Imaging　algorithms　for　visualization　of　defects　play　a　significant　role　in　Lamb　wave-based　research　of　nondestructive　testing　and　structural　health　monitoring.　In　classical　algorithms,　the　position　or　distribution　of　defects　is　located　by　mapping　the　amplitude　or　phase　information　of　signals　from　the　time　domain　to　every　discrete　spatial　grid　of　the　structure.　It　is　time-consuming.　In　this　study,　the　diversity,　statistical,　and　fuzzy　characteristics　of　the　elliptic　imaging　algorithm　are　analyzed　first;　then,　an　intelligent　defect　location　algorithm　is　proposed　based　on　the　evolutionary　strategy　and　the　K-means　algorithm.　The　position　of　defects　can　be　identified　by　observing　the　distribution　of　individuals.　There　are　six　parts　in　the　proposed　algorithm,　including　the　data　structure　design,　adaptive　population　screening,　adaptive　population　reproduction,　diversity　maintenance　mechanism,　and　cutoff　criterion.　Considering　the　statistical　and　fuzzy　characteristics　in　the　detection,　several　specific　input　parameters　are　defined　in　our　algorithm,　such　as　the　distance-dependent　screening　threshold,　path-dependent　residual　vector,　and　path-independent　residual.　To　maintain　the　diversity　of　individuals　in　the　analysis,　we　have　made　two　adjustments　to　the　evolutionary　strategy:　one　is　to　optimize　the　population　screening　and　reproduction　steps　with　the　K-means　algorithm,　and　the　other　is　to　add　a　diversity　maintenance　method　into　the　evolutionary　strategy.　The　effectiveness　of　the　proposed　intelligent　defect　location　algorithm　is　verified　by　numerical　simulations　and　experiments.　Numerical　studies　indicate　that　the　proposed　algorithm　has　a　reliable　performance　in　the　detection　of　defects　with　different　shapes　and　sizes.　In　the　experimental　research,　we　demonstrate　that　the　efficiency　of　the　proposed　algorithm　is　about　200　times　faster　than　the　elliptic　imaging　algorithm.　And　the　optimum　parameter　setting　of　the　algorithm　is　investigated　by　analyzing　the　influence　of　parameter　setting　on　the　detection.