No abstract

Nowadays, the energy sector is experiencing a profound transition. Among all renewable energy sources, wind energy is the most developed technology across the world. To ensure the profitability of wind turbines, it is essential to develop predictive maintenance strategies that will optimize energy production while preventing unexpected downtimes. With the huge amount of data collected every day, machine learning is seen as a key enabling approach for predictive maintenance of wind turbines. However, most of the effort is put into the optimization of the model architectures and its parameters, whereas data-related aspects are often neglected. The goal of this paper is to contribute to a better understanding of wind turbines through a data-centric machine learning methodology. In particular, we focus on the optimization of data preprocessing and feature selection steps of the machine learning pipeline. The proposed methodology is used to detect failures affecting five components on a wind farm composed of five turbines. Despite the simplicity of the used machine learning model (a decision tree), the methodology outperformed model-centric approach by improving the prediction of the remaining useful life of the wind farm, making it more reliable and contributing to the global efforts towards tackling climate change.

Abstract. In the case of stereolithography 3D printing technology, detaching formed model from the tank with photopolymer is a lengthy process. Forces, which appear during removing of solid photopolymer layerformed in stereolithography 3D DLP printer, can destroy the built model. In this article the detachment force is measured, obtained results arestatistically analyzed and relation between detach force, area of produced layer and thickness of the layer are verified. Linear dependence between detach force and built area is determined. On the other hand, relation between detach force and thickness of the layer is not confirmed.

This article describes a method of in-situ process monitoring in the digital light processing (DLP) 3D printer. It is based on the continuous measurement of the adhesion force between printing surface and bottom of a liquid resin bath. This method is suitable only for the bottom-up DPL printers. Control system compares the force at the moment of unsticking of printed layer from the bottom of the tank, when it has the largest value in printing cycle, with theoretical value. Implementation of suggested algorithm can make detection of faults during the printing process possible.

Abstract. Polymers that solidify under light radiation are commonly used in digital light processing (DLP) 3D printing. A wide range of photopolymers use photoinitiators that react to radiation in range of ultraviolet (UV) wavelength. In the present study we provided measurement of radiant fluence in the UV wavelength range from 280 nm to 400 nm for two data projectors and compared effect of radiation on quality of 3D printing. One projector is commonly used DLP projector with high energy lamp. Second one is an industrial projector, in which RGB light emitting diodes (LEDs) are replaced by UV LEDs with wattage at the level of 3.6 % of the first one. Achieved data confirmed uneven distribution of radiant energy on illuminated area. These results validate, that undesired heating light causes internal stress inside built models that causes defects in final products.