Contrôle acoustique d'un parc éolien

Baldwin Dumortier 1
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Currently, acoustic studies are required to set wind farms up. They must ensure the tranquility of the inhabitants around the farms in accordance with current regulations. For this purpose, acoustic measurements are made during a couple of weeks. When measuring, the wind turbines are periodically stopped in order to evaluate the difference between ambient noise levels (with the turbines on) and residual noise levels (with the turbines off). A curtailment plan is then computed and sent to the wind farm owner in order to set it up in the local turbine control system (SCADA). Currently, the curtailment plan roughly depends on the weather conditions and the time of the day which are allegedly correlated to the acoustic variables. In practice, it frequently leads to violations of the acoustic constraints or electrical power loss. This is because the acoustic conditions constantly and strongly evolve over time: the wind turbine noise level finely depends on the weather conditions and the residual noise level depends on all the other acoustic sources and has therefore a stochastic nature. The goal of the thesis is to design a principled real-time control algorithm for wind farms. To do so, we investigate the use of a black-box source separation system that estimates the residual noise level and the wind turbine noise level. We first provide a theoretical formulation of the problem by accounting for specific practical issues, by defining the variables of the problem and by binding these issues to the state of the art. Then, we propose two complete control solutions and run an experimental evaluation. The first solution is a deterministic algorithm based on a constrained combinatorial optimization algorithm, which is inspired by the current approach for controlling wind farms while exploiting the source separation system. Moreover, we present a study of its ability to fulfill the French acoustic constraints that are computed as temporal medians of the acoustic variables. The second solution is stochastic and based on a state-space model defined by means of Gaussian uncertainties. It features a nonlinear Kalman filter in order to fuse the uncertainties of the model and of the source separation system, an Expectation-Maximization algorithm that computes the uncertainties for a specific farm, and a robust variant of the deterministic algorithm that takes the estimated uncertainties into account when computing the optimal command
Complete list of metadatas

Cited literature [1 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01897853
Contributor : Abes Star <>
Submitted on : Wednesday, October 17, 2018 - 4:29:05 PM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Long-term archiving on : Friday, January 18, 2019 - 3:07:46 PM

File

DDOC_T_2018_0131_DUMORTIER.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01897853, version 1

Citation

Baldwin Dumortier. Contrôle acoustique d'un parc éolien. Systèmes et contrôle [cs.SY]. Université de Lorraine, 2018. Français. ⟨NNT : 2018LORR0131⟩. ⟨tel-01897853⟩

Share

Metrics

Record views

215

Files downloads

159