More Like this

1. Time-Series Data-Driven Machine Learning of Milling Chattering

   https://doi.org/10.1115/1.4069196  

   Hu, L; Gao, R; Guo, Y B (October 2025, Journal of Manufacturing Science and Engineering)

   Abstract Milling is a critical manufacturing process to produce high-value components in aerospace, tooling, and automotive industries. However, milling is prone to chatter, a severe vibration that damages surface quality, cutting tools, and machines. Traditional experimental and mechanistic methods of chatter prediction have significant limitations. This study presents a data-driven machine learning (ML) model to predict and quantify milling chatter directly based on time-series vibration data. Three ML models, including hybrid long short-term memory (LSTM)—fully convolutional network (FCN) model, gated recurrent unit (GRU)—FCN model, and temporal convolutional network (TCN) models, have been developed and verified by incorporating milling parameters to enhance prediction accuracy and stability. Among the proposed models, the best-performing ML model (GRU-FCN) demonstrates strong performance in chatter prediction and severity quantification, providing actionable insights with improved computational efficiency. The integration of milling parameters into the ML model notably enhances the prediction accuracy and stability, proving particularly effective in real-time monitoring scenarios. 

   more » « less
2. Trochoidal milling: investigation of dynamic stability and time domain simulation in an alternative path planning strategy

   https://doi.org/10.1007/s00170-018-03280-y  

   Akhavan Niaki, F; Pleta, A; Mears, L; Potthoff, N; Bergmann, Jim A; Wiederkehr, P (July 2019, International journal, advanced manufacturing technology)

   Trochoidal milling is an alternative path planning strategy with the potential of increasing material removal rate per unit of tool wear and therefore productivity cost while reducing cutting energy and improving tool performance. These characteristics in addition to low radial immersion of the tool make trochoidal milling a desirable tool path in machining difficult-to-cut alloys such as nickel-based superalloys. The objective of this work is to study the dynamic stability of trochoidal milling and investigate the interaction of tool path parameters with stability behavior when machining IN718 superalloy. While there exist a few published works on dynamics of circular milling (an approximated tool path for trochoidal milling), this work addresses the dynamics of the actual trochoidal tool path. First, the chip geometry quantification strategy is explained, then the chatter characteristic equation in trochoidal milling is formulated, and chatter stability lobes are generated. It is shown that unlike a conventional end-milling operation where the geometry of chips remains constant during the cut (resulting in a single chatter diagram representing the stability region), trochoidal milling chatter diagrams evolve in time with the change in geometry (plus cutter entering and exiting angles) of each chip. The limit of the critical depth of cut is compared with conventional end milling and shown that the depth of cut can be increased up to ten times while preserving stability. Finally, the displacement response of the cutting tool is simulated in the time domain for stable and unstable cutting regions; numerical simulation and theoretical results are compared. 

   more » « less
3. Intermethod comparison and evaluation of near surface residual stress in aluminum parts subject to various milling parameters

   https://doi.org/10.1007/978-3-030-30098-2  

   Chighizola, Christopher R.; D’Elia, Christopher R.; Hill, Michael R. (June 2019, Residual Stress, Thermomechanics & Infrared Imaging and Inverse Problems, Volume 6; Proceedings of the 2019 Annual Conference on Experimental and Applied Mechanics)

   Near surface residual stress (NSRS) induced by machining (e.g., milling) is known to drive distortion in machined aluminum, particularly in thin complex geometries with tight tolerance requirements where large distortion is undesirable. The understanding and characterization of NSRS in milled aluminum parts is important and should be included in the design and manufacturing process. There exist a variety of experimental tests characterizing these stresses. The objective of this paper is to assess the quality of three experimental methods for evaluating NSRS in prismatic aluminum parts subject to various milling parameters. The three methods are: hole-drilling, slotting, and x-ray diffraction, all of which include incremental material removal. The aluminum parts are cut from stress-relieved plate, AA7050-T7451. A combination of milling table and tool speeds are used to machine a flat surface in the parts. Measurements are made at specified locations and depths on each part. NSRS data from the hole drilling and slotting measurements were comparable; NSRS data from x-ray diffraction differed and was less repeatable. NSRS data for different milling parameters shows that the depth of NSRS increases with feed per tooth but is unaffected by different cutting speeds. 

   more » « less
4. Learning-Based Adaptive Optimal Control of Linear Time-Delay Systems: A Policy Iteration Approach

   https://doi.org/10.1109/TAC.2023.3273786  

   Cui, Leilei; Pang, Bo; Jiang, Zhong-Ping (May 2023, IEEE Transactions on Automatic Control)

   This paper studies the adaptive optimal control problem for a class of linear time-delay systems described by delay differential equations (DDEs). A crucial strategy is to take advantage of recent developments in reinforcement learning (RL) and adaptive dynamic programming (ADP) and develop novel methods to learn adaptive optimal controllers from finite samples of input and state data. In this paper, the data-driven policy iteration (PI) is proposed to solve the infinite-dimensional algebraic Riccati equation (ARE) iteratively in the absence of exact model knowledge. Interestingly, the proposed recursive PI algorithm is new in the present context of continuous-time time-delay systems, even when the model knowledge is assumed known. The efficacy of the proposed learning-based control methods is validated by means of practical applications arising from metal cutting and autonomous driving. 

   more » « less
5. Tool wear area estimation through in-process edge force coefficient in trochoidal milling of Inconel 718

   Shah A.; Agarwal A.; Mears L. (January 2023, Manufacturing letters)

   The rapid wear and premature failure of the cutting tool are prone to happen due to increased forces during machining difficult-to-cut materials such as Inconel 718. The application of alternative toolpath such as trochoidal milling has significantly improved tool life and reduced the overall cycle time of the process. The wear pattern of the tool has a direct impact on the cutting forces, which increases with tool deterioration. The cutting forces in milling are modeled through the mechanistic force model and can be designated through a set of force coefficients, i.e. cutting and edge representing the shearing and ploughing phenomenon of metal removal. It has been established in the literature that tool wear has a considerable effect on the value of edge force coefficients. This paper aims to determine the in-process edge force coefficients for the trochoidal toolpath and correlates them with the corresponding flank wear area. The proposed correlation will further assist in predicting the level of flank wear area based on the force values in trochoidal milling. 

   more » « less