| In the chemical production process,both chemical equipment and chemical processes put strict requirements on the power system.For example,the DCS system of chemical enterprises needs a stable and reliable power supply.The process of electrolytic plating requires a small voltage and large current DC power supply system.Faced with the different characteristics of the electricity used by various chemical companies in the chemical park,a smarter power monitoring system is needed.At present,China's power system backbone network generally uses SCADA and WAMS systems,while the monitoring of power distribution networks is relatively lagging.This paper mainly proposes a monitoring system for the failure of distribution network in chemical parks.Using the light synchronous phasor test device of each node of the power distribution network,the grid state of each node is monitored,the suspected fault data is uploaded to the server through the 4G network,and the synchronized phasor is deeply learned in the cloud platform to further judge the fault,and the system is further determined.The main device is the lightweight phasor test unit at each node.The ?PMU uses GPS synchronous timing to realize synchronous phasor acquisition of the whole network.The discrete Fourier transform is used to obtain the frequency domain data,and the frequency domain data is pre-judged through the decision tree,and the suspected data is locally stored and uploaded to the cloud server.The pre-processing of the front-end data filters out most of the normal data,slowing the storage pressure and wireless transmission pressure,and reducing the possibility of network shackles.The set of recording terminals has built-in machine learning algorithms,which can completely judge the fault data,and simplify the traditional PMU structure,which greatly saves the terminal cost,makes the distribution network available for a large number of applications,and has certain application value and prospect. |
PDF Full Text Request