Showing papers on "Tool wear published in 2018"

Effects of nano-cutting fluids on tool performance and chip morphology during machining Inconel 718

Abstract: Flood cooling is a typical cooling strategy used in industry to dissipate the high temperature generated during machining of Inconel 718. The use of flood coolant has risen environmental and health concerns which call for different alternatives. Minimum quaintly lubricant (MQL) has been successfully introduced as an acceptable coolant strategy; however, its potential to dissipate heat is much lower than the one achieved using flood coolant. MQL-nano-cutting fluid is one of the suggested techniques to further improve the performance of MQL particularly when machining difficult-to-cut materials. The main objective of this study is to investigate the effects of two types of nano-cutting fluids on tool performance and chip morphology during turning of Inconel 718. Multi-walled carbon nanotubes (MWCNTs) and aluminum oxide (Al2O3) gamma nanoparticles have been utilized as nano-additives. The novelty here lies on enhancing the MQL heat capacity using different nano-additives-based fluids in order to improve Inconel 718 machinability. In this investigation, both nano-fluids showed better results compared to the tests performed without any nano-additives. Significant changes in modes of tool wear and improvement in the intensity of wear progression have been observed when using nano-fluids. Also, the collected chips have been analyzed to understand the effects of adding nano-additives on the chip morphology. Finally, it has been found that MWCNT nano-fluid has shown better performance than Al2O3 nano-fluid.

Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth

Abstract: Nowadays, face milling is one of the most widely used machining processes for the generation of flat surfaces. Following international standards, the quality of a machined surface is measured in terms of surface roughness, Ra, a parameter that will decrease with increased tool wear. So, cutting inserts of the milling tool have to be changed before a given surface quality threshold is exceeded. The use of artificial intelligence methods is suggested in this paper for real-time prediction of surface roughness deviations, depending on the main drive power, and taking tool wear, $$V_{B}$$ into account. This method ensures comprehensive use of the potential of modern CNC machines that are able to monitor the main drive power, N, in real-time. It can likewise estimate the three parameters -maximum tool wear, machining time, and cutting power- that are required to generate a given surface roughness, thereby making the most efficient use of the cutting tool. A series of artificial intelligence methods are tested: random forest (RF), standard Multilayer perceptrons (MLP), Regression Trees, and radial-based functions. Random forest was shown to have the highest model accuracy, followed by regression trees, displaying higher accuracy than the standard MLP and the radial-basis function. Moreover, RF techniques are easily tuned and generate visual information for direct use by the process engineer, such as the linear relationships between process parameters and roughness, and thresholds for avoiding rapid tool wear. All of this information can be directly extracted from the tree structure or by drawing 3D charts plotting two process inputs and the predicted roughness depending on workshop requirements.

Tool condition monitoring using spectral subtraction and convolutional neural networks in milling process

Abstract: Process monitoring is necessary in machining operation to increase productivity, improve surface quality, and reduce unscheduled downtime. Tool wear and breakage are important and common source of machining problems due to high temperatures and forces of the machining process. Therefore, it is highly beneficial to develop an online tool condition monitoring (TCM) system. This paper investigates a robust tool wear monitoring system for milling operation. Recent developments in machine learning, in particular deep learning methods, result in significant improvement in automation of different industries. Therefore, in this research, we employed convolutional neural network (CNN) as a well-established and powerful deep learning algorithm for tool wear estimation. Wavelet packet-based features are extracted for tool wear monitoring as a powerful time-frequency fault indicator. Moreover, a hybrid feature extraction method is proposed using wavelet time-frequency transformation and spectral subtraction algorithms to intensify the effect of tool wear in the signal and reduce the effect of other cutting parameters. CNN-based monitoring systems are compared with three other machine learning methods (support vector machine, Bayesian rigid network, and K nearest neighbor method) as the baseline. The research is validated using different datasets. The algorithms are implemented and compared using experimental force and vibration signals from LIPPS lab of ETS university as well as using current signals as the fault indicator from Nasa_Ames dataset.

Online Tool Wear Monitoring Via Hidden Semi-Markov Model With Dependent Durations

Abstract: The tool wear monitoring (TWM) system that could estimate tool wear conditions and predict remaining useful life (RUL) is important to meet the high precision requirement and improve productivity in automated machining. Due to its good properties in representing nonstationary and complex physical process, hidden semi-Markov Model (HSMM) is adapted to model the progressive tool wear in this paper. In order to describe the time-variant transition probability of tool wear states and the state duration dependency, the HSMM is improved by learning the duration parameters and RUL distribution database. The Forward algorithm is utilized for online tool wear estimation and remaining life prognosis, and an online implementation approach is developed to reduce computational cost. Experimental results show that the approach is effective and the proposed method of duration dependency modeling leads to more accurate TWM in high speed milling.

Modeling and optimization of tool wear in MQL-assisted milling of Inconel 718 superalloy using evolutionary techniques

Abstract: The Inconel 718 alloy, a difficult-to-cut superalloy with an extensive demand on aircraft and nuclear industries, being a low thermally conductive material exhibits a poor machinability. Consequently, the cutting tool is severely affected, and the tool cost is increased. In this context, an intelligent solution is presented in this paper—investigation of minimum quantity lubrication (MQL) and the selection of best machining conditions using evolutionary optimization techniques. A series of milling experiments on Inconel 718 alloy was conducted under dry, conventional flood, and MQL cooling modes. Afterward, the particle swarm optimization (PSO) and bacteria foraging optimization (BFO) were employed to optimize the cutting speed, feed rate, and depth-of-cut to minimize the flank wear (VBmax) parameter of a cutting tool. Though both the PSO and BFO models performed well, the validated results showed the superiority of PSO. Furthermore, it was found that the MQL performed better than the dry and flood cooling condition with respect to the reduction of the tool flank wear.

Modeling and optimization of tool vibration and surface roughness in boring of steel using RSM, ANN and SVM

Abstract: In this paper, statistical models were developed to investigate effect of cutting parameters on surface roughness and root mean square of work piece vibration in boring of stainless steel. A mixed level design of experiments was prepared with process variables of nose radius, cutting speed and feed rate. According to design of experiments, eighteen experiments were conducted on AISI 316 stainless steel with PVD coated carbide tools. Surface roughness, tool wear and vibration of work piece were measured in each experiment. A laser Doppler vibrometer was used to measure vibration of work piece in the form of acousto optic emission signals. These signals were processed and transformed in to different frequency zones using a fast Fourier transformer. Analysis of variance was used to identify significant cutting parameters on surface roughness and root mean square of work piece vibration. Predictive models like response surface methodology, artificial neural network and support vector machine were used to predict the surface roughness and root mean square of work piece vibration. Cutting parameters were optimized for minimum surface roughness and root mean square of work piece vibration using a multi response optimization technique.

Influence of Ranque-Hilsch vortex tube and nitrogen gas assisted MQL in precision turning of Al 6061-T6

Abstract: Dry machining is undesirable to produce precision surface due to thermal adversities especially for a low melting point material such as Al 6061-T6. Likewise, the conventional flood cooling is neither economically viable nor eco-friendly. In this context, three novel cooling-lubrication (C/L) technologies namely the nitrogen gas cooling (NGC), nitrogen gas assisted minimum quantity lubrication (NGMQL) and Ranque-Hilsch vortex tube (RHVT) NGMQL are investigated along with the air cooling (AC) in turning with an attempt to reduce surface roughness (Ra) and tool flank wear (VBmax). The machining was conducted using uncoated WC insert at two-levels of cutting speed and feed rate; and, as medium of cooling/lubrication the nitrogen gas and/or canola oil is employed. The SEM and 3D topographic images were analyzed for the machined surfaces, worn tool surfaces and chips. Results showed that the RHVT-NGMQL revealed the least surface roughness and tool wear (∼75% improvement compared to other C/Ls). Notable wear modes were: in dry cutting the plastic deformation, BUE and adhesion; in NGC the BUE; in NGMQL the rubbing and adhesion; in RHVT-NGMQL the adhesion. In micro-level, no significant difference in chip structure was found for the studied C/L methods In addition, the Composite Desirability optimization was adopted to systematically minimize Ra and VB max concurrently. It was found that the optimum speed vc = 160 m/min and feed rate f = 0.06 mm/rev under RHVT-NGMQL C/L condition has the potential to generate a precision surface with a roughness value

Predicting tool wear with multi-sensor data using deep belief networks

Abstract: Tool wear is a crucial factor influencing the quality of workpieces in the machining industry. The efficient and accurate prediction of tool wear can enable the tool to be changed in a timely manner to avoid unnecessary costs. Various parameters, such as cutting force, vibration, and acoustic emission (AE), impact tool wear. Signals are collected by different sensors and then constitute the raw data. There are two main types of methods used to make predictions, namely model-based and data-driven methods. Data-driven methods are typically preferred when a mathematical model is not available. In such a situation, artificial intelligent methods, such as support vector regression (SVR) and artificial neural networks (ANNs), are applied. Recently, deep learning algorithms have been widely used because of their accuracy, computing speed, and excellent performance in solving nonlinear problems. In this study, a deep learning network called deep belief network (DBN) is applied to predict the flank wear of a cutting tool. To confirm the superiority of the DBN in predicting tool wear, the performance of the DBN is compared with the performances obtained using ANNs and SVR in terms of the mean-squared error (MSE) and the coefficient of determination (R2), considering data from more than 900 experiments.

Effect of cryogenic coolant on turning performance characteristics during machining of 17-4 PH stainless steel: A comparison with MQL, wet, dry machining

Abstract: Nowadays, metal cutting industries are looking towards new sustainable manufacturing methods to reach the target set by the environmentally conscious regulations in terms of usage and disposal of chemical contaminant conventional coolants without sacrificing the productivity. Machining with cryogenic coolants is an efficient, emerging sustainable manufacturing process. In the current work, a low cost external spray cooling cryogenic machining setup has been developed to spray the cryogenic coolant at the machining zone. In the current work, cryogenic coolant (liquid nitrogen) was used to machine the 17-4 precipitated hardenable stainless steel (PH SS) at varying depth of cut conditions and the results were compared with a minimum quantity lubrication (MQL), wet and dry machining environments. The investigative parameters considered in the present study were cutting temperature, tool wear (flank and rake), surface integrity (surface roughness and surface topography) and chip morphology. Cryogenic machining has given beneficial results compared to other machining environments. Hence, cryogenic machining is the most promising technique for machining of 17-4 PH SS. From the health and environmental point of view, cryogenic machining is a clean manufacturing technique.

Application of audible sound signals for tool wear monitoring using machine learning techniques in end milling

Abstract: Due to the demands of Computer-Integrated Manufacturing (CIM), the Tool Condition Monitoring (TCM) system, as a major component of CIM, is essential to improve the production quality, optimize the labor and maintenance costs, and minimize the manufacturing loses with the increase in productivity. To look for a reliable, efficient, and cost-effective solution, various monitoring systems employing different types of sensing techniques have been developed to detect the tool conditions as well as to monitor the abnormal cutting states. This paper explores the use of audible sound signals as sensing approach to detect the cutting tool wear and failure during end milling operation by using the Support Vector Machine (SVM) learning model as a decision-making algorithm. In this study, sound signals collected during the machining process are analyzed through frequency domain to extract signal features that correlate actual cutting phenomenon. The SVM method seeks to provide a linguistic model for tool wear estimation from the knowledge embedded in this machine learning approach. The performance evaluation results of the proposed algorithm have shown accurate predictions in detecting tool wear under various cutting conditions with rapid response rate, which provides the good solution for in-process TCM. In addition, the proposed monitoring system trained with sufficient signals collected from different positions has been proved to be position independent to monitor the tool wear conditions.

Frequency and Time-Frequency Analysis of Cutting Force and Vibration Signals for Tool Condition Monitoring

Abstract: Tool condition monitoring systems are essential in micromilling applications. A tool’s slenderness requires high-precision monitoring systems for online measurements. In most cases, tool health is indirectly estimated by processing and analyzing the cutting process parameters. In that sense, the main challenge lies in the proper selection of the process parameters and their processing techniques, so that a robust and accurate assessment of the tool’s health is obtained. This paper proposes a frequency- and time-frequency-based analysis of cutting force and vibration signals for estimating the tool condition of a high-speed micromilling process. Measurements obtained from different cutting conditions were utilized in the analysis. The results indicate variations in the dominant frequencies, which result from tool wear. Furthermore, it is important to note that the analysis results obtained from the two process signals provide more reliable results and improve the sensing bandwidth.

Evaluating Hole Quality in Drilling of Al 6061 Alloys

Abstract: Hole quality in drilling is considered a precursor for reliable and secure component assembly, ensuring product integrity and functioning service life. This paper aims to evaluate the influence of the key process parameters on drilling performance. A series of drilling tests with new TiN-coated high speed steel (HSS) bits are performed, while thrust force and torque are measured with the aid of an in-house built force dynamometer. The effect of process mechanics on hole quality, e.g., dimensional accuracy, burr formation, surface finish, is evaluated in relation to drill-bit wear and chip formation mechanism. Experimental results indicate that the feedrate which dictates the uncut chip thickness and material removal rate is the most dominant factor, significantly impacting force and hole quality. For a given spindle speed range, maximum increase of axial force and torque is 44.94% and 47.65%, respectively, when feedrate increases from 0.04 mm/rev to 0.08 mm/rev. Stable, jerk-free cutting at feedrate of as low as 0.04 mm/rev is shown to result in hole dimensional error of less than 2%. A low feedrate along with high spindle speed may be preferred. The underlying tool wear mechanism and progression needs to be taken into account when drilling a large number of holes. The findings of the paper clearly signify the importance and choice of drilling parameters and provide guidelines for manufacturing industries to enhance a part’s dimensional integrity and productivity.