A Novel Stacked Generalization Ensemble-Based Hybrid PSVM-PMLP-MLR Model for Energy Consumption Prediction of Copper Foil Electrolytic Preparation

At present, the energy consuming during electrolytic copper foil preparation accounts for more than 75% of total consumption. In real-life production, process parameters are set by operator empirically and system may not work at operating point with minimum Therefore, it is critical to establish an effective model predicting electrolysis consumption guide design. this paper, a novel hybrid (named PSVM-PMLP-MLR) based on stacked ensemble learning proposed. The divided into two parts: base-learning meta-learning model. support vector machine (SVM) multilayer perceptron (MLP) different input structures established former first. Then particle swarm algorithm employed determine optimal value SVM weight MLP minimizing mean absolute percentage error (MAPE). multiple linear regression (MLR) finally as compute final predictions. Experimental results show that coefficient reached 0.987, compared traditional models, accuracy improved 10.29% 8.28%, respectively.