Wear Classification Research Articles

Tool Wear Classification Based on Support Vector Machine and Deep Learning Models

Tool Wear Classification Based on Support Vector Machine and Deep Learning Models

Experimental investigation of different machine learning approaches for tool wear classification based on vision system of milled surface

Experimental investigation of different machine learning approaches for tool wear classification based on vision system of milled surface

An automatic workflow for the quantitative evaluation of bit wear based on computer vision

As global oil exploration ventures into deeper and more complex territories, drilling bit wear and damage have emerged as significant constraints on drilling efficiency and safety. Despite the publication of official bit wear evaluation standards by the International Association of Drill Contractors (IADC), the current lack of quantitative and scientific evaluation techniques means that bit wear assessments rely heavily on engineers' experience. Consequently, forming a standardized database of drilling bit information to underpin the mechanisms of bit wear and facilitate optimal design remains challenging. Therefore, an efficient and quantitative evaluation of bit wear is crucial for optimizing bit performance and improving penetration efficiency.This paper introduces an automatic standard workflow for the quantitative evaluation of bit wear and the design of a comprehensive bit information database. Initially, a method for acquiring images of worn bits at the drilling site was developed. Subsequently, the wear classification and grading models based on computer vision were established to determine bit status. The wear classification model focuses on the positioning and classification of bit cutters, while the wear grading model quantifies the extent of bit wear. After that, the automatic evaluation method of the bit wear is realized. Additionally, bit wear evaluation software was designed, integrating all necessary functions to assess bit wear in accordance with IADC standards. Finally, a drilling bit database was created by integrating bit wear data, logging data, mud-logging data, and basic drilling bit data.This workflow represents a novel approach to collecting and analyzing drilling bit information at drilling sites. It holds potential to facilitate the creation of a large-scale information database for the entire lifecycle of drilling bits, marking the inception of intelligent analysis, design, and manufacture of drilling bits, thereby enhancing performance in challenging drilling conditions.

Isotopological remeshing and statistical shape analysis: Enhancing premolar tooth wear classification and simulation with machine learning

ObjectiveThe aim of this study was to evaluate the accuracy of a combined approach based on an isotopological remeshing and statistical shape analysis (SSA) to capture key anatomical features of altered and intact premolars. Additionally, the study compares the capabilities of four Machine Learning (ML) algorithms in identifying or simulating tooth alterations. Methods113 premolar surfaces from a multicenter database were analyzed. These surfaces were processed using an isotopological remeshing method, followed by a SSA. Mean Euclidean distances between the initial and remeshed STL files were calculated to assess deviation in anatomical landmark positioning. Seven anatomical features were extracted from each tooth, and their correlations with shape modes and morphological characteristics were explored. Four ML algorithms, validated through three-fold cross-validation, were assessed for their ability to classify tooth types and alterations. Additionally, twenty intact teeth were altered and then reconstructed to verify the method's accuracy. ResultsThe first five modes encapsulated 76.1% of the total shape variability, with a mean landmark positioning deviation of 10.4 µm (±6.4). Significant correlations were found between shape modes and specific morphological features. The optimal ML algorithms demonstrated high accuracy (>83%) and precision (>86%). Simulations on intact teeth showed discrepancies in anatomical features below 3%. ConclusionThe combination of an isotopological remeshing with SSA showed good reliability in capturing key anatomical features of the tooth. Clinical significanceThe encouraging performance of ML algorithms suggests a promising direction for supporting practitioners in diagnosing and planning treatments for patients with altered teeth, ultimately improving preventive care.

Learning More with Less Data in Manufacturing: The Case of Turning Tool Wear Assessment through Active and Transfer Learning

Monitoring tool wear is key for the optimization of manufacturing processes. To achieve this, machine learning (ML) has provided mechanisms that work adequately on setups that measure the cutting force of a tool through the use of force sensors. However, given the increased focus on sustainability, i.e., in the context of reducing complexity, time and energy consumption required to train ML algorithms on large datasets dictate the use of smaller samples for training. Herein, the concepts of active learning (AL) and transfer learning (TL) are simultaneously studied concerning their ability to meet the aforementioned objective. A method is presented which utilizes AL for training ML models with less data and then it utilizes TL to further reduce the need for training data when ML models are transferred from one industrial case to another. The method is tested and verified upon an industrially relevant scenario to estimate the tool wear during the turning process of two manufacturing companies. The results indicated that through the application of the AL and TL methodologies, in both companies, it was possible to achieve high accuracy during the training of the final model (1 and 0.93 for manufacturing companies B and A, respectively). Additionally, reproducibility of the results has been tested to strengthen the outcomes of this study, resulting in a small standard deviation of 0.031 in the performance metrics used to evaluate the models. Thus, the novelty presented in this paper is the presentation of a straightforward approach to apply AL and TL in the context of tool wear classification to reduce the dependency on large amounts of high-quality data. The results show that the synergetic combination of AL with TL can reduce the need for data required for training ML models for tool wear prediction.

Research on tool wear classification of milling 508III steel based on chip spectrum feature

Research on tool wear classification of milling 508III steel based on chip spectrum feature

Tool Wear Classification in Chipboard Milling Processes Using 1-D CNN and LSTM Based on Sequential Features

The paper presents the comparative analysis of Long short-term memory (LSTM) and one-dimensional convolutional neural networks (1-D CNNs) for tool wear classification in chipboard milling processes. The complexity of sequence data in various fields makes selecting the right model for sequence classification very important. This research aims to show the distinct capabilities and performance nuances of LSTM and 1-D CNN models, leveraging their inherent strengths in understanding temporal dependencies and feature extraction, respectively. Through a series of experiments, the study unveils that while both models demonstrate competencies in handling sequence data, the 1-D CNN model, with its superior feature extraction capabilities, achieved the best performance, boasting an accuracy of 94.5% on the test dataset. The insights gained from this comparison not only help to understand LSTM and 1-D CNN models better, but also open the door for future improvements in using neural networks for complex sequence classification challenges.

Classification of Progressive Wear on a Multi-Directional Pin-on-Disc Tribometer Simulating Conditions in Human Joints-UHMWPE against CoCrMo Using Acoustic Emission and Machine Learning

Human joint prostheses experience wear failure due to the complex interactions between Ultra-High-Molecular-Weight Polyethylene (UHMWPE) and Cobalt-Chromium-Molybdenum (CoCrMo). This study uses the wear classification to investigate the gradual and progressive abrasive wear mechanisms in UHMWPE. Pin-on-disc tests were conducted under simulated in vivo conditions, monitoring wear using Acoustic Emission (AE). Two Machine Learning (ML) frameworks were employed for wear classification: manual feature extraction with ML classifiers and a contrastive learning-based Convolutional Neural Network (CNN) with ML classifiers. The CNN-based feature extraction approach achieved superior classification performance (94% to 96%) compared to manual feature extraction (81% to 89%). The ML techniques enable accurate wear classification, aiding in understanding surface states and early failure detection. Real-time monitoring using AE sensors shows promise for interventions and improving prosthetic joint design.

A Remote Access Server with Chatbot User Interface for Coffee Grinder Burr Wear Level Assessment Based on Imaging Granule Analysis and Deep Learning Techniques

Coffee chains are very popular around the world. Because overly worn coffee grinder burrs can downgrade the taste of coffee, coffee experts and professional cuppers in an anonymous coffee chain have developed a manual method to classify coffee grinder burr wear so that worn burrs can be replaced in time to maintain the good taste of coffee. In this paper, a remote access server system that can mimic the ability of those recognized coffee experts and professional cuppers to classify coffee grinder burr wear has been developed. Users only need to first upload a photo of coffee granules ground by a grinder to the system through a chatbot interface; then, they can receive the burr wear classification result from the remote server in a minute. The system first uses image processing to obtain the coffee granules’ size distribution. Based on the size distributions, unified length data inputs are then obtained to train and test the deep learning model so that it can classify the burr wear level into initial wear, normal wear, and severe wear with more than 96% accuracy. As only a mobile phone is needed to use this service, the proposed system is very suitable for both coffee chains and coffee lovers.

Influence of illumination on the image-based classification accuracy of wear on milling tools

For reasons of cost savings and resource conservation, it is of great interest to the machining industry to utilise the entire service life of milling tools. Image-based machine learning methods are suitable for classifying tool wear. In this context, the influence of two different illumination sources during image data collection on the performance of a CNN for the classification of wear on milling tools was investigated. The series of tests shows that both the use of diffuse illumination and direct illumination are suitable for collecting image data on the basis of which a high-performance CNN can be trained.

Intelligent monitoring of milling tool wear based on milling force coefficients by prediction of instantaneous milling forces

The spindle current of a machine tool contains a wealth of machining information and by analyzing its signal characteristics wear monitoring of milling tools can be achieved. Most current research in tool wear monitoring has been achieved by intelligent classification methods, but such methods are unable to identify wear states when cutting parameters change. To address this challenge, the paper proposes a new tool wear monitoring framework that identifies the wear state of milling cutters under different cutting parameters. The first step is to establish the mapping relationship between the spindle current signal and the milling force signal through neural networks under a variety of cutting parameters. Based on the mapping property between two signals, a TCN-LSTM based neural network prediction model is proposed to achieve accurate prediction of milling forces by spindle current signal. Various cutting information is then calculated based on the predicted milling forces and PLC communication, and a method is proposed to identify the machining status of the tool: the milling force coefficient monitoring method. The method reflect the wear status of the milling cutter by monitoring the range of threshold values, making the identification of the tool wear state without interference from variable spindle speeds, feeds and depths of cut. The proposed method provides a new solution for tool wear monitoring, breaking the inherent thinking of intelligent tool wear classification, and the experimental results prove the effectiveness and generality of the proposed method.

Tool wear classification based on maximal overlap discrete wavelet transform and hybrid deep learning model

Tool wear classification based on maximal overlap discrete wavelet transform and hybrid deep learning model

Physics-informed hidden markov model for tool wear monitoring

Tool wear monitoring (TWM) is an important part of modern intelligent machining. An efficient and accurate monitoring system will effectively improve machining accuracy and reduce processing costs. At present, the methods for TWM can generally be divided into three categories: physics-based models, data-driven models, and hybrid models. These current approaches are suffered from either low prediction accuracy, insufficient model training, or poor result interpretability due to the nature of the model construction approaches. To overcome the shortcomings of these methods, a physics-informed hidden Markov model (PI-HMM) proposed in this study fully integrates the advantages of the above two methods. Firstly, the model constrains the division of hidden states through the tool wear physical model to improve the physical consistency of the model. Secondly, according to the process parameters and the labels generated by the tool wear physical model, the training set is expanded to solve the problem of insufficient training data of the data model. Finally, the influence of real-time features is added to the established wear state output model and the physical data fusion training strategy is used to train the model to realize the classification of tool wear state and the regression of wear value. The experimental results show that the proposed model in this study achieves an average recognition rate of 0.995 for wear classification and an average coefficient of determination (R2) of 0.968 for wear regression.

A Study on Wheel Member Condition Recognition Using 1D–CNN

The condition of a railway vehicle’s wheels is an essential factor for safe operation. However, the current inspection of railway vehicle wheels is limited to periodic major and minor maintenance, where physical anomalies such as vibrations and noise are visually checked by maintenance personnel and addressed after detection. As a result, there is a need for predictive technology concerning wheel conditions to prevent railway vehicle damage and potential accidents due to wheel defects. Insufficient predictive technology for railway vehicle’s wheel conditions forms the background for this study. In this research, a real-time tire wear classification system for light-rail rubber tires was proposed to reduce operational costs, enhance safety, and prevent service delays. To perform real-time condition classification of rubber tires, operational data from railway vehicles, including temperature, pressure, and acceleration, were collected. These data were processed and analyzed to generate training data. A 1D–CNN model was employed to classify tire conditions, and it demonstrated exceptionally high performance with a 99.4% accuracy rate.

Image-based feature extraction for inline quality assurance and wear classification in high-speed blanking processes

Wear is one of the key factors that determine the efficiency of multi-stage processes that include blanking operations. Since wear in these processes not only causes unplanned downtime but also directly affects product quality, inline detection of wear and its effect on product quality is of major importance. However, current quality assurance (QA) methods are limited to manual offline inspection by operators at predefined intervals, so that 100% inspection of the product and description of the state of wear is not found in industrial practice. The aim of this work is therefore to develop an optical system that enables in-line acquisition of product images and the associated control of blanking-specific quality features up to stroke rates of 300 strokes per minute (spm). In order to make the system attractive to small- and medium-sized enterprises (SME), the system is designed to minimize integration and investment costs using commercially available components. By combining the system with a methodology for extracting blanking-specific features, so-called key performance parameters (KPPs), the condition of the blanked surface as a relevant quality parameter is derived directly from the workpiece image. To demonstrate the transferability of the methodology to industrial applications, two use cases are investigated. In the first case, the KPPs are used directly to determine the quality of the blanked workpiece and are compared with reference measurements. Here, the KPPs are quantified with a mean absolute error of 18 μm compared to a ground truth. In the second case, the KPPs are used to build a machine learning (ML) model to estimate the wear of the blanking tool. Here, an accuracy of 92% is achieved in classifying the actual wear state.

Tool wear classification in precision machining using distance metrics and unsupervised machine learning

Tool wear classification in precision machining using distance metrics and unsupervised machine learning

3-dimensionally printed patient-specific glenoid drill guides vs. standard nonspecific instrumentation: a randomized controlled trial comparing the accuracy of glenoid component placement in anatomic total shoulder arthroplasty

Traditional, commercially-sourced patient-specific instrumentation (PSI) systems for shoulder arthroplasty improve glenoid component placement but can involve considerable cost and outsourcing delays. The purpose of this randomized controlled trial was to compare the accuracy of glenoid component positioning in anatomic total shoulder arthroplasty (aTSA) using an in-house, point-of-care, 3-dimensionally (3D) printed patient-specific glenoid drill guide versus standard non-specific instrumentation. This single-center randomized controlled trial included 36 adult patients undergoing primary aTSA. Patients were blinded and randomized 1:1 to either the PSI or the standard aTSA guide groups. The primary endpoint was accuracy of glenoid component placement (version and inclination), which was determined using a metal-suppression CT scan taken between 6 weeks to 1 year postoperatively. Deviation from the preoperative 3D templating plan was calculated for each patient. Blinded postoperative CT measurements were performed by a fellowship-trained shoulder surgeon and a musculoskeletal radiologist. Nineteen patients were randomized to the patient-specific glenoid drill guide group, and 17 were allocated to the standard instrumentation control group. There were no significant differences between the two groups for native version (p = 0.527) or inclination (p = 0.415). The version correction was similar between the two groups (p = 0.551), and the PSI group was significantly more accurate when correcting version than the control group (p = 0.042). The PSI group required a significantly greater inclination correction than the control group (p = 0.002); however, the two groups still had similar accuracy when correcting inclination (p = 0.851). For the PSI group, there was no correlation between accuracy of component placement and native version, native inclination, or Walch classification of glenoid wear (p > 0.05). For the control group, accuracy when correcting version was inversely correlated with native version (p = 0.033), but accuracy was not correlated with native inclination or Walch classification of glenoid wear (p > 0.05). The intraclass correlation coefficient (ICC) was 0.703 and 0.848 when measuring version and inclination accuracy respectively. When compared to standard instrumentation, the use of in-house, 3D-printed, patient-specific glenoid drill guides during aTSA led to more accurate glenoid component version correction and similarly accurate inclination correction. Additional research should examine the influence of proper component position and use of patient-specific instrumentation on clinical outcomes.

NJUST-CCTD: An Image Database for Milling Tool Wear Classification with Deep Learning

NJUST-CCTD: An Image Database for Milling Tool Wear Classification with Deep Learning

Digital Twin Framework for Lathe Tool Condition Monitoring in Machining of Aluminium 5052


 
 
 Digital Twin (DT) is a virtual representation of a product system that exhibits the properties and analyzes the system’s functions. The significant impact of DT extends to several fields, which increases productivity and reduces wastage. This article focuses on developing a Digital twin model of a Lathe machine for Tool Condition Monitoring (TCM). DT implementation in industries is challenging due to simulating online cutting forces and wear. Even though several pieces of research have been carried out in the prediction of tool conditions using machine learning, Artificial Neural network models, only a few pieces of research have been made in digital twins for TCM. This article provides the technique for implementing the DT model of a lathe tool. The feasibility of the DT Model framework is verified by a case study of the turning process with a CNC Lathe machine while machining of Aluminium 5052 workpiece using Titanium Nitride coated tool inserts. The sensor’s data are acquired and fed to the microcontroller for real-time data acquisition. The real-time dataset is processed in the DT model for monitoring and predicting the tool conditions. The tool wear classification using the DT model is achieved. Developing the Digital Twin model in machining increases productivity and assists in predictive maintenance.
 
 

Methodology for Tool Wear Detection in CNC Machines Based on Fusion Flux Current of Motor and Image Workpieces

In the manufacturing industry, computer numerical control (CNC) machine tools are of great importance since the processes in which they are used allow the creation of elements used in multiple sectors. Likewise, the condition of the cutting tools used is paramount due to the effect they have on the process and the quality of the supplies produced. For decades, methodologies have been developed that employ various signals and sensors for wear detection, prediction and monitoring; however, this field is constantly evolving, with new technologies and methods that have allowed the development of non-invasive, efficient and robust systems. This paper proposes the use of magnetic stray flux and motor current signals from a CNC lathe and the analysis of images of machined parts for wear detection using online and offline information under the variation in cutting speed and tool feed rate. The information obtained is processed through statistical and non-statistical indicators and dimensionally reduced by linear discriminant analysis (LDA) and a feed-forward neural network (FFNN) for wear classification. The results obtained show a good performance in wear detection using the individual signals, achieving efficiencies of 77.5%, 73% and 89.78% for the analysis of images, current and stray flux signals, respectively, under the variation in cutting speed, and 76.34%, 73% and 63.12% for the analysis of images, current and stray flux signals, respectively, under the variation of feed rate. Significant improvements were observed when the signals are fused, increasing the efficiency up to 95% for the cutting speed variations and 82.84% for the feed rate variations, achieving a system that allows detecting the wear present in the tools according to the needs of the process (online/offline) under different machining parameters.