Search

Accurately predicting the concentration trend of dissolved gas in oil has a positive effect on the evaluation of transformer status and life assessment. In order to improve the accuracy of dissolved gas in oil prediction, a dissolved gas in oil prediction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and time convolution network (TCN) is proposed in this paper. Firstly, the CEEMDAN method is used to decompose the original sequence of dissolved gas in oil into multiple intrinsic mode functions(IMFs), separating the stable and unstable IMFs. Secondly, TCN are established for IMFs, then predictions based on these trained TCNs are made. Finally, the prediction results of IMFs are overlaid to reconstruct the prediction results of the original sequence. Analysis in this paper shows that the root mean square error, mean absolute error and maximum error of the prediction method are 1.01 μL/L, 1.53 μL/L, 5.54 μL/L respectively, which are reduced by 53.47%, 41.18%, 13.36% compared to the case without using the CEEMDAN. When using CEEMDAN, the three errors are the smallest compared to commonly used recurrent neural networks. The proposed dissolved gas in oil prediction method has higher prediction accuracy and can provide more effective support for condition based maintenance strategy.

To solve the problems such as braking energy of pure diesel locomotive can only be wasted and pure battery locomotives have low traction power and short cruising range, bidirectional DC/DC circuit of traction battery is integrated into the traction converter in diesel electric hybrid locomotive. To effectively use energy of diesel engine and traction battery, it presents an energy optimal control proposal for diesel electric hybrid locomotive. Under the traction condition, according to the demand power of traction motor and auxiliary load and the current allowable output power of traction battery, it controls the optimal energy supply of diesel generator and traction battery, and gives priority to the use of traction battery to provide energy to load in order to save fuel. Under the braking condition, according to the size of electric braking energy, it gives priority to auxiliary load consumption or traction battery energy recovery. Since the maximum allowable charging current is affected by SOC, temperature and other conditions, this paper introduces the optimal control of electric braking energy under several special conditions. In order to quickly response to complex energy conversion process, bidirectional DC/DC circuit adopts adaptive flexible charge discharge control, which can adaptively select to work in Boost or Buck mode. The judgment method is simpler and more accurate, and can switch to each other safely and flexibly. Test results show that through the optimal energy control, the energy of diesel generator and traction battery can be used reasonably, and the electric braking energy can be recovered effectively, which improves the fuel economy from the load side and significantly improves the energy utilization rate.