We propose a real-time information propagation arithmetic neural network (PANN) that minimizes the loss of power generation output of the system in the event of sudden changes in the module due to strong external typhoons or earthquakes at the solar power generation facility site. In addition, we propose a new double-sided module reflector that can reduce the local loss of power generation efficiency of the single-sided module reflector that is currently widely distributed, as well as the environmental pollution and inconvenience of maintenance work of the existing double-sided module. We present a computational network that can detect the faulty solar panel in real-time by checking the fault status of the installed solar panel and using a real-time computation method through a node-to-node diffusion method. In particular, this method recognizes the power loss part due to sudden changes in the module in real time and can take emergency measures for various nonlinear field facilities through a neural structure that finds the optimal distance up, down, left, and right. To confirm the characteristics of the loss reduction control of the field facility, we confirmed that the system was configured as a 7-degree-of-freedom control model using the PANN neural network learning structure method and improved the power generation output. PANN (Propagation Arithmetic Neural Networks) and various module systems are proposed for the real-time recovery of faulty solar panels and improving module system efficiency.

This paper dealt with the propagation characteristics of acoustic signal in insulation oil for the purpose of improving the reliability of AE (acoustic emission) method used for condition monitoring of oil-immersed transformers. A discharge source was placed in insulation oil and AE sensors (fc :140 kHz) were attached on the oil tank to study the changes of velocity and propagation path with the depth and distance. The average velocity was 1,436 m/s and the velocity decreased with the increase of depth from the oil surface to 430 mm. The propagation paths were classified into three sections by the shortest reflection path of the detected signal. The minimum distinguishable distance in each section was 70 mm. It was also verified that PD (partial discharge) with a magnitude over than 500 pC can be detected by the AE sensors.

This paper dealt with a defect identification algorithm which is based on single partial discharge (PD) pulse analysis in gas insulated structure. Four types of electrode systems such as a needle-plane, a plane-needle, a free particle and a crack inside spacer were fabricated to simulate defects in gas insulated switchgear (GIS). We measured single PD pulse by an oscilloscope with a sampling rate of 5 GS/s and a frequency bandwidth of 1 GHz. Data aquisition and signal processing were controlled by a LabVIEW program. Physical shapes of PD pulses were compared with kurtosis, skewness and time-based parameters as rising time, falling time and pulse-width. These parameters were analysed by an algorithm with a back propagation algorithm (BPA). By applying the algorithm, the identification rate was 97% for the needle-plane electrode, 96% for the plane-needle electrode, 91% for the free particle and 93% for the crack inside spacer. The results verified that the algorithm could identify the type of defects in GIS.

Frequency domain measurement of propagation loss for ultra high frequency (UHF) partial discharge in the winding of power transformer using a spectrum analyzer and pulse generator is presented. We compared the performance of the method using a network analyzer with and without a winding. Using a network analyzer simplifies the measurement and offers better dynamic range and frequency range. It also provides precise propagation loss within the winding in frequency domain at UHF range. We applied this method to measure UHF propagation loss of transformer mock-up, modeled 154 kV 20 MVA power in KEPCO substation.