Control　parameters　of　classical　control　system　are　expected　to　be　online　tuned　and　optimized　by　intelligent　methods,　in　order　to　improve　performance　and　help　engineers　reduce　a　lot　of　repetitive　work　in　dangerous　and　harmful　working　environments.　Main　ideas　and　works　of　this　paper　are　as　follows:Firstly,　change　ratio　based　expert　PID　control　method　(EA-PID)　is　proposed　to　expand　range　of　control　parameters.　Expert　rule　table　(ERT)　of　expert　PID　control　method　(E-PID)　is　replaced　by　change　ratio　table　(CRT)　of　EA-PID.　Adjusted　parameters　of　EA-PID　are　the　results　of　multiplying　change　ratios　in　current　adjusting　cycle　and　control　parameters　in　previous　adjusting　cycle.　Secondly,　NARX　prediction-based　NARX-E-PID　and　NARX-EA-PID　are　proposed.　The　NARX　neural　network　is　designed　as　a　time　series　predictor　to　predict　the　output　of　the　control　system,　then　control　parameters　are　adjusted　according　to　the　predicted　output.　Thirdly,　comparative　simulations　of　all　the　above　methods　are　implemented　to　verify　the　improved　effects.　Finally,　theoretical　analysis　is　provided　to　ensure　the　stability　of　control　systems.　Effect　are　as　follows:　Firstly,　comparative　simulations　verify　that　the　improved　methods　have　faster　control　speed,　smaller　steady-state　error,　less　overshoot,　and　better　ability　of　anti-interference.　Secondly,　theoretical　analysis　shows　that　the　unstable　control　systems　with　adjusted　parameters　can　be　changed　into　a　stable　system　by　stability　judgment　in　each　adjusting　cycle.