To realize smart manufacturing in various machining processes, tool condition monitoring (TCM) systems are employed to detect the state of the tool in optimizing tool conditions and preventing catastrophic failures. However, many developed TCM systems lack flexibility and require extensive setup. To address these issues, the proposed algorithm takes advantage of repetitive machining operations in mass production settings and adopts similarity analysis to realize TCM by comparing the signals collected from the tool with known conditions against the signals generated by the tool to be monitored. To validate the effectiveness of the proposed TCM system, a case study was performed in which the power signal was collected and used in the similarity analysis. According to this case study, it has been proved that the proposed TCM algorithm is able to accurately predict the state of the tool, i.e., tool wear, with a very simple and flexible solution. Furthermore, several tool condition-induced machining parameters have been evaluated to satisfy various monitoring requirements. Nearly all evaluated machining parameters validated the performance and flexibility of the TCM algorithm.