The MARG(Magnetic, Angular Rate, and Gravity) sensor system, which consists of a MEMS tri-axis accelerometer, a MEMS tri-axis gyroscope and a MEMS tri-axis magnetometer, has a wide application prospect in the wearable...
详细信息
The MARG(Magnetic, Angular Rate, and Gravity) sensor system, which consists of a MEMS tri-axis accelerometer, a MEMS tri-axis gyroscope and a MEMS tri-axis magnetometer, has a wide application prospect in the wearable computing field. But due to the difficulty of removing gravity and the error cumulating, the MARG sensors have not been applied to the motion trajectory analysis and computing. This paper presents a method for trajectory analysis and computing with the Finite Automation tool using MARG sensors. The information needed to adjust the acceleration signal is offered when the state of the motion is recognized by Finite Automation. The method is used on the base of gravity removing process, which is implemented by the orientation estimation using gradientdescentalgorithm. This method can accurately implement the segmentation and analysis of a complex motion and get the trajectory of the motion, which helps us recognize and comprehend the meaning of the motion. In this paper, the method is applied to the arm motion trajectory analysis and computing, experiment result shows the efficiency of the method.
This paper attempts to solve the optimal power allocation(OPA) problem for smart grid system in a new distinguished *** the numerical optimization approaches including traditional convex optimization and heuristic sea...
详细信息
This paper attempts to solve the optimal power allocation(OPA) problem for smart grid system in a new distinguished *** the numerical optimization approaches including traditional convex optimization and heuristic search methods almost occupy the addressing of such ***,these optimization algorithms may suffer from high computational complexity when the system scales up,which would inevitably create a gap between the theoretical algorithm design and real-time algorithm *** this paper,we aim to provide a new learning based approach to handle the real-time OPA problem in smart grid *** key idea behind this approach is to treat the input and output of traditional OPA optimization algorithm as an unknown nonlinear mapping,which is then approximated by recent popular learning based tools such as deep neural network(DNN).As long as the constructed DNN can accurately learn such nonlinear mapping,then the OPA problem can be solved in real *** main contribution is to theoretically show that the traditional decentralized gradient-based optimization algorithm for OPA problem can be accurately approximated by a well-constructed ***,experimental case studies validate the effectiveness and advantages of our proposed method.
Resistance spot welding (RSW) is still the most successful sheet metal joining method in the automobile industry. However, an effective quality evaluation method has not yet been developed. Real-time quality inspectio...
详细信息
ISBN:
(纸本)078038248X
Resistance spot welding (RSW) is still the most successful sheet metal joining method in the automobile industry. However, an effective quality evaluation method has not yet been developed. Real-time quality inspection of RSW is necessary in order to deal with all kinds of problems during welding. This paper developed an experimental system using for measuring electrode displacement. Accordingly based on electrode displacement curve proposes a neuro-fuzzy algorithm to inference nugget diameter online. Inference results showed that among the total number of specimens, 88% were successfully inferred within a range of 1.5% error.
暂无评论