Intelligent Characterization of Spark-Assisted Chemical Engraving (SACE) Process Using Time Series Classification

Spark-Assisted Chemical Engraving (SACE) requires precise control over key factors to overcome gas film instability and achieve reproducible optimal resolution and machining speed. This paper presents a substantial advancement in the SACE micromanufacturing technique by introducing a composite algorithm. This algorithm leverages deep learning and time series classification, employing a Temporal Convolutional Network (TCN) and a Long Short-Term Memory (LSTM) architecture for sequence-to-sequence intelligent classification. These classifiers are trained and optimized using Bayesian optimization, achieving impressive accuracies of 97.12% for TCN and 96.64% for LSTM. The algorithm utilizes TCN's superior performance to calculate derived parameters like gas film formation time, lifetime, mean discharge current and energy, and discharging frequency. Its versatility is demonstrated across various experimental conditions, showcasing its potential for rapid and accurate systematic studies. By highlighting the algorithm's applicability in real-time process control for SACE, this study establishes a foundation for future advancements in the field of glass micro manufacturing.