Optimal　design　of　the　water　distribution　network　is　a　multi-dimension　complex　optimization　problem.　In　this　paper,　an　auxiliary　individual　oriented　crossover　genetic　algorithm　is　adopted　to　optimize　the　problem.　Auxiliary　individual　oriented　crossover　operator　adopts　oriented　crossover　framework　and　assistant　individual　technique　which　is　beneficial　to　multidimensional　network　problem.　The　simulation　experiment　is　designed　to　test　the　performance　of　the　improved　algorithm.　In　the　experiment,　the　improved　algorithm　is　used　to　optimize　the　two　classical　pipeline　networks.　The　results　show　that　the　algorithm　can　obtain　the　optimal　engineering　cost　with　low　computational　cost.　©　2019　IEEE.