Reverse power relays are utilised to trip turbine generators to avoid prime mover damage and directional relay is most widely used as the main protection for these conditions. An intentional time delay is ordinarily u...
详细信息
Reverse power relays are utilised to trip turbine generators to avoid prime mover damage and directional relay is most widely used as the main protection for these conditions. An intentional time delay is ordinarily utilised to overcome the possible maloperation of these relays. However, the intentional time delay to prevent maloperation is not an ideal solution. As this time delay increases the reverse power relay operation time, which means that the motoring action of the synchronous generator persist for a longer time, making the prime mover more vulnerable to active power drawn by the generator. This study proposes a new flux-based approach to detect reverse power condition in the synchronous generators. The proposed scheme uses the analysis of angular velocity and accelerationdata that are calculated from the estimated magnetic flux at the machine stator terminals. The basic idea of the technique stems from the principle that the stator and rotor magnetic fluxes rotate together at synchronous speed and will not be affected by system disturbances for a short interval according to highly inductive characteristics of the synchronous machine. The main advantage of this predictive algorithm is its speed, security and sensitivity to detect the reverse power conditions.
At present, the study of upper limb posture recognition is still in the primary stage, due to the diversity of the objective environment and the complexity of the human body posture, the upper limb posture has no Publ...
详细信息
ISBN:
(数字)9781728176475
ISBN:
(纸本)9781728176475;9781728176482
At present, the study of upper limb posture recognition is still in the primary stage, due to the diversity of the objective environment and the complexity of the human body posture, the upper limb posture has no Public dataset. In this paper, an upper extremity data acquisition system is designed, with a three-channel data acquisition mode, collect acceleration signal and gyroscope signal as sample data. The data sets were pre-processed with de-weighting, interpolation, and feature extraction. With the goal of recognizing human posture, experiments with KNN, logistic regression, and random gradient descent algorithms were conducted. In order to verify the superiority of each algorithm, the data window was adjusted to compare the recognition speed, computation time and accuracy of each classifier. For the problem of improving the accuracy of human posture recognition, a neural network model based on full connectivity is developed. In the process of constructing the network model, the effects of different hidden layers, activation functions, and optimizers on the recognition rate were experimentally for the comparative analysis, the softplus activation function with better recognition performance and the adagrad optimizer are selected. Finally, by comparing the comprehensive recognition accuracy and time efficiency with other classification models, the fully connected neural network is verified in the human posture Superiority in Identification.
暂无评论