The state of the grinding wheel during the grinding process must be closely monitored because it has a direct impact on the workpiece's surface precision. The fluctuation in the machine sound during the grinding process is critical for the field operator to determine whether the grinding wheel is worn or not. The tool condition utilized in the machining process is typically defined by its wear state, which is a significant element in determining the manufacturing processes' machining efficiency. The purpose of this review is to provide a method for estimating the tool condition of a grinding wheel by studying different techniques such as an image sensor, machine learning algorithms, Decision Tree, and Acoustic Emission sensing. The simplified wear model's statistical characteristics, mean, standard deviation, and entropy were compared. Finally, machine learning methods and other techniques were utilized to combine statistical information to predict the grinding wheel's wear status. The results indicate that the Acoustic emission using machine learning could predict the tool wear with a high accuracy of 99%. Additionally, the field operator might evaluate the grinding wheel's wealth by changing the grinding sound or adding noise filters