Online monitoring method of nuclear power plant system based on isolation forest method and sliding window method

An online monitoring method of a nuclear power plant system based on an isolation forest method and a sliding window method, comprising the following steps:

• step 1:
• acquiring historical operation data of a nuclear power plant in a normal state, and performing standardized preprocessing on the historical operation data of the nuclear power plant in a normal state by a maximum and minimum normalization method, so as to obtain historical operation dimensionless sample data X of the nuclear power plant in a normal state;
• step 2:
• acquiring real-time operation data of the nuclear power plant, performing standardized preprocessing on the real-time operation data of the nuclear power plant by the maximum and minimum normalization method, and adding the real-time operation data of the nuclear power plant after the standardized preprocessing to X by a sliding window method, so as to form training data X′, wherein
• assuming that a length of a sliding window is T, the historical operation dimensionless sample data X of the nuclear power plant in a normal state is expressed as:
• X={x1,x2, . . . ,xT-1,xT}
• after acquiring the real-time operation data xt of the nuclear power plant, deleting a first data of the sliding window, and adding the real-time operation data xt to the end of the sliding window at the same time, so as to form the training data X′:
• X′={x2,x3, . . . ,xTxt};
• step 3:
• inputting the training data X′ into an isolation forest model for abnormal detection training, and calculating an abnormal score of the real-time operation data comprising:
• step 3.1:
• performing random sampling on the training data X′ multiple times, constructing an isolated tree by using data obtained from each random sampling, setting a maximum depth of the isolated tree as 1, and integrating a plurality of isolated trees into the isolation forest model:
• l=ceiling [log2(φ)],
• wherein φ represents a number of subsamples, and y=ceiling(x) represents a round-up function, that is, the smallest integer greater than or equal to x is taken;
• step 3.2:
• calculating the abnormal score of the real-time operation data based on the isolation forest model:
• c
• ⁡
• (
• n
• )
• =
• {
• 2
• ⁢
• H
• ⁡
• (
• n
• -
• 1
• )
• -
• 2
• ⁢
• (
• n
• -
• 1
• )
• n
• n
• >
• 1
• 0
• otherwise
• ,
• ⁢
• s
• ⁡
• (
• x
• ,
• n
• )
• =
• 2
• -
• E
• ⁡
• [
• h
• ⁡
• (
• x
• )
• ]
• c
• ⁡
• (
• n
• )
• ,
• wherein n represents a sample size contained in a root node of the isolated tree, c(n) represents an average path length of the plurality of isolated trees, H(n) represents a harmonic function, H(n)=ln(n)+ε, ε=0.5772156649 represents an Euler's constant, h(x) represents a path length of the real-time operation data xt of the nuclear power plant in the isolated tree, E[h(x)] represents an expected value of the path length of the real-time operation data xt in the plurality of isolated trees of the isolation forest, and s represents the abnormal score of the real-time operation data;
• and
• step 3.3:
• if the abnormal score is greater than 0.5, determining that a state of the nuclear power plant system is abnormal at a current moment, and issuing an alarm;
• otherwise, determining that the state of the nuclear power plant system is normal at the current moment, acquiring the real-time operation data of a next moment, and returning to step 2;
• and
• step 4:
• monitoring, by the isolation forest model, the state of the nuclear power plant system based on the abnormal score to realize online real-time monitoring for the state of the nuclear power plant system.