High-speed machining is a technique that maintains a high interest in the manufacture of metal parts for the excellent results it provides, both in surface finish and in economic benefits. In the industry, the tendency is to incorporate data management and analysis techniques to generate information that helps improve the surface roughness results in machining. A good alternative to improve the surface quality results in the manufacture of metal parts is using predictive models of the surface roughness. In this document, we present work done with experimental data obtained from two high-speed machining (HSM) machines with different types of tools and cutting conditions, conducted under an experimental design with interest in three of factors commonly studied to generate surface roughness models: tool characteristics, cutting conditions, and characteristics of the machined material. Steel and aluminum alloys were used in the experimentation. The results are contrasted with prior experiences that use the same experimental design but with different soft computing techniques and they are also contrasted with the results of similar previous works. Our results show accuracies ranging from 61.54% to 88.51% on the datasets, which are competitive results when compared with the other approaches. We also find the axial cut-depth is the most influential feature for the slots datasets and the hardness and diameter of the cutting tool are the most influential features for the geometries datasets.
High-speed machining is a technique that maintains popularity in the manufacture of metal parts, with high levels of usability in the metalworking industry to manufacture metal parts with high levels of quality in surface finish [
In the industrial field of mechanical cutting, the tendency is to incorporate data managing and analysis techniques to generate information that helps improve machining surface quality [
Surface roughness average is the most used parameter to estimate the surface quality according to [
An extended research has been conducted into the applicability of artificial intelligence and soft computing techniques for surface roughness prediction in mechanical cutting over the last years, follow previous works as [
For example, in [
The profitability of metal cutting operations depends to a great extent on factors such as precision in mechanical cutting, excellent surface finish, and minimum wear of the tool [
There are multiple works on the literature that use soft computing to estimate surface roughness or to study the factors that can affect surface roughness. However, in our review of the literature for this work, there were few works that used decision trees and to the best of our knowledge, no previous works with the specific technique of Gradient Boosted Trees to generate a predictive model of surface roughness.
This document presents a surface roughness prediction model that considers a subset of elements involved in the milling process that is related to the machined piece, the tool, and characteristics of the machine tool. To generate the predictive model of surface roughness, metal alloy pieces commonly used in the industry have been employed. The data used to generate the model are the result of experiments on two different machines and, in each one, various combinations of variables that typically influence the surface quality results in the milling process have been used.
The rest of the document is structured as follows. Section
The surface quality or surface roughness is intimately connected with the appearance of the machined or manufactured surface, which is normally expressed with a Ra value [
The Ra value is usually calculated by integrating the arithmetic mean of the absolute values of ordinates
Although low-speed machining can provide better surface roughness, it reduces the efficiency of the industry, implies more machining time, and consequently increases production costs [
Currently, there is plenty of face milling research aimed at predicting surface roughness, a parameter that will decrease with respect to changes in other parameters like increased tool wear or flank wear, cutting force, depth-cut, or feed per tooth. There are several works that have been presented in the last 5 years in the topic of predicting surface roughness based on artificial intelligence techniques. For example, on [
Fuzzy logic and regression analysis were used in [
Furthermore, in [
In spite of the high number of works, such as those described above, the in-process measurement of surface roughness is difficult and often unfeasible. Therefore, as it has been said in the introduction, having techniques to predict surface quality using postprocess data is a way of working that is gaining interest in the parts manufacturing industry. In this sense, predictive models have much to contribute.
In artificial intelligence, predictive tasks are one of the central topics of machine learning that involves inducing a model from training data (known as training instances), then this model can be applied to future instances to predict a target variable of interest [
Many scientific articles in the literature work with predictive algorithms and particular training instances in a domain selected according to research interests. One advantage of working with training instances in a domain is that the predictive algorithm will find a more precise model that can generate good values of the target variable in the presence of new data.
There are several recent works in which artificial intelligence techniques are used to estimate the surface roughness in machining. In [
Learning based on decision trees is a type of predictive model that uses a decision tree to go from observations of an object (represented as the branches of a tree) to a certain conclusion about a target value of the object (represented by the tree leaves). It is used in statistics, data mining, and machine learning and has had several applications, both at the academic level and in the industry [
This classifier is one of the easiest modeling techniques to interpret thanks to its graphic representation; they are didactic and easy to understand. They base their predictions on inductive learning; that is, they consider the values that the different attributes or variables take, creating in this way, a series of rules to be able to determine what value the dependent variable will take based on certain situations. It should be noted that the results delivered by the decision tree depend to a large extent on the volume of data contained in each category. The accuracy of the model with respect to reality will be better the greater the amount of data available of that combination of features.
Finally, in the industry of crafting pieces from machine-cutting, it is highly important to also obtain information about the factors that affect surface roughness and to also have the ability to influence such factors. In particular, decision trees are a useful technique to explain the aforementioned information, according to the works of [
The term boosting refers to a family of algorithms that convert weak learners into strong learners, understanding that a weak learner is only slightly better than a random choice, while a strong learner has an almost perfect performance [
There are many works that use artificial intelligence techniques. The Gradient Boosting model is a machine learning technique that can be used in both regression and classification problems. The techniques of gradient boosting use an ensemble of weak models, in the case of this work trees, which together allow forming a stronger model. The ensemble is constructed in a stage-wise process by gradient descent in function space. The final model is a function that takes as input a vector of attributes
On the other hand, one of the reasons for using GBT in contrast to other predictive models is that ensemble methods, in general, are usually the classifiers/regressors that deliver the best
One of the advantages of ensemble models is that their tuning process is reliable and easy when compared to other approaches such as artificial neural networks [
High-speed machining is a type of milling operation. Milling is defined in previous works [
On the field of machining processes, there are many inputs and parameters that have an influence on the resulting surface roughness; some of them can be controlled while others cannot be directly controlled [ Experiment Preparation. Two different kinds of experiments (Exp-1 and Exp-2) were implemented. Accordingly, two types of probes have been used. For Exp-1, we prepared test pieces of steel F-114 (F-114 is the Spanish notation for this steel ( Experimentation. This step consists of performing the milling for each one of the prepared experiments. The different setup of Exp-1 and Exp-2 are made using all the combinations of values for the predictor variables, these are described in Table Preprocessing. In this step, the Exp-1 and Exp-2 datasets are prepared. In detail, this step consists of computing the average values of surface roughness (Ra) and associating this result with the experimental conditions (i.e., the values of the predictor variables). Model Generation. In this step the models for Exp-1 and Exp-2 are generated through machine learning; the details are in Sections Analysis of Results. This analysis is done in two dimensions: (1) checking the quality of the models and (2) validating its practical utility. For (1), classical machine learning metrics (e.g., recall, precision, and accuracy) were used to measure the performance obtained in the classification of surface roughness. For (2), the validation is done by comparing results (the GBT models) with other classifiers that have been used in the literature.
Variables used in the study including symbols, units, and values/ranges.
Variable | Symbol | Unit | Values/Ranges |
---|---|---|---|
Axial Depth of Cut | ap | mm | Exp-1 = |
Exp-2 = | |||
| |||
Advance Speed-Feed Rate | F | mm/min | Exp-1 = |
Exp-2 = | |||
| |||
Diameter of the Tool | diam | mm | Exp-1 = |
Exp-2= | |||
| |||
Hardness of the Material | HB | 85-150 | |
| |||
Rotating Speed | n | rpm | Exp-1 = |
Exp-2 = | |||
| |||
Radial Depth of Cut | ae | mm | Exp-2 = |
| |||
Number of Teeth | flutes | Exp-1 = | |
Exp-2 = |
As mentioned before, two different experiments were designed to obtain the experimental data: one for machining slots on steel F-114 test specimens (Exp-1) and another for machining geometries using aluminum alloy (Exp-2). Each of these two experiments was performed initially in a machining center and later in a second machining center with different characteristics to the first, to validate the experimental design and the predictive model of surface roughness obtained in the first machining center. Also, in both experiments the machining centers were equipped with high-pressure coolant fluid: Houghton HOCUT b-750 cutting oil at 5%, a type of coolant fluid frequently used in the industry for its high quality and anticorrosive properties [
Predictive models have been used by authors on this domain in order to analyze the behavior of machines in particular cutting conditions. For example, Pimenov et al. [
The experimentation in HSM is generally expensive; thus, for the experimentation described in this paper the experimental model described in [
In each of the experiments (Exp-1 and Exp-2) conditions were set related to the tool, machine (cutting conditions), and material to be machined or test specimen. In that order, said characteristics are described below for each experiment. Table
Exp-1 was designed to generate linear cuts over steel probes and measure surface roughness on a linear surface; the tool characteristics were its diameter and the number of flutes. Karnasch tools (models 30.6455 and 30.6465) of different diameters were used. Considering standard machining of slots in the manufacture of molds, four different diameters of tools were used: 6,8,10 and 12 mm, and for each type of diameter, variations of 2 and 6 flutes were used per tool (flutes). Two slots lengths were made for each diameter and flutes variation (2x4x2), for a total of 16 experimental-tool combinations.
The characteristics of the cutting conditions are the axial depth of cut (ap), advance speed/feed rate (F), and spindle rotation speed (n). The machining of slots was done with F = 1500 mm/min and n = 5000 rpm initially, and then increments of 25, 50, and 75% of the initial F and n were applied. For each of the experimental-tool combination (described above) variations of ap (0.2, 0.4, 0.6, and 1.0), F (1500, 1875, 2250, and 2625), and n (5000, 6250, 7500, and 8750) were applied (see Table
Examples of combinations of the variables described above (Table
Examples of machining cutting conditions and Ra values in Exp-1.
Machine | diam | flutes | ap | F | n | Ra |
---|---|---|---|---|---|---|
1 | 6 | 2 | 0.2 | 1500 | 5000 | Smooth |
6 | 6 | 0.4 | 1500 | 6250 | Smooth | |
8 | 2 | 0.6 | 1875 | 5000 | Semi-Fine | |
8 | 6 | 1 | 2250 | 6250 | Smooth | |
10 | 6 | 0.2 | 2625 | 5000 | Semi-Fine | |
10 | 2 | 0.4 | 1875 | 8750 | Fine | |
| ||||||
2 | 6 | 2 | 0.2 | 2250 | 5000 | Smooth |
6 | 2 | 0.4 | 2250 | 7500 | Semi-Fine | |
6 | 6 | 0.6 | 1500 | 8750 | Smooth | |
8 | 2 | 1 | 1875 | 6250 | Fine | |
8 | 6 | 0.2 | 2250 | 5000 | Smooth | |
10 | 6 | 0.4 | 2625 | 7500 | Smooth |
In order to calculate the surface roughness average (Ra), partial values of surface roughness in a slot were measured. In order to do this, contact profilometers were used such as described in [
In accordance with ISO: 4288 (1996) and ISO: 1302 (2002), there are several discrete values for Ra that are related to continuous values (all values in nanometers) [
Discretization of variables of the Exp-1 model.
State | F | n | ap | Ra |
---|---|---|---|---|
[lower, upper) | [lower, upper) | [lower, upper) | ||
0 | | | 0.2 | Smooth = |
1 | | | 0.4 | Fine = |
2 | | | 0.6 | Semi-Fine = |
3 | | | 1 | Medium = |
Exp-2 was designed to generate nonlinear cuts (geometries) to measure surface roughness on a radial surface. The tool characteristic was tool diameter (diam); tools Karnash of different diameters (10, 12, 16, and 20 mm) were used, but the same number of flutes (4 flutes). The characteristics of the cutting conditions for Exp-2 are ae, ap, f, and n (see Table
The machining of geometries was performed with n = 8000 rpm initially; after making increments of 20% for each subsequent value the set n =
As it has been said above, the surface roughness labels were assigned in accordance with the average roughness established in ISO: 4288 and ISO: 1302 (see Table
Examples of cutting conditions of geometries and Ra values in Exp-2.
Machine | F | diam | ae | ap | HB | n | Ra |
---|---|---|---|---|---|---|---|
M1 | 500 | 10 | 10 | 10 | 111 | 8000 | Smooth |
675 | 10 | 10 | 5 | 110 | 8000 | Smooth | |
750 | 10 | 5 | 10 | 111 | 8000 | Smooth | |
550 | 12 | 10 | 5 | 112 | 8000 | Smooth | |
675 | 12 | 5 | 10 | 111 | 8000 | Fine | |
750 | 12 | 5 | 5 | 110 | 8000 | Fine | |
500 | 12 | 10 | 10 | 111 | 9600 | Fine | |
675 | 12 | 5 | 5 | 111 | 9600 | Fine | |
750 | 12 | 10 | 10 | 111 | 9600 | Fine | |
| |||||||
M2 | 500 | 12 | 10 | 10 | 85 | 12000 | Smooth |
675 | 12 | 10 | 5 | 85 | 12000 | Smooth | |
750 | 12 | 10 | 10 | 85 | 15000 | Fine | |
500 | 16 | 10 | 5 | 85 | 15000 | Smooth | |
675 | 16 | 5 | 10 | 85 | 15000 | Smooth | |
750 | 16 | 5 | 5 | 85 | 15000 | Smooth | |
500 | 20 | 5 | 10 | 85 | 15000 | Smooth | |
675 | 20 | 5 | 5 | 87 | 15000 | Smooth |
A summary of both the class labels and the continuous variables discretization (described above) is shown in Table
Discretization of the continuous variables of the Exp-2 model.
State | HB | ae | ap | Ra |
---|---|---|---|---|
[lower, upper) | [lower, upper) | |||
0 | | 0.5 | 5 | Smooth = |
1 | | 0.5 | 5 | Fine = |
2 | | 1 | 10 | Semi-Fine = |
3 | | 1 | 10 | Ground = |
Additional information for each dataset.
Data set | Description of the data |
---|---|
Slots | Maximal number of slots per test piece: 31 |
Minimum number of slots per test piece: 15 | |
Number of experiments (4 variations of ap for each slot): 462 | |
Number of partial measurements of surface roughness: 1848 | |
| |
Geometries | Maximal number of geometries per test piece: 8 |
Minimum number of geometries per test piece: 6 | |
Number of experiments (2 variations of ae for each geometry): 768 | |
Number of partial measurements of surface roughness: 1638 |
To obtain the models described above, RapidMiner Studio 7.6 ® (free version) will be used. This tool allows for obtaining various machine learning models from the data [
The workflow implemented in RapidMiner.
The datasets have been acquired following the experimental design described in [
In this research, a series of methods will be evaluated, measuring the performance obtained in the classification of the variables of interest. The different evaluation metrics to be used in this work will be detailed below; in particular, the performance indicators to be used to compare methods are
Based on the data obtained in the experiments, we will obtain a confusion matrix. This matrix will facilitate the analysis needed to determine where classification errors occur. The confusion matrix is a table that shows the distribution of errors in the different categories. The performance indicators necessary to evaluate the performance of the classifier to be implemented, specifically
Confusion matrix.
True Class | |||
---|---|---|---|
Positive | Negative | ||
Predicted Class | Positive | | |
Negative | | |
The original data was split into 80% for training and hyperparameter tuning and 20% for testing the final model in order to obtain an unbiased estimate. The optimal model was found using K-fold cross-validation with 3-folds and using a grid search. For GBT the optimized parameters were number of trees: maximal depth: minimum rows:
There are other parameters in this model that remained fixed for simplicity and thus they were not optimized. In particular, they are the number of bins (20), the learning rate (0.1), and the sample rate (1.0). The optimal hyperparameters alongside its accuracy on cross-validation and the test set are shown in Table
List of hyperparameters used for both machines with each model and general results.
Experiment | Number of Trees (per class) | Maximal Depth | Minimum Rows | Accuracy on Grid Search Cross-Validation | Accuracy on Test Set |
---|---|---|---|---|---|
Slots (M1) | 40 | 4 | 5 | 82.51% +- 1.76% (82.50% micro average) | 78.00% |
Slots (M2) | 60 | 6 | 4 | 89.67% +- 4.64% (89.62% micro average) | 61.54% |
Geometries (M1) | 100 | 8 | 10 | 87.51% +- 2.93% (87.50% micro average) | 88.51% |
Geometries (M2) | 40 | 4 | 8 | 89.57% +- 0.74% (89.58% micro average) | 85.71% |
The results obtained are shown for the slots dataset of both machines with the models given by GBT; both the confusion matrices and the models obtained in each case are presented. Table
Confusion matrix for the slots dataset M1 (GBT).
True Smooth | True Fine | True Semi-Fine | True Medium | Class Precision | |
---|---|---|---|---|---|
Pred. Smooth | 6 | 0 | 0 | 0 | 100.00% |
Pred. Fine | 3 | 19 | 4 | 0 | 73.08% |
Pred. Semi-fine | 1 | 1 | 6 | 2 | 60.00% |
Pred. Medium | 0 | 0 | 0 | 8 | 100.00% |
| |||||
Class Recall | 60.00% | 95.00% | 60.00% | 80.00% | |
Table
Importance of the variables for the slots dataset M1.
Variable | Importance | Relative Importance | Percentage (%) |
---|---|---|---|
Axial Depth of Cut | 219.5075 | 1.0000 | 47.15% |
Ration Speed | 107.3826 | 0.4892 | 23.06% |
Diameter of the Tool | 86.7459 | 0.3952 | 18.63% |
Advance Speed | 49.5846 | 0.2259 | 10.65% |
Number of Teeth | 2.3563 | 0.0107 | 0.51% |
Table
Confusion matrix for the slots dataset M2 (GBT).
True Smooth | True Fine | True Semi-Fine | True Medium | Class Precision | |
---|---|---|---|---|---|
Pred. Smooth | 2 | 1 | 0 | 66.67% | 2 |
Pred. Fine | 0 | 12 | 4 | 75.00% | 0 |
Pred. Semi-fine | 0 | 5 | 2 | 28.57% | 0 |
| |||||
Class Recall | 100.00% | 66.67% | 33.33% | | 100.00% |
Table
Importance of the variables for the slots dataset M2.
Variable | Importance | Relative Importance | Percentage (%) |
---|---|---|---|
Axial Depth of Cut | 62.5060 | 1.0000 | 38.09 |
Diameter of the Tool | 51.2562 | 0.8200 | 31.23 |
Rotation Speed | 23.4585 | 0.3753 | 14.29 |
Number of Teeth | 17.0898 | 0.2734 | 10.41 |
Advance Rate | 9.8038 | 0.1568 | 5.97 |
The results obtained for the geometries dataset of both machines with the models given by GBT are shown below; both the confusion matrices and the models obtained in each case are presented.
Table
Confusion matrix for the M1 geometries dataset (GBT).
True Smooth | True Fine | True Semi-Fine | True Medium | Class Precision | |
---|---|---|---|---|---|
Pred. Smooth | 23 | 3 | 0 | 0 | 88.46% |
Pred. Fine | 0 | 12 | 1 | 3 | 75.00% |
Pred. Semi-fine | 0 | 0 | 35 | 0 | 100.00% |
Pred. Medium | 2 | 1 | 0 | 7 | 70.00% |
| |||||
Class Recall | 92.00% | 75.00% | 97.22% | 70.00% | |
Table
Importance of the variables for the M1 geometries dataset.
Variable | Importance | Relative Importance | Percentage (%) |
---|---|---|---|
Hardness of the Material | 413.6821 | 1.0000 | 45.82 |
Diameter of the Tool | 188.2179 | 0.4550 | 20.85 |
Advance Speed-Feed Rate | 122.5317 | 0.2962 | 13.57 |
Rotation Speed | 118.9302 | 0.2875 | 13.17 |
Radial Depth of Cut | 39.7190 | 0.0960 | 4.40 |
Axial Depth of Cut | 19.8198 | 0.0479 | 2.20 |
Table
Confusion matrix for the M2 geometries dataset (GBT).
True Smooth | True Fine | True Semi-Fine | True Medium | Class Precision | |
---|---|---|---|---|---|
Pred. Smooth | 6 | 0 | 0 | 0 | 100.00% |
Pred. Fine | 3 | 14 | 0 | 2 | 73.68% |
Pred. Semi-fine | 1 | 0 | 14 | 0 | 93.33% |
Pred. Medium | 0 | 1 | 0 | 8 | 88.89% |
| |||||
Class Recall | 60.00% | 93.33% | 100.00% | 80.00% | |
Table
Importance of the variables for the M2 geometries dataset.
Variable | Importance | Relative Importance | Percentage (%) |
---|---|---|---|
Diameter of the Tool | 169.6404 | 1.0000 | 33.13 |
Rotation Speed | 119.9600 | 0.7071 | 23.42 |
Hardness of the Material | 97.2817 | 0.5735 | 19.00 |
Radial Depth of Cut | 92.2594 | 0.5439 | 18.02 |
Advance Speed-Feed Rate | 17.5635 | 0.1035 | 3.43 |
Axial Depth of Cut | 15.4129 | 0.0909 | 3.00 |
Figure
Pie charts for the importance of variables in each experiment and machine.
We compare the GBT models with other classifiers that have been used in the literature, such as SVM with RBF kernels or other powerful classifiers like Random Forests. In order to have a fair comparison, we find the optimal parametrization for each one of the compared algorithms using the same strategy as before.
For SVM we used a 1-vs-1 scheme for multiclass classification and we tried two kinds of kernels (RBF and Linear) with the parameters C in the range (0.00001, 0.0001, 0.001, 0.01, 0.1, 1.0, 10, 100, 1000, 10000, 100000) and gamma in the range (0.00001, 0.0001, 0.001, 0.01, 0.1, 1.0, 10, 100, 1000, 10000, 100000). For Random Forests we considered as hyperparameters the Number of Trees (range: 10, 20, 30, 40, 50, 60, 70, 80, 90, 100) and Maximal Depth (range: 1, 2, 3, 4, 5, 6, 7, 8), which are analogous to the parameters of GBT.
The optimal hyperparameters are then used to train 10 classifiers using a hold-out strategy with randomly sampled data from the original dataset. The idea is now to find an estimate of the accuracy of each classifier on the test set and average the results of the 10 classifiers for the different samples. All methods were evaluated using accuracy. We perform a 1-factor (i.e., choice of method) Analysis of Variance (ANOVA) for each dataset and report the corresponding p-values.
The results are shown in Table
Comparison between models in each dataset.
Dataset | GBT | SVM | Random Forests | p-value |
---|---|---|---|---|
Slots M1 | Accuracy: 83.20% +- 6.27% | Accuracy: 80.20% +- 5.02% | Accuracy: 87.60% +- 6.64% | 0.2746 |
Slots M2 | Accuracy: 72.69% +- 7.19% | Accuracy: 75.77% +- 4.88% | Accuracy: 77.31% +- 9.80% | 0.4308 |
Geometries M1 | Accuracy: 85.29% +- 2.56% | Accuracy: 82.76% +- 2.47% | Accuracy: 86.44% +- 3.20% | 0.0263 |
Geometries M2 | Accuracy: 83.68% +- 4.98% | Accuracy: 83.27% +- 4.64% | Accuracy: 86.12% +- 4.26% | 0.3817 |
The ANOVA reveals that there is no statistically significant difference for the slots (M1 and M2) and Geometries M2, while there is a potentially significant difference in the performance of the methods on Geometries M1. Further inspection reveals that there’s a difference between RBF SVM and the other two methods, but there’s no significant difference between GBT and Random Forests. This suggests that the results from GBT are competitive with other classifiers in the state of the art.
Previous works generate surface roughness predictive models using several soft computing techniques; however, there are no standard models to predict surface roughness, the models being usually generated under specific conditions of machining, coolant, machine tool, and tool. In the literature, it is possible to find works in which artificial neural networks or Bayesian networks are applied to generate predictive models of surface roughness; also classic decision trees have been used as a technique for pattern identification in the behavior of variables that influence surface roughness in the industry [
A recently published work is [
In this work, we use real training data and we have also obtained a graphical representation of knowledge using classic decision trees to complement the results obtained by GBT; in this way the joint result provides greater graphic expressivity regarding conditional influences and the values of the predictor variables on the class labels than, for example, Bayesian networks. This is important since it can be easily used to create a domain representation model and can also be interpreted to generate rules that contain dynamic knowledge of the machining process, which facilitates the construction of knowledge and inference bases for an eventual expert system of surface quality prediction in real time under concrete tool conditions, material to be machined, and machine tool.
All the pieces-of-knowledge derived from this research and other obtained from previous related works can be used, for example, to generate inference rules that help to establish the impact of measures of predictor variables on the surface roughness class. Figure
Syntax diagrams for two if-statements related to machining conditions and the relevance of variables for M-1 and M-2.
Finally, the ability of Gradient Boosted Trees to determine the importance of each variable with respect the labels could be considered similar to the ability of Bayesian networks to model influences between these variables and the labels. This is very important in the domain of micro- and nanomachining, where precision in the machining influences heavily the final results. Again, the knowledge gained here can be combined with previous knowledge that has been obtained by elicitation from experts or from state of the art, analysis of results, among others, so that this knowledge can be represented in a knowledge base and used by a Rule-based System or Decision Support System. In order to obtain conclusions about surface roughness as influenced by the predictive variables or to be able to predict surface roughness given a dataset or a particular data record.
The integration of AI algorithms into computational solutions and techniques for analyzing large amounts of data are gaining interest in the modern industry. This integration is part of what some authors call the sixth technological revolution [
Previous works, such as [
As a soft computing and AI approach, this work falls in the second group, with the advantage that the resulting model in each experiment has a high accuracy value in comparison with other techniques such as decision trees, thanks to the accuracy of the GBT algorithm. A potential improvement that could be made to our model is incorporating the characteristics of the coolant used and study the behavior of the conditional influences on the surface roughness.
The main contributions of this work are the predictive model itself and the subsequent analysis of variable importance. In particular, our results show accuracies ranging from 61.54% to 88.51% on the datasets, which are competitive results when compared with the other approaches shown in this paper. An important advantage of applying this model is that we have been able to analyze which variables have the most impact on the predictive ability of our model in a natural way. In this context, we find that the axial cut-depth is the most influential feature for the slots datasets. The axial cut deep is the axial contact length between the cutting tool and the workpiece [
As a potential future line of work and for practical applications, the results of this study could form the basis of a decision support system. In particular, such a system could use the knowledge contained in the predictive models as a core knowledge base. In particular, since the predictive model GBT is based on decision trees, it would be relatively easy to extract the information from the tree branches as a knowledge base. These branches could be used as rule sets for technicians and other users to interpret and understand the current behavior of the machining systems. Furthermore, this knowledge base could be enriched with more data as it becomes available, although this avenue of work would eventually lead to concerns of scalability of such a decision support system.
Finally, as has been said in the discussion, the application of the GBT algorithm (derived from decision trees) is not very common in the industry, even though decision trees are one of the most widely used machine learning techniques because of the ease they provide in generating clear production rules and being easily understood by end users. This brings confidence to the predictive models presented here in the presence of new cases that might be taken as input to predict surface roughness.
The data used to support the findings of this study are available from the corresponding author upon request.
The authors declare that they have no conflicts of interest.
The authors want to thank the Centro de Automática y Robótica at CSIC (Spain) for the use of the Kondia machine tool where a part of the experimentation was made. The authors also acknowledge the collaboration of Nicolas Correa S.A. and thank Dr. Andrés Bustillo from Nicolas Correa, who enabled the rest of experimentation in this company, using the Versa machining center.