Automatic analysis of faulty low voltage network asset using deep neural networks

作     者：Mastroleo, Marcello Ugolotti, Roberto Mussi, Luca Vicari, Emilio Sassi, Federico Sciocchetti, Francesco Beasant, Bob McIlroy, Colin 

作者机构：Camlin Italy Str Budellungo 2 Parma Italy Camlin Technol 31 Ferguson Dr Lisburn North Ireland 

出 版 物：《JOURNAL OF ENGINEERING-JOE》 

年 卷 期：2018年第2018卷第15期

页      面：851-855页

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 

主　　题：probability neural nets fault diagnosis power engineering computing power distribution faults data analysis power distribution reliability power cables deep neural network electrical distribution network electric vehicles distribution network operators recording devices low-voltage cables automatic faulty LV network asset analysis power system heat pumps cable fault probabilty damaged network fast recovery automatic failure source identification variational autoencoder VAE data analysis 

摘      要：Electrical distribution network is constantly ageing worldwide. Therefore, probability of cable faults is increasing over time. Fast recovering of damaged networks is of vital importance and a quick and automatic identification of the failure source may help to promptly recover the functionality of the network. The scenario we are taking into consideration is a vast number of recording devices spread across a network that constantly monitor low voltage cables. When the current of a cable reaches a very high value, data is sent to a central server which analyses it through a variant of a Variational Auto Encoder (VAE), a deep neural network. This VAE has been trained by using historical data collected from several hundreds of faults recorded, but in which only a handful of them has been labelled by an on-site analysis of the fault. Data used for training is simply the recorded levels of voltages and currents, after a simple pre-processing step. The final goal is to let the network distinguish if the fault occurred in a point of the cable, on a joint, or at the pot-end located at the termination. A preliminary evaluation of its ability to generalise over the non-labelled samples shows encouraging results.