State Key Laboratory of Power Transmission and Distribution Equipment and System Safety and New Technology

Abstract In view of the high complexity of the vibration signal of the converter transformer and the large amount of data, the construction of the feature extraction model of the converter transformer based on the vibration signal is difficult and the accuracy is not high. This paper proposes a feature extraction model of commutation vibratiob signals based on Markov transition field and residual convolutional neural network. This paper first divides the interval according to the signal amplitude and calculates its Markov transition field matrix, and then obtains the two-dimensional representation of the one-dimensional vibration signal by calculating the Markov transition field matrix through the transition matrix. Finally, the feature extraction of the vibration map is performed through the residual convolutional neural network. Analysis of the actual measured data at the converter station shows that the average working condition recognition accuracy of the model in this paper reaches 93.1%. It is better than classic time series processing networks such as long and short-term memory networks and one-dimensional convolutional neural networks. It solves the problem of difficulty in building and training long vector deep learning networks by constructing two-dimensional representations of one-dimensional vectors. It is based on commutation The research on fault detection methods of variable vibration signals provides the basis.

Based on aeolian vibration and piezoelectric effect, a cantilever energy harvester is proposed to supply energy to a micro-meteorological online monitoring sensing system for transmission lines. According to the Hamiltonian variational principle and Gauss's law, the distributed parameter coupling model of the piezoelectric cantilever energy harvesting module in the system is established, and the theoretical analytical expression of the output response of the energy harvesting module is derived by the Galerkin decomposition method and the force electrolytic coupling method. The influences of external excitation frequency and external load resistance on the output response of the system energy harvesting module are discussed. The results indicate that the highest output power is obtained when the external excitation frequency is equal to the natural frequency of the structure. Besides, the optimal external load resistance is always exciting with maximum electric power and the smallest vibration displacement. Finally, through indoor tests, the practicability of the self-powered micro-meteorological online monitoring system proposed in this paper is demonstrated. The research results in this paper can provide theoretical and experimental reference for the study of self-energy harvesting of transmission line online monitoring systems, and help for the safe operation and risk warning of transmission lines.

In various optical feedback cavity-enhanced spectroscopies (OF-CESs) based on absorption or scattering, conventional phase-locking methods are constrained by their ability to handle only minor phase deviations. This limitation is due to the source of an error signal for phase adjustment. This paper introduces a robust approach for phase-locking, which combines the shape and intensity of cavity transmission profiles to identify phase deviations. The advantage of this combination is that it can always generate a suitable error signal, irrespective of the phase's position in the entire 2π period. The outstanding performance of the corresponding servo loop under severe airflow shocks demonstrates that our approach significantly increases the feasibility of applying various OF-CES setups for real-time, in situ gas detection in harsh environments.

In order to fully excavate scheduling, periodic characteristics of power load, raise the reliability and economy of the energy storage and distribution network planning, based on the year of the three typical load curves, on the basis of similarity analysis, through the orderly clustering analysis. distribution network planning, based on the year of the three typical load curves, on the basis of similarity analysis, through the orderly clustering method for all kinds of load curves according to the time series of annual finer clustering, and the time series of annual finer clustering. method for all kinds of load curves according to the time series of annual finer clustering, The minimum time unit of dynamic configuration of mobile The minimum time unit of dynamic configuration of mobile energy storage in distribution network is planned according to month, and a method of energy storage planning and configuration of active distribution network based on load ordered clustering. The minimum time unit of dynamic configuration of mobile energy storage in distribution network is planned according to month, and a method of energy storage planning and configuration of active distribution network based on load ordered clustering is proposed. Finally, IEEE33 node system is adopted to verify the proposed scheme. The calculation results show that the energy storage configuration scheme considering the actual time sequence characteristics of the load is more economical and can reflect the actual operation of the distribution network. The calculation results show that the energy storage configuration scheme considering the actual time sequence characteristics of the load is more economical and can reflect the actual operation of the distribution network. The scheme is an effective extension of the flexible use of energy storage equipment in the distribution network, and can better serve the variable operation of active distribution network load, so as to better play the role of energy storage.