^{1}

^{1}

^{1}

^{1}

Artificial neural network is a powerful technique of computational intelligence and has been applied in a variety of fields such as engineering and computer science. This paper deals with the neural network modeling and prediction of surface roughness in machining aluminum alloys using data collected from both force and vibration sensors. Two neural network models, including a Multi-Layer Perceptron (MLP) model and a Radial Basis Function (RBF) model, were developed in the present study. Each model includes eight inputs and five outputs. The eight inputs include the cutting speed, the ratio of the feed rate to the tool-edge radius, cutting forces in three directions, and cutting vibrations in three directions. The five outputs are five surface roughness parameters. Described in detail is how training and test data were generated from real-world machining experiments that covered a wide range of cutting conditions. The results show that the MLP model provides significantly higher accuracy of prediction for surface roughness than does the RBF model.

As a powerful technique of computational intelligence, artificial neural network (ANN) has been applied in a variety of fields such as engineering and computer science [

In metal machining, an important operation in modern engineering manufacture, ANN has been employed to develop various models for tool condition monitoring and the prediction of machining performance measures, such as cutting forces, cutting vibrations, tool wear, tool life, and machined surface roughness [

The present study deals with the neural network modeling and prediction of surface roughness in machining aluminum alloys using data collected from both force and vibration sensors. As a critical machining performance measure, surface roughness represents the machined surface quality and significantly affects the fatigue life of machined products [

The primary scientific contribution of the present study is that it takes into account the effect of tool-edge radius in machining for neural network modeling and prediction. Fang [

The remainder of this paper is arranged in the following order. First, the inputs and outputs of the MLP and RBF models are described, followed by an introduction to how the two models were established. Then, described is how training and test data (for use in neural network modeling and prediction) were generated from machining experiments involving a wide range of cutting conditions. Experimental set-up and measurements are also described. Next, the results of MLP and RBF neural network modeling and prediction are presented and analyzed. Finally, conclusions are made at the end of the paper.

In the present study, the MLP and RBF neural network models include the following eight inputs: 1) cutting speed Vc (m/min), 2) ratio of the feed rate to the tool-edge radius f/rn, 3) cutting force Fc (N), 4) feed force Ff (N), 5) passive force Fp (N), 6) cutting vibration in the direction of the cutting speed Vx (g), 7) cutting vibration in the direction of the feed rate Vy (g), and 8) cutting vibration in the direction of the depth of cut Vz (g).

Note that for the second input listed above, the effect of the tool-edge radius in machining is represented by the ratio of the feed rate to the tool-edge radius. This is because the effect of the tool-edge radius depends on the feed rate employed in machining [

The outputs of the MLP and RBF models are five surface roughness parameters (μm). The meaning of these surface roughness parameters has been well explained in relevant literature [

Based on a back-propagation algorithm, Multi-layer Perceptron (MLP) neural networks are among the most popular networks and have been widely applied in engineering research involving the modeling of metal machining [

In the present study, computer codes for establishing the MLP model were developed using the MATLAB software package [

Using a different mathematical method called curve fitting in a high dimensional space, Radial Basis Function (RBF) neural networks are a relatively new class of neural networks [

In this study, computer codes for establishing the RBF model were also developed based on the MATLAB software package [

The MLP and RBF network models must be trained first using a set of training data. Then, the prediction accuracy of the two models can be validated using a set of test data. In the present study, all training and test data were generated from real-world machining experiments, rather than from virtual computer simulation experiments. A total of 45 sets of training and test data were generated, with each set including 13 data points, i.e., the eight in-puts and five outputs described in Section 2.1. Among these 45 sets, 38 sets (84%) were randomly selected as training data, and the remaining 7 sets (16%) were used as test data. The following two sub-sections describe the experimental set-up and measurements that were involved in data generation.

3D cutting experiments were conducted on a CNC turning center (HAAS SL10). The work material was a 2024-T351 aluminum alloy bar (ASTM B211 grade). This material has been widely applied in a variety of industries [

Three coated carbide inserts, TPG432 KC8050 made by Kennametal Inc., were used. These tool inserts had different average tool-edge radii: 45.5 μm, 54.7 μm, and 72.4 μm, respectively. They were carefully chosen to represent three different levels of tool-edge radius values in order to study their effects on surface roughness.

The cutting speeds varied at three levels: 150 m/min, 250 m/min, and 350 m/min. The feed rates varied at five levels based on the ratio of the feed rate to the tool-edge radius: 1.0, 1.5, 2.0, 2.5, and 3.0. The depth of cut was kept constant at 0.8 mm, the same as the tool nose radius. No coolants were used in the machining experiments in order to facilitate the experimental measurements of cutting forces, cutting vibrations, and machined surface roughness.

Cutting forces were measured online for each experiment using a three-component quartz dynamometer (Kistler 9257B), a multi-channel dual-mode charge amplifier (Kistler 5010 B), and a computer data acquisition system (Labview). MATLAB was employed to filter the high-frequency noise from the collected signals. A MATLAB code was written to determine the average values of the three components of cutting forces, i.e., the cutting force Fc, the feed force Ff, and the passive force Fp.

Cutting vibrations were simultaneously measured online for each machining experiment using a Triaxial ICP accelerometer (356A61) that was fixed to the tool holder. The accelerometer sensed the vibration signals in the x-, y-, and z-directions, i.e., the cutting speed, feed rate, and depth of cut directions, respectively. The sensed vibration signals were sent to a low noise signal conditioner (PCB 482A22), an ICP accelerometer conditioning module (NI SCXI-1530/1531), and a computer for signal processing and display. The root mean square (RMS), i.e., the average of the squared values of the vibration amplitude, was calculated.

The machined surface roughness was measured offline after each machining experiment using a fine contour measuring instrument (Mitutoyo type-SV602). This instrument measured five surface roughness parameters: Ra, Rq, Rp, Rmax, and Rz. Three equally spaced locations around the circumference of the workpiece were involved in the measurement, and the average values of measurements were used.

Figures 1-5 show the results of MLP and RBF training. As seen from these figures, both MLP and RBF models were well trained and reflect the fluctuation of training data generated under a wide range of cutting conditions.

Figures 6-10 show the comparisons of prediction accuracy between MLP and RBF models for each surface roughness parameter. As can be seen clearly, the pre-dictions by the MLP model is more close to the test data (i.e., experimentally-measured surface roughness parameters). Although the RBF model generates networks faster than the conventional training algorithms like traingdm used in MLP, the number of hidden neurons added by RBF to the network is nearly equal to the number of input patterns. This makes RBF a large network. In comparison, MLP generates a much more compact network and is able to generalize well on the test data.

Tables 1-4 further show the comparison of two primary surface roughness parameters, Ra and Rmax, between the MLP and RBF models. The mean squared error shown in these tables is defined as 1/2 (measured value − predicted value)^{2}. The smaller the mean squared error, the higher the prediction accuracy.

Experiment number | Measured | Predicted by MLP | Mean squared error |
---|---|---|---|

1 | 0.100 | 0.1022 | 2.42E-06 |

2 | 0.099 | 0.1028 | 7.22E-06 |

3 | 0.563 | 0.4909 | 0.002599 |

4 | 0.506 | 0.3136 | 0.018509 |

5 | 0.193 | 0.2485 | 0.001540 |

6 | 0.229 | 0.2959 | 0.002238 |

7 | 0.274 | 0.2778 | 7.22E-06 |

Experiment number | Measured | Predicted by RBF | Mean squared error |
---|---|---|---|

1 | 0.100 | 0.2919 | 0.018413 |

2 | 0.099 | 0.2951 | 0.019228 |

3 | 0.563 | 0.3232 | 0.028752 |

4 | 0.506 | 0.2103 | 0.043719 |

5 | 0.193 | 0.1056 | 0.003819 |

6 | 0.229 | 0.2908 | 0.001910 |

7 | 0.274 | 0.2511 | 0.000262 |

Experiment number | Measured | Predicted by MLP | Mean squared error |
---|---|---|---|

1 | 0.657 | 0.7435 | 0.003741 |

2 | 0.698 | 0.7995 | 0.005151 |

3 | 3.940 | 3.1252 | 0.331950 |

4 | 3.874 | 2.7394 | 0.643659 |

5 | 1.433 | 1.7016 | 0.036073 |

6 | 1.558 | 1.6623 | 0.005439 |

7 | 1.791 | 1.6771 | 0.006487 |

Experiment number | Measured | Predicted by RBF | Mean squared error |
---|---|---|---|

1 | 0.657 | 2.4589 | 1.623422 |

2 | 0.698 | 2.216 | 1.152162 |

3 | 3.940 | 2.5905 | 0.910575 |

4 | 3.874 | 1.9925 | 1.770021 |

5 | 1.433 | 1.0239 | 0.083681 |

6 | 1.558 | 2.0052 | 0.099994 |

7 | 1.791 | 1.8686 | 0.003011 |

Comparing the values of mean squared errors listed in

This paper has described how a Multi-Layer Perceptron (MLP) and a Radial Basis Function (RBF) neural network model were developed to predict surface roughness in the machining of 2024-T351 aluminum alloy. The models take into account the effects of the tool-edge radius (via the ratio of the feed rate to the tool-edge radius), the cutting speed, cutting forces, and cutting vibrations on machined surface roughness. The results show that as compared to the RBF model, the MLP model offers significantly higher accuracy of prediction for machined surface roughness, especially for maximum roughness height. We suggested that the MLP model be used in the modeling and prediction of surface roughness in machining 2024-T351 aluminum alloy.

N. Fang,N. Fang,P. Srinivasa Pai,N. Edwards, (2016) Neural Network Modeling and Prediction of Surface Roughness in Machining Aluminum Alloys. Journal of Computer and Communications,04,1-9. doi: 10.4236/jcc.2016.45001