The article aims to develop a method for monitoring tool wear by analyzing chaotic characteristics in acoustic emission signals. Researchers used chaotic theory to analyze the acoustic emission signal from cutting tools, looking at both qualitative and quantitative aspects. They reconstructed the strange attractor track and Poincare map, computed correlation dimension and max Lyapunov exponent, and analyzed the results using the least square method. The findings indicate that chaotic patterns exist in the acoustic emission signal, and the correlation dimension and max Lyapunov exponent are related to the tool wear state. This study offers a new approach for predicting and monitoring tool wear online.