AI Article Synopsis

  • The increasing power of wind turbines is aimed at lowering wind energy costs during the transition from fossil fuels to renewable sources.
  • To develop critical components like the wind turbine's main gearbox, it's essential to test the drivetrain under the actual loads it will face.
  • A new methodology using strain gauges and accelerometers has been created to accurately compute gearbox input loads in multiple directions, showing potential for effective drivetrain testing.

Article Abstract

As wind energy is paving the way for the energy transition from fossil to renewable energy sources, the ongoing trend of increasing the rated power of wind turbines aims to reduce the overall cost of wind energy. The resulting increase in drivetrain loads motivates the need for wind turbine (WT) drivetrain testing in the development phase of critical components such as the WT main gearbox (GB). While several WT system test benches allow for the application of emulated rotor loads in six degrees of freedom (6-DOF), the drivetrain input loads can significantly differ from the GB 6-DOF input loads due to the design of the drivetrain under test. However, currently available load measurement solutions are not capable of sensing GB input loads in 6-DOF. Thus, this work aims to develop a methodology for converging signals from a purposely designed sensor setup and turbine specific design parameters to compute the GB 6-DOF input loads during WT testing. Strain gauges (SG) and accelerometers have been installed on the low-speed shaft (LSS) of a WT drivetrain under test at the 4MW WT system test bench at the Center for Wind Power Drives. Using the data of the aforementioned sensors, a methodology for computing the GB input loads is developed. The methodology is validated through comparison to the applied loads data provided by the aforementioned test bench. The results demonstrate the high promise of the proposed method for estimating the GB input loads during WT drivetrain testing.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9964197PMC
http://dx.doi.org/10.3390/s23041824DOI Listing

Publication Analysis

Top Keywords

input loads
28
drivetrain testing
12
loads
10
wind turbine
8
loads drivetrain
8
wind energy
8
system test
8
6-dof input
8
drivetrain test
8
test bench
8

Similar Publications

In this paper, we introduce FUSION-ANN, a novel artificial neural network (ANN) designed for acoustic emission (AE) signal classification. FUSION-ANN comprises four distinct ANN branches, each housing an independent multilayer perceptron. We extract denoised features of speech recognition such as linear predictive coding, Mel-frequency cepstral coefficient, and gammatone cepstral coefficient to represent AE signals.

View Article and Find Full Text PDF

Data on full stationary wave-field measurement of a suspended steel plate punctually loaded.

Data Brief

February 2025

Institut Camille Jordan, UMR-CNRS 5208, École Centrale de Lyon, 36 Avenue Guy de Collongue, 69134, Écully, France.

The dataset presented contains the experimental structural response, in the frequency domain, of a suspended steel plate to a point force excitation. The plate is excited by a mechanical point force generated by a Brüel & kJær shaker with a white noise signal input from 3.125 Hz to 2000 Hz.

View Article and Find Full Text PDF

Fatigue failure poses a serious challenge for ensuring the operational safety of critical components subjected to cyclic/random loading. In this context, various machine learning (ML) models have been increasingly explored, due to their effectiveness in analyzing the relationship between fatigue life and multiple influencing factors. Nevertheless, existing ML models hinge heavily on numeric features as inputs, which encapsulate limited information on the fatigue failure process of interest.

View Article and Find Full Text PDF
Article Synopsis
  • The study focused on creating and testing Cobalt-doped zinc oxide nanoparticles as a photocatalyst for degrading the antibiotic ciprofloxacin (CIPF) under visible LED light.
  • It was found that 10% Cobalt-doped ZnO nanoparticles were the most effective, achieving over 99% degradation of CIPF in just 90 minutes, and maintained their efficiency across three cycles of use.
  • The research also optimized the conditions for maximum degradation efficiency using statistical methods and simulated data using Artificial Neural Networks, achieving a strong correlation for the model’s accuracy.
View Article and Find Full Text PDF

Hearing loss is highly related to acoustic injuries and mechanical damage of ear tissues. The mechanical responses of ear tissues are difficult to measure experimentally, especially cochlear hair cells within the organ of Corti (OC) at microscale. Finite element (FE) modeling has become an important tool for simulating acoustic wave transmission and studying cochlear mechanics.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!