Hydrogen-fueled　Wankel　rotary　engine　has　excellent　power　density　and　low　backfire　possibility,　however,　as　well　as　the　severe　knock.　The　knock　is　closely　related　to　the　in-cylinder　combustion　process,　therefore,　the　present　work　is　conducted　to　identify,　predict　and　classify　the　knock　by　data-driven　based　on　combustion　parameters　in　the　hydrogen-fueled　Wankel　rotary　engine.　The　results　show　that:　Knock　type　can　be　identified　well　according　to　knock　intensity　and　crank　angle　of　peak　knock　pressure　through　the　Gaussian　Mixture　Model.　There　are　141　strong　knock　cycles　and　809　weak　knock　cycles　in　test　data.　Compared　with　Support　Vector　Machines　and　Backpropagation　Neural　Networks,　Multiple　Linear　Regression　has　a　better　global　performance　in　knock-level　prediction　based　on　combustion　parameters.　The　maximum　pressure　rising　rate　and　CA50　have　more　significant　impacts　on　knock,　the　partial　of　regression　coefficients　of　which　is　about　0.42　and　-0.58,　respectively.　In　particular,　due　to　different　formation　mechanisms,　the　prediction　models　of　two　types　of　knock　are　recommended　to　be　established　separately.　In　addition,　the　Support　Vector　Machine　can　be　applied　to　conduct　knock　classification.　Among　kernel　functions　in　Support　Vector　Machine,　the　linear　kernel　function　can　achieve　optimal　mean　test　accuracy,　about　88.66　%.