AI Case Study
Rice University researchers improve on the state-of-the-art for wind turbine icing detection with a CNN
Researchers from Rice University and other institutes develop an improved system for detecting icing on wind turbine blades which can affect performance and power generation. The CNN classification system, combined with anomaly detection, outperforming the state-of-the-art on real-world data.
The researchers investigate whether it was possible to analyse "only the signals from the standard pre-installed sensors (eg., from SCADA) in the wind turbine in an attempt to design a deployable system for blade icing detection. Wind farms usually locate in remote mountainous or rough sea regions, which makes monitoring and maintenance more challenging. A fault detection system will help to avoid premature breakdown, to reduce maintenance cost, and to support for further development of a wind turbine"
From the research paper: "many wind farms are located in areas with a high probability of ice occurrence. Blade icing may cause serious problems, such as measurement errors, power losses, overproduction, mechanical failures, and electrical failures. As a consequence, icing detection becomes a priority in order to avoid such problems".
"Experimental results show that WaveletFCNN outperforms the original FCNN not only for this frozen blade monitoring application but also for extensive applications from the UCR time series archive. The anomaly monitoring algorithm is also verified by the simulated real time setup and shows promising results. We plan to deploy this prototyped system in real-world wind farms in the near future."
"In a nutshell, we first compute the discrete wavelet coefficients of the input signal to a specific level, which can be viewed as a hyper-parameter of WaveletFCNN, according to the famous pyramid algorithm; then we put the original signal and the detail coefficients at each level into separated sub convolutional neural networks in order to capture the knowledge embedded in different scales from the wavelet spectrum; lastly, the global pooling outputs from each sub network are concatenated for generating the final classification outcomes. In order to generate accurate and robust anomaly detection in real time, we propose an algorithm that use sliding window and majority vote. The trained classifier will provide a prediction for the sequence within the active window. Each time the active window moves, a prediction will be made, so that all the blocks except the first block in the last active window will get a new prediction".
Data from Goldwind Inc., the world's largest wind turbine manufacturer: "Three wind turbines’ monitoring data are obtained, which represents the running time of Machine 1 for 305.77 hours, Machine 2 for 695.59 hours and Machine 3 for 329.28 hours. The raw data is collected from the supervisory control and data
acquisition (SCADA) system which includes hundreds of dimensions. According to the engineers’ domain-specific knowledge, 28 continuous variables relevant to frozen blades are preserved as the input multivariate signals