Table 6.

Developed machining process optimization based on cutting force and MRR.

Approach	Objective	Methods	Feedback	Machining Process
Offline	Power-constrained optimization [31]	An iterative optimization approach constrained with the spindle power to estimate feedrates minimizing the production time	Offline spindle power and feedrate (in the previous operation)	Milling
Offline	Spindle power control [14]	Multi-objective optimization is developed to improve machining efficiency and reduce fluctuations in the spindle power based on an ANN-based model of spindle power		Milling
Offline	Cutting force control [164]	A machining time minimizer is developed based on the simulation of cutting engagements and predicting cutting forces. The optimizer maximizes the cutting forces through the tool path by manipulating the feedrate		Milling
Online	Cutting force control [165]	An online force control system was developed that automatically adjusts feedrate based on the force signal. To prevent vibration damage, a chatter suppression control module was added to the system by analyzing the force feedback.	Force sensor	Turning
Online	Cutting force control [166]	Nonlinear mechanistic machining force model identification with Bayesian inference and recursive least square estimator	Directional strain gauge-based force sensors	Turning
Offline/ Online	Cutting force control [162]	Combination of offline cutting force optimization using artificial neural network (ANN) as the predictive model and particle swarm optimization (PSO) along with online feedforward force control using neural control to adjust the feedrate by assigning a feedrate override percentage	Cutting force signals	Milling
Offline/ Online	Cutting force, dynamic stability and cutting temperature [13]	A hybrid optimization, monitoring, and control (HOMC) system was introduced considering the machining primary limits of chatter, tool deflection, and thermal stresses	Spindle power, vibration and acoustic emission	Milling