Tool Wear Prediction Research Articles

Tool Wear Prediction Based on Residual Connection and Temporal Networks

Tool Wear Prediction Based on Residual Connection and Temporal Networks

Tool Wear Prediction Based on Adaptive Feature and Temporal Attention with Long Short-Term Memory Model

Tool Wear Prediction Based on Adaptive Feature and Temporal Attention with Long Short-Term Memory Model

Machine Tool Wear Prediction Technology Based on Multi-Sensor Information Fusion.

The intelligent monitoring of cutting tools used in the manufacturing industry is steadily becoming more convenient. To accurately predict the state of tools and tool breakages, this study proposes a tool wear prediction technique based on multi-sensor information fusion. First, the vibrational, current, and cutting force signals transmitted during the machining process were collected, and the features were extracted. Next, the Kalman filtering algorithm was used for feature fusion, and a predictive model for tool wear was constructed by combining the ResNet and long short-term memory (LSTM) models (called ResNet-LSTM). Experimental data for thin-walled parts obtained under various machining conditions were utilized to monitor the changes in tool conditions. A comparison between the ResNet and LSTM tool wear prediction models indicated that the proposed ResNet-LSTM model significantly improved the prediction accuracy compared to the individual LSTM and ResNet models. Moreover, ResNet-LSTM exhibited adaptive noise reduction capabilities at the front end of the network for signal feature extraction, thereby enhancing the signal feature extraction capability. The ResNet-LSTM model yielded an average prediction error of 0.0085 mm and a tool wear prediction accuracy of 98.25%. These results validate the feasibility of the tool wear prediction method proposed in this study.

Multi-sectional SVD-based machine learning for imagery signal processing and tool wear prediction during CNC milling of Inconel 718

Multi-sectional SVD-based machine learning for imagery signal processing and tool wear prediction during CNC milling of Inconel 718

Efficient Tool Wear Prediction in Manufacturing: BiLPReS Hybrid Model with Performer Encoder

Efficient Tool Wear Prediction in Manufacturing: BiLPReS Hybrid Model with Performer Encoder

MS-DenseNet-GRU tool wear prediction method based on attention mechanism

Tool wear was an inevitable physical phenomenon in the cutting procedure. Serious tool wear has a direct effect on the level of processing quality and the effectiveness of production, and it even leads to abnormal cutting processes and a series of safety problems. Effective tool wear prediction can provide a basis for the rational use and replacement of tools to improve tool efficiency and ensure the stable operation of the machining process. Therefore, a tool wear prediction method combining multiple deep learning modules was proposed. To begin, the vibration signal was broken up using the complete ensemble empirical mode decomposition with adaptive noise algorithm. Then, the intrinsic mode functions with a strong correlation with the original signal were screened out according to the Pearson correlation coefficient for signal reconstruction. Additionally, the DenseNet module, the gate recurrent unit (GRU) module and the efficient channel attention module were deeply integrated to build a multi-scale DenseNet-GRU tool wear prediction model with attention mechanisms by learning the relationship of mapping between signal features and tool wear. Finally, the model was trained and tested using milling experimental data. The experiments’ outcomes demonstrated that the suggested method can accurately and reliably estimate the tool wear value. Compared with the DenseNet model, convolutional neural network–long short-term memory model, and DenseNet-GRU model, it further shows that it had superior performance in prediction accuracy and generalization ability. The research results can provide certain technical support for the prediction of tool wear intelligently, which is vital to raising the quality of processing, reducing production costs, and promoting the manufacturing industry’s intelligent development.

Tool Wear Prediction Based on LSTM and Deep Residual Network

To improve the accuracy and efficiency of tool wear predictions, this study proposes a tool wear prediction model called LSTM_ResNet which is based on the long short-term memory (LSTM) network and the Residual Network (ResNet). The model utilizes LSTM layers for processing, where the first block and loop blocks serve as the core modules of the deep residual network. The model employs a series of methods including convolution, batch normalization (BN), and Rectified Linear Unit (ReLU) to enhance the model’s expression and prediction capabilities. The performance of the LSTM_ResNet model was evaluated using experimental data from the PHM2010 datasets and two different depths (64 and 128 layers), training both LSTM_ResNet models for 200 epochs. The 64-layer model’s root mean square error (RMSE) values are 3.36, 4.35, and 3.59, and the mean absolute error (MAE) values are 2.42, 2.85, and 2.21; using 128 layers, the RMSE values are 3.66, 3.99, and 3.77, and the MAE values are 2.49, 2.73, and 3.01. The results indicate that the 64-layer LSTM has smaller average errors, suggesting that compared to other common network structures, the LSTM_ResNet network has a higher performance. This research provides an effective solution for tool wear prediction and helps to improve the technical level of tool wear prediction in China.

Machine learning models for prediction and classification of tool wear in sustainable milling of additively manufactured 316 stainless steel

Machine learning (ML) is a subfield of Artificial Intelligence (AI) that uses data, learns the hidden pattern from the data, and makes predictions for future instances with greater accuracy and prediction capabilities, not hallucination (overfitting) with the current data. The application of ML is quite popular in the machining sector because the ML models can be used to predict tool wear, surface roughness and other important machining aspects. With this aim, the present work evaluates the tool wear and class separation by predicting the variation of flank wear (Vb) as a test dataset. A predictive model is proposed for utilizing minimum quantity lubrication (MQL), cryogenic, and MoS2+MQL conditions. Predictions are made using several machine learning (ML) methods, including linear regression, support vector machine, random forest, and multilayer perceptron. The study's findings show that Multi-layer perceptron (MLP) is superior to other methods in classification, with a prediction accuracy of over 95% on average across both training and testing datasets. Even with limited information, the proposed method can help classify situations and recommend the best course of action for machining.

An investigation on using artificial intelligence models to predict crater wear of tungsten carbide tool

In this study, artificial intelligence (AI) tools were utilised to predict and analyse the progression of crater wear in cutting tools made of tungsten carbide during machining of aluminium 7075 alloy with a CNC lathe. The study investigated the impact of corner radius, feed rate, cutting speeds, and cut depth on the wear of the tools. Thirty experiments were conducted, with 24 used for training 11 independent AI models and the remaining 6 used for testing. This study stands out for its novelty as it pioneers the evaluation of 11 distinct AI models for the prediction of tool wear. With a high level of accuracy and a lower average deviation, the most effective model identified in this study was the gradient boosting model. By integrating AI algorithms into manufacturing processes, the monitoring of tool wear becomes more efficient, leading to reduce experiments, minimise testing costs, predict tool life, prevent failures, and boost productivity.

A multi-target predictive model for predicting tool wear and surface roughness

To simultaneously predict tool wear and surface roughness accurately during machining, this paper develops a multi-target predictive model that leverages a novel two-step feature-integration approach and Multi-kernel Gaussian process autoregressive regression (MK-GPAR). Compared with the traditional Gaussian process autoregressive regression (GPAR) models, the MK-GPAR demonstrates an enhanced capability in capturing detailed structures within heterogeneous data originating from various sources or disparate data forms. The weight coefficients of the kernel functions in MK-GPAR are typically assigned a value of 1 to minimize their influence on the predictive model. Furthermore, when compared to conventional multi-target predictive models like Gradient Boosting, Support Vector Regression (SVR), and K-Nearest Neighbors (KNN), the GPAR not only delivers higher-accuracy predictions for tool wear and surface roughness but also provides corresponding confidence intervals (CI). However, the CI of predictions for tool wear and surface roughness provided by MK-GPAR are inconsistent, which will seriously affect the reliability of the evaluation of the prediction results. The proposed two-step feature-integration approach is employed to enhance signal features effectively, reduce noise, and mitigate its adverse impact, thus enhancing the consistency and smoothness of the CI. The two-step feature-integration approach integrates principal component analysis (PCA) and orthogonal neighborhood preserving projections (ONPP) to merge force and vibration signal features obtained from the fixture's monitoring signals. Following the two-step feature-integration (first PCA, then ONPP) process, the MK-GPAR is utilized to build a multi-target predictive model for tool wear and surface roughness prediction. The impact of the proposed two-step feature-integration method on the prediction performance of the MK-GPAR is demonstrated revealed milling experiments. The experimental findings indicate that the proposed two-step feature-integration method significantly enhances the accuracy of predictions and the consistency of CI of the MK-GPAR. This research lays the foundation for implementing the multi-target predictive model in real industrial environments to predict tool wear and surface roughness.

Local regularization assisted split augmented Lagrangian shrinkage algorithm for feature selection in condition monitoring

Feature selection plays a vital role in improving the efficiency and accuracy of condition monitoring by constructing sparse but effective models. In this study, an advanced feature selection algorithm named the local regularization assisted split augmented Lagrangian shrinkage algorithm (LR-SALSA) is proposed. The feature selection is realized by solving a l1-norm optimization problem, which usually selects more sparse and representative features at less computational costs. The proposed algorithm operates in two stages, namely variable selection and coefficient estimation. In the stage of variable selection, the primal problem is converted into three subproblems which can be solved separately. Then individual penalty parameters are applied to every coefficient of the model when dealing with the first subproblem. Under the Bayesian evidence framework, an iterative algorithm is derived to optimize these hyperparameters. During the optimization process, redundant variables will be pruned to guarantee model sparsity and improve computational efficiency at the same time. In the second stage, the coefficients for the selected model terms are determined using the least squares technique. The superior performance and efficiency of the proposed LR-SALSA method are validated through two numerical examples and a real-world cutting tool wear prediction case study. Compared with the existing methods, the proposed method can generate a sparse model and ensure a good trade-off between estimation accuracy and computational efficiency.

Hybrid physics data-driven model-based fusion framework for machining tool wear prediction

Hybrid physics data-driven model-based fusion framework for machining tool wear prediction

Tool Wear Monitoring System Using Seq2Seq

The advancement of smart factories has brought about small quantity batch production. In multi-variety production, both materials and processing methods change constantly, resulting in irregular changes in the progression of tool wear, which is often affected by processing methods. This leads to changes in the timing of tool replacement, and failure to correctly determine this timing may result in substantial damage and financial loss. In this study, we sought to address the issue of incorrect timing for tool replacement by using a Seq2Seq model to predict tool wear. We also trained LSTM and GRU models to compare performance by using R2, mean absolute error (MAE), and mean squared error (MSE). The Seq2Seq model outperformed LSTM and GRU with an R2 of approximately 0.03~0.037 in step drill data, 0.540.57 in top metal data, and 0.16~0.45 in low metal data. Confirming that Seq2Seq exhibited the best performance, we established a real-time monitoring system to verify the prediction results obtained using the Seq2Seq model. It is anticipated that this monitoring system will help prevent accidents in advance.

An online monitoring method of milling cutter wear condition driven by digital twin

Real-time online tracking of tool wear is an indispensable element in automated machining, and tool wear directly impacts the processing quality of workpieces and overall productivity. For the milling tool wear state is difficult to real-time visualization monitoring and individual tool wear prediction model deviation is large and is not stable and so on, a digital twin-driven ensemble learning milling tool wear online monitoring novel method is proposed in this paper. Firstly, a digital twin-based milling tool wear monitoring system is built and the system model structure is clarified. Secondly, through the digital twin (DT) data multi-level processing system to optimize the signal characteristic data, combined with the ensemble learning model to predict the milling cutter wear status and wear values in real-time, the two will be verified with each other to enhance the prediction accuracy of the system. Finally, taking the milling wear experiment as an application case, the outcomes display that the predictive precision of the monitoring method is more than 96% and the prediction time is below 0.1 s, which verifies the effectiveness of the presented method, and provides a novel idea and a new approach for real-time on-line tracking of milling cutter wear in intelligent manufacturing process.

Plasticity-Induced Heating: Revisiting the Energy-Based Variational Model.

Temperature evolution during plastic deformation is of great importance for the design of manufacturing processes, as well as for the analysis and prediction of tool wear. However, the results from experimental- and numerical-type research are still often contradictory. In this paper, we analyze methods for estimating plasticity-induced heating directly from displacement fields that can be recorded during experiments or extracted from simulation results. In terms of computational methodology, the thermodynamically motivated energy-based variational formulation of the coupled thermo-mechanical boundary-value problem is adapted to the problem at hand. Since an analysis of this variational formulation exhibits challenges and distinct inconsistencies with respect to the problem at hand, an alternative approach is proposed. This alternative approach is essentially a purely thermal finite element simulation, and it is conducted using a heat source term that is empirically based on the fraction of irreversible deformation work converted to heat. Our approach estimates plasticity-induced heating based on the strain and strain rate data derived from displacement fields. We therefore incorporate thermo-visco-plastic constitutive behavior (Johnson-Cook) with a thermodynamically motivated model that specifies the fraction of plastic work converted to heat (the Taylor-Quinney coefficient).

Artificial Neural Network-Based Tool Wear Prediction in Turning AISI 1040 Medium Carbon Steel Blanks

The objective of this paper was to investigate the Cutting Speed, Feed Rate and Depth of Cut to predict Tool wear during Turning of AISI 1040 Medium Carbon Steel Blanks using Artificial Neural Network Approach. The significance of the cutting parameters was investigated using the Analysis of Variance and results revealed the feed rate as the most influential factor, followed by the interaction of cutting speed and depth of cut. The Artificial Neural Network model exhibited notable correlation coefficients (R) in training (0.81301), validation (0.99932), and test (0.99922) datasets, with an overall coefficient of 0.86662, affirming the model's efficacy in predicting tool wear. The minimum predicted tool wear (0.1007mm) was observed at a 0.50mm depth of cut, cutting speed of 200m/min, and feed rate of 0.15mm/rev, demonstrating a close alignment with the observed data. The ANN predictions effectively capture the intricate relationship between tool wear and process parameters, substantiated by high correlation coefficients.

Auxiliary input-enhanced siamese neural network: A robust tool wear prediction framework with improved feature extraction and generalization ability

Tool wear monitoring is essential for automated and resilient manufacturing, as it can prevent catastrophic failures caused by severe wear on cutting edges during machining. The conventional tool wear monitoring approaches depend on features extracted from signals, which require sensitive signals and consistent tool wear. In practical scenarios, however, neither the sensitivity of collected signals to the tool wear status nor the consistency of the actual tool wear evolution is hard to meet the requirement of the tool condition monitoring algorithm, which greatly limit the wide spread of its industrial applications. To overcome this challenge, we propose an Auxiliary Input-enhanced Siamese Neural Network (AISNN) framework by incorporating a Siamese structure into the feature extraction part of a convolutional neural network (CNN), and introducing an auxiliary input to its nonlinear regression part. The Siamese structure, instead of extracting features directly from signals, distinguishes the difference between the features extracted from signals of the examined cut and the first cut, and uses this difference as the indicator of tool wear status. Moreover, the auxiliary input provides an additional feature that has heavy dependence on the tool wear, which enables the model learning the general wear evolution of the examined cutting tool. The effectiveness of the proposed AISNN framework is verified in a set of milling experiments where input signal is insensitive to the flank wear of cutting tool and different tools’ wear evolution exhibits obvious inconsistency. Compared to the traditional CNN, the proposed AISNN significantly improves the accuracy on the verification set from 63% to 95% and on the testing set from 50% to 81%. The results demonstrate that the AISNN framework achieves significant improvement in feature extraction and generalization ability. The proposed AISNN, as a universal framework, can empower most existing deep learning-based tool wear prediction methods, enhancing their robustness in handling insensitive signals and inconsistent wear evolution and thereby promoting more industrial applications.

A Novel Piecewise Cubic Hermite Interpolating Polynomial-Enhanced Convolutional Gated Recurrent Method under Multiple Sensor Feature Fusion for Tool Wear Prediction.

The monitoring of the lifetime of cutting tools often faces problems such as life data loss, drift, and distortion. The prediction of the lifetime in this situation is greatly compromised with respect to the accuracy. The recent rise of deep learning, such as Gated Recurrent Unit Units (GRUs), Hidden Markov Models (HMMs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Attention networks, and Transformers, has dramatically improved the data problems in tool lifetime prediction, substantially enhancing the accuracy of tool wear prediction. In this paper, we introduce a novel approach known as PCHIP-Enhanced ConvGRU (PECG), which leverages multiple-feature fusion for tool wear prediction. When compared to traditional models such as CNNs, the CNN Block, and GRUs, our method consistently outperformed them across all key performance metrics, with a primary focus on the accuracy. PECG addresses the challenge of missing tool wear measurement data in relation to sensor data. By employing PCHIP interpolation to fill in the gaps in the wear values, we have developed a model that combines the strengths of both CNNs and GRUs with data augmentation. The experimental results demonstrate that our proposed method achieved an exceptional relative accuracy of 0.8522, while also exhibiting a Pearson's Correlation Coefficient (PCC) exceeding 0.95. This innovative approach not only predicts tool wear with remarkable precision, but also offers enhanced stability.

Research on multi-signal milling tool wear prediction method based on GAF-ResNext

Research on multi-signal milling tool wear prediction method based on GAF-ResNext

Tool wear prediction through AI-assisted digital shadow using industrial edge device

Flank wear of drilling tools in manufacturing is among the main factors affecting product quality and productivity. In this study, an AI-assisted digital shadow was created for the instant prediction of the drilling flank tool wear. The drilling data were collected simultaneously using an industrial edge device and a rotary dynamometer. Feature engineering was conducted on the collected data from devices in time and frequency domains. A recurrent neural network (RNN) based on bidirectional long short-term memory (Bi-LSTM) and bidirectional gated recurrent unit (Bi-GRU) architectures was implemented on specified tool wear regions dataset. The digital shadow was created using the industrial edge device and the predictive AI model to minimize costs by reducing the need for expensive multi-sensors, manufacturing downtime, and tool underuse or overuse in a smart manufacturing system. The proposed model predicts with high accuracy and computational time efficiency and can be integrated into digital twin systems.