Dynamic Equivalent Modeling for Black-box Microgrids Under Multi-operating-point by Using LSTM

Since the high penetration of distributed energy sources complicates the dynamics of electrical power systems,accurate dynamic models are indispensable for study on the transient behavior of the microgrid(MG).In some practices,the lack of full detailed information results in failure of dif-ferential equation based dynamic modeling,which leads to a demand for a black-box MG modeling method.It is a critical challenge to maintain the effectiveness of the black-box model under a wide operating range and various fault conditions.In this paper,inspired by the mathematical equivalence between the recurrent neural network(RNN)and differential-algebraic equations(DAEs),a dynamic equivalent modeling method,using long short-term memory(LSTM),is presented to tackle this challenge.At first,the modeling equivalence and advantages of our basic idea are explained.Then,modeling procedures,including data preparation and design guidelines,are presented.Finally,the proposed method is applied to a multi-microgrid testing system for performance evaluation.The results,under various scenarios,reveal that the proposed modeling method has an adequate capability for representing the dynamic behaviors of a black-box MG under grid fault and operating point changing conditions.Index Terms-Deep learning,dynamic behavior,dynamic equivalent model,microgrid,neural network.

Dynamic analysis of C/C composite finger seal

A seal device as an important component of aeroengines has decisive influence on per- formance, reliability, and working life of aeroengines. With the development of aeroengines, demands on the performance characteristics of seal devices are made strictly. Finger seal as a novel kind of sealing device, recently attracts more and more attentions in academic circles and engineer- ing fields at home and abroad. Research on finger seals has been extensively developed, especially on leakage and wear performances under dynamic conditions. However, it is a pity that the work on finger seals has been limited with a single approach that is improving the performance by structural optimization; in addition, the technology of dynamic analysis on finger seals is weak. Aiming at the problems mentioned above, a distributed mass equivalent dynamic model of finger seals considering the coupling effect of overlaid laminates is established in the present paper, the dynamic perfor- mance of 2.5 dimension C/C composite finger seal is analyzed with the model, and then the effects of fiber bundle density and fiber bundle preparation direction on finger seal＇s dynamic performance are discussed, as well as compared with those of Co-based alloy finger seal. The current work is about dynamic analysis of finger seals and application of C/C composite in this paper may have much academic significance and many engineering values for improving research level of finger seal dynamics and exploring feasibility of C/C composite being used for finger seals.