|
Sl no | Purpose | Algorithms | Input parameters | Ref. (Year) |
|
1 | Optimization of machining parameters | MOGA, AI | Tool path cutting force | [1] (2019) |
2 | Multi-objective optimization | Modified harmony search Algorithm, GA | Cutting velocity, DOC, feed | [2] (2017) |
3 | Carbon emission quantification and prediction, cutting parameter optimization | Regression, MOTLBO | Speed, feed, depth of cut | [3] (2015) |
4 | Surface roughness prediction | Multiple linear Regression (MLR) | Speed, feed, depth of cut, flank wear, vibration | [4] (2015) |
5 | Microhardness and grain size prediction | RF, GA | Cutting speed, feed rate, tool edge radius, tool coating status | [5] (2015) |
|
Cases of Milling processes using Machining Learning Algorithms |
1 | Prediction model of milling surface roughness | Genetic algorithm range analysis | Milling depth, milling row spacing, speed | [6] (2019) |
2 | Tool condition monitoring | Adaptive neuro-fuzzy Inference, ANFIS model | Sound pressure, Cutting force | [7] (2018) |
3 | Tool wear monitoring | K-NN, SVM | Tool images | [8] (2017) |
4 | Tool breakage detection | SVM, SVR | Cutting force and power consumption data | [9] (2005) |
5 | Tool wear prediction | RF | Cutting force, vibration, Acoustic emission | [10] (2017) |
|
Cases of grinding processes using machining learning algorithms |
1 | Monitoring of surface roughness (Ra) and surface shape peak valley | IFSVR | Acoustic emission, grinding force, vibration | [11] (2015) |
2 | Material removal prediction method | XGBoost learning algorithm | Contact time, belt velocity Mesh size | [12] (2019) |
|
Cases of drilling processes using machining learning algorithms |
1 | Evaluation of quality and geometric profile circularity, dimensional error, delamination | Logical analysis of data | Thrust force, cutting force, torque | [13] (2015) |
2 | Detection of influx and loss | Random forests, support vector machine | Time-indexed drilling measurement parameters | [14] (2019) |
|