Abstract
The power system on the offshore platform is of great importance since it is the power source for oil and gas exploitation, procession and transportation. Transformers constitute key equipment in the power system, and partial discharge (PD) is its most common fault that should be monitored and identified ın a timely and accurate manner. However, the existing PD classifiers cannot meet the demand for real-time online monitoring due to their disadvantages of high memory consumption and poor timeliness. Therefore, a new MobileNets convolutional neural network (MCNN) model is proposed to identify the PD pattern of transformers based on the phase resolved partial discharge (PRPD) spectrum. The model has the advantages of low computational complexity, fast reasoning speed and excellent classification performance. Firstly, we make four typical defect models of PD and conduct a test in a laboratory to collect the PRPD spectra as the data sample. In order to further improve the feature expression ability and recognition accuracy of the model, the lightweight attention mechanism Squeeze-and-Excitation (SE) module and the nonlinear function hard-swish (h-swish) are added after constructing the MCNN model to eliminate the potential accuracy loss in PD pattern recognition. The MCNN model is trained and tested with the pre-processed PRPD spectrum, and a variety of methods are used to visualize the model to verify the effectiveness of the model. Finally, the performance of MCNN is compared with many existing PD pattern recognition models based on convolutional neural network (CNN), the results show that the proposed MCNN can further reduce the number of parameters of the model and improve the calculation speed to achieve the best performance on the premise of good recognition accuracy.
Highlights
As one of the core pieces of equipment, the transformer directly affects the safe, efficient and economic operation of the power system, so it is especially important to ensure the safe and stable operation of the transformer
Based on the phase resolved partial discharge (PRPD) images measured by the transformer simulation experiment, the model is trained according to the steps in Section 2.5; the model construction is completed
The weighted sum of the feature maps contained in the last convolutional layer in the MobileNets convolution neural network (MCNN) model and their corresponding weights are obtained as the result of CAM
Summary
As one of the core pieces of equipment, the transformer directly affects the safe, efficient and economic operation of the power system, so it is especially important to ensure the safe and stable operation of the transformer. Back-propagation neural network (BPNN) and support vector machine (SVM) are widely used [10,11,12] These machine learning algorithms, which rely on the artificial construction of PD features, are highly subjective and have large recognition errors [13]. PRPS spectra obtained from the field experiments and simulation are used as input data, and classical CNN model LeNet-5 is used as classifier [16]. These models have fewer layers and cannot fully extract the PD features. In order to solve the above problems, a transformer PD pattern recognition method based on MobileNets convolution neural network model is proposed.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
