Previous　studies　on　Lamb　wave　touchscreen　(LWT)　were　carried　out　based　on　the　assump-tion　that　the　unknown　touch　had　the　consistent　parameters　with　acoustic　fingerprints　in　the　reference　database.　The　adaptability　of　LWT　to　the　variations　in　touch　force　and　touch　area　was　investigated　in　this　study　for　the　first　time.　The　automatic　collection　of　the　databases　of　acoustic　fingerprints　was　realized　with　an　experimental　prototype　of　LWT　employing　three　pairs　of　transmitter–receivers.　The　self-adaptive　updated　weight　coefficient　of　the　used　transmitter–receiver　pairs　was　employed　to　successfully　improve　the　accuracy　of　the　localization　model　established　based　on　a　learning　method.　The　performance　of　the　improved　method　in　locating　single-and　two-touch　actions　with　the　reference　database　of　different　parameters　was　carefully　evaluated.　The　robustness　of　the　LWT　to　the　variation　of　the　touch　force　varied　with　the　touch　area.　Moreover,　it　was　feasible　to　locate　touch　actions　of　large　area　with　reference　databases　of　small　touch　areas　as　long　as　the　unknown　touch　and　the　reference　databases　met　the　condition　of　equivalent　averaged　stress.　©　2021　by　the　authors.　Licensee　MDPI,　Basel,　Switzerland.