Abstract Water leakage management is required for urban water supply industry to minimize water loss and yield good economic benefit. There are many factors that influence urban pipeline leakage. To study these pipeline leakage factors, Grey relational analysis(GRA) is proposed to analyze and evaluate all the factors and draw a order of factors influencing on pipeline leakage. According to the order, a prediction model on some important factors is set up for the leakage by means of the multiple linear regress analysis and the prediction was made for the initial leakage time after the supply networks came into use. It will contribute to the change of passive management mode in water supply industry, so that the leakage can be prevented and controlled as early as possible.