An Autoencoder‐Based Process Control Method for Chemical Mechanical Polishing: Noise Robustness and Control Cost Reduction

In the chemical mechanical polishing (CMP) process in semiconductor manufacturing, run‐to‐run (R2R) process control is critical for consistently producing high‐quality products. R2R process control optimizes equipment parameters to maintain product specifications within target ranges while compensating for process noise. In this paper, we propose a novel method to overcome two limitations of existing R2R process control algorithms in the CMP process. The first limitation is that the relationships between control variables, which can be represented by their ratios, are crucial but not adequately considered. The proposed method overcomes this limitation by preserving control variable ratios derived from historical process data, thus ensuring robust process control under high‐intensity noise conditions. The second limitation is that existing methods cannot prioritize control variables when multiple combinations of these variables can reach the target. Adjusting each control variable has a different associated cost, but current approaches fail to consider these cost differences. Consequently, they cannot consider the priorities of control variables, which may lead to unnecessary costs in the control process. The proposed method introduces a priority‐based approach for control variable adjustments, which can reduce overall process control costs. Furthermore, by incorporating an autoencoder to estimate process environment changes, the proposed method achieves superior performance across various process control metrics compared with traditional R2R algorithms. These improvements enable more robust and cost‐effective process control in the increasingly complex CMP process.