Probabilistic Multi-Layer Perceptrons for Wind Farm Condition Monitoring

2024-04-25

arXiv.org

AI Summary

To address the need for SCADA data-driven condition monitoring in wind farms, this paper proposes a wind-farm-level monitoring system based on Probabilistic Multilayer Perceptrons (PMLPs). Methodologically, the approach integrates SCADA features across multiple turbines, models power output uncertainty via a heteroscedastic normal assumption, and—novelty—the first integration of deep probabilistic modeling with wind-farm-level transfer learning (fine-tuning) to enable cross-turbine knowledge sharing and operational-condition adaptation. Additionally, a CUSUM control chart criterion tailored to practical运维 requirements is designed for early anomaly detection. Experiments on real-world wind farm data demonstrate that the proposed system significantly outperforms existing probabilistic forecasting models: it maintains high-accuracy single-turbine power prediction while substantially improving anomaly detection sensitivity and robustness against varying operating conditions and sensor noise.

Technology Category

• Machine Learning: Probabilistic Circuits and Graphical Models
• Reasoning under Uncertainty: Relational Probabilistic Models
• Multiagent Systems: Multiagent Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Machine learning and data science for the Web
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

We provide a condition monitoring system for wind farms, based on normal behaviour modelling using a probabilistic multi-layer perceptron with transfer learning via fine-tuning. The model predicts the output power of the wind turbine under normal behaviour based on features retrieved from supervisory control and data acquisition (SCADA) systems. Its advantages are that (i) it can be trained with SCADA data of at least a few years, (ii) it can incorporate all SCADA data of all wind turbines in a wind farm as features, (iii) it assumes that the output power follows a normal density with heteroscedastic variance and (iv) it can predict the output of one wind turbine by borrowing strength from the data of all other wind turbines in a farm. Probabilistic guidelines for condition monitoring are given via a cumulative sum (CUSUM) control chart, which is specifically designed based on a real-data classification exercise and, hence, is adapted to the needs of a wind farm. We illustrate the performance of our model in a real SCADA data example which provides evidence that it outperforms other probabilistic prediction models.

Problem

• Monitor wind farm conditions effectively.
• Predict wind turbine power output.
• Enhance predictions using transfer learning.

Innovation

• Probabilistic Multi-Layer Perceptron
• Transfer Learning via Fine-Tuning
• CUSUM Control Chart for Monitoring