•The Bayesian Ascent algorithm can monotonically increase the total wind farm power.•The cooperative control strategy can further increase the total wind farm power.•The decentralized wind farm ...control approach can reduce the required iterations.•A data-driven, cooperative wind farm control approach is a promising alternative.
This study investigates the feasibility of using a data-driven optimization approach to determine the coordinated control actions of wind turbines that maximize the total wind farm power production. Conventionally, for a given wind condition, an individual wind turbine maximizes its own power production without taking into consideration the conditions of other wind turbines. Under this greedy control strategy, the wake formed by the upstream wind turbine, resulting in reduced wind speed and increased turbulence intensity inside the wake, would affect and lower the power productions of the downstream wind turbines. To increase the overall wind farm power production, cooperative wind turbine control approaches have been proposed to coordinate the control actions that mitigate the wake interference among the wind turbines and would thus increase the total wind farm power production. This study explores the use of a data-driven approach to identify the optimum coordinated control actions of the wind turbines using limited amount of data. Specifically, we study the feasibility of the Bayesian Ascent (BA) algorithm, a probabilistic optimization algorithm based on non-parametric Gaussian Process regression technique, for the wind farm power maximization problem. The BA algorithm is employed to maximize an analytical wind farm power function that is constructed based on wind farm configurations and wind conditions. The results show that the BA algorithm can achieve a monotonic increase in the total wind farm power production using a small number of function evaluations and has the potentials to be used for real-time wind farm control.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
•The continuous wake model describes well the wake profile behind a wind turbine.•The wind farm power function describes well the power production of a wind farm.•Cooperative control increases the ...wind farm power efficiency by 7.3% in average.•SCP can be employed to efficiently optimize the control actions of wind turbines.
This paper describes the use of a cooperative wind farm control approach to improve the power production of a wind farm. The power production by a downstream wind turbine can decrease significantly due to reduced wind speed caused by the upstream wind turbines, thereby lowering the overall wind farm power production efficiency. In spite of the interactions among the wind turbines, the conventional (greedy) wind turbine control strategy tries to maximize the power of each individual wind turbine by controlling its yaw angle, its blade pitch angle and its generator torque. To maximize the overall wind farm power production while taking the wake interference into account, this study employs a cooperative control strategy. We first derive the wind farm power as a differentiable function of the control actions for the wind turbines in a wind farm. The wind farm power function is then maximized using sequential convex programming (SCP) to determine the optimum coordinated control actions for the wind turbines. Using an example wind farm site and available wind data, we show how the cooperative control strategy improves the power production of the wind farm.
Full text
Available for:
GEOZS, IMTLJ, KILJ, KISLJ, NUK, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
This paper describes a data-driven approach for real-time control of a physical system. Specifically, this paper focuses on the cooperative wind farm control where the objective is to maximize the ...total wind farm power production by using control actions as an input and measured power as an output. For real time, data-driven wind farm control, it is imperative that the optimization algorithm is able to improve a target wind farm power production by executing as small number of trial actions as possible using the wind farm power monitoring data. To achieve this goal, we develop a Bayesian ascent (BA) algorithm by incorporating into the Bayesian optimization framework a strategy that regulates the search domain, as used in the trust region method. The BA algorithm is composed of two iterative phases, namely, learning and optimization phases. In the learning phase, the BA algorithm approximates the target function using Gaussian process regression to fit the measured input and output of the target system. In the optimization phase, the BA algorithm determines the next sampling point to learn more about the target function (exploration) as well as to improve the target value (exploitation). Specifically, the sampling strategy is designed to ensure that the input is selected within a trust region to improve the target value monotonically by gradually changing the input for a target system. The results from simulation studies using an analytical wind farm power function and experimental studies using scaled wind turbines show that the BA algorithm can achieve an almost monotonic increase in the target value.
Quality control is a fundamental component of many manufacturing processes, especially those involving casting or welding. However, manual quality control procedures are often time-consuming and ...error-prone. In order to meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. Recently, Convolutional Neural Networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this article, a system is proposed for the identification of casting defects in X-ray images, based on the Mask Region-based CNN architecture. The proposed defect detection system simultaneously performs defect detection and segmentation on input images, making it suitable for a range of defect detection tasks. It is shown that training the network to simultaneously perform defect detection and defect instance segmentation results in a higher defect detection accuracy than training on defect detection alone. Transfer learning is leveraged to reduce the training data demands and increase the prediction accuracy of the trained model. More specifically, the model is first trained with two large, openly available image datasets before fine-tuning on a relatively small metal casting X-ray dataset. The accuracy of the trained model exceeds the state-of-the art performance of the Grupo de Inteligencia de Máquina database of X-ray images (GDXray) Castings dataset and is fast enough to be used in a production setting. The system also performs well on the GDXray Welds dataset. A number of in-depth studies are conducted to explore how transfer learning, multitask learning, and multi-class learning influence the performance of the trained system.
•Design and prototype implementation of a fault-tolerant SHM system.•Various sensor faults can be detected autonomously.•Analytical redundancy for detecting and isolating sensor faults in real ...time.•Fully decentralized approach, as opposed to traditional strategies.•Laboratory experiments for validating the prototype SHM system.
One of the most critical issues when deploying wireless sensor networks for long-term structural health monitoring (SHM) is the correct and reliable operation of sensors. Sensor faults may reduce the quality of monitoring and, if remaining undetected, might cause significant economic loss due to inaccurate or missing sensor data required for structural assessment and life-cycle management of the monitored structure. This paper presents a fully decentralized approach towards autonomous sensor fault detection and isolation in wireless SHM systems. Instead of physically installing multiple redundant sensors in the monitored structure (“physical redundancy”), which would involve substantial penalties in cost and maintainability, the information inherent in the SHM system is used for fault detection and isolation (“analytical redundancy”). Unlike traditional centralized approaches, the analytical redundancy approach is implemented distributively: Partial models of the wireless SHM system, implemented in terms of artificial neural networks in an object-oriented fashion, are embedded into the wireless sensor nodes deployed for monitoring. In this paper, the design and the prototype implementation of a wireless SHM system capable of autonomously detecting and isolating various types of sensor faults are shown. In laboratory experiments, the prototype SHM system is validated by injecting faults into the wireless sensor nodes while being deployed on a test structure. The paper concludes with a discussion of the results and an outlook on possible future research directions.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
The intensity of many natural hazards, such as hurricanes, floods, tornadoes, etc., are increasing as a consequence of climate change. This increase in intensity coupled with the increase in ...population density, particularly along the coasts, is only magnifying the impact of such events. In order to quantify and mitigate the risk due to the hazards and to prepare for the potential impacts in a region, it is necessary to collect the information of existing buildings that are pertinent to natural hazard analysis and risk management. Gathering the building information in a region- or city-scale is a laborious and expensive undertaking. This paper presents a framework for regional scale building information generation/gathering to support regional hazard analysis. In this framework, different types of data are acquired from multiple sources (satellite and street view images, property tax assessment data, etc.) and are fused to semantically profile each building in a city. Specifically, deep learning technique is employed to extract building information from street or satellite images. A novel data mining tool is developed to overcome the data scarcity issue, quantify the uncertainty and enrich the data repository. With this framework, building inventories of cities are created to provide the data needed for disaster and risk management planning and simulations.
•A novel city-scale building information modeling framework is created for the first time•The framework can fuse and enhance heterogeneous data using neural networks•Convolutional neural networks (ConvNets) are trained to extract building information from satellite or street view images•Spatial patterns and variations of regional building information are discovered using neural networks•To show its capability of large-scale natural hazard risk management, we demonstrate the workflow using a hurricane scenario
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
AbstractSatellite and street view images are widely used in various disciplines as a source of information for understanding the built environment. In natural hazard engineering, high-quality ...building inventory data sets are crucial for the simulation of hazard impacts and for supporting decision-making. Screening the building stocks to gather the information for simulation and to detect potential structural defects that are vulnerable to natural hazards is a time-consuming and labor-intensive task. This paper presents an automated method for extracting building information through the use of satellite and street view images. The method is built upon a novel transformer-based deep neural network we developed. Specifically, a multidomain learning approach is employed to develop a single compact model for multiple image-based deep learning information extraction tasks using multiple data sources (e.g., satellite and street view images). Our multidomain Vision Transformer is designed as a unified architecture that can be effectively deployed for multiple classification tasks. The effectiveness of the proposed approach is demonstrated in a case study in which we use pretrained models to collect regional-scale building information that is related to natural hazard risks.
To address the grand challenges brought about by urbanization, “smart city” has become a ubiquitous concept for sustaining urban and economic growthwhile addressing the environmental and social ...issues created by that growth. While numerous articles and reports have been written about smart cities, a universal definition of what constitutes a smart city has yet to emerge with widespread consensus. A common theme to most definitions is the utilization of information and communication technologies (ICT) as an enabler to support city development, enhance urban services, and increase stakeholder access to information. Using this theme as a defining element, smart cities are quickly emerging around the world with city-wide investments in ICT to drive technological innovation, to support the development of new industries, to spur a stronger economy, to maintain a sustainable environment, and to enhance the quality of life of citizens.
In high seismic risk regions, it is important for city managers and decision makers to create programs to mitigate the risk for buildings. For large cities and regions, a mitigation program relies on ...accurate information of building stocks, that is, a database of all buildings in the area and their potential structural defects, making them vulnerable to strong ground shaking. Structural defects and vulnerabilities could manifest via the building's appearance. One such example is the soft‐story building—its vertical irregularity is often observable from the facade. This structural type can lead to severe damage or even collapse during moderate or severe earthquakes. Therefore, it is critical to screen large building stock to find these buildings and retrofit them. However, it is usually time‐consuming to screen soft‐story structures by conventional methods. To tackle this issue, we used full image classification to screen them out from street view images in our previous study. However, full image classification has difficulties locating buildings in an image, which leads to unreliable predictions. In this paper, we developed an automated pipeline in which we segment street view images to identify soft‐story buildings. However, annotated data for this purpose is scarce. To tackle this issue, we compiled a dataset of street view images and present a strategy for annotating these images in a semi‐automatic way. The annotated dataset is then used to train an instance segmentation model that can be used to detect all soft‐story buildings from unseen images.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK