Electro-hydraulic　shaking　table　(EHST)　is　widely　used　to　simulate　earthquake　excitation　in　structural　seismic　tests.　However,　the　nonlinear　characteristics　of　the　EHST,　such　as　oil　flow,　friction,　and　dead　zone,　often　lead　to　the　distortion　of　seismic　wave　acceleration　tracking　and　even　cause　the　failure　of　the　test.　This　paper　describes　the　first　application　of　Echo-State　Networks　(ESNs)　to　achieve　high-precision　seismic　acceleration　tracking　of　the　EHST.　The　nonlinear　control　ability　of　the　conventional　three-variable　control　(TVC)　algorithm　in　the　EHST　is　discussed.　An　online　learning　compensation　control　framework　using　ESNs　for　“Transfer　System”　(The　“Transfer　System”　denotes　the　nonlinear　EHST　controlled　by　TVC)　is　proposed.　The　least　mean　square　(LMS)　algorithm　based　on　filtered-X　is　used　to　train　the　“ESN-Controller”　online,　and　the　initial　transients　of　the　“ESN-Controller”　are　reduced　by　using　an　estimation　model　of　the　actual　“Transfer　System”　and　a　conditional　switch.　The　offline　iterative　control　(OIC)　and　nonlinear　signal-based　control　(NSBC)　are　taken　as　the　baseline　algorithms　of　the　proposed　online　learning　compensation　control.　Simulation　results　show　that　the　proposed　online　learning　compensation　control　achieved　excellent　control　with　Pearson　correlation　coefficients　of　reference　and　responses　above　99.6%,　whereas　the　OIC　and　NSBC　provided　insufficient　control.　Moreover,　the　proposed　online　learning　compensation　control　can　also　reduce　the　control　error　caused　by　the　non-optimal　TVC　gains　in　the　linear　part　of　the　EHST.　This　work　throws　new　light　on　the　study　of　the　online　learning　control　algorithm　of　the　EHST.　©　2023　Elsevier　Ltd