Three in-process tool wear monitoring systems have been developed in this research. They are: (1) the multiple linear regression based in-process tool wear prediction (MLR-ITWP) system; (2) the artificial neural networks based in-process tool wear prediction (ANN-ITWP) system; and (3) the statistics assisted fuzzy-nets based in-process tool wear prediction (S-FN-ITWP) system.;Before these above-mentioned systems were developed and evaluated, statistical approaches had been implemented to analyze and identify the most significant force signal for tool wearing monitoring system. This study demonstrates that the average peak cutting forces in the Y direction (the direction that is perpendicular to the table feed) is the most effective cutting force representation for tool wear monitoring.;Following with this discovery, the first system (MLR-ITWP system) was developed using a multiple linear regression model through 100 experimental data sets. Another nine data sets were used to test the system. The average tool wear prediction error of the MLR-ITWP system was +/-0.039 mm through the testing data. The second system (ANN-ITWM system) was developed using back-propagation artificial neural network through the same experimental data and tested with another nine data sets. The average tool wear prediction error of this ANN-ITWM system was +/-0.037 mm. The third system (S-FN-ITWM system) was developed using fuzzy-nets assisted statistically through the same experimental data and tested with another nine data sets. The average tool wear prediction error was +/-0.023 mm.;The scope of this research is to provide systems that can be integrated into smart computer numerical control (CNC) machine development in tool monitoring system. The success of this research provides the researcher better position in further related research.