scholarly journals A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms

2021 ◽  
Vol 7 (11) ◽  
pp. 227
Author(s):  
Hiba Alqaysi ◽  
Igor Fedorov ◽  
Faisal Z. Qureshi ◽  
Mattias O’Nils
Keyword(s):  
Object Detection ◽  
Wind Turbines ◽  
Wind Farms ◽  
Detection Accuracy ◽  
Ensemble Model ◽  
Challenging Problem ◽  
Training Set ◽  
Bird Detection ◽  
Set Up ◽  
Small Bird

Object detection for sky surveillance is a challenging problem due to having small objects in a large volume and a constantly changing background which requires high resolution frames. For example, detecting flying birds in wind farms to prevent their collision with the wind turbines. This paper proposes a YOLOv4-based ensemble model for bird detection in grayscale videos captured around wind turbines in wind farms. In order to tackle this problem, we introduce two datasets—(1) Klim and (2) Skagen—collected at two locations in Denmark. We use Klim training set to train three increasingly capable YOLOv4 based models. Model 1 uses YOLOv4 trained on the Klim dataset, Model 2 introduces tiling to improve small bird detection, and the last model uses tiling and temporal stacking and achieves the best mAP values on both Klim and Skagen datasets. We used this model to set up an ensemble detector, which further improves mAP values on both datasets. The three models achieve testing mAP values of 82%, 88%, and 90% on the Klim dataset. mAP values for Model 1 and Model 3 on the Skagen dataset are 60% and 92%. Improving object detection accuracy could mitigate birds’ mortality rate by choosing the locations for such establishment and the turbines location. It can also be used to improve the collision avoidance systems used in wind energy facilities.

Model Tests for a Floating Windturbine on Three Different Floaters

2012 ◽  
Author(s):  
Bonjun Koo ◽  
Andrew J. Goupee ◽  
Kostas Lambrakos ◽  
Richard W. Kimball
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Wind Farms ◽  
Model Tests ◽  
Floating Platform ◽  
Scaled Model ◽  
Advantages And Disadvantages ◽  
Near Shore ◽  
Set Up ◽  
Floating Platforms

Wind energy is a promising alternate energy resource. However, the on-land wind farms are limited by space, noise, and visual pollution, and therefore many countries build wind farms near shore. Up to now, most of offshore wind farms have been built in relatively shallow water (less than 30m) with fixed tower type wind turbines. Recently, several countries plan to move wind farms to deep water offshore locations to find stronger and steadier wind fields as compared to near shore locations. For the wind farms in deeper water, floating platforms have been proposed to support the wind turbine. The model tests described in this paper were performed at MARIN (Maritime Research Institute Netherlands) with a model set-up corresponding to a 1:50 Froude scaling. The wind turbine was a scaled model of the National Renewable Energy Lab (NREL) 5MW, horizontal axis reference wind turbine supported by three different generic floating platforms: a spar, a semi-submersible and a tension-leg platform (TLP). The wave environment used in the tests is representative of the offshore in the state of Maine. In order to capture coupling between the floating platform and the wind turbine, the 1st bending mode of the turbine tower was also modeled. The main purpose of the model tests was to generate data on coupled motions and loads between the three floating platforms and the same wind turbine for the operational, design, and survival seas states. The data are to be used for calibration and improvement of existing design analysis and performance numerical codes. An additional objective of the model tests was to establish advantages and disadvantages among the three floating platform concepts on the basis of test data. The paper gives details of the scaled model wind turbine and floating platforms, the set-up configurations, and the instrumentation to measure motions, accelerations and loads as well as wind turbine rpm, torque and thrust for the three floating wind turbines. The data and data analysis results are the subject of another paper in this conference [1].

scholarly journals Comprehensive Bird Preservation at Wind Farms

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 267
Author(s):  
Dawid Gradolewski ◽  
Damian Dziak ◽  
Milosz Martynow ◽  
Damian Kaniecki ◽  
Aleksandra Szurlej-Kielanska ◽  
...  
Keyword(s):  
Wind Turbines ◽  
Development Process ◽  
Detection Method ◽  
Vision System ◽  
Wind Farms ◽  
Component Selection ◽  
Decision Making System ◽  
Bird Mortality ◽  
Bird Detection ◽  
Validation Tests

Wind as a clean and renewable energy source has been used by humans for centuries. However, in recent years with the increase in the number and size of wind turbines, their impact on avifauna has become worrisome. Researchers estimated that in the U.S. up to 500,000 birds die annually due to collisions with wind turbines. This article proposes a system for mitigating bird mortality around wind farms. The solution is based on a stereo-vision system embedded in distributed computing and IoT paradigms. After a bird’s detection in a defined zone, the decision-making system activates a collision avoidance routine composed of light and sound deterrents and the turbine stopping procedure. The development process applies a User-Driven Design approach along with the process of component selection and heuristic adjustment. This proposal includes a bird detection method and localization procedure. The bird identification is carried out using artificial intelligence algorithms. Validation tests with a fixed-wing drone and verifying observations by ornithologists proved the system’s desired reliability of detecting a bird with wingspan over 1.5 m from at least 300 m. Moreover, the suitability of the system to classify the size of the detected bird into one of three wingspan categories, small, medium and large, was confirmed.

Detection and localization of helipad in autonomous UAV landing: a coupled visual-inertial approach with artificial intelligence

2020 ◽  
Vol 71 (7) ◽  
pp. 828-839
Author(s):  
Thinh Hoang Dinh ◽  
Hieu Le Thi Hong
Keyword(s):  
Neural Network ◽  
Unmanned Aerial Vehicles ◽  
Fiducial Marker ◽  
Localization Algorithm ◽  
Challenging Problem ◽  
Autonomous Landing ◽  
Aerial Vehicles ◽  
Set Up ◽  
Detection And Localization ◽  
Rotary Wing

Autonomous landing of rotary wing type unmanned aerial vehicles is a challenging problem and key to autonomous aerial fleet operation. We propose a method for localizing the UAV around the helipad, that is to estimate the relative position of the helipad with respect to the UAV. This data is highly desirable to design controllers that have robust and consistent control characteristics and can find applications in search – rescue operations. AI-based neural network is set up for helipad detection, followed by optimization by the localization algorithm. The performance of this approach is compared against fiducial marker approach, demonstrating good consensus between two estimations

scholarly journals Monitoring Wind Turbine Gearbox with Echo State Network Modeling and Dynamic Threshold Using SCADA Vibration Data

Energies ◽  
2019 ◽  
Vol 12 (6) ◽  
pp. 982 ◽  
Author(s):  
Xin Wu ◽  
Hong Wang ◽  
Guoqian Jiang ◽  
Ping Xie ◽  
Xiaoli Li
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Operating Conditions ◽  
Dynamic Threshold ◽  
Detection Accuracy ◽  
Echo State Network ◽  
Monitoring Method ◽  
Vibration Data ◽  
Static Monitoring ◽  
Threshold Monitoring

Health monitoring of wind turbine gearboxes has gained considerable attention as wind turbines become larger in size and move to more inaccessible locations. To improve the reliability, extend the lifetime of the turbines, and reduce the operation and maintenance cost caused by the gearbox faults, data-driven condition motoring techniques have been widely investigated, where various sensor monitoring data (such as power, temperature, and pressure, etc.) have been modeled and analyzed. However, wind turbines often work in complex and dynamic operating conditions, such as variable speeds and loads, thus the traditional static monitoring method relying on a certain fixed threshold will lead to unsatisfactory monitoring performance, typically high false alarms and missed detections. To address this issue, this paper proposes a reliable monitoring model for wind turbine gearboxes based on echo state network (ESN) modeling and the dynamic threshold scheme, with a focus on supervisory control and data acquisition (SCADA) vibration data. The aim of the proposed approach is to build the turbine normal behavior model only using normal SCADA vibration data, and then to analyze the unseen SCADA vibration data to detect potential faults based on the model residual evaluation and the dynamic threshold setting. To better capture temporal information inherent in monitored sensor data, the echo state network (ESN) is used to model the complex vibration data due to its simple and fast training ability and powerful learning capability. Additionally, a dynamic threshold monitoring scheme with a sliding window technique is designed to determine dynamic control limits to address the issue of the low detection accuracy and poor adaptability caused by the traditional static monitoring methods. The effectiveness of the proposed monitoring method is verified using the collected SCADA vibration data from a wind farm located at Inner Mongolia in China. The results demonstrated that the proposed method can achieve improved detection accuracy and reliability compared with the traditional static threshold monitoring method.

scholarly journals Geometric property-based convolutional neural network for indoor object detection

2021 ◽  
Vol 18 (1) ◽  
pp. 172988142199332
Author(s):  
Xintao Ding ◽  
Boquan Li ◽  
Jinbao Wang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Geometric Property ◽  
Ground Truth ◽  
Geometric Constraints ◽  
Depth Information ◽  
Training Set ◽  
Object Knowledge ◽  
The Mean

Indoor object detection is a very demanding and important task for robot applications. Object knowledge, such as two-dimensional (2D) shape and depth information, may be helpful for detection. In this article, we focus on region-based convolutional neural network (CNN) detector and propose a geometric property-based Faster R-CNN method (GP-Faster) for indoor object detection. GP-Faster incorporates geometric property in Faster R-CNN to improve the detection performance. In detail, we first use mesh grids that are the intersections of direct and inverse proportion functions to generate appropriate anchors for indoor objects. After the anchors are regressed to the regions of interest produced by a region proposal network (RPN-RoIs), we then use 2D geometric constraints to refine the RPN-RoIs, in which the 2D constraint of every classification is a convex hull region enclosing the width and height coordinates of the ground-truth boxes on the training set. Comparison experiments are implemented on two indoor datasets SUN2012 and NYUv2. Since the depth information is available in NYUv2, we involve depth constraints in GP-Faster and propose 3D geometric property-based Faster R-CNN (DGP-Faster) on NYUv2. The experimental results show that both GP-Faster and DGP-Faster increase the performance of the mean average precision.

scholarly journals Transcription Alignment of Historical Vietnamese Manuscripts without Human-Annotated Learning Samples

2021 ◽  
Vol 11 (11) ◽  
pp. 4894
Author(s):  
Anna Scius-Bertrand ◽  
Michael Jungo ◽  
Beat Wolf ◽  
Andreas Fischer ◽  
Marc Bui
Keyword(s):  
Object Detection ◽  
State Of The Art ◽  
Positive Impact ◽  
Detection System ◽  
Training Data ◽  
Detection Accuracy ◽  
Current State ◽  
Alignment Task ◽  
Scanned Image ◽  
Automatic Transcription

The current state of the art for automatic transcription of historical manuscripts is typically limited by the requirement of human-annotated learning samples, which are are necessary to train specific machine learning models for specific languages and scripts. Transcription alignment is a simpler task that aims to find a correspondence between text in the scanned image and its existing Unicode counterpart, a correspondence which can then be used as training data. The alignment task can be approached with heuristic methods dedicated to certain types of manuscripts, or with weakly trained systems reducing the required amount of annotations. In this article, we propose a novel learning-based alignment method based on fully convolutional object detection that does not require any human annotation at all. Instead, the object detection system is initially trained on synthetic printed pages using a font and then adapted to the real manuscripts by means of self-training. On a dataset of historical Vietnamese handwriting, we demonstrate the feasibility of annotation-free alignment as well as the positive impact of self-training on the character detection accuracy, reaching a detection accuracy of 96.4% with a YOLOv5m model without using any human annotation.

scholarly journals Offshore Wind Energy Resource Assessment across the Territory of Oman: A Spatial-Temporal Data Analysis

2021 ◽  
Vol 13 (5) ◽  
pp. 2862
Author(s):  
Amer Al-Hinai ◽  
Yassine Charabi ◽  
Seyed H. Aghay Kaboli
Keyword(s):  
Data Analysis ◽  
Wind Energy ◽  
Wind Turbines ◽  
Energy Resource ◽  
Wind Farms ◽  
Offshore Wind ◽  
Wind Data ◽  
Offshore Wind Energy ◽  
Offshore Wind Turbines ◽  
Wind Potential

Despite the long shoreline of Oman, the wind energy industry is still confined to onshore due to the lack of knowledge about offshore wind potential. A spatial-temporal wind data analysis is performed in this research to find the locations in Oman’s territorial seas with the highest potential for offshore wind energy. Thus, wind data are statistically analyzed for assessing wind characteristics. Statistical analysis of wind data include the wind power density, and Weibull scale and shape factors. In addition, there is an estimation of the possible energy production and capacity factor by three commercial offshore wind turbines suitable for 80 up to a 110 m hub height. The findings show that offshore wind turbines can produce at least 1.34 times more energy than land-based and nearshore wind turbines. Additionally, offshore wind turbines generate more power in the Omani peak electricity demand during the summer. Thus, offshore wind turbines have great advantages over land-based wind turbines in Oman. Overall, this work provides guidance on the deployment and production of offshore wind energy in Oman. A thorough study using bankable wind data along with various logistical considerations would still be required to turn offshore wind potential into real wind farms in Oman.

scholarly journals Wealth of Wind and Visitors: Tourist Industry Attitudes towards Wind Energy Development in Iceland

Land ◽  
2021 ◽  
Vol 10 (7) ◽  
pp. 693
Author(s):  
Anna Dóra Sæþórsdóttir ◽  
Margrét Wendt ◽  
Edita Tverijonaite
Keyword(s):  
Land Use ◽  
Wind Energy ◽  
Wind Turbines ◽  
Wind Farm ◽  
Service Providers ◽  
Wind Farms ◽  
Energy Development ◽  
Tourism Industry ◽  
Land Use Conflicts ◽  
Wind Energy Development

The interest in harnessing wind energy keeps increasing globally. Iceland is considering building its first wind farms, but its landscape and nature are not only a resource for renewable energy production; they are also the main attraction for tourists. As wind turbines affect how the landscape is perceived and experienced, it is foreseeable that the construction of wind farms in Iceland will create land use conflicts between the energy sector and the tourism industry. This study sheds light on the impacts of wind farms on nature-based tourism as perceived by the tourism industry. Based on 47 semi-structured interviews with tourism service providers, it revealed that the impacts were perceived as mostly negative, since wind farms decrease the quality of the natural landscape. Furthermore, the study identified that the tourism industry considered the following as key factors for selecting suitable wind farm sites: the visibility of wind turbines, the number of tourists and tourist attractions in the area, the area’s degree of naturalness and the local need for energy. The research highlights the importance of analysing the various stakeholders’ opinions with the aim of mitigating land use conflicts and socioeconomic issues related to wind energy development.

Operation and approximation based on the history of failure modes recorded by SCADA system of Amougdoul Moroccan wind farm using FMECA maintenance model

2021 ◽  
pp. 0309524X2199245
Author(s):  
Kawtar Lamhour ◽  
Abdeslam Tizliouine
Keyword(s):  
Wind Turbines ◽  
Wind Farm ◽  
Failure Modes ◽  
Wind Farms ◽  
Scada System ◽  
History Of ◽  
Criticality Analysis ◽  
Maintenance Model ◽  
Reliability And Availability ◽  
Critical Subsystems

The wind industry is trying to find tools to accurately predict and know the reliability and availability of newly installed wind turbines. Failure modes, effects and criticality analysis (FMECA) is a technique used to determine critical subsystems, causes and consequences of wind turbines. FMECA has been widely used by manufacturers of wind turbine assemblies to analyze, evaluate and prioritize potential/known failure modes. However, its actual implementation in wind farms has some limitations. This paper aims to determine the most critical subsystems, causes and consequences of the wind turbines of the Moroccan wind farm of Amougdoul during the years 2010–2019 by applying the maintenance model (FMECA), which is an analysis of failure modes, effects and criticality based on a history of failure modes occurred by the SCADA system and proposing solutions and recommendations.

scholarly journals A new multi-scale backbone network for object detection based on asymmetric convolutions

2021 ◽  
Vol 104 (2) ◽  
pp. 003685042110113
Author(s):  
Xianghua Ma ◽  
Zhenkun Yang
Keyword(s):  
Object Detection ◽  
Image Features ◽  
Detection Accuracy ◽  
Mobile Platforms ◽  
Multi Scale ◽  
Backbone Network ◽  
Aspect Ratios ◽  
Pascal Voc ◽  
Scale Characteristics ◽  
Detection Speed

Real-time object detection on mobile platforms is a crucial but challenging computer vision task. However, it is widely recognized that although the lightweight object detectors have a high detection speed, the detection accuracy is relatively low. In order to improve detecting accuracy, it is beneficial to extract complete multi-scale image features in visual cognitive tasks. Asymmetric convolutions have a useful quality, that is, they have different aspect ratios, which can be used to exact image features of objects, especially objects with multi-scale characteristics. In this paper, we exploit three different asymmetric convolutions in parallel and propose a new multi-scale asymmetric convolution unit, namely MAC block to enhance multi-scale representation ability of CNNs. In addition, MAC block can adaptively merge the features with different scales by allocating learnable weighted parameters to three different asymmetric convolution branches. The proposed MAC blocks can be inserted into the state-of-the-art backbone such as ResNet-50 to form a new multi-scale backbone network of object detectors. To evaluate the performance of MAC block, we conduct experiments on CIFAR-100, PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO 2014 datasets. Experimental results show that the detection precision can be greatly improved while a fast detection speed is guaranteed as well.

Sign in / Sign up

Export Citation Format

Share Document