The Promise of Causal Reasoning in Reliable Decision Support for Wind Turbines

Chatterjee, Joyjit; Dethlefs, Nina

Abstract

The global pursuit towards sustainable development is leading to increased adaptation of renewable energy sources. Wind turbines are promising sources of clean energy, but regularly suffer from failures and down-times, primarily due to the complex environments and unpredictable conditions wherein they are deployed. While various studies have earlier utilised machine learning techniques for fault prediction in turbines, their black-box nature hampers explainabil-ity and trust in decision making. We propose the application of causal reasoning in operations & maintenance of wind turbines using Supervisory Control & Acquisition (SCADA) data, and harness attention-based convolutional neural networks (CNNs) to identify hidden associations between different parameters contributing to failures in the form of temporal causal graphs. By interpreting these non-obvious relationships (many of which may have potentially been disregarded as noise), engineers can plan ahead for unforeseen failures, helping make wind power sources more reliable.

Citation

Chatterjee, J., & Dethlefs, N. (2020, August). The Promise of Causal Reasoning in Reliable Decision Support for Wind Turbines. Paper presented at Fragile Earth: Data Science for a Sustainable Planet. KDD 2020, Virtual Conference

• Presentation Conference Type: Conference Paper (unpublished)
• Conference Name: Fragile Earth: Data Science for a Sustainable Planet. KDD 2020
• Start Date: Aug 24, 2020
• End Date: Aug 24, 2020
• Deposit Date: Jul 11, 2022
• Publicly Available Date: Aug 18, 2022
• Keywords: Wind energy; Explainable AI; Causal reasoning; Deep learning
• Public URL: https://hull-repository.worktribe.com/output/4028466
• Publisher URL: https://ai4good.org/what-we-do/fragile-earth/kdd-2020/
• Additional Information: Paper and recording can be accessed from the workshop website.