Wear　over　time　affects　engine＇s　reliability　and　efficiency.　On-line　wear　monitoring　could　provide　timely　information　about　engine　health　condition.　In　the　current　study,　on-line　monitoring　of　engine　wear　via　an　on-line　visual　ferrograph　was　performed　in　reliability　tests　of　gasoline　engines,　and　a　wavelet-analysis-based　differential　method　of　data　analysis　for　wear　condition　estimation　was　proposed.　The　tests　were　designed　for　220h,　which　consist　of　a　running-in　stage　of　20h　and　a　thermal　shock　cycle　test　stage　of　200h.　One　of　the　tests　was　terminated　because　of　failures　in　the　main　bearings　and　crankshaft　journal　at　146th　hour　of　thermal　shock　cycle　test,　while　the　other　two　completed　successfully　without　failures.　Index　of　particle　coverage　area,　which　represents　wear-debris　concentration　in　lube　oil,　was　studied,　and　piecewise　trend-extraction　of　index　of　particle　coverage　area　was　achieved　by　wavelet　decomposition　and　reconstruction.　The　first-order　differential　of　the　index　of　particle　coverage　area　trend　was　used　to　represent　the　wear　rate　or　the　generation　rate　of　debris　for　health　condition　assessment　of　engines.　Off-line　oil　analyses　were　performed　in　laboratory　via　an　analytical　ferrograph,　and　engine　disassembly　results　of　the　engines　were　given　to　determine　the　causes　of　engine　failures　if　it　happened.　It　is　found　that　favorable　trend　extraction　from　index　of　particle　coverage　area　could　be　achieved　by　the　segmented　wavelet　de-noising.　Moreover,　on-line　visual　ferrograph　monitoring　estimated　the　engine　wear　at　macro-levels　effectively,　and　it　provided　an　advance　warning　for　the　failures　after　the　continued　deterioration　of　the　engine　wear.　The　study　and　application　of　this　method　can　make　early　failure　prediction　of　engine　and　avoid　serious　fault.