Tool Wear Tests Research Articles

Optimising Sensor Placement for Tool Condition Monitoring: A Comparative Analysis of Acoustic Emission Data

In the monitoring of machining processes and in the context of tool condition monitoring, the position of acoustic emission sensors affects the quality of the resulting information. This drives this comparative study which presents a comparison of acoustic emission data recorded simultaneously by a sensor attached to the side of the milling table and another sensor near the spindle during a tool wear test on a CNC milling machine. The signal information is clearly influenced by the different positions. Whereas the signals near the spindle are dominated by vibrations of the spindle motor during machining, these strong contributions do not occur in the recorded data of the machining process detected by the sensor mounted to the table. However, the position of the sensor near the spindle has the advantage of maintaining a constant distance to the source of the acoustic emissions of the machining process, as the sensor moves with the tool. In contrast, the sensor attached to the milling table is affected from the fact that the distance to the milling tool is constantly changing. This results in different dominant frequencies, that are analysed in this study. To analyse both the entire frequency range and the higher frequencies, two distinct approaches are employed, one without and one with the use of a high-pass filter. Furthermore, the recorded signals were used to calculate the characteristic features, namely the Partial Powers, thereby enabling assessment of the condition of the tool. The results demonstrate that this single feature type is sufficient for training a machine learning model to predict the tool wear, focusing on the flank wear width. This study analyses the efficiency of wear prediction with respect to both sensors and frequency spectra, and compares the results. In this context, the most accurate predictions were achieved with Gaussian process regression models.

Characterization of low-damage cutting of alfalfa stalks by self-sharpening cutters made of gradient materials

Abstract The use of self-sharpening cutters can increase crop survival and regrowth by reducing the extent of stem damage incurred during the mowing stage and reducing the healing time at the harvest site. In this study, a self-sharpening cutter was prepared using a two-stage rare earth catalytic carbon–nitrogen–boron co-infiltration process, and the self-sharpening and wear-resistant properties of the cutter were verified by using metallographic organization testing, hardness testing, friction and wear performance testing, and the homemade tool wear test bench, and the low-damage cutting characteristics of the cutter were examined through field tests on alfalfa. The results show that the thickness of the penetration layer on the back face of a self-sharpening cutter made of gradient material is about 800 μm, with a maximum hardness of 1,800 HV. The coefficient of friction of the gradient material self-sharpening cutter is 67% lower than that of the commercially available 65Mn cutter. Gradient material self-sharpening cutter wear resistance is 2.15 times more than that of commercially available 65Mn cutter. The gradient material self-sharpening cutter reduces cutting damage by 11.42% compared to the commercially available 65Mn cutter. The application and promotion of self-sharpening cutting blades with gradient materials reduce alfalfa cutting damage, thereby improving reproductive yield.

Tool wear monitoring based on scSE-ResNet-50-TSCNN model integrating machine vision and force signals

In the realm of mechanical machining, tool wear is an unavoidable phenomenon. Monitoring the condition of tool wear is crucial for enhancing machining quality and advancing automation in the manufacturing process. This paper investigates an innovative approach to tool wear monitoring that integrates machine vision with force signal analysis. It relies on a deep residual two-stream convolutional model optimized with the scSE (concurrent spatial and channel squeeze and excitation) attention mechanism (scSE-ResNet-50-TSCNN). The force signals are converted into the corresponding wavelet scale images following wavelet threshold denoising and continuous wavelet transform. Concurrently, the images undergo processing using contrast limited adaptive histogram equalization and the structural similarity index method, allowing for the selection of the most suitable image inputs. The processed data are subsequently input into the developed scSE-ResNet-50-TSCNN model for precise identification of the tool wear state. To validate the model, the paper employed X850 carbon fibre reinforced polymer and Ti–6Al–4V titanium alloy as laminated experimental materials, conducting a series of tool wear tests while collecting pertinent machining data. The experimental results underscore the model’s effectiveness, achieving an impressive recognition accuracy of 93.86%. When compared with alternative models, the proposed approach surpasses them in performance on the identical dataset, showcasing its efficient monitoring capabilities in contrast to single-stream networks or unoptimized networks. Consequently, it excels in monitoring tool wear status and promots crucial technical support for enhancing machining quality control and advancing the field of intelligent manufacturing.

Machining of Hard-to-cut AISI 4462 Duplex Stainless Steel with an Environmentally Friendly Approach with Vortex Tube

Machining is a manufacturing process that can be used to produce precision machine parts and has many advantages. The first is the ability to achieve superior surface quality. Tool wear is an inevitable phenomenon that occurs during machining. It is affected by many machining conditions; therefore, this process needs to be monitored and controlled. In this study, tool wear and surface roughness tests were carried out on AISI 4462 duplex stainless-steel materials, known to be a hard-to-cut material. For this purpose, tool wear and surface roughness analyses were implemented by using the environmentally friendly vortex tube cooling system in addition to wet turning conditions for the first time. For both methods, experiments were conducted at a 1 mm depth of cut, 120 m/min cutting speed, and 0.1 mm/rev feed with a 90 mm cutting length for each pass. Both tool wear and surface roughness were examined at the end of each pass. The analysis showed that wet turning gave better results in terms of tool life (19.8 minutes of tool life) compared to 11.1 minutes of tool life in vortex turning. In contrast, the surface roughness values differed up to two times in some experiments, and the vortex tube experiments gave better surface roughness values in all passes. In addition, the vortex tube experiments showed less built-up-edge (BUE) formation than the wet-turning experiments.

Intelligent Health Monitoring of Machine Tools Using a Bayesian Multibranch Neural Network

Online health monitoring of machine tools is an essential technique for tool life extension, manufacturing productivity improvement and product quality improvement. In the era of industrial big data, numerous deep learning (DL)-based methods have been proposed to achieve these goals. However, in complex and dynamic manufacturing processes, practical concerns such as uncertainty quantification and anti-noise capabilities of the DL-based methods are rarely considered. Thus, in this study, a novel multi-branch Bayesian Neural Network (BNN) is developed for the reliable and robust online health monitoring of Computer Numerical Control (CNC) machine tools. With the proposed model, the heterogeneous fault information extracted from multiple sensors can be simultaneously integrated in a deep convolutional neural network (DCNN)-multiple layer perceptron (MLP)-based multi-branch neural network to enhance the health monitoring accuracy and robustness. Furthermore, the proposed multi-branch neural network is extended into a BNN to improve its uncertainty quantification capabilities. The proposed method is evaluated on the tool wear tests of three cutting tools. Tool wear estimation results indicate that the proposed method outperforms comparative methods and achieves the best prediction accuracy and robustness on all three health monitoring tasks investigated in this study. We also found that the proposed method can accurately classify tool wear stages and reach up to 95% mean classification accuracy, which is the best among comparative methods. Also, measures, such as coverage probability of estimation interval (EICP) and normalized mean estimation interval width (NMEIW), are used to assess the capability of quantifying the confidence intervals (CIs) of the tool wear estimations. Results show that the proposed method achieves superior CIs quantification performance with the average EICP and NMEIW values of 95.77% and 0.27 on all three health monitoring tasks.

Prediction of tool wear based on GA-BP neural network

The anisotropy and nonuniformity of wood-plastic composites (WPCs) affect the milling tool, which rapidly wears during high-speed milling of WPCs. Thus, the evolution mechanism of tool failure becomes complicated, and the prediction of tool wear cannot be precisely described mathematically. A neural network based on tool wear test was proposed to predict the tool wear condition during high-speed milling of WPCs. The traditional backpropagation (BP) neural network easily falls into the local optimal solution. A genetic algorithm (GA-BP) neural network prediction model was established by using the GA to optimise its initial weight and threshold. The BP model and the GA-BP model were evaluated in terms of mean square error and training times, and the generalisation verification was applied to the prediction model. After analysing and comparing the results of the two models, the GA-BP neural network model has better training speed and accuracy under the test conditions. The relative error between the predicted value and the actual value is controlled within 5%.

Self-sharpening property of porous metal-bonded aggregated cBN wheels during the grinding of Ti–6Al–4V alloys

Grinding process with cubic boron nitride (cBN) superabrasive wheels has been the subject of extensive research during high efficiency and precision machining difficult-to-cut materials in aerospace and aviation industries. However, the grinding performance and tool-life of conventional cBN abrasive wheels are severely affected by the probable macro-fracture and pull-out of cBN grains owing to their anisotropic crystalline structure. In this case, porous metal-bonded grinding wheels coupled with high-performance aggregated cBN abrasive grains were developed to improve tool performance and machined surface integrity. Characterisation of morphologies, including as-sintered aggregated cBN abrasive grains, pore structures and grain wear evolutions, was performed. The grinding ratio, grinding forces, force ratio and ground surface roughness were evaluated through single-grain grinding of Ti–6Al–4V alloys. Experimental results indicated that the porous aggregated cBN wheels had abundant chip storage space and excellent wear resistance. A stable grinding force ratio and small ground surface roughness were obtained during the tool wear tests due to the combined characteristics of microfracture and partial macrofracture of multi-layer cBN particles.

The effects of cooling applications on tool life, surface quality, cutting forces, and cutting zone temperature in turning of Ni-based Inconel 625

Due to their high-temperature resistance, nickel-based super alloys are used in many fields, especially in the aviation and aerospace industries. In addition to these advantages, there are some machining difficulties. Some cooling methods are used to minimize the machining difficulties of these materials. For this purpose, in this study, tool life, tool wear, surface roughness (Ra), cutting forces (Fc), and cutting zone temperature (T) were investigated in turning Inconel 625 super alloys under different cooling conditions. Experiments were carried out under three different cutting conditions (dry, minimum quantity lubrication [MQL], and vortex cooling methods). Three feed rates (0.08, 0.1, and 0.12 mm/rev) and three cutting speeds (60, 80, and 100 m/min) were used. Tool wear tests were conducted at average cutting speed and feed rate (80 m/min and 0.1 mm/rev). After the experiments, it was found out that the cooling application positively affects in terms of tool life, cutting zone temperature, and surface roughness. The lowest wear occurred as 0.136 mm in experiments with MQL. The best values for cutting forces, surface roughness, and cutting zone temperatures were also obtained with MQL.

Voltage- and Current-Measurement Based Force Estimation in Broaching Using Synchronous Motor Drive

Monitoring the cutting force in broaching provides valuable information about the tool condition as well as the effect of the process on the workpiece surface integrity. This study uses a synchronous-motor-drive broaching machine and deals with the motor-current based indirect-measurement of the cutting force, which is based on detecting the variation of the motor torque during cutting. Most current-based methods need to model the relationship between the motor current and the cutting force. However, when the feed drive mechanism is modeled to obtain this relationship, modeling errors occur. For accurate modeling, a calibration test using a force sensor is necessary before performing the indirect-force measurement. Therefore, this study focuses on the energy conversion from electrical power to mechanical power, and it identifies this relationship based on the voltage equation of the drive motor by using not only current measurement but also voltage measurement. Then, a developed model with the identified relationship calculates the cutting force, excluding electrical and mechanical losses that do not contribute to the process. By conducting a tool-wear test in broaching of Inconel 718, a possible application of the indirect force measurement system was demonstrated.

Comparison of machining performance under MQL and ultra-high voltage EMQL conditions based on tribological properties

This novel work presents the comparison of a newly developed ultra-high voltage electrostatic minimum quantity lubrication (EMQL) using a customized nozzle with the MQL technique as an alternative cooling/lubricating method in turning processes of 15–5 PHSS. The optimum voltage for EMQL within the range of 0–25 kV has been identified based on tribological performance. Besides, surface roughness has been measured to identify the impact of electrostatically charged mist for turning 15-5 PHSS. Finally, tool wear tests are performed for MQL and EMQL at optimized voltage. The EMQL at optimized electrostatic voltage resulted in 38% decreased tool wear as compared to conventional MQL for 2400 mm cutting length.

Characterization and life prediction of single-pass honing tool for fuel injection nozzle

Single-pass honing is an important machining method for finish machining of holes, which can meet the requirement for high efficiency and consistency of holes. Characterization and life prediction of single-pass honing tool are necessary to improve the machining accuracy of holes honed, especially dimension accuracy. Single-pass honing tool is a single layer abrasive tool with fixed dimension, which still remains problematic for characterization and life prediction. For fuel injection nozzles with bore diameter under 1 mm, the stiffness of the single-pass honing tool is poor. This article presents a novel analytical model that predicts life of the tool with poor stiffness. Firstly, according to the bore diameter and dimension tolerance, the single-pass honing tool is designed and manufactured. Based on the prepared single-pass honing tool, the measurement and characterization methods are established. Furthermore, the tool wear tests are carried out, and the tool contour evolution model is established to predict the tool life.

Numerical simulation of tool wear in drilling Inconel 718 under flood and cryogenic cooling conditions

This paper aims to model and simulate tool wear in drilling of Inconel 718 under two different cooling conditions, using an innovative numerical procedure. Although tool wear models can be implemented in most of finite element analysis (FEA) software to calculate the tool wear rate, there is a great limit due to the inability of all these software to update the geometry of the worn tool. In order to overcome this limitation, a subroutine able to modify the tool geometry based on a given tool wear model was developed and implemented in DEFORM 3D, an implicit FEA software. Experimental tests were performed to measure tool wear in drilling using conventional metal working fluids (MWF) and liquid nitrogen (LN2) cooling. Experimental data were used to calibrate the tool wear model and to validate the drilling models. A comparison between simulated and measured results demonstrated the suitability of the developed drilling model to predict tool wear under both MWF and LN2 cooling conditions. Therefore, the developed model can be efficiently used to evaluate the influence of the cutting conditions (including cooling conditions) on tool wear, minimizing the number of expensive and time-consuming tool wear tests.

Multi-objective optimization of turning parameters for targeting surface roughness and maximizing material removal rate in dry turning of AISI 316L with PVD-coated cermet insert

The intention of investigating the alternative cutting tool performance, namely cermet insert to support the usage of coated cemented carbide for enhancing the productivity in turning of hard to cut materials such as stainless steels, is the rationality of this research. Therefore, the aim of this study is to determine the influence of cutting parameters such as cutting speed, feed and depth of cut on surface roughness (Ra) and material removal rate (MRR) during dry turning of AISI 316L using cermet insert (GC1525). Experimental tests were carried out according to Taguchi L27 orthogonal array. The technique of response surface methodology and analysis of variance were also used to develop the quadratic regression model. Four optimization cases were performed using the desirability function to find the optimal cutting parameters by targeting Ra and maximizing MRR, unlike other researches that have focused only on minimizing Ra. Based on the results, it was found that the most predominant parameter affecting the Ra was the feed with 79.61% of contribution, while the MRR was strongly influenced by the depth of cut followed by cutting speed and feed, respectively. Tool wear tests were also performed and the results indicated that the tool life of cermet tool was measured as 30 min at cutting speed of 340 m/min.

Study on Technological Effects of a Precise Grooving of AlSi13MgCuNi Alloy with a Novel WCCo/PCD (DDCC) Inserts.

The WCCo/PCD (Diamond Dispersed Cemented Carbide—DDCC) manufactured with the use of PPS (pulse plasma sintering) are modern materials intended for cutting tools with the benefits of tungsten carbides and polycrystalline diamonds. Nevertheless, the cutting performance of DDCC materials are currently not recognized. Thus this study proposes the evaluation of technological effects of a precise groove turning process of hard-to-cut AlSi13MgCuNi alloy with DDCC tools. The conducted studies involved the measurements of machined surface topographies after grooving with different cutting parameters. In addition, the tool life and wear tests of DDCC inserts were conducted during grooving process and the obtained results were compiled with values reached during machining with cemented carbide tools. It was also proved that grooving of AlSi13MgCuNi alloy with DDCC inserts enables 5 times longer tool life and almost 3-fold increase of cutting path compared to values obtained during grooving with H3 and H10 cemented carbide inserts. Ultimately, the feed value of f = 0.15 mm/rev and cutting speed in a range of 800 m/min ≤ vc ≤ 1000 m/min during grooving with DDCC inserts can be defined as an optimal machining parameters, enabling the maximization of tool life and improvement in surface quality.

Identification of oxidation process of TiALN coatings versus heat resistant aerospace alloys based on diffusion couples and tool wear tests

This paper presents results of both oxidation and tool wear tests concerning the couples consisting of Ni-and Ti-based alloys and TiAlN coating to determine its oxidation behaviour. Firstly, oxidation tests are performed in a special chamber at temperatures ranging from 700°C to 1000°C in air atmosphere. Secondly, the wear tests were carried out keeping the same temperature range. The surface morphologies, chemical elements and produced phases were analysed with SEM, EDS and XRD techniques. The results show that protective Al2O3 films are formed on the TiAlN coating surface. The prediction methodology for oxidation process and corresponding tool wear is proposed.

An Enhanced Deep Learning-Based Fusion Prognostic Method for RUL Prediction

This article proposes a novel deep learning based fusion prognostic method for remaining useful life (RUL) prediction of engineering systems. The proposed framework strategically combines the advantages of bidirectional long short-term memory (BLSTM) networks and particle filter (PF) method and meanwhile mitigates their limitations. In the proposed framework, BLSTM networks are applied for further extracting, selecting, and fusing discriminative features to form predicted measurements of the identified degradation indicator. Simultaneously, PF is utilized to estimate system state and identify unknown parameters of the degradation model for RUL prediction. Hence, the proposed fusion prognostic framework has two innovative features: first, the preprocessed features from raw multisensor data can be intelligently extracted, selected, and fused by the BLSTM networks without specific domain knowledge of feature engineering; second, the predicted measurements with uncertainties obtained from the BLSTM networks will be properly represented by the PF in a transparent manner. Moreover, the developed approach is experimentally validated with machining tool wear tests on a computer numerical control (CNC) milling machine. In addition, the popular techniques employed in this field are also investigated to compare with the proposed method.

Deep heterogeneous GRU model for predictive analytics in smart manufacturing: Application to tool wear prediction

Smart manufacturing arises the growing demand for predictive analytics to forecast the deterioration and reliability of equipment. Many machine learning algorithms, especially deep learning, have been investigated for the above tasks. However, long-term prediction is still considered as a challenging issue. To address this problem, this paper presents a hybrid prediction scheme accomplished by a newly developed deep heterogeneous GRU model, along with local feature extraction. Specifically, to capture the temporal pattern hidden in the sequential input, a local feature extraction method is designed by integrating expertise knowledge into the deep learning model for enhanced feature learning. Next, an intermediate layer is designed in the deep heterogeneous GRU model structure to capture the inherent relation for long-term prediction. The proposed model is optimized by systematic feature engineering and optimal hyperparameter searching. Finally, experimental studies on tool wear test are performed to validate the superiority of the presented model over conventional approaches.

Influence of deep cryogenic cooling on tool wear and surface roughness of coated tungsten carbide inserts using statistical techniques

Tool life enhancement with improved machining performance of existing turning inserts during hard turning process is an essential industrial requirement to reduce the manufacturing cost and to improve the surface finish with higher accuracy. The objective of this paper is to study the effects of Deep Cryogenic Cooling on coated tungsten carbide inserts and to evaluate their tool wear and resulting surface finish by conducting turning experiments on P20 tool steel material. To evaluate these properties, turning experiments were carried out as per the Taguchi’s design of experiments technique, by considering the three experimental parameters namely turning speed, depth of cut and feed rate. The effect of these parameters on tool wear and surface finish of the workpiece are analyzed by analysis of variance technique. The results indicated that feed rate had the highest influence of 71.85% on the surface finish of the machined surface, whereas the depth of cut influenced 14.86% & followed by turning speed which had 4.91% influence on surface finish. Similarly, for tool wear, it was found that turning speed had a significance value of 39.95% on tool wear followed by the depth of cut (37.95%) and feed rate (18.85%). The experimental data were used to develop the regression correlations for surface finish, and tool wear and confirmation tests were carried out to validate the models. The comparison between predicted and experimental values indicated a maximum deviation of around ±8% for surface roughness and ±11% for the observed tool wear. And scanning electron microscopic analysis of deep cryogenic treated inserts indicates a homogeneous distribution of η-carbides in cobalt matrix and a grain size refinement of α-phase compared to untreated inserts.

Evaluation of Cutting Tool Wear of Earth Pressure Balance Shield in Granular Soil Based on Laboratory Test

Abstract Cutting tool wear is a critical problem for tunneling in soft ground with the earth pressure balance shield. In this study, a cutting tool tester was developed in the China University of Geosciences in Beijing, and a series of tool wear tests were conducted to investigate the characteristics of tool wear in granular soils. The characteristics of cutting tool wear can be quantitatively assessed through the ratio (M0 − M)/M0 (i.e., tool wear rate, %; M0 and M are the mass of the tested blocks before and after the wear test, respectively). The effects of five important factors, including mineralogy, moisture, soil conditioner, test time, and sand content, on tool wear were considered in various test conditions. According to the primary test results, it is observed that (1) high soil hardness produced significantly higher tool wear than low soil hardness in dry condition; (2) with increasing water content, the tool wear gradually increased to a maximum value and then decreased; (3) the foam conditioner mixed in sandy gravel reduced the tool wear dramatically regardless of the cutting tool material, e.g., cemented carbide and Q235 steel; (4) the tool wear increased with the test time in the dry sand mixture, and their relationship showed a good agreement with a power function; and (5) the tool wear decreased as the sand content increased in dry sand-gravel soil mixtures. The reasons for these phenomena were also explored.

Analiza procesu zużycia narzędzi wykonanych ze stali 1.2344 oraz stopu MP159 w procesie zgrzewania tarciowego z przemieszaniem (FSW) blach ze stopu Aluminium 7075 T6

The study presents an analysis of wear of tools made of 1.2344 steel and MP159 alloy for the process of obtaining an overlap joint in 1.0 mm and 0.8 mm sheet metal made of 7075 T6 aluminum alloy using friction stir welding (FSW) technology. Tool geometry was designed at the Czestochowa University of Technology. Evaluation of tool wear was conducted based on the measurements of geometry of working area of tools by means of a multisensory meter system and based on the assessment of the working area by means of a stereoscope after individual stages of wear tests. Furthermore, based on the results of a static tensile strength test and metallographic examinations of the specimens sampled from the joints obtained during tool wear tests, the effect of the degree of tool wear on joint quality was also evaluated. Analysis of the results revealed that both the tool made of 1.2344 steel and that made of MP159 alloy were substantially worn, increasing the risk of further use of the tools for the joint material (7075-T6) after obtaining the joint with length of 200m, which suggests their low durability. Furthermore, modification of tool geometry caused by wear led to insignificant improvements in joint strength. Therefore, the results of wear measurement set directions for further modification of tool geometry, also due to the fact that despite a substantial wear, the tools continued to yield high-quality joints without defects. As demonstrated in the study, the type of tool material does not only impact on tool life but also, as it was the case in their geometry, has a significant effect on the quality of obtained joints. Although the tool made of MP159 alloy was worn more than the tool made of 1.2344 steel, it allowed for obtaining the joints with substantially better strength parameters.