In　order　to　insure　good　performance　of　the　voltage　boosting　circuit　in　the　kneepad　used　for　curing　osteoarthritis,　the　circuit　parameters　should　be　optimized.　An　improved　particle　swarm　optimization　algorithm　is　used　to　optimize　the　circuit　parameters　that　control　the　output　strength.　At　the　same　time,　in　order　to　insure　the　calculability　of　the　objective　function　in　the　searching　process　of　the　particle　swarm,　neural　network　is　used　to　model　the　voltage　boosting　circuit.　The　neural　network　is　trained　and　tested　using　the　experimental　data.　Finally　the　performances　of　the　voltage　boosting　circuits　with　both　optimized　parameters　and　original　parameters　are　tested　and　compared　respectively.　The　test　result　proves　that　the　voltage　boosting　circuit　with　optimized　parameters　using　the　proposed　algorithm　can　insure　smoother　voltage　boosting,　and　possesses　better　performance.