In metal cutting processes, cutting conditions have an influence on reducing the production cost and time and deciding the quality of a final product. This paper presents a new methodology for continual improvement of cutting conditions. It is called GELCC (generation and evolutionary learning of cutting conditions). GELCC is a key component of an operation planning system for milling operations. It performs the following three functions: 1. The modification of recommended cutting conditions obtained from a machining data handbook. 2. The incremental learning of obtained cutting conditions using fuzzy ARTMAP neural networks. 3. The substitution of better cutting conditions for those learned previously by a proposed replacement algorithm. Various simulations illustrate the performance of GELCC, and then the simulation results for a given part are provided and discussed.