<p>The harsh working environment of the front-end mechanism of mining electric shovels poses significant challenges for intelligent excavation. The intelligent mining electric shovel relies on the dynamic model of the front-end mechanism during excavation trajectory planning and tracking control, but accurately constructing the dynamic model of large electric shovels is difficult. Therefore, a dynamic model parameter identification framework for intelligent mine shovel is proposed in this paper. Firstly, the dynamic model of the front-end working mechanism of the intelligent mine electric shovel (IMES) is constructed based on the Lagrange method, and it is simplified and linearized. Then, an optimal excavation excitation trajectory optimization method based on high order polynomials is proposed to generate excitation trajectory. In order to improve the identification accuracy, a hybrid filtering method combining mean filtering and wavelet filtering is proposed in this paper, which is used to process the experimental data of optimal excitation trajectory and ensure that the data meet the identification requirements. Finally, two identification methods of dynamic model parameters are proposed, which are based on adaptive ridge regression and optimization algorithm. Through these two methods, the dynamic parameters of IMES are identified respectively under different uncertain disturbance conditions. Through numerical simulation and experimental verification, the feasibility of the framework for dynamic parameter identification of IMES is proved. The proposed framework provides theoretical support for subsequent trajectory planning and adaptive tracking control of IMES.</p>