On-line Tool Wear Monitoring Research Articles

Online monitoring and measurements of tool wear for precision turning of stainless steel parts

Online monitoring and measurements of tool wear were carried out using cutting forces for precision turning of stainless steel parts. The best combination of features was selected from 14 features extracted from force signals by using a Sequential Forward Search algorithm. Back-propagation neural networks (BPNs) used two features for online classification. When the adaptive neuro-fuzzy inference system (ANFIS) was applied, seven features were needed for the classification. For online measurements, only one feature is needed for BPN. Three features are needed for ANFIS for online measurements. For online classification of turning tool conditions, a 2 × 20 × 1 BPN can achieve a success rate of higher than 86% while a 7 × 2 ANFIS can reach a success rate of higher than 96%. For online measurements of tool wear, the estimation error can be as low as 1.37% when a 1 × 20 × 1 BPN was used while the error can be as low as 0.56% using a 3 × 3 ANFIS. Therefore, the 3 × 3 ANFIS can be used first to predict the degradation of tool conditions during the turning process. It can also be used to measure the tool wear online so as to take feedback control action to enhance accuracy of the process. Once the detected tool wear is close to the worn-out threshold, the 7 × 2 ANFIS will be then applied to classify the tool conditions in order to stop the turning operation on time automatically so as to assure the quality of products and to avoid catastrophic failure.

Machine Tool Condition Monitoring Based on an Adaptive Gaussian Mixture Model

Indirect, online tool wear monitoring is one of the most difficult tasks in the context of industrial machining operation. The challenge is how to construct an effective model that can consistently exemplify the degradation propagation of tool performance (i.e., tool wear) based on a continuous acquisition of multiple sensor signals. This paper proposes an adaptive Gaussian mixture model (AGMM) to provide a comprehensible and robust indication (i.e., Kullback–Leibler (KL) divergence) for quantifying tool performance degradation. Based on dynamic learning rate, parameter updating, and merge and split of Gaussian components, AGMM is capable of online adaptively learning the dynamic changes of tool performance in its full life. Furthermore, the performance changes of tools are quantified by measuring the distance between two density distributions approximated by the AGMM and the baseline GMM trained by the normal data, respectively. Experimental results of its application in a machine tool test demonstrate the effectiveness of the AGMM-based KL-divergence indication for assessment of tool performance degradation.

Online tool wear monitoring using portable digital assistant (PDA)

Real-time tool wear monitoring is an important technique need to be developed to fulfill the demand from the fast development in machining industry. This paper proposed a new method of online tool wear monitoring using portable digital assistant (PDA)-based device to monitor progression of flank wear land during turning process by on-line detecting and analyzing the machining force signals. The machining tests were carried out on turning machine, and Kistler 9255B dynamometer was used to measure the cutting force signal, which was amplified and displayed in the DasyLab software. The measured cutting force signals stored in Dasylab was then analyzed using I-kaz 3D. The analysis was successfully done using newly developed program, C++ language and Visual Basic embedded to display the result on the PDA. This new developed program was installed on PDA to monitor the tool flank wear progression by three modes of different color which include: green (good condition), yellow (transition zone) and red (end of cutting). Therefore, it gives early warning related to the damage and failure of cutting tool, consequently helps the operation of machine to be smoothly operated in order to produce an acceptable quality in manufacturing process. Key words: Real time monitoring, tool flank wear, I-kaz 3D, cutting force signal, portable digital assistant (PDA).

Study of Adaptive Model Parameter Estimation for Milling Tool Wear

In a modern machining system, tool wear monitoring systems are needed to get higher quality production. In precision machining processes, especially surface quality of the manufactured part can be related to tool wear. This increases industrial interest for in-process tool wear monitoring systems. For the modern unmanned manufacturing process, an integrated system composed of sensors, signal processing interface and intelligent decision making model are required. In this study, a new method for on-line tool wear monitoring is presented under varying cutting conditions. The proposed method uses wear feature extraction based on process modeling and parameter estimation. An adaptive estimation model of milling tool wear in variable cutting parameters is built based entirely on milling power. The adaptive model traces the properties of cutting process by combining process state signal, cutting conditions, power model. The tool wear feature is obtained from the estimated parameters of the model and carried on in the theoretical and experimental study. Experiment results have proved that changes of the parameters in the cutting power model significantly indicate tool wear independently of varying cutting conditions and it makes tool wear a recognized process with high precision.

Monitoring online cutting tool wear using low-cost technique and user-friendly GUI

Cutting tool wear is known to affect tool life, surface quality and production time. Because of this an online tool wear measurement and monitoring system has been developed, using a low-cost sensor. The system is able to detect and analyze signals relating to the deflection of the tool holder from the cutting force, and the corresponding estimation of wear is displayed on the computer screen. New statistical analysis is used to identify and characterise the changes in signals from the sensors. A two-channel strain gauge is mounted at the tool holder to measure the deflection in both tangential direction and feed direction. The signal is transmitted to the signal conditioning device, then to data acquisition, and finally to the computer system. MATLAB software is used as the platform software to develop a user-friendly graphical user interface (GUI) for online monitoring purposes. Results show that this developed online monitoring system, using the strain gauge signal, is an effective method of detecting the progression of flank wear width during machining. This is an efficient and low-cost method which can be used in the real machining industry to predict the level of wear in the cutting tool.

A Multifeature Approach to Tool Wear Estimation Using 3D Workpiece Surface Texture Parameters

This work presents a new way to determine the condition of a cutting tool based on 3D texture parameters of workpiece surface. Recently, a laser holographic interferometer has been developed to rapidly measure a large workpiece surface and generate a 3D surface height map with micron level accuracy. This technique enables online surface measurement for machined workpieces. By measuring and analyzing workpiece surface texture, the interaction between the tool’s cutting edges and the workpiece surface can be extracted as a spatial signature. It can then be used as a warning sign for tool change because the workpiece produced by a heavily worn tool exhibits more irregularities in its surface texture than that produced by a normal tool. Multiple texture parameters such as image intensity histogram distribution parameter, 3D peak-to-valley height, and 3D surface waviness parameter are employed to indicate the onset of severe tool wear. In this work, aluminum (Al308) and compacted graphite iron parts were machined by a polycrystalline diamond insert and a multiphase coated tungsten carbide insert, respectively. After that, multiple 3D surface texture features of workpieces samples under different phases of tool wear were analyzed in order to assess tool wear conditions. The experimental results verify that these surface texture features can be used as good indicators for online tool wear monitoring.

Monitoring of Drilling Tool Condition through Spindle Current

Drill wear or breakage often damages the work piece and/or machine tool. Spindle motor current reflects the cutting process and the signal can be easily and inexpensively obtained. This paper presents a strategy for on-line drilling tool wear and breakage monitoring. It employs Wavelet Transform (WT) of the spindle current signature to perform monitoring. A moving window technique is used to extract the cutting portion of data from the entire data sequence. A low pass de-nosing filter is employed to remove noise from the current signal. Features were extracted using WT node energy and selected based on their ability to detect tool wear and chipping. The Progression of tool wear based on feature of WT detail level 4 is analyzed and pointed out status of worn or chipped tool. Experimental results validate performance of the proposed algorithm.

Intelligent Tool Condition Monitoring In High-Speed Turning Of Titanium Ti-6Al-4V Alloy

Intelligent Tool Condition Monitoring (TCM) is an essential requirement in the drive towards automated machining operations. In this paper, a Multi-Layered Perceptron (MLP) neural net-work model has been developed for on-line condition monitoring of tool wear in high-speed turning of Titanium-based alloy (Ti-6Al-4V). Machining trials were conducted for typical rough and finish turning operations with cutting speed (90 – 120 m/min), feed rate (0.15 – 0.2 mm/rev), and depth of cut (0.5 -2.0 mm) using uncoated cemented carbide (K10 grade) inserts with Inter-national Standard Organization (ISO) designation “CNMG 120412”. The tool maximum flank wear (VBmax), cutting forces (feed force, Fx, and tangential force, Fz), and spindle motor power were measured during each machining operation. The cutting parameters (cutting speed, feed rate, and depth of cut), and cutting force and spindle power were used in isolation or in combi-nation as input dataset in training the neural network to predict wear land on cutting tool at different stages of wear propagation (light, medium and heavy). The neural network model was designed using Matlab® neural toolbox. Accuracy of model for the prediction of tool wear at dif-ferent wear stages were evaluated based on the Percentage Error (PE) for both roughing and finishing operations. Results showed that, the heavy wear stage (PE = ±5%) was predicted more accurately compared to the light (PE = +5 to -10%) and medium (PE = +25 to -30%) wear stages. The combination of the force, power signals and cutting parameters improved perform-ance of the model.Keywords: Artificial neutral network, Turning, Ti-6Al-4V alloy; Tool wear, Condition monitoring

Development of a tool wear observer model for online tool condition monitoring and control in machining nickel-based alloys

Online monitoring and in-process control improves machining quality and efficiency in the drive towards intelligent machining. It is particularly significant in machining difficult-to-machine materials like super alloys. This paper attempts to develop a tool wear observer model for flank wear monitoring in machining nickel-based alloys. The model can be implemented in an online tool wear monitoring system which predicts the actual state of tool wear in real time by measuring the cutting force variations. The correlation between the cutting force components and the flank wear width has been established through experimental studies. It was used in an observer model, which uses control theory to reconstruct the flank wear development from the cutting force signal obtained through online measurements. The monitoring method can be implemented as an outer feedback control loop in an adaptive machining system.

A tool wear observer model for flank wear monitoring in the milling of Nickel-based alloys

Tool wear monitoring is of great industrial importance in machining Nickel-based alloys. This paper presents the research effort to develop a tool wear observer model for flank wear monitoring in the milling of Nickel-based alloys. It aims at an online tool wear monitoring system that is capable of predicting tool wear in real time by measuring the cutting force variation. The correlation between the cutting force components and the flank wear width has been established through experimental studies. An observer model is developed to estimate the flank wear growth from the measured cutting force signals.

On-line monitoring of tool wear in turning operation in the presence of tool misalignment

A vision system using high-resolution CCD camera and back-light was developed for the on-line measurement of nose wear of cutting tool inserts. Initial study showed that the system is sensitive to several factors in the work environment such as misalignment of cutting tool, presence of micro-dust particles, vibration and intensity variation of ambient light. An algorithm using Wiener filtering, median filtering, morphological operations and thresholding was developed to decrease the system error caused by these factors. A conforming method was used to overcome misalignment of the tool insert during offline and on-line measurement. The algorithm, combined with a subtraction method, was applied to measure the nose wear area of the inserts under different machining conditions.

An approach based on current and sound signals for in-process tool wear monitoring

This paper presents a tool condition monitoring system (TCMS) for on-line tool wear monitoring in turning. The proposed TCMS was developed taking into account the necessary trade-off between cost and performance to be applicable in practice, in addition to a high success rate. The monitoring signals were the feed motor current and the sound signal. The former was used to estimate the feed cutting force using the least squares version of support vector machines (LS-SVM). Singular spectrum analysis (SSA) was used to extract information correlated with tool wear from the sound signal. The estimated feed cutting force and the SSA decomposition of the sound signal alone with the cutting conditions constitute the input data to the TCMS. Again LS-SVM was used to estimate tool condition and its reliability for on-line implementation was validated by experiments using AISI 1040 steel. The results showed that the proposed TCMS is fast and reliable for tool condition monitoring.

On-line tool wear monitoring using geometric descriptors from digital images

A new method based on a computer vision and statistical learning system is proposed to estimate the wear level in cutting inserts in order to identify the time for its replacement. A CNC parallel lathe and a computer vision system have been used to obtain 1383 flank images. A binary image for each of the former wear flank images have been obtained by applying several pre-processing and segmenting operations. Every wear flank region has been described by means of nine geometrical descriptors. LDA (linear discriminant analysis) shows that three out of the nine descriptors provide the 98.63% of the necessary information to carry out the classification, which are eccentricity, extent and solidity. The result obtained using a finite mixture model approach shows the presence of three clusters using these descriptors, which correspond with low, medium and high wear level. A monitoring approach is performed using the tool wear evolution for each insert along machining and the discriminant analysis. This evolution represents the probability of belonging to each one of the wear classes (low, medium and high). The estimate of the wear level allows to replace the tool when the wear level is located at the end of the M class (medium), preventing that the tool enters into the H class (high).

EFFECT OF TOOL WEAR ON MICROSTRUCTURE, MECHANICAL PROPERTIES AND ACOUSTIC EMISSION OF FRICTION STIR WELDED 6061 Al ALLOY

Tool condition is one of the main concerns in friction stir welding (FSW), because the geometrical condition of the tool pin including size and shape is strongly connected to the microstructure and mechanical performance of the weld. Tool wear occurs during FSW, especially for welding metal matrix composites with large amounts of abrasive particles, and high melting point materials, which significantly expedite tool wear and deteriorate the mechanical performance of welds. Tools with different pin-wear levels are used to weld 6061 Al alloy, while acoustic emission (AE) sensing, metallographic sectioning, and tensile testing are employed to evaluate the weld quality in various tool wear conditions. Structural characterization shows that the tool wear interferes with the weld quality and accounts for the formation of voids in the nugget zone. Tensile test analysis of samples verifies that both the ultimate tensile strength and the yield strength are adversely affected by the formation of voids in the nugget due to the tool wear. The failure location during tensile test clearly depends on the state of the tool wear, which led to the analysis of the relationships between the structure of the nugget and tool wear. AE signatures recorded during welding reveal that the AE hits concentrate on the higher amplitudes with increasing tool wear. The results show that the AE sensing provides a potentially effective method for the on-line monitoring of tool wear.

アコースティックエミッションフィードバック制御による超精密加工の精度向上

In order to improve machining accuracy of diamond turning, an acoustic emission (AE) feedback control scheme is considered in this paper. An acoustic emission root means square (AErms) signal is utilized to integrate additional AE feedback control loop with a conventional position feedback control system. In preliminary experiments in advance of the AE feedback control design, a correlation between a machining error and a measured AErms has been verified. Based on the preliminary experiments, the AE feedback control system has been designed. The designed controller calculates a compensation signal for the conventional position feedback system to improve the machining accuracy. Machining tests using a diamond turning machine showed that the proposed controller accomplishes 20 percent reduction of machining error compared to conventional position feedback control. Machining tests using various diamond cutting tools showed that the AE feedback can be applied for on-line tool wear monitoring.

Fusion of hard and soft computing techniques in indirect, online tool wear monitoring

Indirect, online tool wear monitoring is one of the most difficult tasks in the context of process monitoring for metal-cutting machining processes. Based on a continuous acquisition of certain process parameters (signals such as cutting forces or acoustic emission) with multi-sensor systems, it is possible to estimate or to classify certain wear parameters. However, despite of intensive scientific research during the past decades, the development of reliable and flexible tool wear monitoring systems is an ongoing attempt. This article introduces a new, hybrid technique for tool wear monitoring in turning which fuses a physical process model (hard computing) with a neural network model (soft computing). The physical model describes the influence of cutting conditions (such as tool geometry or work material) on measured force signals and it is used to normalize these force signals. The neural model establishes a relationship between the normalized force signals and the wear state of the tool. The advantages of this approach are demonstrated by means of experimental results. Moreover, it is shown that the consideration of process parameters, cutting conditions, and wear in one model (either physical or neural) is extremely difficult and that existing hybrid approaches are not adequate. The ideas presented in this article can be transferred to many other process monitoring tasks.

On-line tool wear monitoring during ultrasonic machining using tool resonance frequency

Ultrasonic machining is effective for materials of extreme hardness, although the tool also experiences wear, causing a reduction of machining efficiency. The present work proposes a new method of monitoring tool wear during ultrasonic machining. Theoretical analysis as well as experimental measurements are presented. Both results show a strong correlation between the tool length and the resonance frequency of the ultrasonic system, this observation leading to the concept of tool wear monitoring by resonance frequency. The resolution of monitoring is sufficiently high, viz. down to tens of micrometers in tool length. The machining process can be on-line monitored and stopped for tool change based on a pre-set tool-length limit.

Tool Wear Monitoring in Turning: A Neural Network Application

Tool wear monitoring is the most difficult task in the area of tool condition monitoring for metal-cutting manufacturing processes. The main objective is to improve the process reliability, but the production costs need to be reduced as well. This article summarises a new approach for online and indirect tool wear estimation or classification in turning using neural networks. This technique uses a physical process model describing the influence of cutting conditions (such as the feed rate) on measured process parameters (here: cutting force signals) in order to separate signal changes caused by variable cutting conditions from signal changes caused by tool wear. Features extracted from the normalised process parameters are taken as inputs of a dynamic, but nonrecurrent neural network that estimates the current state of the tool. It is shown that the estimation error can be reduced significantly with this combination of a hard computing and a soft computing technique. The article represents an extended summary of the author's investigations and publications in the area of online and indirect tool wear monitoring in turning by means of artificial neural networks.

Using a data fusion neural network in the tool wear monitoring of a computer numerical control turning machine

The cutting force and the vibration signal of a computer numerical control (CNC) turning machine centre are detected for on-line tool wear monitoring. The feature elements are first extracted from the detected signals. The feature indices are obtained from the feature elements through data preprocessing. Six data fusion methods are used for integrating the feature indices to obtain the fusion indices. The obtained fusion indices are used as the input data of a neural network for online tool wear monitoring. The feasibility of coupling a neural network algorithm with different data fusion methods is investigated, based on the monitored data. The research results show that using a data fusion neural network in tool wear monitoring is feasible.

Modeling micro-end-milling operations. Part III: influence of tool wear

The characteristics of the cutting forces were studied at different usage levels and the analytical model of the micro-end-milling operations was modified to represent the tool wear. A new expression was derived from the model to estimate the remaining tool life from experimental data. The parameters of the model are estimated by using genetic algorithms. The difference between the simulated and experimental cutting force profiles for new and worn tools was less than 8%. The remaining tool life was estimated with typically 10% error from the experimental data. Maximum error was 20%. The introduced analytical model and genetic algorithm-based parameter estimation approach is very convenient for on-line tool wear monitoring without extensive experimental study.