The complex industrial environment and poor data quality inherent in electrolytic copper foil production often lead to inaccurate energy consumption predictors, and consequently unreliable energy optimization. Given the difficulty in further improving the accuracy of energy consumption predictors, this article proposes a high-reliability stochastic prediction-based ensemble optimization (SPEO) method for energy saving of copper foil electrodeposition. The approach begins by introducing stochastic prediction to establish a standard stochastic prediction optimization framework, wherein filtering operations are applied to mitigate the adverse effects of prediction errors on the optimization process. Subsequently, reliability analysis methods are employed to derive reliability metrics based on optimization results generated by energy consumption predictors of varying accuracy. Finally, these metrics are comprehensively incorporated to integrate multiple optimizers, along with their respective optimal result feedback, thereby enhancing the generalizability and stability of the method. Experimental evaluations using real-world data from an industrial electrodeposition process demonstrate the superiority of the proposed SPEO method.
The process parameter settings of electrolytic copper foil (ECF) electrodeposition face challenges due to insufficient data within individual production domains and barriers to cross-domain data sharing. Coordinating federated predictor training with client-side process parameter search remains a practical challenge in cross-domain ECF production. We propose FedO, a two-phase federated optimization framework for process parameter settings in ECF electrodeposition. Our approach coordinates federated EC predictor training with local process parameter search through an aggregation procedure independent of optimizer internals. The framework operates in two phases: local autonomous optimization, where clients generate high-quality initial solutions, followed by federated collaborative optimization, where global aggregation integrates cross-domain knowledge. Additionally, we incorporate adaptive parameter screening, dynamic learning rate decay, and an elite retention strategy to enhance generalization and stability. Experimental results demonstrate the superiority of the proposed framework over existing methods and its compatibility with the six tested optimizers.