Steam Leakage Detection in Nuclear Power Systems based on Gaussian Filtering and Frame Difference Method

The nuclear power system contains high-temperature and high-pressure steam inside. Once steam leakage occurs, it can lead to a loss of system function, and even cause casualties in severe cases. Therefore, it is urgent to carry out steam leakage detection in nuclear power system. At present, steam leakage is mainly detected through pressure gauges. If there is a small leakage when the system pressure is high, but the pressure reduction is not enough to attract the attention of operators, it will lead to the failure to detect steam leakage in a timely manner. Therefore, this detection method has certain drawbacks. This article introduces computer vision technology to monitor the nuclear power system and uses frame difference method to detect steam leakage in the high-temperature and high-pressure circuit system. The results show that this method can effectively detect the steam leakage in the early stage and give an early warning for the steam leakage detection video with the frame rate less than 26. This method provides a new idea for steam leakage detection of nuclear power system and can be effectively applied to engineering field, and also provides reference for leakage detection of high-temperature and high-pressure media in other fields.