Tool Wear Condition Research Articles

Tool wear condition monitoring across machining processes based on feature transfer by deep adversarial domain confusion network

Tool wear condition monitoring across machining processes based on feature transfer by deep adversarial domain confusion network

Tool wear classification based on convolutional neural network and time series images during high precision turning of copper

Artificial intelligent techniques are critical in predicting tool wear in the machining process. Effective assessment of the rate and state of tool wear are important in the high-speed turning process and makes it possible to replace the tool before catastrophic wear occurs. It is well known that cutting forces are often used as an indicator to monitor tool wear during the machining process. However, how to use deep learning methods to incorporate cutting forces, accurately predicting the tool wear, remains a challenge. In this paper, a novel tool wear classification method based on time series images of cutting forces and convolutional neural networks was proposed. The one-dimensional cutting force signals are converted into two-dimensional time series images using the Gramina Angular Summation Fields method. Then, a modified AlexNet network is used to classify tool wear types based on the processed cutting force time series images. The prediction results show the overall prediction accuracy of the four tool wear categories can reach around 90%. In addition, by balancing the number of cases in the dataset, the prediction accuracy of each category can be improved while the overall prediction accuracy is maintained.

Development of tool wear condition on-line monitoring method for impeller milling based on new data processing approach and DAE-BP-ANN-integrated modeling

Tool wear condition monitoring plays an important role in the maintaining machining accuracy and machining efficiency of complex surface parts. In this study, a new on-line tool wear monitoring method based on a self-developed data processing approach for the impeller milling was proposed. To achieve that, a new tool wear experimental platform was first built to collect both the spindle current signal and thermal deformation data in entire life cycle of cutter. Based on collected data, features of the time domain, frequency domain and time-frequency domain were extracted indiscriminately, and a 38 × 156 feature-sample set was subsequently established. To further reduce the dimensions of this feature-sample set and rise its characterization capability, the feature set was further processed using the sensitivity analysis and deep auto-encoder algorithm. Finally, 12 synthesized features were filtered out and then used to build the mapping model of signal synthesized features to different tool wear conditions by adopting the structural artificial neural network (ANN) integrated with back propagation (BP) algorithm. To verify the reliability of the proposed BP-ANN-integrated tool wear condition monitoring model, another comparison analysis of different data processing approaches was conducted. The comparison results showed that the proposed method for tool wear condition online monitoring had reliable performance and the recognition accuracy was 88.9%.

Tool wear condition monitoring based on multi-sensor integration and deep residual convolution network

In order to guarantee machining quality and production efficiency and as well as to reduce downtime and cost, it is essential to receive information about the cutting tool condition and change it in time if necessary. To this end, tool condition monitoring systems are of great significance. Based on the data fusion technology of multi-sensor integration and the learning ability of deep residual network, a tool wear monitoring system is proposed in this paper. For data acquisition, multiple sensors are used to collect vibration, noise and acoustic emission signals in the machining process. For signal processing, the data fusion method of angular summation of matrices is used, so that the multi-source data are fused into two-dimensional pictures. Then, the feature extraction module of the proposed system uses the pictures as input and takes advantage of the deep residual convolutional network in extracting the deep features from the pictures, and finally the identification module completes the recognition of the tool wear type. To verify its feasibility, a testing bed is built on a CNC milling machine, and multi-sensor data are collected during the machining process of a simple workpiece with one of the two selected cutting tools each time. The proposed system is trained using the collected data and then is used to monitor the wear condition of a new cutting tool by collecting real-time data under similar condition. The results show that the accuracy of wear state recognition is as high as 90%, which verifies the feasibility of the proposed tool wear monitoring system.

Adaptive optimal process control with actor-critic design for energy-efficient batch machining subject to time-varying tool wear

Batch machining systems are essential for improving productivity and quality, but they consume considerable amounts of energy due to the continuous interaction with machine tools, workpieces, and cutting tools. In contrast to single-piece machining that has a short production cycle, the tool wear impacts in batch machining systems on energy consumption cannot be underestimated. However, few studies have focused on adaptive process control subject to time-varying tool wear because process optimization has always been previously considered a static problem. As an alternative to metaheuristic algorithms, reinforcement learning (RL) offers an attractive means for solving such a dynamic, high-dimensional, and high-coupling problem. In the case of turning cylindrical parts, an energy-efficient decision model is developed for the process control of pass operations of batch machining. The decision variables are decoupled by reformulating the problem as the Markov decision process, wherein the tool wear experiences dynamic changes. To solve the problem, an actor-critic RL framework with multi-constraint and multi-objective design is developed. Based on the framework, a dynamic process control method is proposed where the RL agent observes workpiece features, machining requirements, and tool wear states (inputs) and adaptively selects the control parameters such as cutting speed, feed rate, and cutting rate (outputs), with the aim to conserve energy. Two application tests and comparisons against metaheuristic methods are performed. The results indicate that the method can further reduce energy by over 20% compared with energy-efficient optimization ignoring tool wear effects. The learning efficiency of RL is about three times faster than that of metaheuristics. The online sampling time is less than 0.1 millisecond, which facilitates real-time control of process parameters.

Study on wear simulation of diamond abrasive tool for rotary ultrasonic grinding

The aim of this study is to explore the wear mechanism of diamond grinding tools in rotary ultrasonic grinding process and complete the simulation study of micro wear state of diamond grinding tools in different processing stages. Primarily, the morphology of single diamond abrasive grains is analyzed and studied, and a three-dimensional irregular abrasive grain simulation is carried out according to the morphology characteristics of diamond abrasive grains. Then, the center distance and spatial distribution law between diamond grits are obtained by calculation, and the discrete three-dimensional morphology simulation of diamond abrasive end face is completed based on the virtual lattice theory. Through the rotary ultrasonic grinding experiment, the wear form of diamond grits and the mathematical model of the wear amount of diamond grits changing with the removal amount of workpiece material are determined. The wear simulation of diamond abrasive tool with different workpiece removal is completed by using the mathematical model obtained from experiments. Last section, the number of abrasive particles in the simulation model and the wear amount of the abrasive tool are compared and analyzed with the corresponding experimental results. The above research provides a new research method for exploring the wear mechanism of diamond abrasive tools.

Distributed deep learning enabled prediction on cutting tool wear and remaining useful life

To optimise the utilisation cost of cutting tools, it is imperative to develop an online system to efficiently and accurately predict tool wear conditions and remaining useful lives (RULs). With this aim, a novel system is proposed based on deep learning algorithms distributed over an edge-cloud computing architecture. The system is innovative in the following aspects: (i) a lightweight convolutional neural network-random forest (CNN-RF) model is designed to be executed on an edge device to assess tool wear conditions efficiently, which supports severe tool resilience and tool replacement when necessary; (ii) a convolutional neural network-long short-term memory (CNN-LSTM) model is designed to be executed on a cloud to process long-term signals to predict the RUL of the cutting tool, which supports fine-tuning tool parameters dynamically; (iii) a signal compression mechanism is developed to condense the signals of tooling conditions into 2D images so the signal volumes transferred over the network are minimised and signal security is improved. Experiments were performed in a real-world machining workshop for research methodology validation. It showed that the prediction accuracies for tool wear and RUL achieved 90.6% and 93.2%, respectively, and the volume of signals transferred over the network was reduced by 89.0%. The experiments and benchmarks with comparative algorithms demonstrated that the system and its methodology exhibited great potential to reinforce cutting tool optimisation for real-world applications.

ShuffleNet v2.3-StackedBiLSTM-Based Tool Wear Recognition Model for Turbine Disc Fir-Tree Slot Broaching

At present, deep learning technology shows great market potential in broaching tool wear state recognition based on vibration signals. However, traditional single neural network structure is difficult to extract a variety of different features simultaneously and has low robustness, so the accuracy of wear status recognition is not high. In view of the above problems, a broaching tool wear recognition model based on ShuffleNet v2.3-StackedBiLSTM is proposed in this paper. The model integrates ShuffleNet v2.3, which has been channel shuffling, and StackedBiLSTM, a long and short-term memory network, to effectively extract spatial and temporal features for tool wear state recognition. Based on the innovative recognition model, the turbine disc fir-tree slot broaching experiment is designed, and the performance index system based on confusion matrix is adopted. The experimental research and results show that the model has outstanding accuracy, precision, recall, and F1 value, and the accuracy rate reaches 99.37%, which is significantly better than ShuffleNet v2.3 and StackedBiLSTM models. The recognition speed of a single sample was improved to 8.67 ms, which is 90.32% less than that of the StackedBiLSTM model.

Novel tool condition identification based on finite element modelling and support vector machine

Timely and accurate recognition of tool wear condition could reduce the machining cost greatly. However, the problem of sample missing and imbalance affects the classification accuracy of AI models seriously. A novel strategy based on finite element method (FEM) and support vector machine (SVM) is proposed to overcome the above problem. Firstly, several tool wear experiments are carried out to obtain experimental samples. Then, a FEM model is established and verified through experimental samples. Based on the verified FEM model, several simulated sample of missing and imbalanced samples in experiments could be supplemented to compose a complete training set. The SVM model is trained by the complete training set to tool wear condition identification. Milling tool experiments demonstrate that the proposed method can obtain above 96% identification accuracy with a small number of experiments, which is 28% higher than that based on experimental samples. [Submitted 21 February 2022; Accepted 28 July 2022]

A Novel Evaluation Metric Based on Dispersion of Wear Distance for In Situ Tool Condition Monitoring

As the direct performer of the cutting process in computer numerical control (CNC) machine tools, the tool wear condition directly affects the product quality. However, the existing evaluation metrics, e.g., flank wear width and wear area, cannot accurately determine the wear form conversion. In this article, a novel metric based on the dispersion of wear distance is proposed to describe the flank wear forms in more detail. The wear distance refers to the distance projected from the flank wear edge to the main cutting edge. Then, the wear distance of the indirect contact on the tool–chip interface is filtered out by the normal distribution model. Finally, the rate of distance dispersion over time named RDDT is constructed to identify the time nodes during wear forms’ conversion. In the experiment of accelerating milling cutter life, the Mann-Kendall (MK) inspection statistics of the proposed metric is 3.74, and the correlation with the maximum flank wear is 99.58%. Compared with the existing evaluation metrics, RDDT can accurately and robustly identify the two time nodes where the flank wear form changes in the whole life cycle.

Tool wear condition monitoring method of five-axis machining center based on PSO-CNN

The effective monitoring of tool wear status in the milling process of a five-axis machining center is important for improving product quality and efficiency, so this paper proposes a CNN convolutional neural network model based on the optimization of PSO algorithm to monitor the tool wear status. Firstly, the cutting vibration signals and spindle current signals during the milling process of the five-axis machining center are collected using sensor technology, and the features related to the tool wear status are extracted in the time domain, frequency domain and time-frequency domain to form a feature sample matrix; secondly, the tool wear values corresponding to the above features are measured using an electron microscope and classified into three types: slight wear, normal wear and sharp wear to construct a target Finally, the tool wear sample data set is constructed by using multi-source information fusion technology and input to PSO-CNN model to complete the prediction of tool wear status. The results show that the proposed method can effectively predict the tool wear state with an accuracy of 98.27%; and compared with BP model, CNN model and SVM model, the accuracy indexes are improved by 9.48%, 3.44% and 1.72% respectively, which indicates that the PSO-CNN model proposed in this paper has obvious advantages in the field of tool wear state identification.

Branched Neural Network based model for cutter wear prediction in machine tools

Cutter wear has a great impact on machining quality, which is particularly true when demand for machining accuracy is high. Therefore, cutter wear analysis is critical in assuring high machining quality and long tool life. However, it is highly dangerous and difficult to monitor and determine tool wear conditions during machining. This paper proposes a method of real-time machining status monitoring using the data collected by external sensors without interfering with the machining process. A tool wear forecast model is introduced in this article. Multiple process parameters and sensor data are collected. Due to missing data, however, data preprocessing is done applying the interpolation or extrapolation approach and data are standardized in order to create an artificial intelligence-based model. The said model will then be used to forecast tool wear during different processing stages and be compared with other different models, such as: AdaBoost, Support Vector Machine, Decision Tree, and Random Forest. The model developed in this study is based on a Branched Neural Network, which generates the best prediction results among all publicly available algorithms. This approach helps reduce the mean absolute error and root-mean-square error values and can improve by 0.11 in R2.

A Dual-Stage Attention Model for Tool Wear Prediction in Dry Milling Operation.

The intelligent monitoring of tool wear status and wear prediction are important factors affecting the intelligent development of the modern machinery industry. Many scholars have used deep learning methods to achieve certain results in tool wear prediction. However, due to the instability and variability of the signal data, some neural network models may have gradient decay between layers. Most methods mainly focus on feature selection of the input data but ignore the influence degree of different features to tool wear. In order to solve these problems, this paper proposes a dual-stage attention model for tool wear prediction. A CNN-BiGRU-attention network model is designed, which introduces the self-attention to extract deep features and embody more important features. The IndyLSTM is used to construct a stable network to solve the gradient decay problem between layers. Moreover, the attention mechanism is added to the network to obtain the important information of output sequence, which can improve the accuracy of the prediction. Experimental study is carried out for tool wear prediction in a dry milling operation to demonstrate the viability of this method. Through the experimental comparison and analysis with regression prediction evaluation indexes, it proves the proposed method can effectively characterize the degree of tool wear, reduce the prediction errors, and achieve good prediction results.

A novel method for online monitoring of surface quality and predicting tool wear conditions in machining of materials

A novel method for online monitoring of surface quality and predicting tool wear conditions in machining of materials

Tool wear and its effect on the surface integrity and fatigue behavior in high-speed ultrasonic peening milling of Inconel 718

Ultrasonic-assisted technology has proven effective for Inconel 718 milling. This study compared tool life and tool wear forms and wear mechanisms at different wear states in high-speed Ultrasonic Peening Milling (UPM) and Conventional Milling (CM). The influence of different tool wear states on the surface integrity index and fatigue performance were systematically analyzed. The results showed 32.5% increase in tool life in UPM owing to lower tool wear compared to that in CM. More important, UPM was significantly more effective in improving machined surface quality and fatigue life with an average increase of 4–17 times.

Tool Wear Monitoring in Milling Based on Fine-Grained Image Classification of Machined Surface Images.

Cutting tool wear state assessment during the manufacturing process is extremely significant. The primary purpose of this study is to monitor tool wear to ensure timely tool change and avoid excessive tool wear or sudden tool breakage, which causes workpiece waste and could even damage the machine. Therefore, an intelligent system, that is efficient and precise, needs to be designed for addressing these problems. In our study, an end-to-end improved fine-grained image classification method is employed for workpiece surface-based tool wear monitoring, which is named efficient channel attention destruction and construction learning (ECADCL). The proposed method uses a feature extraction module to extract features from the input image and its corrupted images, and adversarial learning is used to avoid learning noise from corrupted images while extracting semantic features by reconstructing the corrupted images. Finally, a decision module predicts the label based on the learned features. Moreover, the feature extraction module combines a local cross-channel interaction attention mechanism without dimensionality reduction to characterize representative information. A milling dataset is conducted based on the machined surface images for monitoring tool wear conditions. The experimental results indicated that the proposed system can effectively assess the wear state of the tool.

A Novel Multivariate Cutting Force-Based Tool Wear Monitoring Method Using One-Dimensional Convolutional Neural Network.

Tool wear condition monitoring during the machining process is one of the most important considerations in precision manufacturing. Cutting force is one of the signals that has been widely used for tool wear condition monitoring, which contains the dynamical information of tool wear conditions. This paper proposes a novel multivariate cutting force-based tool wear monitoring method using one-dimensional convolutional neural network (1D CNN). Firstly, multivariate variational mode decomposition (MVMD) is used to process the multivariate cutting force signals. The multivariate band-limited intrinsic mode functions (BLIMFs) are obtained, which contain a large number of nonlinear and nonstationary tool wear characteristics. Afterwards, the proposed modified multiscale permutation entropy (MMPE) is used to measure the complexity of multivariate BLIMFs. The entropy values on multiple scales are calculated as condition indicators in tool wear condition monitoring. Finally, the one-dimensional feature vectors are constructed and employed as the input of 1D CNN to achieve accurate and stable tool wear condition monitoring. The results of the research in this paper demonstrate that the proposed approach has broad prospects in tool wear condition monitoring.

Tool wear state recognition based on WOA-SVM with statistical feature fusion of multi-signal singularity

Tool wear state recognition based on WOA-SVM with statistical feature fusion of multi-signal singularity

Remaining Useful Life Prediction of Milling Cutters Based on CNN-BiLSTM and Attention Mechanism

Machining tools are a critical component in machine manufacturing, the life cycle of which is an asymmetrical process. Extracting and modeling the tool life variation features is very significant for accurately predicting the tool’s remaining useful life (RUL), and it is vital to ensure product reliability. In this study, based on convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), a tool wear evolution and RUL prediction method by combining CNN-BiLSTM and attention mechanism is proposed. The powerful CNN is applied to directly process the sensor-monitored data and extract local feature information; the BiLSTM neural network is used to adaptively extract temporal features; the attention mechanism can selectively study the important degradation features and extract the tool wear status information. By evaluating the performance and generalization ability of the proposed method under different working conditions, two datasets are applied for experiments, and the proposed method outperforms the traditional method in terms of prediction accuracy.

Tool wear state recognition based on feature selection method with whitening variational mode decomposition

• A signal decomposition method based on WVMD is proposed, which makes the intrinsic mode functions independent of each other and can effectively avoid mode mixing phenomenon. • The strong correlation force signal features from sensitive feature set are selected by proposed JIE method . Redundant features unrelated to tool wear are removed to achieve data dimension reduction. • The classification of tool wear state is realized by OPF algorithm, which can effectively reduce calculation time while ensuring classification accuracy . Tool states affect the surface quality and equipment stop time. It is essential to seek a method with high accuracy and efficiency to model and predict tool states. Cutting process signal is usually used to in industry monitoring, which contains lots of fault information. In this paper, the spectrum analysis of milling force is carried out to obtain the signal frequency that can reflect tool wear degree. A force signal decomposition model based on whitening variational mode decomposition (WVMD) is established to screen out sensitive signals, which effectively avoids mode mixing. Joint information entropy (JIE) is adopted to select the force signal features. Compared with other dimensionality reduction algorithms, the optimal feature subset obtained by JIE method can reflect strong relativity between features and the wear state. The classification is realized by the optimal-path forest (OPF) algorithm. According to the experimental results, compared with other recognition models, WVMD-JIE-OPF method has a classification accuracy as high as 98.41%. The training speed of OPF is increased by 58.43% compared with LSSVM, which shows excellent tool condition monitoring performance.