<p>The identification of contact forces in vehicle-track systems is a crucial aspect of railway dynamics, significantly impacting vehicle operation safety and track maintenance. Due to the coupling of wheel-rail contact forces in the longitudinal, lateral, and vertical directions, along with the constraints on the installation of onboard sensors, estimating wheel-rail forces is a highly ill-posed problem. To achieve the decoupling of left and right wheel-rail force estimations, a 7-degree-of-freedom wheel-rail force estimation model is proposed. The main contributions of this paper are as follows: First, a nonlinear governing equation for the wheelset is established. Based on this, an Extended Kalman Filter (EKF)-based algorithm is integrated into a wheel-rail contact force identification procedure. A simulation model is then developed to validate the proposed method. Numerical results demonstrate that this method achieves the highest accuracy in identifying normal forces, followed by lateral forces, and then longitudinal forces and can effectively identify the forces acting on both left and right sides of the wheelset, overcoming the limitation of traditional methods that can only recognize total lateral forces and total yaw moments.</p>