scholarly journals Estimation of Tool Wear and Surface Roughness Development Using Deep Learning and Sensors Fusion

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5338
Author(s):  
Pao-Ming Huang ◽  
Ching-Hung Lee
Keyword(s):  
Surface Roughness ◽  
Deep Learning ◽  
Tool Wear ◽  
Sensor Fusion ◽  
Sensor Selection ◽  
Numerical Control ◽  
Estimation Accuracy ◽  
Machining Parameters ◽  
Estimation Model ◽  
Selection Analysis

This paper proposes an estimation approach for tool wear and surface roughness using deep learning and sensor fusion. The one-dimensional convolutional neural network (1D-CNN) is utilized as the estimation model with X- and Y-coordinate vibration signals and sound signal fusion using sensor influence analysis. First, machining experiments with computer numerical control (CNC) parameters are designed using a uniform experimental design (UED) method to guarantee the variety of collected data. The vibration, sound, and spindle current signals are collected and labeled according to the machining parameters. To speed up the degree of tool wear, an accelerated experiment is designed, and the corresponding tool wear and surface roughness are measured. An influential sensor selection analysis is proposed to preserve the estimation accuracy and to minimize the number of sensors. After sensor selection analysis, the sensor signals with better estimation capability are selected and combined using the sensor fusion method. The proposed estimation system combined with sensor selection analysis performs well in terms of accuracy and computational effort. Finally, the proposed approach is applied for on-line monitoring of tool wear with an alarm, which demonstrates the effectiveness of our approach.

scholarly journals Prediction of Surface Roughness using Sensor Fusion Regression Model

2019 ◽  
Vol 8 (12S) ◽  
pp. 538-540
Keyword(s):  
Surface Roughness ◽  
Tool Wear ◽  
Regression Model ◽  
Sensor Fusion ◽  
Cutting Temperature ◽  
Machining Parameters ◽  
Direct Influence ◽  
Machining Processes ◽  
H13 Steel

Surface roughness decides the quality of machined components during machining processes. Output parameters namely cutting temperature, cutting force, tool wear, vibration etc. have direct influence on surface roughness of machined components. It is anticipated that better prediction would be possible if the above mentioned parameters are collectively considered with machining parameters. In this investigation, an effort was made to fuse machining parameters with cutting temperature to predict surface roughness while machining H13 steel. The developed regression model was tested for its ability to predict surface quality. The results proved that the developed sensor fusion regression model can be used for better prediction of cutting performance

Measurement of roughness on hardened D-3 steel and wear of coated tool inserts

2020 ◽  
pp. 014233122093855
Author(s):  
A Bovas Herbert Bejaxhin ◽  
G Paulraj ◽  
G Jayaprakash ◽  
V Vijayan
Keyword(s):  
Surface Roughness ◽  
Tool Wear ◽  
High Speed ◽  
High Carbon Steel ◽  
Numerical Control ◽  
Cutting Conditions ◽  
Depth Of Cut ◽  
Machining Parameters ◽  
Cnc Turning ◽  
Coated Carbide

This research investigation has been carried out in Computer Numerical Control (CNC) turning of 40–50 Hardness Rockwell C (HRC) hardened high chromium high carbon steel (HCHCR-D3) specimen for the findings of surface roughness (Ra) and the tool wear. The HCHCR-D3 steel, which has excellent abrasion and wear resistance, is machined with the physical vapor deposition (PVD) coated carbide (CNMG) turning insert nomenclature based on shape, clearance angle, tolerance and type of tool inserts. The coatings preferred are Titanium Nitrate (TiN), Aluminium Chromium Nitrate (AlCrN) and Latuma for the coating thickness of 3–4μm. The varying input parameters of speed and depth of cut under constant feed rate are used as machining parameters for this CNC turning operation. The machined surface characterization and tool wear have been investigated analytically in this manuscript along with the predicted results of effective stresses and temperatures under dynamic cutting conditions in Deform 3D can be related. The outcomes indicate that the depth of cut and the hardening effect (HRC) are the major influencing parameter on surface roughness. Less tool wear and machining time are obtained by the usage of coated CNMG tool insert for high-speed cutting conditions which results in minimization of wear interruption and growth in surface improvements.

scholarly journals Findings of performance evaluation of EDM for different materials of electrodes and work pieces- a review

2018 ◽  
Vol 7 (4.5) ◽  
pp. 542
Author(s):  
Harshalkumar R. Mundane ◽  
Dr. A. V. Kale ◽  
Dr. J. P. Giri
Keyword(s):  
Surface Roughness ◽  
Tool Wear ◽  
Performance Measure ◽  
Machining Process ◽  
Machining Parameters ◽  
Spark Erosion ◽  
Pulse On Time ◽  
Pulse Off Time ◽  
Off Time ◽  
Time Pulse

EDM (Spark erosion) is non-conventional machining process which uses as removing unwanted material by electrical spark erosion. EDM Machining parameters affecting to the performance and the industries goal is to produce high quality of product with less time consuming and cost. To achieve these goals, optimizing the machining parameters such as pulse on time, pulse off time, cutting speed, depth of cut, duty cycle, arc gap, voltage etc. The performance measure of EDM is calculated on the basis of Material Remove Rate(MRR), Tool Wear Rate(TWR), and Surface Roughness(SR).The main objective of present work is to investigate of the influence of input EDM (Electro Discharge Machining) parameters on machining characteristics like surface roughness and the effects of various EDM process parameters such as pulse on time, pulse off time, servo voltage, peak current, dielectric flow rate, on different process response parameters such as material removal rate (MRR), surface roughness (Ra), Kerf (width of Cut), tool wear ratio(TWR)and surface integrity factors. In this paper few selected research paper related to Die-sinker EDM with effect of MRR, TWR, surface roughness (SR) and work piece material have been discussed.   

Designing and implementation of a novel online adaptive control with optimization technique in hard turning

2020 ◽  
pp. 095965182095219
Author(s):  
Vahid Pourmostaghimi ◽  
Mohammad Zadshakoyan
Keyword(s):  
Adaptive Control ◽  
Tool Wear ◽  
Hard Turning ◽  
Cutting Tool ◽  
Optimization Technique ◽  
Cutting Parameters ◽  
Numerical Control ◽  
Machining Process ◽  
Machining Parameters ◽  
Optimization Methodology

Determination of optimum cutting parameters is one of the most essential tasks in process planning of metal parts. However, to achieve the optimal machining performance, the cutting parameters have to be regulated in real time. Therefore, utilizing an intelligent-based control system, which can adjust the machining parameters in accordance with optimal criteria, is inevitable. This article presents an intelligent adaptive control with optimization methodology to optimize material removal rate and machining cost subjected to surface quality constraint in finish turning of hardened AISI D2 considering the real condition of the cutting tool. Wavelet packet transform of cutting tool vibration signals is applied to estimate tool wear. Artificial intelligence techniques (artificial neural networks, genetic programming and particle swarm optimization) are used for modeling of surface roughness and tool wear and optimization of machining process during hard turning. Confirmatory experiments indicated that the efficiency of the proposed adaptive control with optimization methodology is 25.6% higher compared to the traditional computer numerical control turning systems.

Optimization of Machining Parameters of Valve Steel SUH03 (X45CrSiMo10-2) Using Gray Based Taguchi Method

2015 ◽  
Vol 813-814 ◽  
pp. 376-381 ◽  
Author(s):  
B. Yazhini ◽  
S. Rajeswari ◽  
Sivasakthivel
Keyword(s):  
Surface Roughness ◽  
Tool Wear ◽  
Signal To Noise Ratio ◽  
Cutting Parameters ◽  
Gray Relational Analysis ◽  
Depth Of Cut ◽  
Machining Parameters ◽  
Nose Radius ◽  
Valve Steel ◽  
Optimal Cutting Parameters

This paper embarks the machining parameters of Turning by optimization using Taguchi’s approach. The optimization is very essential in order to obtain the expected surface quality. The results of cutting parameters of optimization is seen in the Surface Roughness, Tool wear and MRR of the material. The L18 Orthogonal array has been chosen for the optimization of Valve Steel SUH03.The uncoated carbide inserts were used and the four parameters Speed, Feed, Depth of Cut and Nose Radius has been taken as input parameters. The Signal to Noise ratio and Analysis of Variance software has been analyzed using Minitab software through which the optimal cutting parameters of the best surface roughness, tool wear and MRR has been obtained. The final results have been compared by the Gray relational analysis to find the optimum machining conditions of all the parameters.

scholarly journals Experimental Investigation of Cutting Parameters Effects on the Surface Roughness and Tools Wear during the Drilling of Fiber Reinforced Composite Materials

2019 ◽  
Vol 38 (3) ◽  
pp. 717-728 ◽  
Keyword(s):  
Surface Roughness ◽  
Composite Material ◽  
Tool Wear ◽  
Cutting Speed ◽  
Fiber Reinforced Polymer ◽  
Machining Parameters ◽  
Fiber Reinforced ◽  
Minimum Surface ◽  
Reinforced Polymer ◽  
Tools Wear

Optimization of the drilling parameters of the composite material is the key objective of this research, enhancing the surface roughness and minimizing the tool wear. In contrary to the other research, optimizing the machining parameters for a specific composite material for the mass productions, machining parameters are optimized for GFRP (Glass Fiber Reinforced Polymer), CFRP (Carbon Fiber Reinforced Polymer) and KFRP (Kevlar Fiber Reinforced Polymer) for the job shop production. In this research, the machining parameters are optimized for the enhanced surface roughness and minimum tool wear by varying the three types of composite material and three levels of the cutting speed. Nine experiments were performed, which were repeated twice in random manner to eliminate the biasness of the results. In these experiments, PVD (Physical Vapor Deposition) coated carbide inserts are used with the same geometry. Seventeen holes were machined in a single experiment, which surface roughness is measured by cutting the composite plate from middle of the hole and using the Countermatic surface roughness meter at different locations. Average surface roughness is determining for each set of varying parameters and plotted to observe the set of parameters for the minimum surface roughness. It has been observed that the minimum surface roughness are observed at; 1500 rpm in GFRP, 2000 rpm in CFRP and at 2500 rpm in KFRP. Finally, the wear patterns are also observed on the drill inserts using SEM (Scanning Electron Microscope) and it has been found that no prominent wear has been observed in the drill inserts, whereas, prominent depletion of coating are found at the higher cutting speed.

scholarly journals Statistical analysis of energy consumption, tool wear and surface roughness in machining of Titanium alloy (Ti-6Al-4V) under dry, wet and cryogenic conditions

2019 ◽  
Vol 10 (2) ◽  
pp. 561-573 ◽  
Author(s):  
Muhammad Ali Khan ◽  
Syed Husain Imran Jaffery ◽  
Mushtaq Khan ◽  
Muhammad Younas ◽  
Shahid Ikramullah Butt ◽  
...  
Keyword(s):  
Surface Roughness ◽  
Tool Wear ◽  
Effective Means ◽  
Sustainable Manufacturing ◽  
Cutting Speed ◽  
Depth Of Cut ◽  
Machining Parameters ◽  
Specific Cutting Energy ◽  
Cutting Energy ◽  
Positive Effect

Abstract. Productivity and economy are key elements of any sustainable manufacturing system. While productivity is associated to quantity and quality, economy focuses on energy efficient processes achieving an overall high output to input ratio. Machining of hard-to-cut materials has always posed a challenge due to increased tool wear and energy loss. Cryogenics have emerged as an effective means to improve sustainability in the recent past. In the present research the use of cooling conditions has been investigated as an input variable to analyze its effect on tool wear, specific cutting energy and surface roughness in combination with other input machining parameters of feed rate, cutting speed and depth of cut. Experimental design was based on Taguchi design of experiment. Analysis of Variance (ANOVA) was carried out to ascertain the contribution ratio of each input. Results showed the positive effect of coolant usage, particularly cryogenic, on process responses. Tool wear was improved by 33 % whereas specific cutting energy and surface roughness were improved by 10 % and 9 % respectively by adapting the optimum machining conditions.

scholarly journals Surface roughness of thermally treated wood cut with different parameters in CNC router machine

BioResources ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. 5133-5147
Author(s):  
Hüseyin Pelit ◽  
Mustafa Korkmaz ◽  
Mehmet Budakçı
Keyword(s):  
Surface Roughness ◽  
Feed Rate ◽  
Treatment Temperature ◽  
Spindle Speed ◽  
Numerical Control ◽  
Machining Parameters ◽  
End Mill ◽  
Cnc Machine ◽  
Cnc Router ◽  
Thermally Treated

The effects of different machining parameters on surface roughness values of thermally treated pine, beech, and linden woods cut in a computer numerical control (CNC) router machine were examined. Wood specimens were thermally treated at 170, 190, and 210 °C for 2 h. Then, specimens were cut in the radial and tangential directions with three different spindle speeds (12000, 15000, and 18000 rpm) and three different feed rates (3000, 4000, and 6000 mm/min) using two different end mill tools (spiral and straight) on the CNC machine. The end mill type significantly affected the roughness values of the untreated and thermally treated specimens in both directions. Lower roughness values were found in the specimens (especially pine) machined with the straight end mill compared to those machined with the spiral end mill. Roughness generally decreased in the thermally treated specimens. However, thermal treatment temperature did not have a notable effect on roughness. As the spindle speed increased, the roughness values of all specimens decreased. In contrast, as the feed rate increased, the roughness values increased. Therefore, the end mill type, feed rate, and spindle speed were the most influential parameters on the roughness.

scholarly journals The influence of machining parameters on surface roughness of MDF in milling operation

BioResources ◽  
2019 ◽  
Vol 14 (2) ◽  
pp. 3266-3277
Author(s):  
Ümmü K. İşleyen ◽  
Mehmet Karamanoğlu
Keyword(s):  
Surface Roughness ◽  
Feed Rate ◽  
Medium Density Fiberboard ◽  
Spindle Speed ◽  
Numerical Control ◽  
Depth Of Cut ◽  
Machining Parameters ◽  
Milling Operation ◽  
Four Levels ◽  
Tool Diameter

This paper examined the effect of machining parameters on surface roughness of medium density fiberboard (MDF) machined using a computer numerical control (CNC) router. The machining parameters such as spindle speed, feed rate, depth of cut, and tool diameter were examined for milling. The experiments were conducted at two levels of spindle speeds, four levels of feed rates, two levels of tool diameters, and two levels of axial depths of cut. The surface roughness values of MDF grooved by CNC were measured with stylus-type equipment. Statistical methods were used to determine the effectiveness of the machining parameters on surface roughness. The influence of each milling parameter affecting surface roughness was analyzed using analysis of variance (ANOVA). The significant machining parameters affecting the surface roughness were the feed rate, spindle speed, and tool diameter (p < 0.05). There was no significant influence of axial depth of cut on the surface roughness. The surface roughness decreased with increasing spindle speed and decreasing feed rate. The value of surface roughness increased with the increase of tool diameter.

Sign in / Sign up

Export Citation Format

Share Document