This　paper　presents　a　symbiotic　organism　search　(SOS)-based　support　vector　regression　(SVR)　ensemble　for　predicting　the　printed　circuit　board　(PCB)　cycle　time　of　surface-mount-technology　(SMT)　production　lines.　Being　able　to　predict　the　PCB　cycle　time　accurately　is　essential　for　optimising　the　SMT　production　schedule.　Although　a　machine　simulator　can　be　reliably　used　for　single-type　PCB　production,　it　is　time-consuming　and　often　inaccurate　for　the　simulator　to　be　applied　for　highly　mixed　orders　in　multiple　flexible　SMT　production　lines.　Due　to　the　dynamic　changes　in　both　PCB　orders　and　SMT　production　lines,　there　is　a　diverse　set　of　samples,　but　the　size　of　similar　samples　is　relatively　small.　An　SVR　model　is　therefore　used　to　estimate　the　PCB　cycle　time,　and　the　SOS　algorithm　is　employed　to　optimise　the　SVR　parameters.　We　assume　that　uncertainties　during　the　assembly　process　can　be　captured　by　the　characteristics　of　PCB　and　SMT　lines,　which　are　utilised　as　features　to　train　the　SVR　model.　To　enhance　the　performance　of　the　prediction　accuracy,　an　SOS-SVR　ensemble　is　proposed.　Experiments　based　on　datasets　collected　from　a　leading　global　electronics　manufacturer　confirm　the　efficiency　of　the　proposed　approach　compared　to　industrial　solutions　currently　in　place　and　other　machine　learning　methods.