Accurate estimation and prediction of the state of health (SOH) and remaining useful life (RUL) of lithium-ion batteries at the early cycling stage are essential for enabling efficient battery recycling, secondary utilization, and timely warnings. However, the high similarity of battery charging data during early cycling stage, the requirement for extensive data to assess aging, and the complexity of multi-dimensional feature extraction pose significant challenges for existing predictive methods. To address these challenges, A novel framework based on an optimized echo state network for SOH estimation and RUL prediction with early data feature is proposed. Inspired by the idea of phase space reconstruction, the delay time is employed to capture the characteristics of the early voltage profile. A novel improved whale optimization algorithm (IWOA) is employed to optimize the echo state network (ESN), facilitating rapid and precise prediction of both SOH and RUL. Experimental results showed that the root mean square error (RMSE) and mean absolute percentage error (MAPE) for battery SOH can be reduced to 0.33% and 0.27%, respectively, and the RMSE and MAPE for battery RUL can be reduced to 0.4% and 0.43%, respectively. By leveraging early cycle data, the proposed method not only enhances the efficiency and accuracy of SOH estimation and RUL prediction, but also introduces a novel perspective for practical battery management and predictive maintenance, thereby advancing the state-of-the-art in battery health monitoring systems.
Different from other transformable wheel structures, the presence of the drag spring within this mechanism endows the wheel with improved motion smoothness during reverse movement and significant advantages in motor and servo protection. To ensure stable obstacle crossing, the process is systematically analysed and the maximum acceleration is evaluated based on the Zero Moment Point (ZMP) method. Virtual prototyping simulation results show that, during the robot’s reverse motion, the range and standard deviation of the centre of the mass (CoM) velocity fluctuation are reduced by 98.31 % and 98.26 %, respectively; the average torque magnitude optimization rate of the motor reaches 79.73 %, and the average torque standard deviation optimization rate is 76.49 %. Under various urban operating conditions, the servo protection effect is also significant, with the best performance observed in continuous steps climbing scenarios, where the average torque magnitude optimization rate is 93.17 % and the torque fluctuation optimization rate is 90.20 %. Servo protection performance experiment indicate that the designed flexible structure achieves a torque optimization rate of 85.00 %, further validating the advantage of the flexible configuration. Finally, experiments on single-step and continuous-step conditions verify that the robot can traverse a single step of 165 mm in height, and continuous steps of 115 mm in height and 410 mm in width, demonstrating excellent adaptability to urban environments. The results of this study provide a new design approach for protecting motors and servos in current transformable wheel systems based on bionic principles.