Search

Today, power generation from clean and renewable resources such as wind and solar is of great salience. Smart grid technology efficiently responds to the increasing demand for electric power. Intelligent monitoring, control, and maintenance of wind energy facilities are indispensable to increase the performance and efficiency of smart grids (SGs). Integration of state-of-the-art machine learning algorithms and vision sensor networks approaches pave the way toward enhancing the wind farms performance. The generating power in a wind turbine farm is the most critical parameter that should be measured accurately. Produced power is highly related to weather patterns, and a new farm in a near area is also likely to have similar energy generation. Therefore, accurate and perpetual prediction models of the existing wind farms can be led to develop new stations with lower costs. The paper aims to estimate the angular velocity of turbine blades using vision sensors and signal processing. The high wind in the wind farm can cause the camera to vibrate in successive frames, and the noise in the input images can also strengthen the problem. Thanks to couples of solid computer vision algorithms, including FAST (Features from Accelerated Segment Test), SIFT (Scale-Invariant Feature Transform), SURF (Speeded Up Robust Features), BF (Brute-Force), FLANN (Fast Library for Approximate Nearest Neighbors), AE (Autoencoder), and SVM (support vector machines), this paper accurately localizes the Hub and track the presence of the Blade in consecutive frames of a video stream. The simulation results show that determining the hub location and the blade presence in sequential frames results in an accurate estimation of wind turbine angular velocity with 95.36% accuracy. (C) 2021 The Authors. Published by Elsevier Ltd.

Wind Turbine Towers (WTTs) are the main structures of wind farms. They are costly devices that must be thoroughly inspected according to maintenance plans. Today, existence of machine vision techniques along with unmanned aerial vehicles (UAVs) enable fast, easy, and intelligent visual inspection of the structures. Our work is aimed towards developing a vision-based system to perform Nondestructive tests (NDTs) for wind turbines using UAVs. In order to navigate the flying machine toward the wind turbine tower and reliably land on it, the exact position of the wind turbine and its tower must be detected. We employ several strong computer vision approaches such as Scale-Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), Features from Accelerated Segment Test (FAST), Brute-Force, Fast Library for Approximate Nearest Neighbors (FLANN) to detect the WTT. Then, in order to increase the reliability of the system, we apply the ResNet, MobileNet, ShuffleNet, EffNet, and SqueezeNet pre-trained classifiers in order to verify whether a detected object is indeed a turbine tower or not. This intelligent monitoring system has auto navigation ability and can be used for future goals including intelligent fault diagnosis and maintenance purposes. The simulation results show the accuracy of the proposed model are 89.4% in WTT detection and 97.74% in verification (classification) problems.

Diamond Hot-end is a flexible and versatile technology, as it combines multiple colorful filaments in one outend, exploiting the simplicity of a single extrusion 3D printer. The color gamut provided is given by the blending of different filaments in the nozzle tip. However, this technology has several drawbacks: it needs a transition time to be able to move from one color to another one. This produces complications during printing that can be overcome with the aid of a purge tower next to the object to print, where the nozzle can exhaust the old filament and start the new one. Another problem is the accuracy of the details: the system works with multiple extrusion drivers and slight differences in their feeding forces might incur uncontrolled gradients of pressures and artifacts during printing, as result. This generates a hatch that is not overall consistent. However, this can be seen as an advantage when the purpose is the representation of paintings and art. In this paper, we present a workflow with the aim to produce fast impressions of paintings without the use of the purge tower. We use a color-based segmentation of a pre-defined image to create an operational dataset of mixing ratios sorted by the minimum distance on the available color gamut. Moreover, we implement a tool path based on two different algorithms to improve the printing process and avoid most of the artifacts while switching colors. In this way, the historical constraint for multi-color fused filament fabrication of a color transition among different hues is exploited and the use of the purge tower can be avoided with a tradeoff between artifacts and printing time.

Realistic appearance reproduction is of great importancein 3D printing’s applications. Halftoning as a necessary processin printing has a great impact on creating visually pleasantappearance. In this article, we study the aspects of adapting andapplying Iterative Method Controlling Dot Placement (IMCDP)to halftone three-dimensional surfaces. Our main goal is toextend the 2D algorithm to a 3D halftoning approach with minormodifications. The results show high-quality reproduction for allgray tones. The 3D halftoning algorithm is not only free ofundesirable artifacts, it also produces fully symmetric and wellformedhalftone structures even in highlight and shadow regions.

As 3D printing is becoming increasingly popular, thedemand for high quality surface reproduction is also increasing.Like in 2D printing, halftoning plays an important role in thequality of the surface reproduction. Developing advanced 3Dhalftoning methods for 3D printing and adapting them to thestructure of the surface is therefore essential for improvingsurface reproduction quality. In this paper, an extension of aniterative 2D halftoning method to 3D is used to apply differenthalftone structures on 3D surfaces. The results show that usingdifferent halftones based on the 3D geometrical structure of thesurface and/or the viewing angle in combination with the structure of the texture being mapped on the surface canpotentially improve the quality of the appearance of 3D surfaces.