In this research, the neural networks-based in-process adaptive surface roughness control (NN-IASRC) system employing multiple cutting tools was successfully developed for end-milling operations. The dynamometer sensor was used to monitor the uncontrolled cutting tool conditions to increase the accuracy of the surface roughness control. An empirical approach was applied to discover the proper cutting force signals, the average resultant peak force in XY plane ( Fap) and the absolute average force in the Z direction (Faz). These two forces were employed to represent the uncontrollable cutting tool conditions for surface roughness control. A statistical method was employed to verify that the cutting tools could influence the surface roughness, and obtain the correlation between surface roughness and the cutting force signals for the preparation of constructing the NN-IASRC system.;A neural networks theorem was successfully applied to build the NN-IASRC system. The neural networks associated with sensing technology were applied as a decision-making technique to control the surface roughness for a wide range of machining parameters. The NN-IASRC system consisted of two subsystems. One was the in-process neural networks based surface roughness prediction (INN-SRP) system, which was employed to predict the surface roughness. The other was the neural networks based adaptive machining parameters control (NN-APMC) system, which was utilized to adjust the adaptive degree of feed rate when the quality of predicted surface roughness did not fit the desired one. The accuracy of the INN-SRP system was 93%, and 100% for the NN-IASRC system. The high accuracy of results within a wide range of machining parameters indicates that the system can be practically applied in industry.