Improving the prediction accuracy of aerospace engine production line yields is of significant importance for enhancing production efficiency and optimizing production scheduling in enterprises. To address this, a novel method called Convolutional Neural Networks-Improved Support Vector Regression (CNN-ISVR) has been proposed for predicting the production line yield of aerospace engines. The method first divides the factors influencing production line yield into production cycle and real-time status information of the production line and then analyzes the key feature factors. To solve the problem of poor prediction performance in traditional SVR models due to the subjective selection of kernel function parameters, an improved SVR model is presented. This approach combines the elite strategy genetic algorithm with the hyperparameter optimization method based on grid search and cross-validation to obtain the best penalty factor and kernel function width of the Radial Basis Function (RBF) kernel function. The extracted features of production data are then used for prediction by inputting them into the improved support vector regression model, based on a shallow CNN without dimensionality reduction. Finally, the prediction accuracy of the CNN-ISVR model is evaluated using the three commonly used evaluation metrics: Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE) and coefficient of determination (R²). The model’s prediction results are then compared to those of other models. The CNN-ISVR hybrid model is shown to outperform other models in terms of prediction accuracy and generalization ability, demonstrating the effectiveness of the proposed model.

In this study, a fuzzy adaptive impedance control method integrating the backstepping control for the PAM elbow exoskeleton was developed to facilitate robot-assisted rehabilitation tasks. The proposed method uses fuzzy logic to adjust impedance parameters, thereby optimizing user adaptability and reducing interactive torque, which are major limitations of traditional impedance control methods. Furthermore, a repetitive learning algorithm and an adaptive control strategy were incorporated to improve the performance of position accuracy, addressing the time-varying uncertainties and nonlinear disturbances inherent in the exoskeleton. The stability of the proposed controller was tested, and then corresponding simulations and an elbow flexion and extension rehabilitation experiment were performed. The results showed that, with the proposed method, the root mean square of the tracking error was 0.032 rad (i.e., 21.95% less than that of the PID method), and the steady-state interactive torque was 1.917 N·m (i.e., 46.49% less than that of the traditional impedance control). These values exceeded those of the existing methods and supported the potential application of the proposed method for other soft actuators and robots.