Wear Estimation Research Articles

The effect of cutting speed and work piece hardness on turning performance of nickel based super Alloy-718 using ceramic cutting inserts

The present investigation pertains to a series of experiments on plain turning of Inconel 718 with Al–Oxide (620), mixed oxide (6050) and silicon nitride (6190) ceramic cutting tools. The effect of cutting speed and hardness of material (being cut) on flank wear of tools and surface finish of work piece was studied. Inconel 718 with three hardness values (26 HRC, 35 HRC and 45 HRC) was used to assess the turning performance. Three cutting speeds (145 m min−1, 230 m min−1 and 360 m min−1) were used while feed rate and depth of cut was fixed at 0.19 mm min−1 and 0.3 mm respectively. Optical microscopy was used for estimation of tool flank wear and mechanisms of wear were established. Work piece hardness and cutting speed were found to be and also most influencing factors for tool life. Cutting forces observed to be higher for harder work piece and for mixed oxide cutting tool. The influence of cutting speed on chip formation was manifested in the form of continuous chip at a cutting speed of 145 m min−1. Segmented chip at higher cutting speed (above 230 m min−1) was observed for all the three cutting tools. Significant difference in tool flank wear and surface finish was observed for different work piece hardness and cutting speed with different cutting inserts for constant duration of machining time (3 min). Al-Oxide cutting insert provided better surface finish and low flank wear compared to silicon nitride and mixed oxide cutting inserts irrespective of the work piece hardness and cutting speed. Further, 45 HRC Inconel 718 possesses better surface finish and 26 HRC Inconel 718 possess better tool flank wear resistance in turning operation.

A novel transformer-based neural network model for tool wear estimation

This paper proposes a novel Transformer-based neural network model for accurate tool wear estimation to improve production quality and efficiency in intelligent manufacturing. The proposed method can realize indirect measurement of tool wear. Initially, the raw multi-sensor signals are processed into three kinds of temporal feature data. Next, three identical submodels are utilized to deal with the above feature data, respectively. Finally, the outputs of these three submodels are concatenated together as the input of a multi-layer fully connected network for the final estimation of tool wear. Concretely, the submodels used in this work are based on the Transformer model and self-attention mechanism to capture long-term dependency. This is the first attempt to adopt Transformer and self-attention for tool wear estimation. Besides, some improvements are made in this work. For example, a long short-term memory network is employed to enhance the ability of capturing position information. In addition, a submodel framework is applied to process the temporal feature data in parallel, which helps improve the model performance. The proposed method is demonstrated through a real-world milling dataset, including more than 900 experiments. Also, the superiority of the proposed method is verified by the comparison with other advanced methods.

Estimation of tool wear and optimization of cutting parameters based on novel ANFIS-PSO method toward intelligent machining

Compacted graphite iron (CGI) plays an important role in contemporary manufacturing of automobile engine, and coated tool is the best choice for milling of CGI. But studies about the estimation of the wear of coated tool are still rare and incomplete. As tool wear is the main factor that affects the quality of machined surface, in this study, we proposed an intelligent model-adaptive neuro fuzzy inference system (ANFIS) to estimate the tool wear, and ANFIS was learned by the improved particle swarm optimization (PSO) algorithm. As the PSO algorithm is easy to fall into the local minimum, the vibration and communication particle swarm optimization (VCPSO) algorithm was proposed by introducing the self-random vibration and inter-particle communication mechanisms. Besides that, to obtain the optimal combination of milling parameters, the multi-objective optimization based on minimum cutting power, surface roughness and maximum material removal rate (MRR) was studied using VCPSO algorithm. The experimental results showed that the ANFIS learned by VCPSO algorithm (ANFIS-VCPSO) has better performance for the estimation of tool wear compared with other intelligent models. The VCPSO algorithm was tested using Benchmark functions, and the results showed VCPSO algorithm has the global optimization ability. Meantime, the best combinations of milling parameters under different tool wear status were obtained through VCPSO algorithm. The proposed ANFIS-VCPSO model as a new intelligent model can be applied for real-time tool wear monitoring, which can improve the machining efficiency and prolong tool life. In order to meet the requirements of green and intelligent manufacturing, the best combination of milling parameters was also obtained in this work.

Individual Service Life-Time of the High Pressure Rotor of the Steam Turbine T-250/300-240

Research of the TC and the SSS of the high pressure rotor of the steam turbine T-250/300-240 taking into account the results of repair and restoration works; estimation of low cycle and static wear, as well as residual resource; comparison of cyclic damage, residual working time and CHP rotor life before and after repair and restoration works, taking into account the adjusted stock ratios. The object of the study is to extend the life of the steam turbine T-250/300-240. The subject of the study is the assessment of low cycle and static wear, thermal and stress-strain state, damage, residual life of the CHP rotor of the steam turbine T-250/300-240, taking into account structural changes and circuitry. The scientific novelty of the obtained results consists in solving, on the basis of settlement research, the actual problem of managing the resource of energy equipment, namely: improved determination of the thermal and stress-deformed state of the CHP rotor of the steam turbine T-250/300-240; The evaluation of low cycle and static tiredness and the formulated proposals for increasing the reliability of the work of RHP; the evaluation and comparison of the residual resource before and after structural changes with the account of the adjusted stock factors is improved. The practical significance of the results obtained includes the calculated data regarding the TC, SSS and the residual life of the turbine T-250/300-240 at the Kyiv TPP-5 PJSC, taking into account the actual operating conditions and the results of the repair work, and the recommendations are based on the possibility of continuing the operation of the turbine.

Tool wear estimation in machining based on the flank wear inclination angle changes using the FE method

In this study, a FEM-based tool wear approach with a focus on the geometry of the worn tool, especially the changes of flank wear land inclination angle, was developed. The relationship between the variables of the wear rate equation and the average nodal temperature on the flank wear land through integrating FE-simulations of the cutting process and Response Surface Methodology (RSM) was determined in order to define the temperature as a function of wear rate model parameters. Then, that data was used to calibrate the wear rate equation which was obtained by establishing the relationship between the Usui wear rate equation and the geometry of the worn tool, using a MATLAB program. This approach was validated by comparing the predicted flank wear rates and experimental measurements. The estimated flank wear shows some improvement compare to the model with a constant inclination angle.

Prediction of specific wear rate for LM25/ZrO2 composites using Levenberg–Marquardt backpropagation algorithm

In this study, the wear estimation capability of RSM and artificial neural network (ANN) modelling techniques are examined and compared in this study. Though both RSM and ANN model performed well, ANN-based approach is found to be better in fitting to measure output response in comparison with the RSM model. The comparison of the productive capacity of RSM and LMBP (Levenberg–Marquardt backpropagation) neural network architecture for modelling the output, as well as output, predicted for the wear samples in terms of various statistical parameters such as coefficient of determination (R2), etc., has been done. The coefficient of determination (R2) is higher for which the evaluated value shows that the ANN models have a higher modelling ability than the RSM model. The comparison between the experimental value and predicted value obtained by the ANN and RSM models reveals the coefficient of model determination (R2) for the ANN and RSM model is close to unity. The results obtained from the comparison of specific wear rate values using ANN and RSM were proved to be close to the reading recorded experimentally with a 99% confidence level.

Tool Wear Estimation in End Milling of Titanium Alloy Using NPE and a Novel WOA-SVM Model

Accurate identification of the tool wear states in machining of titanium alloys continues to be a thorny problem. Rapid construction of accurate and effective tool wear predictive models with regard to various titanium alloys is indispensable for promoting the development of intelligent manufacturing. This article presents a novel WOA-SVM model that integrates support vector machine (SVM) and whale optimization algorithm (WOA), which is utilized for accurate estimation of the tool wear in end milling of titanium alloy Ti-6Al-4V under variable cutting conditions. The signal features in three domains are extracted from the original cutting forces and constitute the “complete features” that are adopted as the monitoring features. Besides, neighborhood preserving embedding (NPE) is utilized to fuse the monitoring features and realize dimension reduction, which aims at improving the modeling efficiency of the novel WOA-SVM model. The experimental results show that under the premise of guaranteeing prediction accuracy, the utilization of NPE reduces the modeling time-consumption of WOA-SVM by more than 90%. In comparison with the commonly used methods (such as PSO-SVM and GSA-SVM), WOA-SVM takes on comparable prediction accuracy and can reduce the modeling time-consumption by more than 30% in most cases. Moreover, the WOA-SVM model has better prediction accuracy and stability than other classical methods, such as k-nearest neighbor (k-NN), feedforward neural network (FFNN), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and classification and regression tree (CART). Therefore, the combination of NPE and WOA-SVM provides a guarantee for rapidly constructing accurate tool wear predictive models in machining of titanium alloys.

Monitoring tool wear using wavelet package decomposition and a novel gravitational search algorithm–least square support vector machine model

Monitoring tool wear has drawn much attention recently since tool failure will make it hard to guarantee the surface integrity of workpieces and the stability of manufacturing process. In this paper, the integrated approach that combines wavelet package decomposition, least square support vector machine, and the gravitational search algorithm is proposed for monitoring the tool wear in turning process. Firstly, the wavelet package decomposition is utilized to decompose the original cutting force signals into multiple sub-bands. Root mean square of the wavelet packet coefficients in each sub-band are extracted as the monitoring features. Then, the gravitational search algorithm–least square support vector machine model is constructed by using the extracted wavelet–domain features so as to identify the tool wear states. Eight sets of cutting experiments are conducted to prove the superiority of the proposed integrated approach. The experimental results show that the wavelet–domain features can help to ameliorate the performance of the gravitational search algorithm–least square support vector machine model. Besides, gravitational search algorithm–least square support vector machine performs better than gravitational search algorithm–support vector machine in prediction accuracy of tool wear states even in the case of small-sized training data set and the time consumption of parameters optimization in gravitational search algorithm–least square support vector machine is less than that of gravitational search algorithm–support vector machine under large-sized training data set. What's more, the gravitational search algorithm–least square support vector machine model outperforms some other related methods for tool wear estimation, such as k-NN, feedforward neural network, classification and regression tree, and linear discriminant analysis.

Crack propagation and wear estimation of ceramic tool in cutting inconel 718 based on discrete element method

Abstract The crack propagation and wear evolution of Sialon ceramic tool in cutting Ni-based super-alloy Inconel 718 was researched by the discrete element method(DEM) simulation and experiments. The periodic boundary and three body abrasion methods were introduced, and then a thermal-mechanical coupled model was established to describe the tool-chip tribology behavior. The isolated particles and broken parallel bonds were adopted to evaluate the crack of ceramic tool, and the length and height of spalling were used to estimate the degree of wear. Subsequently, experiments were designed by parameters. The results showed that the DEM model valid reveal the crack propagation process. In addition, process optimization was put forward to ensure comprehensive efficiency in the actual machining course.

Tool Flank Wear Estimation using Emitted Sound Signal Analysis by PCA – SER Based Peak to Peak Measurements

The higher levels degrees of automation for industry 4.0 standards require optimization techniques in production activities including tool wear monitoring. The unmonitored tool may spoil the product if it is worn out more than the permitted levels or micro broken or cracked internally. A novel method suggested in this work utilizes neither extra ordinary calculation nor complex mathematical transformations in tool wear monitoring. This method follows no video capturing and image processing rather follows a simple sound wave monitoring captured at the time conversion process by a microphone. The SER a PCA variant technique with the purpose of used in selecting simply the higher velocity of principal components (PCs) in quantifying the feature extracted while separating noise from sound signals. A SER method is used for the selection of suitable PCs for consideration. The best methods of normalization suitable for the SER method is found and implemented the PCA-SER on signals after filter the signals by butter worth filter to remove noise. This proposed procedure resulted in wide differences and proper annotation in differentiating the degree of tool wear in fresh, slight and severely worn categories.

Optimized tabu search estimation of wear characteristics and cutting forces in compact core drilling of basalt rock using PCD tool inserts

Monitoring of cutting tool wear is crucial in machining operations where planning for longer tool life would result in economical savings. While deterministic and stochastic methods were sought for identifying optimal cutting conditions, efficiency and/or accuracy of the generated model fits were found to suffer when dealing with large number of variables. In this work, we present a novel method for tool wear optimization that combines tabu search algorithm with regression analysis (dubbed TS-REG). First, this method is validated against literature-reported model equation fitting of several modeling studies of turning, end milling, and drilling processes. Corroboration of TS-REG is established having found that it outperforms other techniques such as REG, artificial neural networks (ANN), and genetic algorithm (GA). Then, TS-REG is utilized to estimate tool wear and cutting forces for efficient core drilling of basalt rock, a hard and abrasive component of the Martian surface. For cutting data, this work utilizes previously reported tool wear and force data by Hamade and coworkers of polycrystalline diamond (PCD) compact core drilling experiments. The cutting data is comprised of dependent variables of tool wear (flank wear and cutting edge radius wear) and forces (thrust force and torque)as function of several independent variables (process parameters) namely rake angle, spindle speed, tool feed, rock specimen’s ultimate compressive strength, UCS , specimen rock type, and drilled depth. These independent variables and their combinations resulted in fit equations with total number of 117 different variables. As compared with conventional REG and ANN fit estimates of the same data, TS-REG was found to yield the best statistical estimates of tool wear and cutting forces model equations where all dependent parameters were included in the model. Statistical metrics used for assessment of the fitted models were p-value, R-squared, and mean absolute percentage error.

Modelling stochastic excitations for a fast wear calculation methodology

Modelling and simulation of wheel profile evolution is a time-consuming process in which the variables that affect simulation cases are usually selected and tuned through an iterative process, in order to find the right setup for a specific case. In a previous work, a fast and reliable methodology for wear prediction was developed, systematic and applicable in general terms for any arbitrary network, vehicle fleet or operating conditions. Here variables that influence the running behaviour of the vehicle along a track were classified into two groups (deterministic or statistical), according to the kind of method to be used to consider them in the wear calculation process. The deterministic method was already defined in [1], while this paper focuses on the definition of the statistical method. This methodology is illustrated through the study of track irregularities: first, their actual effect on wear is analysed and then, their representation as stochastic variables in the developed methodology is presented. The whole methodology is based on quasi-static simulations instead of dynamic simulations for calculating the wheel-rail contact parameters, so a special effort is made in ensuring that, when these parameters are defined by a statistical method, the methodology for wear estimation continues being valid.

EXPERIMENTAL INVESTIGATION ON TAPPING OF Al6061/SiC METAL MATRIX COMPOSITE WITH 2 AND 4 MICRONS TiAlN COATED STRAIGHT FLUTED HSS MACHINE TAPS

The objective of this work is to evaluate the performance of straight fluted HSS machine taps with 2 microns and 4 microns thickness of TiAlN coating on tapping of Al6061/SiC metal matrix composite. The methodology includes the fabrication of Al6061/SiC Metal matrix composite by stir casting process with 5, 7.5 and 10 weight percent SiC particles. Tapping operation was performed under dry conditions with different cutting speed and constant feed rate equal to the pitch of the thread. The specimens were drilled and tapped with HSS M8X1.25 machine taps coated with TiAlN coating of 2 and 4 micron thickness, in a CNC vertical machining center. The performance of HSS machine taps was evaluated in terms of tapping torque, tool flank wear, and quality of threads produced. Torque and thrust were measured using a drill tool dynamometer of Kistler make. Quality of threaded holes was analyzed by capturing the thread profile using a metallurgical microscope. The estimation of progressive flank wear of HSS machine taps was done using the profile projector. Increase in weight percentage of SiC particles and tapping speed would increase the torque required for tapping, rate of flank wear of the tool and decrease the quality of threaded holes. The progressive flank wear was found higher in machine taps with 2 microns thickness of TiAlN coating when compared to taps with 4 microns thickness of TiAlN coating. Influence of cutting speed on progressive flank wear of HSS machine tap was found to be higher compared to the thickness of TiAlN coating on the tap and weight percentage of SiC.

An investigation into tapping of Al6061/SiC metal matrix composite with straight flute HSS machine tap

The present study deals with tapping of Al6061/SiC metal matrix composite. Stir casting technique was used for the fabrication of composite. Castings were produced by varying weight percentages of SiC (5%, 7.5% and 10%) of 23μm size in Al6061. The tapping experiments were conducted for the machinability study of Al6061/SiC metal matrix composite using M8 x 1.25 HSS machine taps. The tapping operation was performed under dry condition with different cutting speeds. Torque required for tapping was measured using piezoelectric based 4-component drill tool dynamometer. Surface morphology and profile of thread surfaces were analysed using Scanning Electron Microscope (SEM) and metallurgical microscope. Estimation of progressive flank wear of machine taps was undertaken using profile projector. The performance of HSS machine tap was evaluated in terms of tapping torque, tool flank wear, and surface characteristics of thread surfaces. The flank wear of uncoated HSS machine tap increased with the increase in weight percentage of SiC in Al/SiC composite for a particular cutting speed. Further, when the matrix materials were reinforced by the same kind and the same weight percentage of SiC particles, the flank wear of the tool was found to increase with cutting speed. In addition, the damage caused to thread profiles increased with the increase in cutting speed and weight percentage of SiC.

Surface as a carrier of information about the tribological process

Production processes and the processes of wear leave their fingerprints on the surface texture of machine components. Therefore, surface texture is, without a doubt, a carrier of information about these processes. The specialized analysis of surface texture can deliver much useful information about the changes of the surface that occurred during tribological processes as well as information about the phenomena occurring during these processes. This paper presents the kind of analysis done on the basis of the piston skirt surface texture after engine operating conditions. This important engine element was chosen as an object of research since, according to the literature review, the analysis of this surface type is complicated because the base (valley) structure has a deterministic character, but the plateau structure – a random one. The approach presented in the paper gives the possibility to obtain information about changes of particular surface texture layers, thus providing such information as the initial height of the original profile (before wear) and the standard deviation of the plateau part of the surface of the piston skirt. The impact of wear processes on the participation of the particular components of the surface texture is also pointed out. On the basis of the information derived from the model, the method of estimation of local linear wear of the piston skirt is introduced. The possibilities of this approach are presented and discussed as well as a critical analysis of the results.

Proposal of Wear Estimation Method for Mooring Chain of Floating Structures

Up to now, wear estimation method for mooring chain of floating facilities has not been established, and it currently relies on empirical methods. In this research, numerical analysis combining 1) wear analysis between links by finite element method and 2) response analysis of mooring system was performed to establish a method for estimating wear amount of mooring chain during operation. The validity of the proposed method was confirmed by comparing with the actual measurement value in the actual sea area. As a result, it was found that the wear amount estimated by our proposed method is generally close to the measured value. However, it was also confirmed that the estimated wear amount at the touchdown point between the seabed and mooring chain was considerably overestimated. That result could be attributed to insufficient consideration of the effects caused between the links ( e.g. snap load, elastic deformation and friction), the behavior of the links ( e.g. sticking, rolling and non-contact) and the external forces ( e.g. wind and current ).

Acoustic emission signal source separation for a flank wear estimation of drilling tools

The knowledge of the tool wear condition is essential for the dimensional accuracy of the workpiece. Commonly used systems for wear monitoring are usually based on the piezoelectric force measurement. However, in industry these systems are difficult to integrate. A suitable to integrate sensor type is the acoustic emission (AE) sensor. In this paper the main focus will be on the flank wear of drilling tools. For the investigation of the emitted frequency of the flank wear different analogy experiments needs to be realized. With the help of machine learning algorithms the recorded data will be classified.

Quantitative Wear Estimation for Mooring Chain of Floating Structures and Its Validation

Quantitative Wear Estimation for Mooring Chain of Floating Structures and Its Validation

Micromechanical estimation of the effective wear of elastoplastic fiber-reinforced composites

A micromechanical approach recently elaborated for estimating the effective wear of linearly elastic heterogeneous materials is, in the present work, extended to elastoplastic fibrous composites consisting of an elastoplastic matrix reinforced by elastic unidirectional fibers. The local wear behavior of both the fiber and matrix phases is assumed to be governed by the well-known Archard law. It is shown that: (i) when the normal force supported by an elastoplastic fibrous composite is smaller than a critical value, the effective wear of the composite complies still with Archard law; (ii) once the normal force applied to the composite is larger than the critical value, the effective wear of the composite depends nonlinearly on the normal force so that Archard law is no longer valid. Using the composite cylinder assemblage (CCA) model and adopting the Tresca yield criterion for the matrix phase, the effective wear of elastoplastic fiber-reinforced composites is analytically and explicitly estimated while distinguishing different elastic and elastoplastic stages. These results contribute to developing a micromechanical approach of theoretical and practical interest for understanding and designing the tribological properties of nonlinear inhomogeneous materials.

Lifetime prediction of linear slide rails based on surface abrasion and rolling contact fatigue-induced damage

The research presented in this paper deals with the development of an integrated numerical model for the estimation of the incremental surface wear and damage accumulation in linear slide rails. The target is the estimation of the progressive increment of the end-point deflection of the last member of the slide rail during the operational lifetime. The surface abrasion is accounted for by utilizing a modified Archard equation with the aim of estimating the amount of wear along the vertical direction of the slide rails members. In addition to that, the Lemaitre damage model is utilized for the estimation rolling contact fatigue (pitting), considering the total strain and not only the plastic strain. Experiments have been carried out on a small-scale slide rail testing machine in order to define the wear increment on the slide rail inner groove for increasing number of cycles and, accordingly, estimate the modified Archard model constants. In addition to that, the wear parameters for the Lemaitre damage model have been inversely calibrated from the results of tensile tests. A numerical model has been implemented in ABAQUS/Explicit and an external geometry-update subroutine has been employed to update the geometry of the slide rail groove for increasing number of cycles as a consequence of wear and roll contact fatigue. The comparison between numerical and experimental results on real rails have shown a maximum deviation equal to 12.9%, supporting the reliability of the proposed approach.