Multi-island cavities are characterized by complex geometries, irregular boundaries, and discretely distributed islands. Tool paths generated by traditional zigzag cutting often suffer from frequent tool retractions, excessive non-cutting motion, and interference caused by islands. To address these issues, this paper proposes a deep reinforcement learning-based tool path generation method. First, the machining region of a complex cavity is discretized into driving lines, and continuous line groups are constructed through geometric processing and a grouping algorithm. In this way, the tool path generation problem is transformed into a multi-stage sequential decision-making problem, and a Markov Decision Process model is established. On this basis, a Deep Q-Network with prioritized experience replay is employed, enabling the agent to learn the endpoint visiting sequence through interaction with the environment and thereby reduce the total non-cutting motion distance. Compared with the local heuristic method and the classical zigzag scan algorithm, the proposed method reduces the total non-cutting motion distance and the number of tool retractions, especially for complex multi-island cavities. The results indicate that the proposed method has good adaptability and global optimization capability, providing a new solution for tool path generation in zigzag cutting of complex aero-engine cavities.

Trochoidal milling is known for its advantages in machining difficult-to-machine materials as it facilitates chip removal and tool cooling. However, the conventional trochoidal tool path presents challenges such as lower machining efficiency and longer machining time due to its time-varying cutter-workpiece engagement angle and a high percentage of non-cutting tool paths. To address these issues, this paper introduces a parameter-variant trochoidal-like (PVTR) tool path planning method for chatter-free and high-efficiency milling. This method ensures a constant engagement angle for each tool path period by adjusting the trochoidal radius and step. Initially, the nonlinear equation for the PVTR toolpath is established. Then, a segmented recurrence method is proposed to plan tool paths based on the desired engagement angle. The impact of trochoidal tool path parameters on the engagement angle is analyzed and coupled this information with the milling stability model based on spindle speed and engagement angle to determine the desired engagement angle throughout the machining process. Finally, several experimental tests are carried out using the bull-nose end mill to validate the feasibility and effectiveness of the proposed method.

Ruled surfaces found in engineering parts are often blended with a constraint surface, like the blade surface and hub surface of a centrifugal impeller. It is significant to accurately machine these ruled surfaces in flank milling with interference-free and fairing tool path, while current models in fulfilling these goals are complex and rare. In this paper, a tool path planning method with optimal cutter locations (CLs) is proposed for 5-axis flank milling of ruled surfaces under multiple geometric constraints. To be specific, a concise three-point contact tool positioning model is firstly developed for a cylindrical cutter. Different tool orientations arise when varying the three contact positions and a tool orientation pool with acceptable cutter-surface deviation is constructed using a meta-heuristic algorithm. Fairing angular curves are derived from candidates in this pool, and then curve registration for cutter tip point on each determined tool axis is performed in respect of interference avoidance and geometric smoothness. On this basis, an adaptive interval determination model is developed for deviation control of interpolated cutter locations. This model is designed to be independent of the CL optimization process so that multiple CLs can be planned simultaneously with parallel computing technique. Finally, tests are performed on representative surfaces and the results show the method has advantages over previous meta-heuristic tool path planning approaches in both machining accuracy and computation time, and receives the best comprehensive performance compared to other multi-constrained methods when machining an impeller.