AbstractExtraction rate and energy consumption are two important indicators of the sugarcane milling system, which are calculated by offline experiments and inspection methods. Soft sensors are inferential models, which are enabling online prediction of these indicators. Selection of input variables is one of the most critical issues in soft sensors design. So a deep feature extraction method is proposed by combining mutual information theory and hybrid chicken swamp algorithm to determine the input and parameters of model. Then, input the obtained variables into the data‐driven model of deep kernal extreme learning machine (DK‐ELM) with optimized parameters to realize the prediction of extraction and hourly energy consumption. It combines the kernel method with the multi‐layer ELM. Experiments are conducted to verify the effectiveness and superiority of the modeling method. Comparing the proposed framework with the four experiments designed on a sugarcane milling system, the proposed framework for predicting extraction and energy consumption with better feasibility and effectiveness, and provided a good reference for end‐point control and judgment of quick direct tapping.Practical ApplicationsExtraction and energy consumption are two important indicators of the milling process and whether they meet standards will affect the smooth operation and economic benefits of sugar production. This study presents a novel modeling method to predict these indicators based on the deep feature extraction and deep kernal extreme learning machine. These methods provided a good reference for end‐point control and judgment of quick direct tapping. In addition, it a new concept for the design of soft sensors for such complex industrial processes.