Tool Wear Measurement Research Articles

Model for tool wear prediction in face hobbing plunging of bevel gears

This paper deals with tool wear investigations for face hobbing plunging of bevel gears. Initially, the influence of process parameters and tool geometry on tool wear is analyzed both in cutting trials and with the help of the manufacturing simulation BevelCut. Subsequently, a tool wear model is presented. Input parameters into the model are tool and workpiece data as well as process parameters and chip characteristics. Through the manufacturing simulation BevelCut, which is based on a planar penetration algorithm, chip characteristics such as the maximum chip thickness hcu,max are calculated resolved in time and location along the blade's cutting edge. Combined with the local cutting speed, the chip characteristics are used to determine the thrust force, which is required to calculate the elastic workpiece deformation. The model coefficients are calibrated by multi-variable regression analysis using the results of the cutting trials and simulation results. The quality of the regression is determined with the help of equivalence tests. For verification, the process parameters and tool geometry are varied in series production and the tool wear is assessed. Finally, the modeled tool wear is compared to the measured tool wear.

Automated detection of tool wear in machining and characterization of its shape

Flank wear VBmax remains one of the most essential and used metrics for measuring tool wear. VBmax is used to characterize tool wear rate, machinability of materials, the quality of machined surface. While VBmax measures the size of wear scar, the shape of the tool wear remains less used but not the least applicable for such characterization. However, quantification of the wear shape requires a more detailed information about the wear contour. This study develops an Image Processing solution for automated tool wear detection and applies Delaunay triangulation and implenarity parameter for characterizing the shape of the wear scar. Validation of the approach has been performed for machining stainless steel 316L without and with abrasive Al2O3 and SiO2 inclusions. It is shown that VBmax and area parameters of the wear scar are insensitive to wear shape, while implenarity can accurately quantify irregularity, curvature, asymmetry of the scar. The results also show a strong relationship between the tool wear shape, the hardness and size of inclusions in the steel.

ConvLSTM-Att: An Attention-Based Composite Deep Neural Network for Tool Wear Prediction

In order to improve the accuracy of tool wear prediction, an attention-based composite neural network, referred to as the ConvLSTM-Att model (1DCNN-LSTM-Attention), is proposed. Firstly, local multidimensional feature vectors are extracted with the help of a one-dimensional convolutional neural network (1D-CNN), which avoids the loss of wear features caused by manual feature extraction. Then the temporal relationship learning between multidimensional feature vectors is performed by introducing a long short-term memory (LSTM) network to make up for the lack of long-short distance dependence of the captured sequence of the CNN network. Finally, an attention mechanism is applied to strengthen the ability to extract key information from tool-wearing temporal features. The proposed ConvLSTM-Att model is trained with the measured tool wear data and then performs as a tool wear predictor. The model is compared with several state-of-the-art models on the PHM tool wear data sets. It significantly outperforms the other models in terms of prediction accuracy, but with similar computational complexity.

Tool-Wear-Estimation System in Milling Using Multi-View CNN Based on Reflected Infrared Images.

A novel method for tool wear estimation in milling using infrared (IR) laser vision and a deep-learning algorithm is proposed and demonstrated. The measurement device employs an IR line laser to irradiate the tool focal point at angles of -7.5°, 0.0°, and +7.5° to the vertical plane, and three cameras are placed at 45° intervals around the tool to collect the reflected IR light at different locations. For the processing materials and methods, a dry processing method was applied to a 100 mm × 100 mm × 40 mm SDK-11 workpiece through end milling and downward cutting using a TH308 insert. This device uses the diffused light reflected off the surface of a rotating tool roughened by flank wear, and a polarization filter is considered. As the measured tool wear images exhibit a low dynamic range of exposure, high dynamic range (HDR) images are obtained using an exposure fusion method. Finally, tool wear is estimated from the images using a multi-view convolutional neural network. As shown in the results of the estimated tool wear, a mean absolute error (MAE) of prediction error calculated was to be 9.5~35.21 μm. The proposed method can improve machining efficiency by reducing the downtime for tool wear measurement and by increasing tool life utilization.

Effect of edge radius on forces, tool wear and surface integrity under edge radius dominated tool-chip contact conditions

Cutting-edge micro-geometry is a crucial factor influencing chip formation and tool performance. This paper investigates the effects of varying cutting edge radius (36–70 µm) on machinability and chip morphology during finish turning Ti6Al4V. An increase in edge radius decreases the cutting to thrust force ratio and produces lower chip thickness due to the increase in plowing zone depth. The machining temperature for the 48 and 52 µm edge radius tools is lower compared to all other tools. At the initial stage, the edge prepared tools exhibit larger flank wear, whereas subsequent flank wears progression is slower for the prepared tools as compared to the sharp tool. BUE and premature chipping is reduced for larger edge radius tool due to better edge stability provided by cutting edge preparation. Beyond the 59 µm edge radius, the process force, machining temperature, tool wear, and surface roughness increased steeply due to the increase in the size of the plowing zone. In addition to cutting force and machining temperature data, surface roughness, tool wear measurements and XRD analysis show that a radius range of 50–55 µm results in optimum performance for finish turning Ti6Al4V.

Opportunities and Challenges in Modelling of Machining Performance with Various Coatings and Lubricants in Inconel 718 Machining

Decades of research and industrial applications have shown the significant impact of tool coatings and lubricants on machining performance, particularly in difficult-to-cut materials such as nickel-based super alloy Inconel 718. However, the ability to quantify and optimize the beneficial effects of coatings and lubricants continues to be primarily driven by empirical approaches. In this paper, a comparison between experimentally measured tool wear and numerically modelled process metrics, such as temperatures and stresses, is presented. Based on the results and observed deviations, future directions for more industrially relevant cutting tool development are proposed. Major challenges include the need for physics-based tribological models that consider different process interactions as well as microstructural and geometric size effects.

Measurement and analysis of tool wear and surface characteristics in micro turning of SLM Ti6Al4V and wrought Ti6Al4V

Parts produced using additive manufacturing (AM) have a significant transition in the features such as surface quality, residual stresses, microhardness, etc. To make the AM component suitable for an application, post-processing of the parts is required to remove the non-desirable features. In this regard, the micro turning of selective laser melted (SLM) Ti6Al4V are conducted to examine the surface characteristics, tool wear and chip morphology. The results obtained for SLM Ti6Al4V are compared with the results of wrought Ti6Al4V. Attributed to the higher strength and hardness, the SLM Ti6Al4V shows a higher tool wear and surface roughness than the wrought Ti6Al4V. The main tool wear mechanisms involved are built-up edge formation, adhesion, abrasion, and edge chipping for both the materials. The surface roughness is found increased with increasing cutting speed and feed. The wrought Ti6Al4V shows less feed marks and chip adhesion compared to SLM Ti6Al4V. Moreover, the materials side flow is observed in SLM Ti6Al4V only. The chips produced are long and continuous for wrought Ti6Al4V, whereas they are discontinuous for SLM Ti6Al4V. Morphology of the chips shows that they are of scaly structure for SLM Ti6Al4V for all the parameters, whereas they are of lamella structure for wrought Ti6Al4V, particularly at low feed and cutting speed.

Hybrid machine learning-enabled multi-information fusion for indirect measurement of tool flank wear in milling

To increase the utilization efficiency of multi-sensor signals and improve the measurement accuracy of tool wear, this study proposes an indirect tool wear measurement method based on multi-information fusion by hybrid machine learning technologies. In this method, triaxial cutting forces and vibration signals are collected and then preprocessed by wavelet packet denoising. The time, frequency, and time–frequency domain features are extracted to reduce the information redundancy, and the kernel principal component analysis is applied to fuse the most sensitive characteristics. A fusion model of least squares support vector regression and the particle swarm optimization algorithm is established to learn the dependency relationship between fused features and tool flank wear. Milling experiments under multiple working conditions are implemented to verify the effectiveness of the proposed method. Experimental results sufficiently demonstrated overall performance of the proposed method is better than that of other comparison methods.

Prediction and evaluation of surface roughness with hybrid kernel extreme learning machine and monitored tool wear

In the modern manufacturing industry, surface roughness is a critical parameter to characterize surface quality. The accurate prediction of surface roughness is of great significance for data-driven intelligent manufacturing. However, it's hard to accurately predict surface roughness in the complex machining process, because of the existence of some uncontrollable factors, such as tool wear. To address the aforementioned issue, a novel hybrid kernel extreme learning machine with Gaussian and arc-cosine kernel function (RBF_Arc_HKELM) was proposed to predict surface roughness. Then an optimized whale optimization algorithm was introduced to improve the prediction accuracy. Considering that tool wear is an indirect quantity and changes dynamically with the cutting process, a novel tool wear monitoring framework with attention mechanism, weighted feature averaging, and deep learning models was proposed. Afterward, the basic cutting parameters combined with the monitored tool wear were fed into the trained RBF_Arc_HKELM model for surface roughness estimation. Finally, surface roughness was evaluated by the established RBF_Arc_HKELM model. To verify the validity and performance of the established models, milling experiments were conducted under different cutting parameter combinations and tool wear levels, and some other intelligent algorithms were also used for surface roughness prediction and tool wear monitoring. Compared with kernel extreme learning machine with RBF (RBF_KELM), support vector regression (SVR), Gaussian process regression (GPR), and light gradient boosting machine (LightGBM), in terms of mean absolute error (MAE), the prediction accuracy of RBF_Arc_HKELM is improved by 17.82 %, 15.36 %, 14.16 %, and 6.26 %, respectively. These results indicated that the proposed model has great leverage in validity and accuracy. Moreover, compared with the measured tool wear as the input, the satisfactory prediction results of surface roughness were also obtained with the monitored tool wear as the input of the RBF_Arc_HKELM model with a drop in prediction accuracy of only 8.66 %.

Tool life prognostics in CNC turning of AISI 4140 steel using neural network based on computer vision

One of the essential requirements for intelligent manufacturing is the low cost and reliable predictions of the tool life during machining. It is crucial to monitor the condition of the cutting tool to achieve cost-effective and high-quality machining. Tool conditioning monitoring (TCM) is essential to determining the remaining useful tool life to assure uninterrupted machining to achieve intelligent manufacturing. The same can be done by direct and indirect tool wear measurement and prediction techniques. In indirect methods, the data is acquired from the sensors resulting in some ambiguity, such as noise, reliability, and complexity. However, in direct methods, the data is available in images resulting in significantly less chances of ambiguity with the proper data acquisition system. The direct methods, which provide higher accuracy than indirect methods, involve collecting images of worn tools at different stages of the machining process to predict the tool life. In this context, a novel tool wear prediction system is proposed to examine the progressive tool wear utilizing the artificial neural network (ANN). Experiments were performed on AISI 4140 steel material under dry cutting conditions with carbide inserts. The cutting speed, feed, depth of cut, and white pixel counts are considered as input parameters for the proposed model, and the flank wear along with remaining tool life is predicted as the output. The worn tool images were captured using an industrial camera during the turning operation at regular intervals. The ANN training set predicts the remaining useful tool life, especially the sigmoid function and rectified linear unit (ReLU) activation function of ANN. The sigmoid function showed an accuracy of 86.5%, and the ReLU function resulted in 93.3% accuracy in predicting tool life. The proposed model’s maximum and minimum root mean square error (RMSE) is 1.437 and 0.871 min. The outcomes showcased the ability of image processing and ANN modeling as the potential approach for developing a low-cost industrial tool condition monitoring system that can measure tool wear and predict tool life in turning operations.

Dense-Block Structured Convolutional Neural Network-Based Analytical Prediction System of Cutting Tool Wear

Cutting tool wear strongly affects machining processes. Conventionally, multiple types of sensors are installed on the main rotating axis and platform of a machine, and signal analysis is used to determine the condition of the tool in real time through machine learning. With the traditional approach, to measure tool wear, it is required to remove the tool and place it underneath the microscope for measurement to obtain relatively precise results. The time cost, however, is relatively high; it is not cost-effective. With the charge-coupled device (CCD) camera installed in the machine tool, tool wear may be estimated through programed processing. The CCD camera, however, will affect spatial configuration in the machine tool and additional time is needed for tool wear measurement upon completion of processing each time. With the accelerometer sensor combining an offline or online tool wear measurement system and using the training method in this research model upon completion of the dataset, forecasting can be done with the precompleted model, which saves the time needed for offline or online wear measurement. However, the deployment of multiple sensors is difficult and expensive in practice. Used in this study were milling data, namely acoustic emission (AE), vibration, and current data from sensors installed on the rotating axis and platform of a machine. The data were from a National Aeronautics and Space Administration (NASA) dataset. The accelerometer data were used to develop a novel machine-learning algorithm. The vibration signals were integrated with other machining parameters. Signal preprocessing was used to reduce interference from environmental noise, and parameter records and feature signals were analyzed. A 1-D convolutional neural network (CNN) model similar to the DenseNet framework was developed. The model was optimized with framework and parameter adjustment and verified using <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula> -fold cross-validation. The model had a mean absolute error (MAE) of 0.06 and a root mean square error (RMSE) of 0.09. Compared with other machine-learning models, the developed model has higher accuracy.

Online tool wear monitoring by super-resolution based machine vision

The tool condition has been a major concern in modern computer numerical control (CNC) machining due to its direct effects on the quality of final product both in the surface and dimensional integrity. The conventional machine vision-based tool condition monitoring (TCM) approaches cannot meet the high precision requirement in micro machining, as the cutting parameters are in micro scale and the spindle works in high rotation speed which makes online tool wear measurement quite difficult. To meet these challenges, this study develops a single image super-resolution (SISR) approach for direct tool wear estimation in micro-milling. Motivated by the self-similarity of tool wear image morphology, this study proposes a sparse decomposition framework by learning dictionaries from the tool wear image pyramid. Based on their multi-scale invariant properties, the similar image patches of coarse scales can be retrieved from fine scales to reconstruct the high-resolution image fastly and in high quality. The reconstructed high-resolution image then can be conveniently applied to wear monitoring, and overcomes the image acquisition deficiencies of the conventional machine vision-based monitoring approaches. Experimental results validate this approach for the tool wear area estimation as well as its generalization of the wear width with regarding to the conventional manual measurements.

Role of sustainable cooling/lubrication conditions in improving the tribological and machining characteristics of Monel-400 alloy

Due to its strong corrosion resistance, high hardness, and ability to maintain its strength at high temperatures, Monel-400 is utilized in the marine, aerospace, and power plant sectors. Monel-400 alloy is hard to machine owing to quick tool wear that causes poor dimensional accuracy. Therefore, an advanced measurement system is required to monitor the insight of machining performance of difficult-to-machine alloys like Monel-400. In the present work, a new cutting technique is presented to increase the efficiency of cryogenic carbon dioxide (CO2) and minimum quantity lubrication (MQL) in the high-performance machining of Monel-400. The combination of both CO2 + MQL (CMQL) is an efficient approach that is supplied to the rake side and compared with dry, CO2 and MQL. Tool wear, surface roughness, temperature, chip morphology and microhardness measurements were performed to enumerate the influence of distinct cutting environments. Based on the findings of the systematic trials, CMQL was found to be the finest effective cooling technique, reducing friction to the greatest possible extent and creating the best possible surface. Under CMQL condition, the flank wear reduction was found to be 51–55 %, 37–47 % and 26–33 % compared to dry, MQL and CO2 conditions, respectively. Even though CMQL effectively reduces friction, the cryo medium outperformed and increased the machined face hardness.

Analysis of high speed drilling AISI 304 under MQL condition through a novel tool wear measurement method and surface integrity studies

Drilling of SS 304 under dry, flood, and MQL at a relatively high cutting speed of 90 m/min and feed of 525 mm/min is studied. A novel flank wear measurement method is developed for accurate measurement of total drill flank wear - as the sum of the conventional flank wear width and the material lost due to erosion of the cutting edges. Comprehensive surface integrity analysis for machining under such “high speed” – micro-hardness, local plastic deformation on the hole wall surface, surface roughness, and surface irregularities, exit burr - is reported for the first time. The presence of “piercing” type material removal near the drill exit is revealed for dry and flood machining. The tool life, cutting force, drilled hole diameter error, and chip morphology are also analyzed. MQL produces a machining performance often exceeding that of flood lubrication with respect to several machinability parameters considered in this study.

An Approach to Measure Tool Wear through Image Processing in Incremental Sheet Metal Forming

The Incremental sheet metal forming (ISF) is come into the light due to its unique forming technique. In ISF, the metal sheets are transformed into the final product without using dedicated died. The plastic deformation of metal sheets is conducted through a simple forming tool. Its processing time resembles that the ISF is suitable for the formation of customized products, prototypes, and low volume production. Tool life in manufacturing processes is an important consideration for productivity. The present study is an approach to use image processing techniques to measure the exact location and amount of tool wear in the ISF tool which is made of 440C steel. Presently the complex histogram plot is under study. Therefore to predict the tool wear, feed-forward backpropagation (FFB) algorithm is utilized. It is reported that the maximum predicted tool wear of 0.0663mm is found in the trail run 05 with an error of 0.0104mm. The best-fitted value of the FFB model is observed at the epoch 05 with the value of 5.922e-005. The overall coefficient of performance i.e. R2 of FFB modeling is reported as 90.52 % with the mean absolute error (MAE) of 0.0042 which shows a good agreement of the prediction model.

Analysis of Acoustic Emissions for Determination of the Mechanical Effects of Scratch Tests

Acoustic Emission (AE) is a promising technique for measuring tool wear online and in real time. In this work, scratch tests were conducted to better understand the “pre-wear” AE response based on loading conditions that were not sufficient to generate galling. The scratch tests used the same type of indenter against two different sheet materials: aluminum and steel. The results showed that AE parameters such as the mean frequency, Centroid frequency and Shannon entropy outperformed other frequency domain techniques by discriminating between the two sheet materials in scratch tests. From the literature, the frequency region of interest was expected to be sub 300 kHz. However, in this study, activity below this threshold was found to be noise, whereas distinct frequencies were found at much higher frequencies than expected. These results are compared against single grit “SG” tests of both mild steel- and nickel-based superalloys to allow comparison of the two test methods and materials used. This comparison showed that the SG tests excited the acoustic emission in ways in which the scratch tests did not. Another factor when using acoustic emissions to monitor sheet metal forming is the differences obtained in energy–frequency mapping, where many report the galling phenomena between a certain amplitude and frequency range. Such results are specific to the setup and the materials/geometries used. Further work presented here compares different scratch tests where energy–frequency mapping is different for different materials/geometries.

On-machine measurement of tool nose radius and wear during precision/ultra-precision machining

On-machine measurement of tool nose radius and wear during precision/ultra-precision machining

Analysis of vegetable oil-based nano-lubricant technique for improving machinability of Inconel 690

Conventional cutting fluids are applied to dissipate the heat generated in the cutting zone during machining. However, the use of metal cutting fluids causes adverse impacts on workers' health and the environment. Minimum quantity lubrication (MQL) has drawn attention to eliminating the use of mineral-based cutting fluids. The effectiveness of MQL can be further enhanced by employing vegetable oil and nanoparticles. Nanofluid-based lubricants result in superior heat transfer capacity and improved lubricity. In this context, the performance of vegetable oil mixed with and without molybdenum disulfide nanoparticles (nMoS2) applied with MQL is investigated during the machining of Inconel 690. The nanoparticles with different concentrations (0.5%, 1%, and 1.5%) are added in canola oil, and friction coefficient, thermal conductivity, viscosity, and wettability of nanofluids are analyzed. The machining experiments are performed under dry, flood cooling, MQL, and nMQL. The machining performance is evaluated by measuring tool wear, surface roughness, chip morphology, cutting temperature, and energy consumption. The findings revealed the superiority of nMQL with 54%, 29%, and 13% reduction in surface roughness and 56%, 39%, and 12% reduction in energy consumption compared to dry, flood cooling, and MQL environments. Also, nMQL has led to longer tool life. The effectiveness of nMQL has resulted in better tribological conditions in the cutting zone with enhanced cooling/lubricating action of vegetable oil and lamellar structure of nMoS2. The results show a significant role of nano-cutting fluid-based lubricant applications in the machining industry to meet energy-saving and sustainability goals without compromising product quality.

Hybrid data-driven and model-informed online tool wear detection in milling machines

Precision machining tool wear is responsible for low product throughput and quality. Monitoring the tool wear online is vital to prevent degradation in machining quality. However, direct real-time tool wear measurement is not practical. This paper presents residual-based anomaly detection models, combining a hybrid model comprised of a physics-based model and a data-driven model (a decision tree or a neural network) to predict signals of interest (e.g., power or forces) under nominal conditions, followed by Page’s cumulative sum test for detecting tool wear on-line using the computer numerical control machine measurements. The most informative features are ranked using dynamic programming and its approximation variants from real-time measurements and machine settings, such as the width of cut, depth of cut, feed rate and spindle speed, that serve as inputs to the predictive models. The baseline nominal model is incrementally updated with experimental data via a gradient boosted adaptation model to generate the residuals that account for discrepancies between the actual machine data under normal conditions and the baseline nominal model predictions. The hybrid model is validated against 20 Mazak milling machine experimental tests and one Haas run-to-failure experiment. The proposed anomaly detector is applied to synthetic data from simulations of the physics-based model at different operating conditions, measurement noise levels, and tool wear levels, and the methods were able to achieve an overall 92% accuracy in data with 1% noise. The anomaly detection methods based on hybrid model reduced the false alarms of either the data-driven or physical-based models alone, and are found to be capable of good online detection of tool wear.

Methodology for Measuring the Cutting Inserts Wear

In the industrial manufacturing, the wear of the cutting tool represents the main factor that causes machine downtime and it has a negative influence over the machined surface roughness and dimensional and position deviations. For this reason, the accurate measurement of tool wear both on-line (during machining) and off-line (outside of the machining process) is a necessity. Due to the continuous technology innovation, finding new and more effective methods to measure precisely the wear represents a permanent interest for research. In this paper, after a review of recent developed methods in this field, showing the methods of measuring wear and indicating the error sources when measuring the wear of cutting inserts, the necessity to have a unitary methodology for measuring the flank wear is emphasized. Applying it could obtain the same wear-measured values in the same conditions. For this purpose, the measurement errors are determined, and a new methodology for measuring the cutting insert wear is developed. It was tested in the case of six worn cutting inserts used for the turning process of specimens (1C45 steel), of 50 mm diameter and 300 mm length. By testing the developed methodology, it was found that the errors that can be made by various researchers while measuring wear are acceptable, leading to results that can be considered correct from a practical point of view. In the paper is also presented how the principle of symmetry is used to characterize the wear of the cutting inserts.