Leakage detection system and method for long petroleum pipeline based on AFPSO-K-means

A leakage detection method for determining a leakage position of petroleum from a petroleum pipeline based on adaptive focusing particle swarm optimization (AFPSO)-K-means, the method comprising:

• initializing a particle swarm, and defining an initial velocity and an initial position of each particle in the particle swarm, the step of initializing the particle swarm and defining the initial velocity and the initial position of each particle in the particle swarm comprising:
• defining a number of sample points of the particles of the particle swarm in the petroleum pipeline to be n;
• detecting the n sample points of the particles of the particle swarm in the petroleum pipeline;
• constructing a data set of the n sample points xi=(xi1, xi2, . . . , xid);
• wherein i=1, 2, . . . , n;
• determining, by a computer processor, a fitness value of each particle based on the data set;
• traversing, by the computer processor, the fitness value of each particle to obtain an optimal position corresponding to the fitness value of each particle and a global optimal position in optimal fitness values of the particle swarm, the step of traversing the fitness value of each particle to obtain the optimal position corresponding to the fitness value of each particle and the global optimal position in the optimal fitness values of the particle swarm comprising:
• taking, by the computer processor, a minimum mean square error as a clustering objective function, and solving the clustering objective function to obtain a cluster center;
• obtaining, by the computer processor, the optimal position corresponding to the fitness value of each particle according to the cluster center;
• and
• obtaining, by the computer processor, the global optimal position in the optimal fitness values of the particle swarm by comparing the optimal fitness values of particles in the particle swarm;
• iteratively updating, by the computer processor, a velocity and a position of each particle based on the optimal position corresponding to the fitness value of each particle;
• when a distance from the position of each particle to the global optimal position in the optimal fitness values of the particle swarm is less than a preset threshold or a number of iterations reaches a preset value, outputting, by the computer processor, a current iteration updated result;
• and
• determining, by the computer processor, an actual leakage position on the petroleum pipeline based on the updated result.