Research On Key Technologies Of Power Cables Measure

With the rapid development of Chinese national economy, the application of power cables becomes more and more widespread. Energy is playing an increasingly important role in industrial and civil fields. And the demanding for power cable-the carrier of power transmission is growing. But because of the power cable manufacturing processes, product quality, the install operating environment and some other reasons, in some cable manufacturers in China, the production of power cables can’t reach national cable production quality standards, which can cause the electricity companies which using the produets and other users get huge losses that may endanger people’s lives and cause property damage. Therefore, rapid and accurate detection of power cable fault and find fault location, for the stable operation of power system and guarantee the quality of the user’s electricity, is of great significance.The article analyses the cable fault and the fault located. The classic cable fault located methods are travelling wave method; we can only get fault waveform from the scene of the accident. And it’s difficult to analyze systematically. The article is based on support vector machine (SVM), proposes a new method of fault location. Support vector machine is a kind of based on statistical learning theory pattern recognition method, overcoming the learning, local extreme value point and dimension disasters and so on many shortcomings of neural network and the traditional classifier, it has the strong generalization ability. In resolving the problems of small sample, nonlinear and high dimensional pattern recognition,it show many special advantages, and can applied to the function fitting and other machine learning problems. At last, using the ATP simulation platform, give the simulation model and the calculation process, analyze the qualitative of power cable fault signals, obtain satisfactory results.