3D laser scanning strategy based on cascaded deep neural network

A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monitoring. Combining the device characteristics, the strategy first proposes a cascaded deep neural network, which inputs 2D point cloud, color image and pitching angle. The outputs are target distance and speed classification. And the cross-entropy loss function of network is modified by using focal loss and uniform distribution to improve the recognition accuracy. Then a pitching range and speed model are proposed to determine pitching motion parameters. Finally, the adaptive scanning is realized by integral separate speed PID. The experimental results show that the accuracies of the improved network target detection box, distance and speed classification are 90.17%, 96.87% and 96.97%, respectively. The average speed error of the improved PID is 0.4239°/s, and the average strategy execution time is 0.1521 s.The range and speed model can effectively reduce the collection of useless information and the deformation of the target point cloud. Conclusively, the experimental of overall scanning strategy show that it can improve target point cloud integrity and density while ensuring the capture of target.

Power system transient stability assessment based on the multiple paralleled convolutional neural network and gated recurrent unit

In order to accurately evaluate power system stability in a timely manner after faults,and further improve the feature extraction ability of the model,this paper presents an improved transient stability assessment(TSA)method of CNN+GRU.This comprises a convolutional neural network(CNN)and gated recurrent unit(GRU).CNN has the feature extraction capability for a micro short-term time sequence,while GRU can extract characteristics contained in a macro long-term time sequence.The two are integrated to comprehensively extract the high-order features that are contained in a transient process.To overcome the difficulty of sample misclassification,a multiple parallel(MP)CNN+GRU,with multiple CNN+GRU connected in parallel,is created.Additionally,an improved focal loss(FL)func-tion which can implement self-adaptive adjustment according to the neural network training is introduced to guide model training.Finally,the proposed methods are verified on the IEEE 39 and 145-bus systems.The simulation results indicate that the proposed methods have better TSA performance than other existing methods.