11 January 2022 in IEEE Transactions on Industrial Electronics
Turntable servo systems are affected by working status changing in actual work, thus, bringing some uncertain factors. Having models that have accurate predictive capabilities can be valuable for control and decision-making purposes. This article proposes a deep residual recurrent neural network (DRRNN) model-augmented attention with physical characteristics, which is used to build an accurate speed prediction model for a turntable servo system. Integrating the known physical features into the design of the residual network model can increase the interpretability of the overall model. Meanwhile, the recurrent neural network-augmented attention model is used to represent the unknown nonlinear characteristics. The addition of the attention mechanism can effectively improve the accuracy of the nonlinear model. Finally, this article proposes an iterative identification method based on the linear and nonlinear model error with alternative compensation. Through alternating error compensation, the linear model’s accuracy can be continuously improved, then the overall and the nonlinear part of the model can be established accurately by retraining the whole model. Experimental results show that the DRRNN model designed in this article can predict the rotational speed in single-step or multistep well. Compared with the traditional mechanism modeling method, the modeling accuracy can be greatly improved.
22 August 2022 in IEEE Transactions on Industrial Informatics
To satisfy the application requirements of the forward/inverse model for various control algorithms used in servo systems, a physics-guided reversible residual neural network (PGRRNN) model is proposed, which is applied to build forward/inverse model for turntable servo systems. With the special design of the network structure, both forward and inverse models can be obtained through one-way training of the model, so that the modeling efficiency is improved. Combining the gated recurrent unit and the fully connected layer as the nonlinear term of the reversible residual unit, the PGRRNN model can capture the relevant information between time series data in the training process, so that the prediction accuracy can be effectively improved. Moreover, by selecting the linear sweeping frequency signals with different amplitudes in series as the input signal, the system can be fully excited and the generalization ability can be effectively improved. Experimental results show that the forward/inverse model built by the proposed method has high precision and good generalization ability. The prediction accuracy of the forward/inverse model is better than that of the models built by the traditional modeling method and our previous work. In addition, the accuracy and real-time performance can be guaranteed simultaneously by adjusting the length of the input sequence and the number of residual units, so it has a certain practical value.
25 April 2025 in Expert Systems with Applications
5 May 2023 in International Journal of Control, Automation, and Systems
4 February 2025 in IEEE Sensors Journal
Lead-through programming (LTP) enables the operators to guide the manipulator directly to the desired target position, significantly improving adaptability and flexibility. However, direct drive manipulators encounter significant challenges in force sensorless LTP due to the high inertia, external force sensitivity, and complications from kinematics singularities. To enhance the interaction compliance and safety, a novel force sensorless LTP control strategy is proposed for direct drive manipulators. Specifically, an enhanced generalized momentum observer (EGMO) based on a nominal model is designed to mitigate phase lag caused by filtering measurement noise through a phase compensation mechanism. Additionally, the introduction of dither signal and radial basis function neural network (RBFNN) learning methods reduces dynamic uncertainties, improving control performance. Then, a kinematics singularity avoidance control method is proposed, which switches between impedance and admittance control by predicting singularity points in advance, enabling the manipulator to avoid kinematic singularity in the task space with minimal position and orientation deviations, promoting a more compliant and safe interaction between the manipulator and the human operator. Finally, the proposed methods are validated on a six-degree-of-freedom (DOF) direct drive manipulator under three typical singular scenarios. The results demonstrate the effectiveness and practicality of the proposed method.
27 January 2025 in Applied Soft Computing