Prediction and visualization analysis of drilling energy consumption based on mechanism and data hybrid drive

To obtain an accurate and reliable energy consumption (EC) prediction model, and to quantify the relationship between drilling power, EC, and energy efficiency. An EC prediction model and multi-angle visualization analysis method driven by mechanism and data are proposed. Firstly, the power and energy models of each stage of the drilling rig are established through detailed power flow theory. Additionally, based on the deviation between the actual EC results and the theoretical mechanism model calculation results, a least squares support vector machine (LSSVM) data compensation model is established, and the LSSVM model parameters are optimized by the improved whale optimization algorithm; after that, multi-angle visualization analysis of energy parameters was performed by drilling power histogram, energy efficiency ring diagram, energy sequence diagram, and energy bubble diagram. Finally, the experiment of curb drilling shows that the prediction error of the hybrid drive model is 2.44%. Compared with the prediction results of the mechanism model and the data-driven model, the average prediction error is reduced by 0.76% and 2.25%, which verifies the high efficiency of the hybrid-driven model. Also, through the multi-angle visualization analysis of energy parameters, the drilling energy saving is 2127.4kJ, and the energy efficiency is improved by 26.71%. • A mechanism analysis and data-driven integrated drilling energy consumption prediction model is established. • The IWOA algorithm was used to optimize the LSSVM parameters. • A multi-angle visual analysis of the energy at each stage of drilling is carried out. • The relationship between drilling power, load energy consumption, and load energy efficiency is explored. • The influence of drilling rig working parameters on drilling energy parameters is studied.