Tool Breakage Research Articles

Intelligent Tool Wear Monitoring Method Using a Convolutional Neural Network and an Informer

Tool wear (TW) is the gradual deterioration and loss of cutting edges due to continuous cutting operations in real production scenarios. This wear can affect the quality of the cut, increase production costs, reduce workpiece accuracy, and lead to sudden tool breakage, affecting productivity and safety. Nevertheless, since conventional tool wear monitoring (TWM) approaches often employ complex physical models and empirical rules, their application to complex and non-linear manufacturing processes is challenging. As a result, this study presents a TWM model using a convolutional neural network (CNN), an Informer encoder, and bidirectional long short-term memory (BiLSTM). First, local feature extraction is performed on the input multi-sensor signals using CNN. Then, the Informer encoder deals with long-term time dependencies and captures global time features. Finally, BiLSTM captures the time dependency in the data and outputs the predicted tool wear state through the fully connected layer. The experimental results show that the proposed TWM model achieves a prediction accuracy of 99%. It is able to meet the TWM accuracy requirements of real production needs. Moreover, this method also has good interpretability, which can help to understand the critical tool wear factors.

A Hybrid Approach for Predicting Critical Machining Conditions in Titanium Alloy Slot Milling Using Feature Selection and Binary Whale Optimization Algorithm

Monitoring the machining process is crucial for providing cost-effective, high-quality production and preventing unwanted accidents. This study aims to predict critical machining conditions related to surface roughness and tool breakage in titanium alloy slot milling. The Siemens SINUMERIK EDGE (SE) Box system collects signals from the spindle and axes of a CNC machine tool. In this study, features were extracted from signals in time, frequency, and time–frequency domains. The t-test and the binary whale optimization algorithm (BWOA) were applied to choose the best features and train the support vector machine (SVM) model with validation and training data. The SVM hyperparameters were optimized simultaneously with feature selection, and the model was tested with test data. The proposed model accurately predicted critical machining conditions for unbalanced datasets. The classification model indicates an average recall, precision, and accuracy of 80%, 86%, and 95%, respectively, when predicting workpiece quality and tool breakage.

Assessment of repeatability in newly developed ultra-precision tool setting method using electrical breakdown for ultra-precision machining

Ultra-precision work coordinate system (WCS) setting by measuring the relative distance between the workpiece and the tool is a key element to further improve the accuracy of ultra-precision machine tools. Touch probe is the most widely used WCS method in conventional machining, yet it cannot be used in ultra-precision machining (UPM) applications due to the nature of contact with the workpiece, potentially resulting in surface damage or tool breakage. Furthermore, indirect methods, such as a touch probe, require the sensor to be replaced with a tool after setting the work coordinate. This induces uncertainty. In this paper, the repeatability of the newly proposed non-contact and direct WCS method using electrical breakdown (E.B.) was evaluated for the use in UPM. The standard deviation of the tool positions after performing the method 11 times was under 40 nm. Using a tungsten carbide tool and aluminum workpiece, the proposed method’s repeatability and surface damage were investigated.

The Comparison of Effects of Liquid Carbon Dioxide and Conventional Flood Cooling on the Machining Conditions During Milling of Nickel-based Superalloys

In this scientific study, the authors have dealt with the slot milling of nickel-based superalloys. These alloys are among the most difficult materials to machine and are widely used in aerospace and energy industries. Due to the properties of the material, slot milling is a particular problem because tool wear happens quickly, and tool breakages are common. When these superalloys are machined, very high temperatures occur in the cutting zone, which cannot leave due to the extremely poor thermal conductivity of the material and will therefore transfer to the edges of the cutting tool, causing it to anneal, break off and fail. So, the researchers initiated a new field of research: cryogenically-assisted machining. In this paper, the authors used two cooling methods, the conventional flood cooling and cryogenic cooling with liquid carbon-dioxide (LCO2). The effects of these cooling methods were tested focusing on the cutting forces, tool wear, chip morphology and surface roughness of the bottom of the slots. The aim was to determine the best cooling methods for these materials. Based on the results, it can be concluded that, LCO2 has a negative effect on cutting forces, tool life and surface roughness. It only has a positive effect on chip formation. It can be see that, the lubricating effect has a greater impact on tool life, tool load and surface roughness of the milled slots than cooling.

Design and fabrication of new oblique gradient cemented carbide tool material for inhibiting the initiation of thermal crack

Compacted graphite iron (CGI) is the preferred material for engines at present. However, in the process of intermittent cutting CGI, the tool is prone to produce thermal cracks, resulting in tool chipping failure. The initiation of thermal crack must be inhibited to solve this problem fundamentally. Therefore, a new idea of designing oblique gradient tool was presented, including selecting appropriate gradient tool material and designing accurate gradient direction angle. According to the proposed design criteria of the tool, five layers of WC-Al2O3 gradient tool materials were designed, so that the thermal conductivity and thermal expansion coefficient of gradient materials were increased along the direction of thermal crack propagation, thus effectively alleviating the concentration of thermal stress. According to the thermal crack initiation area of the tool for milling CGI, the gradient direction angle of the tool was accurately designed to be 71.6°. The accurately designed oblique gradient tool can inhibit the initiation of thermal cracks by reducing thermal stress concentration on the tool, thus preventing the tool breakage failure. The new designed oblique gradient cemented carbide tool TDA-X with excellent cutting performance was successfully fabricated, and the inhibition effect of TDA-X on thermal crack initiation was verified by experiment. The result showed that TDA-X remarkably inhibited the initiation of thermal cracks in the tool much better than the non-oblique gradient tool TDA and the commercial coated carbide tool, thus avoiding the tool chipping, greatly prolonging the tool life and ensuring the quality of machining surface. The successful fabrication of this tool was of great significance to the efficient machining of CGI, and opened up a new idea for the research and development of tools with high cutting performance.

Detection of Anomalous Behavior of Manufacturing Workers Using Deep Learning-Based Recognition of Human–Object Interaction

The increasing demand for industrial products has expanded production quantities, leading to negative effects on product quality, worker productivity, and safety during working hours. Therefore, monitoring the conditions in manufacturing environments, particularly human workers, is crucial. Accordingly, this study presents a model that detects workers’ anomalous behavior in manufacturing environments. The objective is to determine worker movements, postures, and interactions with surrounding objects based on human–object interactions using a Mask R-CNN, MediaPipe Holistic, a long short-term memory (LSTM), and worker behavior description algorithm. The process begins by recognizing the objects within video frames using a Mask R-CNN. Afterward, worker poses are recognized and classified based on object positions using a deep learning-based approach. Next, we identified the patterns or characteristics that signified normal or anomalous behavior. In this case, anomalous behavior consists of anomalies correlated with human pose recognition (emergencies: worker falls, slips, or becomes ill) and human pose recognition with object positions (tool breakage and machine failure). The findings suggest that the model successfully distinguished anomalous behavior and attained the highest pose recognition accuracy (approximately 96%) for standing, touching, and holding, and the lowest accuracy (approximately 88%) for sitting. In addition, the model achieved an object detection accuracy of approximately 97%.

Study on Characteristics of Tool Wear and Breakage of Ultrasonic Cutting Nomex Honeycomb Core with the Disc Cutter

Ultrasonic cutting is an advanced technology for processing Nomex honeycomb materials. The disc cutter is one of the most commonly used tools, whose wear and breakage state have an important impact on the honeycomb material machining process. Currently, the disc cutter lacks systematic characterization methods, and its tool wear laws are not yet clear. This paper conducts a wear experiment of the disc cutter in an ultrasonic cutting Nomex honeycomb core and proposes the attributes of cutting edge rounding (CER), flank wear VB, diameter reduction, and cutting edge breakage width to characterize the tool wear and breakage forms quantitatively. Moreover, the tool wear and breakage forms of the disc cutter are categorized, and the variation laws of the disc cutter wear and breakage characteristics are studied. The experimental study reveals that the wear forms of the disc cutter are mainly cutting edge dulling and flank wear. The CER and flank wear VB increase with increasing cutting length, and the wear mechanism is mainly abrasive wear. The breakage forms are mainly chipping and cracking breakage. The diameter reduction changed slowly, and the cutting edge breakage width tended to increase. The surface quality of the honeycomb gradually deteriorates with the increase of tool wear and breakage. The experimental results are important to study the tool wear mechanism of ultrasonic cutting of the Nomex honeycomb core with the disc cutter as well as tool design and manufacture.

Real-time tool breakage monitoring based on dimensionless indicators under time-varying cutting conditions

Tool breakage occurs randomly during machining operations, which induces more severe impacts on the quality of components compared to progressive tool wear. It is widely acknowledged that the unpredictable changes in cutting conditions will cause fluctuations in the signal amplitude and thus generate false alarms. This study introduced a novel method for tool breakage monitoring based on dimensionless indicators under time-varying cutting conditions. The amplitude ratio (AR) and the energy ratio (ER) were proposed according to the power spectrum of the spindle vibration signal, which represents the change of amplitude and the energy distribution, respectively. The AR and ER are normalized and integrated into a unified indicator for real-time breakage monitoring. The floating monitoring threshold is designed based on the Gaussian distribution. Moreover, the material removal rate (MRR) is selected as a secondary indicator to accurately identify tool breakage based on determining the amplitude fluctuation caused by cutting conditions or teeth breakage. The effectiveness of the proposed method for tool breakage monitoring has been verified under the constant, time-varying, and entry/exit cutting conditions. The results show that the proposed indicators have higher sensitivity than the traditional root mean square (RMS) features and eliminate false alarms during condition change transients. This research provides a potential solution for tool breakage monitoring under complex cutting conditions.

IoPT integration on the factory floor: a case study

Abstract Digital transformation affects many aspects of our everyday lives. This paper focuses on challenges and opportunities in the area of factory automation. It presents the layout and components of the Pilotfabrik Industrie 4.0 of TU Wien as an example of a modern, flexible, and highly digitized smart factory. Furthermore, the paper presents use cases that were implemented based on the available IoPT devices in the Pilotfabrik Industrie 4.0. The first use case aims to improve product quality by detecting chatter – a vibrational phenomenon in machine tools – and taking appropriate countermeasures. The second use case tries to predict tool breakage by closely monitoring the power consumption of the machine tool and, thus, reducing the probability of damaged products.

Material recognition for fault diagnosis in machine tools using improved Mel Frequency Cepstral Coefficients

Identification of material type in structural cracks is crucial for fault diagnosis and structural integrity assessment in multi-component operation systems. In the current literature, acoustic emission (AE) signal analysis has been extensively explored as an effective method for crack monitoring and fatigue damage assessment. Most existing research on crack diagnosis is primarily focused on determining the crack formation in structures using the AE signals corresponding to known materials. However, the material recognition at any given cracking conditions using AE signals has lagged behind, hindering fault detection and damage repair in complex and multi-material structures. This research investigates the feasibility of the synergistic use of Mel Frequency Cepstral Coefficients (MFCC) and K-nearest neighbor (KNN) algorithms for identifying the material type in any arbitrary cracking processes. In the proposed method, MFCC and first-order differential MFCC parameters are extracted from the real-time AE signals. Material-specific cracking characteristics are identified and tuned for material recognition using a KNN classifier. The proposed method is validated using the AE signals of different types of materials acquired under uniaxial tension, and its effectiveness in identifying tool breakage is evaluated through case studies in the milling process. The result indicates that the recognition accuracy of up to 96.21 % can be achieved in tool breakage detection in milling operations by extracting material-specific fracture characteristics.

Fabrication of through-holes of different shapes using foil tool in EDM: Process development and analysis

The use of a foil tool in the electrodischarge machining (EDM) process has been shown to be effective for slicing, fabrication of micro slots, and various other applications. EDM with a foil tool has an advantage over wire-EDM as it allows the use of a foil tool with a thickness less than the wire diameter and to use higher discharge current due to the no risk of tool breakage. This work attempted to fabricate through-holes of various shapes on the D2 steel plate by removing material only from the periphery using a Cu foil tool, rather than the entire cross-sectional area. The thin foil tools are brought into respective shapes by wrapping them around Cu blocks having a cross-sectional area of the respective shapes. Gravity assistance is preferred to be employed as it has been experimentally found that it improves the linear material removal rate (LMRR) up to 24.86% compared to EDM without gravity assistance at various discharge current levels and pulse on time. Further, for a gravity-assisted EDM process using the foil tool, the LMRR has been improved up to 54.43%, with a selection of suitable duty cycle settings. The set of process parameters with the highest LMRR was chosen to fabricate through holes of circular, elliptical, square, and triangular cross-sections. The time required to machine through holes of various shapes was found to be proportional to the perimeter of the cross-section.

High-speed milling of hardened steel under minimal quantity lubrication with liquid nitrogen

Minimal quantity lubrication (MQL) can effectively reduce tool wear and improve surface quality in the high-speed milling of hardened steel, but MQL still suffers from poor cooling effect and oil-film failure at high cutting temperature. Compared with MQL, the cryogenic liquid nitrogen (LN2) or LN2 + MQL method with a highly strong cooling ability can further improve the processing conditions of the high-speed milling of hardened steel. However, the knowledge about the characteristics and mechanisms of the high-speed milling of hardened steel under the cryogenic LN2 and LN2 + MQL cooling is scarce. Thus, high-speed milling of hardened steel under cryogenic LN2 and LN2 + MQL cooling was studied in this paper. The machining characteristics were analyzed, and the machining mechanisms of cooling lubrication, tool wear, and surface deterioration layer formation were discussed. The experimental results show that the tool life of LN2 + MQL is remarkably longer than that of MQL, and high surface quality can be maintained at a long cutting distance. In the high-speed milling of hardened steel under the LN2 and LN2 + MQL modes, adhesion has little effect on tool wear, abrasion and chipping/flaking are the main tool wear mechanisms, and chipping/flaking is the main mechanism of tool breakage. MQL reduces the cutting interface friction using oil-film boundary lubrication, LN2 quickly removes the cutting interface heat using a strong cooling and heat transferability, and LN2 + MQL combines the advantages of both cooling and lubrication. Compared with MQL, the surface hardness of the plastic deformation layer of the LN2 and LN2 + MQL modes is considerably increased, whereas the thickness is smaller, and the strong low-temperature cooling is the main reason for this difference. The increase in tool wear will promote the cutting temperature and material slip deformation, increase the depth of high stress and strain zone and eventually increase the thickness of the plastic deformation surface layer in the LN2 and LN2 + MQL modes. In the two modes of LN2 and LN2 + MQL, there are no oxidation, nitridation, secondary quench hardening, and phase transformation in the surface layer. Severe dislocation strengthening caused by severe plastic deformation of the surface layer is the main hardening mechanism of the workpiece surface layer.

Volume monitoring of the milling tool tip wear and breakage based on multi-focus image three-dimensional reconstruction

Volume monitoring of the milling tool tip wear and breakage based on multi-focus image three-dimensional reconstruction

A semisupervised autoencoder-based method for anomaly detection in cutting tools

Detecting anomalies such as breakage and excessive wear of cutting tools in the machining process is crucial to prevent damage and improve productivity. Data-driven anomaly detection (AD) methods suffer from limited availability of anomaly samples, which is ineluctable in practice owing to strict reliability restrictions. Therefore, we propose a semisupervised AD approach in which only failure-free samples are required to establish an AD model. The key strategy is to learn the characteristics of failure-free samples using an improved autoencoder (AE) and discern observations by deviations from the characteristics. We rebuild the loss function of AE to impel the model to learn the common characteristics in latent space. We propose a factor that reflects the anomaly degree as the decision-making function to implement AD. The proposed approach is verified on an experimental cutting tool breakage dataset and a public cutting tool wear dataset. The experimental results demonstrate the validity of the proposed approach. The comparisons with conventional methods substantiate that the proposed approach outperforms existing AD methods.

Design and Development of an IoT Kit To Predict Cutting Tool Life and Generate Auto Inventory

For the best tool life, machining precision, and maintenance, a cutting tool life prediction is crucial. As a result, an online smart diagnosis service must be created to establish an auto inventory and anticipate the cutting tool life based on temperature data. Due to the fast-cutting velocity and high work material strength, diffusion wear becomes predominant when the cutting temperature rises significantly. Based on sensorial data gathered at the factory level, knowledge-based algorithms conduct online-based inspections on utilized tool life including tool breakage occurrence. Because heat load influences tool wear rate, a thermistor is fitted to the cutting tool to alert the database server when the temperature rises. based on the data.

Occurrence and distribution characteristics of aged microplastics in the surface water, sediment, and crabs of the aquaculture pond in the Yangtze River Delta of China

The artificial breeding of freshwater crabs in China has become the main source, accounting for 45.69 % of the total output in 2020. However, microplastics widely exist in ponds due to the addition of meals, and the aging and breakage of plastic tools, and people know little about the occurrence of microplastics in the environment and the tissues of crabs during the cultivation of crabs in ponds. In this study, the abundance and characteristics of microplastics in ponds and crabs were studied finely, and the types of microplastics produced by meals and tools and the aging degree of microplastics in different media were studied in a typical aquaculture experimental base in the Yangtze Estuary of China. After we digested all the samples, there were microplastics in the water, sediment, and inedible part of crabs and crab meals, mainly in fiber shape, with a particle size of 100~300μm, and they have a certain degree of aging. The abundance of microplastics in surface water ranges from 4.4 to 10.8 items/L, and that in sediment ranges from 28.6 to 54.3 items/100 g·dry weight sediments. The average abundance of microplastics in crabs was 23.9 ± 15.9 items/individual. The content of microplastics in crabs' intestinal tissue was the highest, followed by gills and hepatopancreas. At the same time, the microplastics found in crabs were positively correlated with crab body weight and negatively correlated with hepatopancreas index. The results show that in the process of artificial breeding pond feeding, microplastics will be released from the process of meals dissolving in water, and fall off due to wear and tear during the use of tools. Microplastics found in the water, sediments and the tissues of crabs were all aged. Humans have a risk of ingesting microplastics when they eat the tissues of nonedible parts of crabs.

Recovering cutting tool modal parameters from randomly sampled signals using compressed sensing

A change in the modal parameters of cutting tools could signal tool wear, tool breakage, or other instabilities. The cutting process must be continuously monitored using vibration signals to detect such changes. Since tools vibrate with frequencies of up to a few kHz, continuous monitoring requires sampling at rates of tens of kHz to respect the Nyquist limit. Processing and storing such large data for decision making is cumbersome. To address this issue, this paper discusses the use of a compressed sensing framework that enables non-uniform random sampling at rates below the Nyquist limit. For cutting tools, we show for the first time using synthesized data that it is possible to reconstruct original signals from as few as 1% of the original data. We numerically test the method to characterize the influence of damping, noise, and multiple modes. Recovered modal parameters from the reconstructed signal agree with signals sampled properly.

Combined analysis of acoustic emission and vibration signals in monitoring tool wear, surface quality and chip formation when turning SCM440 steel using MQL

With modern production, Minimum Quantity Lubricant (MQL) technology has emerged as an alternative to conventional liquid cooling. The MQLs is an environmentally friendly lubricant method with low cost while meeting the requirements of machining conditions. In this study, the experimental and analytical results show that the obtained acoustic emission (AE) and vibration signal components can effectively monitor various circumstances in the SCM440 steel turning process with MQL, such as surface quality and chip formation as cutting tool conditions. The AE signals showed a significant response to the tool wear processes. In contrast, the vibration signal showed an excellent ability to reflect the surface roughness during turning with MQL. The chip formation process through the cutting mode parameters (cutting speed, feed and depth of cut) was detected through analysis amplitude of the vibration components Ax, Ay and Az and the AE signal. Finally, Gaussian process regression and adaptive neuro-fuzzy inference systems (GPR-ANFIS) algorithms were combined to predict the surface quality and tool wear parameters of the MQL turning process. Tool condition monitoring devices assist the operator in monitoring tool wear and surface quality limits, stopping the machine in case of imminent tool breakage or lower surface quality. With the unique combination of AE and vibration analysis model and the training and testing samples established by the experimental data, the corresponding average prediction accuracy is 97.57 %. The highest prediction error is not more than 3.8 %, with a confidence percentage of 98 %. The proposed model can be used in industry to predict surface roughness and wear of the tools directly during turning

Non-contact micromachining by a dynamic feed rate controlled electrochemical discharge machining process

Electrochemical discharge machining (ECDM) is an emerging micromachining method to drill advanced non-conductive materials such as Hexagonal boron nitride (hBN). Physical contact of micro tools with work material could cause machining inaccuracies, excessive tool wear, and even tool breakage. In this study, a control system based on monitoring the force generated by the ECDM gas film has been developed to achieve non-contact machining of ECDM by dynamically adjusting the tool feed rate. The accuracy of the control system was verified by accelerometer and Fast Fourier Transformation (FFT) data. In the modules, it was found that a non-contact machining process requires the FFT amplitude to be lower than 42 V for a 1200 rpm tool rotation. The experimental results show consistent micro-holes with an average diameter of 650 µm and less than 20 µm error in the overcut achieved using this control system.

A Neural Network-Based Multi-Sensor On-Line Process Monitoring in Stone Machining

The purpose of this research was to analyze the capacity of different types of machining process signals in tool wear classification of highly non-homogeneous and anisotropic materials, such as stone. The variable physical and mechanical properties of the workpiece material have a significant influence on the selection of cutting parameters. Improper values of cutting parameters can negatively impact tool wear dynamics and potentially result in tool or workpiece breakage due to higher cutting forces. Therefore, servomotor currents, cutting forces, and acoustic emission signals were measured during drilling of three types of stone samples using nine combinations of machining parameters and drill bits with four different wear levels. The capacity of features extracted from those signals to classify tool wear level correctly was analyzed using the artificial neural network algorithm. The features extracted from acoustic emission signals achieved the highest classification accuracies and were insensitive to the type of stone sample.