The rapid development of modern science and technology brings with it a high demand for manufacturing quality. The surface integrity of a machined part is a critical factor which needs to be considered in the selection of the appropriate machining processes. By monitoring and predicting tool wear, it is possible to improve sustainability by reducing the scrap rate due to poor surface integrity. In this work, Data Dependent Systems (DDS), a stochastic modeling and analysis technique, was applied to study spindle motor energy consumption during a hard milling operation. The objective was to correlate the spindle power to tool wear conditions using DDS analysis. The spindle power was monitored and the time series trends were decomposed to study the frequency variation with different severities of tool wear conditions and processing parameters. Analysis of Variance (ANOVA) was also used to determine factors significant to the energy consumption by a spindle motor. Experiments indicate that low-level frequency of spindle power is correlated with the amount of tool wear, cutting speed, and feed per tooth. Results suggest that effective tool wear monitoring may be achieved by focusing on low-level frequencies (0.1 rad/sec) highlighted by DDS methodology.