Research On High Frequency AC Fast Heating Technology Of HT-PEMFC Based On Big Data Analysis

High temperature proton exchange membrane fuel cell(HT-PEMFC)has many advantages,such as high energy conversion rate,environmental friendliness,strong resistance to CO poisoning,simple water and heat management and so on.It has a wide application prospect in mobile power station,cogeneration,power supply and other fields.When the operating temperature of HT-PEMFC is higher than 100 ?,the HT-PEMFC stack must be heated to the operating temperature when it is started at normal temperature.In order to realize the fast start-up of HT-PEMFC and improve the temperature uniformity,a method of heating HT-PEMFC stack with high frequency alternating current is designed.The experiment results show that the temperature of HT-PEMFC stack heated by high frequency alternating current is more uniform,and the heating power can be controlled flexibly.No phenomenon shows that the performance or life of HT-PEMFC stack is affected.With the rapid development of Internet of things technology and big data technology,the traditional industry is undergoing tremendous changes.Various kinds of data generated by equipment operation have more and more value,and the field of fuel cell is no exception.As a complex system,fuel cell has many factors that will have a certain impact on it.If we can collect as much data as possible,we can collect all kinds of data of fuel cell Then the fuel cell can be evaluated from a more comprehensive perspective.In this paper,a complete big data system is designed,which includes data collection,data storage and data analysis.Considering that a large number of fuel cells will be connected to the system in the future and the concurrent carrying capacity of the system is fully considered,the fuel cell operation data will be sent to the cloud server through MQTT protocol,and the system will be decoupled by Kafka,a distributed publish subscribe message system In order to improve the throughput of the system,Hadoop,an open source big data framework,is used to store the data.Considering the strong time correlation of the data generated by fuel cell operation,the OpenTSDB time-series database based on HBase is used to store the data.In the aspect of data analysis,in addition to using big data platform to heat HT-PEMFC with high frequency alternating current,a fault diagnosis algorithm of fuel cell based on PCA is also designed.Experiments are carried out with actual data,and data calculation is carried out with spark,a big data calculation framework.The results show that PCA fault diagnosis algorithm can distinguish the fault data of fuel cell well.