An advanced double-phase stacking ensemble technique with active learning classifier: Toward reliable disruption prediction in Aditya tokamak.

Disruptions in tokamak nuclear reactors, where plasma confinement is suddenly lost, pose a serious threat to the reactor and its components. Classifying discharges as disruptive or non-disruptive is crucial for effective plasma operation and advanced prediction. Traditional disruption identification systems often struggle with noise, variability, and limited adaptability. To address these challenges, we propose an enhanced stacking generalization model called the "Double-Phase Stacking Technique" integrated with Pool-based Active Learning (DPST-PAL) for designing a robust classifier with minimal labor cost. This innovative approach improves classification accuracy and reliability using advanced data analysis techniques. We trained the DPST-PAL model on 162 diagnostic shots from the Aditya dataset, achieving a high accuracy of 98% and an F1-score of 0.99, surpassing conventional methods. Subsequently, the deep 1D convolutional predictor model is implemented and trained using the classified shots obtained from the DPST-PAL model to validate the reliability of the dataset, which is tested on 47 distinct shots. This model accurately predicts the disruptions 7-13 ms in advance with 93.6% accuracy and exhibited no premature alarms or misclassifications for our experimental shots.

First results of fast visible imaging diagnostic in Aditya-U tokamak.

A Fast Visible Imaging Diagnostic (FVID) system, measuring the visible light emission spectrum (400-1000 nm) from tokamak plasma, has been installed on the Aditya-U tokamak to monitor the two-dimensional dynamics of the poloidal cross section of the plasma. In this work, we present the design and installation of the FVID system on the Aditya-U tokamak. The evolution of plasma and plasma-wall interactions is described. The signature of the runaway electron beam in visible imaging and its correlation with other diagnostics is presented. The estimation of the electron cyclotron resonance layer position during pre-ionization is also discussed in this work.

Nondestructive test of brazed cooling tubes of prototype bolometer camera housing using active infrared thermography.

The active infrared thermography technique is used for assessing the brazing quality of an actively cooled bolometer camera housing developed for steady state superconducting tokamak. The housing is a circular pipe, which has circular tubes vacuum brazed on the periphery. A unique method was adopted to monitor the temperature distribution on the internal surface of the pipe. A stainless steel mirror was placed inside the pipe and the reflected IR radiations were viewed using an IR camera. The heat stimulus was given by passing hot water through the tubes and the temperature distribution was monitored during the transient phase. The thermographs showed a significant nonuniformity in the brazing with a contact area of around 51%. The thermography results were compared with the x-ray radiographs and a good match between the two was observed. Benefits of thermography over x-ray radiography testing are emphasized.