Non-intrusive optical measurements of gas turbine engine inlet condensation using machine learning

Abstract

We demonstrate a novel application of supervised machine learning (ML) models to quantify the size, shape, number density, and distribution parameters of a water spray introduced at a gas turbine inlet. Only a limited set of laser scattering and extinction observations, acquired by pairs of photodetectors and cameras, are required for an accurate output. A phase Doppler particle analyzer as well as a conventional extinction inversion method are used to validate the particle size estimation, with the ML method converging closely to both. By measuring a water spray, where a spherical particle shape can be assumed, these size estimate validations could be made, which would have been difficult for a nonspherical particle measurement. By combining all the estimated parameters, the liquid volume fraction as well as the liquid flow rate is estimated and compared to a traceable ultrasonic flowmeter. To our knowledge, this is the first in situ condensation load measurement made at a gas turbine inlet without prior calibration. The ML approach is able to accurately estimate the liquid flow rate, with the majority of the estimates lying within the uncertainty bounds of the flowmeter and a root-mean-square difference of 0.8 L h−1 or 7.4%. Estimating the liquid flow rate using all the particle parameters demonstrates the method’s robustness and readiness for accurately measuring even nonspherical particles. The low number of required optical observations also makes this technique attractive for more generalized inlet particle measurements including sand, dust, and volcanic ash, in addition to condensation.

Particle characterization using optical measurements and neural networks

“…The two wavelengths used for the extinction measurements are to maximize the spectral band, or the range between the two wavelengths. For multi-wavelength extinction measurements, having a narrow spectral band (such as using lasers limited from near-UV to near-IR) places limits on particle size estimation [20,[36][37][38][39]. The use of the 10 330 nm IR laser expands the spectral band, which reduces ambiguities and allows to measure larger particles accurately.…”

“…The use of the 10 330 nm IR laser expands the spectral band, which reduces ambiguities and allows to measure larger particles accurately. A more detailed reasoning behind the choice of the extinction laser wavelengths can be found in the authors' previous work on utilizing multi-wavelength extinction [20].…”

“…The scattering and extinction library was previously used for a gas turbine inlet condensation sensor [20]. The numerical tools and the general structure of the library are similar, while the particle parameters, such as the size range and the material refractive indices are changed to accommodate for sand particles.…”

“…The numerical tools and the general structure of the library are similar, while the particle parameters, such as the size range and the material refractive indices are changed to accommodate for sand particles. A brief explanation of the library and its composition are presented below, but a full description can be found in the cited source [20].…”

“…Based on three scattering observations, the equivalent volume sphere radius of particles found in an external scattering database, as well as simulated nonspherical particles were accurately estimated using three distinct observations [19]. Subsequently, the authors made the first in situ condensation load measurement at a gas turbine inlet without a prior calibration using supervised machine learning models and scattering and extinction measurements as the input [20]. In this presented work, a generalized neural network replaces layers of supervised machine learning models used in our previous efforts.…”