerospace Companies (SBAC) air show at Farnborough. From loss of control until the fatal impact was less than 7 seconds, and as the aircraft was the center of attention (including HRH Queen Elizabeth II), it was photographed from different angles by high quality cine film cameras which enabled extensive analysis. The official accident report would not be issued for 3 and half years, essentially confirming Wing Commander Ken Wallis' own conclusions based on a frame-by-frame viewing of the films - the end result was that Wallis, the most famous autogyro pilot and popularizer since his stellar performance with his WA-116 autogyro "Little Nellie" in the 1967 James Bond film You Only Live Twice, exited from public life and pursued “the autogyro as a working aircraft” for the next 42 years. Although he would later assume the ceremonial role as “Patron of the British Rotorcraft Society” and of The Norfolk and Suffolk Aviation Museum, he steadfastly refused to facilitate construction of his autogyros by amateur builders. (Two unsuccessful models, the Wombat and the Dingbat, would eventually be built by others, the result of what Wallis would label “eyeball engineering”). His sui generis status as a 'developer' had allowed him to develop the most advanced autogyro models (and begin dominating world records for the next three decades), but the British popular rotorcraft movement would not see any benefits, and never recover from the impact in public perception and governmental skepticism as to the safety of the small autorotational aircraft. Coupled with the fact that Igor Bensen had discovered that Campbell Aircraft, its British licensee, had been selling Bensen Gyrocopter plans with its own label (and without paying royalties) and withdrawn its franchise, the popular rotorcraft movement entered into a spiral that was accentuated by the governmental scrutiny of its safety record during the 3 and half years it took to issue the Farnborough accident report, the result of which the British CAA (Civil Aviation Authority) came to be known as the "Campaign Against Aviation", a characterization still employed almost a half-century later. The "catastrophe at Farnborough" marked the beginning of the decline of the popular rotorcraft movement in Britain and to a moribund state from which it has yet to recover.
Rotorcraft with a teetering rotor design are susceptible to a phenomenon known as "mast bumping" or “excessive flapping” which can lead to severe shaft structural damage followed by total separation of the rotor from the vehicle and a potential incursion of the rotor blade into the fuselage. Mast bumping accidents are nearly always fatal and are generally unavoidable once specific flight conditions are met. Certain teetering rotor vehicles are prohibited from specific maneuvers that may lead to mast bumping events. However, specific incidents indicate that certain causes of mast bumping may have not yet been determined, and the extreme danger of the phenomenon makes studies using flight testing impossible. This research uses the Rotorcraft Comprehensive Analysis System (RCAS) to create a physics-based, parameterized model of a nominal teetering rotor helicopter to simulate and assess the mast bumping risk of various level flight conditions and specific maneuvers. This data is used to develop a metric to quantify the mast bumping risk of any maneuver. This model is also used to study the sensitivity of a vehicles mast bumping tendency to conceptual rotor design parameters. Preliminary analyses show a relationship between mast bumping risk and high airspeed, as well as low g-force. Studies on variations in blade mass properties indicate that increasing the blade mass or placing the blade CG farther towards the tip increases mast bumping risk in low speed flight regimes.
Items per page:
50
1 – 50 of 1040