The ever-increasing functional density and complexity of the satellite systems, the harsh space flight environment, as well as the cost reduction measures that require less operator involvement are increasingly driving the need to develop new approaches for fault diagnosis and health monitoring (FD-HM). The data-driven FD-HM approaches use signal processing or data mining to obtain implicit information for the operating state of the system, which is good at monitoring systems extensively and shallowly and is expected to reduce the workload of the operators. However, these approaches for the FD-HM of the satellite system are driven primarily by the historical data and some static physical data, with little consideration for the simulation data, real-time data, and data fusion between the two, so it is not fully competent for the real-time monitoring and maintenance of the satellite in orbit. To ensure the reliable operation of the complex satellite systems, this paper presents a new physical–virtual convergence approach, digital twin, for FD-HM. Moreover, we present an FD-HM application of the satellite power system to demonstrate the effectiveness of the proposed approach.
The artificial potential field method is a highly popular obstacle avoidance algorithm which is widely used in the field of industrial robotics due to its high efficiency. However, the traditional artificial potential field method has poor real-time performance, making it less suitable for modern factory work patterns, and it is difficult to handle situations when the robotic arm encounters singular configurations. In this paper, we propose an improved artificial potential field method in joint space, which effectively improves the real-time performance of the algorithm, and still performs well when the robotic arm falls into a singular configuration. This method solves the gradient of the repulsive potential field in advance by defining the shortest distance from each joint of the robotic arm to the obstacle, and only needs to calculate potential field function once per cycle, which significantly reduces the calculation time. In addition, when a robotic arm falls into a local minimum position in potential field, the algorithm adds a virtual obstacle to make it leave the position, while this virtual obstacle does not require additional input information. Experimental results show that the algorithm obtains short movement paths and requires very little computing time in the face of different obstacles.
1
24 December 2016 in Structural and Multidisciplinary Optimization
Position error-compensation control in the servo system of computerized numerical control (CNC) machine tools relies on accurate prediction of dynamic tracking errors of the machine tool feed system. In this paper, in order to accurately predict dynamic tracking errors, a hybrid modeling method is proposed and a dynamic model of the ball screw feed system is developed. Firstly, according to the law of conservation of energy, a complete multi-domain system analytical model of a ball screw feed system was established based on energy flow. In order to overcome the uncertainties of the analytical model, then the data-driven model based on the back propagation (BP) neural network was established and trained using experimental data. Finally, the data-driven model was coupled with the multi-domain analytical model and the hybrid model was developed. The model was verified by experiment at different velocities and the results show that the prediction accuracy of the hybrid model reaches high levels. The hybrid modeling method combines the advantages of analytical modeling and data-driven modeling methods, and can significantly improve the feed system’s modeling accuracy. The research results of this paper are of great significance to improve the compensation control accuracy of CNC machine tools.
In recent years, physics-informed neural networks (PINNs) have developed significantly as a deep learning technology. In analogy to the selection of grid cells in traditional numerical methods, the distribution of sample points used for training PINN can have a greater impact on the solution accuracy. Based on the Residual-based Adaptive Refinement (RAR) algorithm, many improved adaptive sampling algorithms have been proposed. However, these sampling algorithms rely on residuals as the error indicator and focus only on the sample points within the solution domain. Therefore, we introduce a novel adaptive sampling algorithm EI-RAR. This algorithm incorporates a new expected improvement (EI) function, which increases focus on the sample points at the boundaries of the solution domain. Additionally, EI-RAR integrates attention mechanism with a sample point generation algorithm, aimed at reinforcing the connection between newly-added and existing sample points. To increase the accuracy of solving problems with sharp solutions, we build upon the EI-RAR algorithm by incorporating gradient information of the residual values as a criterion for sample point selection, leading to the development of a second adaptive sampling algorithm EI-Grad. We select residual neural network and combine it with adaptive sampling algorithms for a series of numerical experiments, aiming to reduce the phenomenon of gradient vanishing during the training process. These experiments select the Diffusion equation, Burgers’ equation, Allen-Cahn equation, and Navier-Stokes equation, respectively. Numerical results indicate that, with the same number of residual points, the EI-RAR algorithm is more precise compared to other sampling methods, and the EI-Grad algorithm can also effectively solve partial differential equations with sharp solutions.
18 March 2016 in Journal of Combinatorial Optimization