A fibre optic and machine learning based health monitoring system for superconducting power applications in modern supergrids

The concerns for climate change and the transition to renewables is increasing the relevance of superconducting applications: High Temperature Superconductor (HTS) cables for efficient power transmission, superconducting magnets for nuclear fusion, superconducting fault current limiters (SFCLs) for HVDC grid protection and superconducting compact generators for wind turbines, to name a few. However, to tap into the full potential of HTS applications, the main problem of hotspots needs to be addressed. Hotspots are localized points of heating, which can arise in HTS devices mainly due to the intrinsic inhomogeneity of critical current along the superconductor length. The motivation behind this thesis, was to develop a health monitoring technique for a SFCL device under the European union project FastGrid. This device required a fast hotspot detection time of 10 ms in order to timely open the DC breaker in order to protect the device. During the course of this thesis an extremely fast and economical optical fibre sensing based hotspot detection technique has been developed and patented. The technique uses the Mach-Zehnder Interferometer (MZI) and is an efficient and economical way to detect hotspots in HTS applications. Due to the MZI sensitivity being a composite of strain sensitive and temperature sensitive contributions, the MZI gives an instantaneous response to a hotspot (within 10 ms), because of the quick strain transfer to the optical fibre. The research carried out under this thesis has involved experimentation on HTS tapes (10 cm to 1 m in length). The technique has also been integrated and tested with a SFCL pancake prototype with long lengths of conductor (12 m and 17 m). The thesis has also focused on finite element modelling to better understand the MZI sensitivity. The experimentation and modelling together, has enabled a better understanding of the MZI response to hotspots and the challenges of using MZI for HTS health monitoring. Due to the extremely high sensitivity of the MZI , the MZI output signal can also manifest the environmental noise caused by mechanical vibrations, bubbling in the cryostat and temperature variations, along with the response to heating in the sample. This presents the problems of false alarms and indiscernible response to hotspots. The work done for this thesis has also focused substantially on finding a suitable data analysis technique to supplement the MZI method. A discrete wavelet transform (DWT) based feature extraction together with a machine learning based classification for reliable quench detection has been developed in the course of this work with very encouraging results . This is an important development for the MZI technique as it significantly impacts and improves the MZI reliability and practicality for HTS applications. Additionally, this is also of substantial importance to the progress of HTS applications in the industry, especially the power sector which continues to evolve with the shift towards renewables and will rely more on HTS applications like SFCLs and HTS cables. With a reliable hotspot detection technique like the MZI, we can facilitate mass adoption of such HTS applications.

Optical fibre based quench detection in HTS applications using machine learning classifiers

Arooj Akbar, Bertrand Dutoit, Nicolò Riva

A Mach-Zehnder Interferometer (MZI) based optical fibre sensing technique, developed and patented by EPFL, is an efficient and economical way to detect hotspots in High Temperature Superconductor (HTS) applications. Due to the MZI sensitivity being a composite of strain sensitive and temperature sensitive contributions, the MZI gives an instantaneous response to a quench (within 10 ms), because of the quick strain transfer to the optical fibre. However, the MZI output signal also manifests the environmental noise caused by mechanical vibrations, bubbling in the cryostat and temperature variations, along with the response to the quench. This presents the problems of false alarms and indiscernible response to a quench. Discrete wavelet transform (DWT) has been proven to be a useful tool for feature extraction in different fields requiring signal categorization and hence holds the potential to enable quench recognition in the MZI output. This paper proposes an effective approach of performing DWT based feature extraction on experimental data and subsequently using the extracted features for the MZI response classification using two machine learning based classification techniques: k-nearest neighbours (KNN) and Artificial Neural Network (ANN). For this manuscript, experiments were performed using MZI for quench detection in an HTS tape. Feature extraction was then implemented on these experimental measurements using discrete wavelet coefficients extracted at different decomposition levels from the MZI output; these features were then used to train the KNN and ANN models for identifying quench in the MZI signal. This method could be a valuable supplement to the MZI technique by enabling the development of a real time application that can process the MZI output data as well as eliminate the occurrences of false alarms; thereby facilitating reliable quench detection. With this development, the MZI technique would become an even more attractive solution for the health monitoring of HTS applications.

2022

Fast Hotspot Detection in SFCLs by Exploiting Strain Response in Optical Fiber Sensing

Arooj Akbar, Bertrand Dutoit, Nicolò Riva, Luc Thévenaz, Zhisheng Yang

Superconducting fault current limiters (SFCLs) can be used to limit fault currents in both meshed DC and AC grids by transitioning from superconducting to resistive state, in the presence of high currents. While the device is theoretically a great way to protect grids, the inherent inhomogeneity of critical current along the superconductor length can lead to localized heating, called hotspots, and ultimately destruction of the SFCL device. At EPFL under the European Union project Fastgrid, an extremely efficient Mach-Zehnder interferometer (MZI) based optical fiber sensing technique has been developed and patented that can detect even singular hotspots within 15 ms to protect SFCLs. The MZI response is characterized by a strain sensitive as well as a temperature sensitive contribution. This paper outlines an investigation by means of FEM modeling into the response sensitivity. A 2-D thermal model of the superconducting tape and optical fiber was made to study thermal transfer to the optical fiber from the REBCO tape. The simulation results showed that temperature rise observed in the optical fiber is slower than the MZI response time, proving a strain sensitive response in the experiment measurements. Sound mechanical coupling between the optical fiber and the superconductor tape can enhance strain transfer to the optical fiber and hence reduce hotspot detection time. With this improved performance, the health monitoring for SFCLs can be much more efficient and reliable.

2021

Quench behavior of high-temperature superconductor tapes for power applications: a strategy toward resilience

Nicolò Riva

High-Temperature Superconductors (HTS) can be superconducting in liquid nitrogen 77 K, holding immense promises for our future. They can enable disruptive technologies such as nuclear fusion, lossless power transmission, cancer treatment devices, and technologies for future transportation. In the past years, the numerical models to describe the electrical resistivity of REBCO commercial tapes for devices working near and above the critical current, have been shown to be not accurate or very empirical. The resistivity in this regime, in fact, is not very well known. The lack of this knowledge is a significant issue in developing quality simulation tools. The major challenge in retrieving such properties lies in the fact that when I>Ic, heating effects, and thermal instabilities can quickly destroy the conductor if nothing is done to protect it. Moreover, due to the current sharing between the layers, it is difficult to know the amount of current carried by the superconducting layer and its resistivity. The present work aims to understand better the overcritical current regime combining ultra-fast pulsed current measurements performed on HTS REBCO based coated conductors with Finite Element Modeling. The experimental activities were carried out mostly at EPFL and in part at PM and KIT. The modeling activities were carried out between EPFL and KIT. The major result is a resistivity relationship describing the overcritical current regime to be used in numerical simulations of REBCO tapes. The first part of the thesis illustrates a post-processing method based on the so-called Uniform Current (UC) model to estimate the REBCO material's resistivity in the overcritical from experimental measurements. Pulsed current measurements as short as 15 us and with current magnitude up to 5 Ic were performed in liquid nitrogen bath 77 K on samples from various manufacturers, without damaging the tapes. The second part of the thesis discusses a post-processing method based on regularization of data to treat the experimental measurements extracted in the overcritical current regime. The output of this technique is a look-up table that can be shared with interested partners and used in numerical modeling afterward. The third part of the thesis presents the overcritical current model (rho-\eta\beta): a mathematical relationship of the overcritical current regime based on measurements performed between 77 K and 90 K and in self-field conditions. We compare such models with the power-law model, and we provide a short discussion of the fitting parameters and their typical values. The last part of the thesis discusses the overcritical current model, based on experimental measurements obtained as outlined above. The model was validated experimentally and used to show that for the case of a superconducting fault current limiter when the power-law model is used to model its electro-thermal response, the device quenches faster than with the overcritical model. In conclusion, this work can help optimize the use of superconductors and, consequently, the stabilizer. More interestingly, it opens the study of the overcritical current regime, a new exciting aspect of REBCO commercial tapes. This project has received funding from the Swiss Federal Office of Energy SFOE under grant agreement SI/500193-02.