Publications by authors named "Fengyuan Ma"
Parameter-coupled state space models based on quasi-Gaussian fuzzy approximation.
Sci Rep
October 2024
The accuracy of a fuzzy system's approximation is closely tied to the performance of fuzzy control systems design, while this system's interpretability depends on the description of a mechanical model using human language. This research introduces a quasi-Gaussian membership function characterized by a pair of parameters to achieve the sensitivity of a triangular membership function along with the interpretability of Gaussian membership functions. Consequently, a two-dimensional (2-D) quasi-Gaussian membership function is derived, and a method for establishing quasi-Gaussian fuzzy systems (QGFS) using a rectangular grid is proposed.
View Article and Find Full Text PDFFast reconstruction of milling temperature field based on CNN-GRU machine learning models.
Front Neurorobot
September 2024
Article Synopsis
- The paper discusses the growing use of robots in milling processes and highlights challenges like high temperature at the tool's front that affect tool life and machining quality.
- It introduces a new model using Gated Convolutional Recurrent Neural Network (CNN-GRU) to solve the inverse heat conduction problem for accurately reconstructing the tool's temperature field during milling.
- The proposed model utilizes knowledge distillation to enhance speed and accuracy, demonstrating strong performance with low error rates, even under noisy conditions, proving its effectiveness in improving robotic milling precision.