In　order　to　solve　the　problems　of　poor　portability,　complex　implementation,　and　low　efficiency　in　the　traditional　parameter　training　of　the　Belief　rule-base,　an　artificial　bee　colony　algorithm　combined　with　Gaussian　disturbance　optimization　was　introduced,　and　a　novel　Belief　rule-base　parameter　training　method　was　proposed.　By　the　light　of　the　algorithm　principle　of　the　artificial　bee　colony,　the　honey　bee　colony　search　formula　and　the　cross-border　processing　method　were　improved,　and　the　Gaussian　disturbance　was　employed　to　prevent　the　search　from　falling　into　a　local　optimum.　The　parameter　training　was　implemented　in　combination　with　the　constraint　conditions　of　the　Belief　rule-base.　By　fitting　the　multi-peak　function　and　the　leakage　detection　experiment　of　oil　pipelines,　the　experimental　error　were　compared　with　the　traditional　and　existing　parameter　training　methods　to　verify　its　effectiveness.　©　Springer　Nature　Singapore　Pte　Ltd.　2018.