A　real-time　electric　nose　(E-nose)　with　a　metal　oxide　sensor　(MOS)　array　was　developed　to　monitor　5　highly　flammable　liquids　(ethanol,　tetrahydrofuran,　turpentine,　lacquer　thinner,　and　gasoline)　in　this　work.　We　found　that　temperature　had　a　significant　impact　on　the　test　results　and　temperature　control　could　efficiently　improve　the　performance　of　our　E-nose.　The　results　of　our　qualitative　analysis　showed　that　principal　component　analysis　(PCA)　could　not　efficiently　distinguish　these　samples　compared　to　a　back-propagation　artificial　neural　network　(BP-ANN)　which　had　a　100%　accuracy　rate　on　the　test　samples.　Quantitative　analysis　was　performed　by　regression　analysis　and　the　average　errors　were　9.1%–18.4%.　In　addition,　through　anti-interference　training,　the　E-nose　could　filter　out　the　potential　false　alarm　caused　by　mosquito　repellent,　perfume　and　hair　jelly.　©　2020　by　the　authors.　Licensee　MDPI,　Basel,　Switzerland.