Data-Driven Soft Sensor for Optical Intensity Estimation in High-Power Plasma Source

Inductively coupled plasma (ICP) sources are used in multiple industrial and research applications varying from material reactors, semiconductor fabrication, and nuclear fusion-based reactors. Experiments using ICP source are prone to noise due to the presence of high-power radio frequency (RF) radiation as well as the high voltage (HV). In order to operate such plasma sources, we need rich set of diagnostics that supports the control system as well as the operators in order to derive the important plasma parameters. Some of these sensors are prone to degradation and need constant maintenance and testing that creates challenges during operations. In order to monitor the performance and also mitigate the risks associated with the sensor failure, soft sensors can offer an alternative low-cost approach in estimating the physical parameters. Although soft sensors have found applications in industrial environments, limited implementation has been seen in experimental systems. Hence, in this article, we propose a soft sensor model for an optical (light) sensor which is one of the critical sensors used in ICP and other plasma sources. The proposed model is developed using data-driven machine-learning (ML) and deep-learning (DL) algorithms for a plasma-based system operating under noisy environments. After a thorough exploration, a comparatively better performance was observed using the artificial neural network (ANN)-based models. The ANN model was trained with various hyper parameters in order to obtain a test ${R}^{\,{2}}$ score of 0.91 that was able to model the transient behavior of the sensor. After the model development, it was used for performing fault identification in the signal by comparing the predicted signal with actual signal. The article presents the steps followed in developing the data-driven models for the plasma light sensor and its application for sensor fault identification along with associated challenges.