Tool Wear Diagnosis Research Articles

Microservice-based digital twin system towards smart manufacturing

Digital Twin (DT) is a promising technology that offers versatile services to enhance manufacturing intelligence. However, the agility, reliability and analysis capabilities of existing DT services are severely challenged when applied and deployed at large-scale production lines. To address the aforementioned issues, a microservice-based DT system with redundant architecture is proposed. First, a scalable microservice-based DT system compatible with standard and tailored plug-and-play DT services is constructed for DT protocol adaptation, stream processing, information and model management. Concurrently, a generic information model is proposed to represent the entire production lifecycle from design, operation, and maintenance in a structured manner. Second, an industrial multi-task DT model is introduced, leveraging the aforementioned architecture, to effectively achieve parallel monitoring of surface roughness and tool wear. Finally, industrial manufacturing cases are introduced to verify the feasibility and effectiveness of the proposed system. The results show that heterogeneous DT data are transferred and managed reliably, with a mean absolute percentage error of 1.28% for surface roughness prediction, and 85.71% accuracy in tool wear diagnosis.

Diagnosis of Tool Wear and Fracture through Cutting Force Frequency Analysis of Stainless Steel Cutting End Mill Tools

Diagnosis of Tool Wear and Fracture through Cutting Force Frequency Analysis of Stainless Steel Cutting End Mill Tools

Tool remaining useful life prediction using bidirectional recurrent neural networks (BRNN)

Nowadays, new challenges around increasing production quality and productivity, and decreasing energy consumption, are growing in the manufacturing industry. In order to tackle these challenges, it is of vital importance to monitor the health of critical components. In the machine tool sector, one of the main aspects is to monitor the wear of the cutting tools, as it affects directly to the fulfillment of tolerances, production of scrap, energy consumption, etc. Besides, the prediction of the remaining useful life (RUL) of the cutting tools, which is related to their wear level, is gaining more importance in the field of predictive maintenance, being that prediction is a crucial point for an improvement of the quality of the cutting process. Unlike monitoring the current health of the cutting tools in real time, as tool wear diagnosis does, RUL prediction allows to know when the tool will end its useful life. This is a key factor since it allows optimizing the planning of maintenance strategies. Moreover, a substantial number of signals can be captured from machine tools, but not all of them perform as optimum predictors for tool RUL. Thus, this paper focuses on RUL and has two main objectives. First, to evaluate the optimum signals for RUL prediction, a substantial number of them were captured in a turning process and investigated by using recursive feature elimination (RFE). Second, the use of bidirectional recurrent neural networks (BRNN) as regressive models to predict the RUL of cutting tools in machining operations using the investigated optimum signals is investigated. The results are compared to traditional machine learning (ML) models and convolutional neural networks (CNN). The results show that among all the signals captured, the root mean squared (RMS) parameter of the forward force ({F}_{y}) is the optimum for RUL prediction. As well, the bidirectional long-short term memory (BiLSTM) and bidirectional gated recurrent units (BiGRU), which are two types of BRNN, along with the RMS of {F}_{y} signal, achieved the lowest root mean squared error (RMSE) for tool RUL, being also computationally the most demanding ones.

An Improved ResNet-1d with Channel Attention for Tool Wear Monitor in Smart Manufacturing.

Tool wear is a key factor in the machining process, which affects the tool life and quality of the machined work piece. Therefore, it is crucial to monitor and diagnose the tool condition. An improved CaAt-ResNet-1d model for multi-sensor tool wear diagnosis was proposed. The ResNet18 structure based on a one-dimensional convolutional neural network is adopted to make the basic model architecture. The one-dimensional convolutional neural network is more suitable for feature extraction of time series data. Add the channel attention mechanism of CaAt1 to the residual network block and the channel attention mechanism of CaAt5 automatically learns the features of different channels. The proposed method is validated on the PHM2010 dataset. Validation results show that CaAt-ResNet-1d can reach 89.27% accuracy, improving by about 7% compared to Gated-Transformer and 3% compared to Resnet18. The experimental results demonstrate the capacity and effectiveness of the proposed method for tool wear monitor.

Multisensor-based tool wear diagnosis using 1D-CNN and DGCCA

Multisensor-based tool wear diagnosis using 1D-CNN and DGCCA

Investigation of Gaussian mixture clustering model for online diagnosis of tip-wear in nanomachining

This paper studied an unsupervised machine learning method to achieve real-time diagnosis of tip wear in tip-based nanomachining with an Atomic Force Microscope (AFM). The unsupervised Gaussian Mixture Model (GMM) was applied for online pattern recognition using the collected process data. In this work, the time varying signal of machining force was collected and managed in the form of moving data windows. The characteristics of the nanomachining force signal, including the maximum force, peak to peak force, and the variance, were calculated as the data of extracted features to indicate the tip wear conditions. Outliers were identified and removed using the Mahalanobis Distance Detection. A GMM model was trained using the historical processing data, in which the tip wear states were identified by clustering the feature parameters of each data frame. The change of the tip conditions was detected and tracked through the changing numbers of the tip failure points in the data windows. Experiment results showed that the highest and the average recognition accuracy of the proposed model was 1 and 0.8367 with the longest and the average calculation time of 0.031 s and 0.025 s. Compared with supervised and semi-supervised machine learning algorithms, the GMM based on unsupervised machine learning model has slightly lower recognition accuracy, but much shorter calculation time, which is suitable for online automatic diagnosis of tool wear in large-scale nanomanufacturing in real time.

Analysis of the Suitability of Signal Features for Individual Sensor Types in the Diagnosis of Gradual Tool Wear in Turning

There are many items in the literature indicating that certain signal features (SFs) of cutting forces, vibrations or acoustic emission are useful for the diagnosis of tool wear in certain single experiments. There is no answer to whether these SFs are universal. The novelty of this article is an attempt to answer these questions and propose a large set of SFs related to tool wear, but without including superfluous SFs. The analysis of the usefulness of the signal properties for the state of the cutting tool in turning was carried out on a large experiment. A number of various SFs obtained for various signal analysis methods were selected for the study. It is found that no SF is always related to the tool wear, so we define many different signal characteristics that can be related to the tool wear (basic set) and automatically select those associated with it in a given machining case. To this end, the relationship between the measures and the wear of the tool was analyzed. Interrelated measures were excluded from it. The obtained results can be used to build a new generation of more effective tool wear diagnostics systems. One of the goals of the tool wear diagnosis system is to save the energy used. The results can also enable the refinement of existing algorithms that predict the energy consumption of a machine.

Recurrent neural networks with long term temporal dependencies in machine tool wear diagnosis and prognosis

Data-driven approaches for machine tool wear diagnosis and prognosis are gaining attention in the past few years. The goal of our study is to advance the adaptability, flexibility, prediction performance, and prediction horizon for online monitoring and prediction. This paper proposes the use of a recent deep learning method, based on Gated Recurrent Neural Network architecture, including Long Short Term Memory (LSTM), which try to captures long-term dependencies than regular Recurrent Neural Network method for modeling sequential data, and also the mechanism to realize the online diagnosis and prognosis and remaining useful life (RUL) prediction with indirect measurement collected during the manufacturing process. Existing models are usually tool-specific and can hardly be generalized to other scenarios such as for different tools or operating environments. Different from current methods, the proposed model requires no prior knowledge about the system and thus can be generalized to different scenarios and machine tools. With inherent memory units, the proposed model can also capture long-term dependencies while learning from sequential data such as those collected by condition monitoring sensors, which means it can be accommodated to machine tools with varying life and increase the prediction performance. To prove the validity of the proposed approach, we conducted multiple experiments on a milling machine cutting tool and applied the model for online diagnosis and RUL prediction. Without loss of generality, we incorporate a system transition function and system observation function into the neural net and trained it with signal data from a minimally intrusive vibration sensor. The experiment results showed that our LSTM-based model achieved the best overall accuracy among other methods, with a minimal Mean Square Error (MSE) for tool wear prediction and RUL prediction respectively.

A Study on the Application of Synchronized Chaotic Systems of Different Fractional Orders for Cutting Tool Wear Diagnosis and Identification

Machining refers to a variety of processes, in which a cutting tool is used to remove the unwanted material from a workpiece. Tool wear, advertently or inadvertently, occurs after long-time use. It is crucial to monitor the tool wear so that the cutting tool can deliver the best performance and meet the technological challenges nowadays. In this paper, through different fractional-order chaotic systems, i.e., Chen–Lee, Lorenz, and Sprott, extension theory is proposed to predict the tool life. The results of the three chaotic systems are compared. The centroid of the 2-D plane of dynamic errors is used as the characteristics. Four wear states are defined in accordance with different levels of surface roughness, i.e., normal, slight, moderate, and severe. The boundaries of the four states are identified according to the locations of the centroid generated with the systems of different fraction orders. The boundaries are then fed into the extension model, and the relational function calculation is performed. In this way, the identification of tool state can be easily achieved. The experiment results indicate that Chen–Lee system and the Lorenz systems exhibit the same diagnosis rate (97.375%), higher than that of the Sprott system (35.75%). It is demonstrated that the two chaotic systems are fit for use with the method proposed in this paper. It is also proven that Chen–Lee and Lorenz fractional-order master–slave chaotic systems are very effective for tool life monitoring. The robustness of diagnosis is also greatly improved.

Online Tool Condition Monitoring Based on Parsimonious Ensemble.

Existing methodologies for tool condition monitoring (TCM) still rely on batch approaches which cannot cope with a fast sampling rate of a metal cutting process. Furthermore, they require a retraining process to be completed from scratch when dealing with a new set of machining parameters. This paper presents an online TCM approach based on Parsimonious Ensemble+ (pENsemble+). The unique feature of pENsemble+ lies in its highly flexible principle where both the ensemble structure and base-classifier structure can automatically grow and shrink on the fly based on the characteristics of data streams. Moreover, the online feature selection scenario is integrated to actively sample relevant input attributes. This paper presents advancement of a newly developed ensemble learning algorithm, pENsemble, where the online active learning scenario is incorporated to reduce the operator's labeling effort. The ensemble merging scenario is proposed which allows reduction of ensemble complexity while retaining its diversity. Experimental studies utilizing two real-world manufacturing data streams: 1) metal turning and 2) 3-D-printing processes and comparisons with well-known algorithms were carried out. Furthermore, the efficacy of pENsemble+ was examined using benchmark concept drift data streams. It has been found that pENsemble+ incurs low structural complexity and results in a significant reduction of the operator's labeling effort.

The Application of GA-BP Algorithm in Prediction of Tool Wear State

In CNC shaping milling machine, the prediction of the state of tool wear has important application significance to improve productivity, reduce scrap rate and avoid security risks. In this paper, the detection and control system of disk milling cutter is set up by the current monitoring method, the input characteristic quantity and target characteristic quantity of BP neural network for tool wear diagnosis are measured, and the disk milling cutter wear condition prediction neural network is established based on the GA-BP algorithm. At last, the online prediction of milling cutter wear state is realized. The network test results show that the prediction rate of tool wear condition is more than 92.78%.

Comparison of various tool wear prediction methods during end milling of metal matrix composite

Abstract In this paper, the problem of tool wear prediction during milling of hard-to-cut metal matrix composite Duralcan™ was presented. The conducted research involved the measurements of acceleration of vibrations during milling with constant cutting conditions, and evaluation of the flank wear. Subsequently, the analysis of vibrations in time and frequency domain, as well as the correlation of the obtained measures with the tool wear values were conducted. The validation of tool wear diagnosis in relation to selected diagnostic measures was carried out with the use of one variable and two variables regression models, as well as with the application of artificial neural networks (ANN). The comparative analysis of the obtained results enable.

Particle learning in online tool wear diagnosis and prognosis

Automated Tool condition monitoring is critical in intelligent manufacturing to improve both productivity and sustainability of manufacturing operations. Estimation of tool wear in real-time for critical machining operations can improve part quality and reduce scrap rates. This paper proposes a probabilistic method based on a Particle Learning (PL) approach by building a linear system transition function whose parameters are updated through online in-process observations of the machining process. By applying PL, the method helps to avoid developing a complex closed form formulation for a specific tool wear model. It increases the robustness of the algorithm and reduces the time complexity of computation. The application of the PL approach is tested using experiments performed on a milling machine. We have demonstrated one-step and two-step look ahead tool wear state prediction using online indirect measurements obtained from vibration signals. Additionally, the study also estimates remaining useful life (RUL) of the cutting tool inserts.

Milling tool wear diagnosis by feed motor current signal using an artificial neural network

In this paper, a Multi-layer perceptron (MLP) neural network was used to predict tool wear in face milling. For this purpose, a series of experiments was conducted using a milling machine on a CK45 work piece. Tool wear was measured by an optical microscope. To improve the accuracy and reliability of the monitoring system, tool wear state was classified into five groups, namely, no wear, slight wear, normal wear, severe wear and broken tool. Experiments were conducted with the aforementioned tool wear states, and different machining conditions and data were extracted. An increase in current amplitude was observed as the tool wear increased. Furthermore, effects of parameters such as tool wear, feed, and cut depth on motor current consumption were analyzed. Considering the complexity of the wear state classification, a multi-layer neural network was used. The root mean square of motor current, feed, cut depth, and tool rpm were chosen as the input and amount of flank wear as the output of MLP. Results showed good performance of the designed tool wear monitoring system.

COMPARISON OF PERFORMANCES OF FUZZY LOGIC WITH ECHOSTATE NEURAL NETWORK FOR DIAGNOSIS AND PROGNOSIS OF SINGLE POINT TOOL WEAR ESTIMATION USING HYBRID ALUMINIUM SILICON CARBIDE METAL MATRIX COMPOSITE

In this research work, prognosis and diagnosis of tool wear for the polycrystal diamond (PCD) tool has been done by using fuzzy logic and Echostate Neural Network during machining of Al6061 metal matrix composite. Diagnosis refers to estimation of amount of tool worn out and prognosis refers to estimation of remaining tool life. The performances of fuzzy logic and ESNN with respect to diagnosis and prognosis of PCD tool wear has been compared.

Self adaptive diagnosis of tool wear with a microcontroller

Tool wear monitoring is very important for economical reasons. In this paper a new and very economical solution is presented. The idea is to use easily available microcontroller based hardware, which is very cheap due to mass production. The cheap hardware is combined together with sophisticated software. The use of regression analysis techniques together with fuzzy logic makes the system self adaptive, i.e., the system can monitor new tools automatically after a short learning period. The automatic learning period typically only lasts in the order of 5% of the total tool life time of an individual tool and thus makes the introduction of the method really simple and effective. The article focuses on the introduction and use of microcontroller based hardware but also covers and summarizes the principles behind the new approach which makes it possible to use hardware with limited capability. A more detailed description of the physical and mathematical background can be found in the given references. The proposed approach is tested with data from drilling tests.

Diagnosis of tool wear based on regression analysis and fuzzy logic

Diagnosis of tool wear based on regression analysis and fuzzy logic

SURFACE ROUGHNESS AND CUTTING TOOL-WEAR DIAGNOSIS BASED ON BAYESIAN NETWORKS

Next-generation manufacturing systems demand more intelligent features such as diagnosis, adaptation, etc. One of the main goals in machining systems is to find an appropriate trade-off among cutting tool condition, surface roughness and productivity. However, both surface roughness and cutting tool wear are impractical to measure online. This work proposes a multi-sensor system for indirect monitoring based on Bayesian Networks (BN) framework. Unlike classical modelling techniques, a important advantage of BN models are their ability to deal with the stochastic nature of the machining process. We discuss BN models based on their precision and reliability for different discretization sizes of their continuous variables. Early results show that models with high discretization exhibit a reliability of 89.5% for the surface roughness prediction and 97.3% for the cutting tool wear diagnosis. However, lower discretization presents better reliability but worse diagnosis.

The effects of progressive wear on the frequency characteristic of acoustic emission acquired during face milling

Acoustic emission (AE) provides a non-intrusive means of monitoring insert flank wear in face milling. Progressive wear tests of carbide inserts in eight-point milling of annealed En24 steel were instrumented with piezoelectric AE transducers and a non-contact optical interferometer, from which AE frequency information could be extracted. Mean AE frequency was found generally to decrease with wear in agreement with other published studies. Tool indexed measurements enabled the time evolution of the frequency content to be studied on the timescale of a single pass of the insert. The results may be explained by a simple analytical model for AE frequency associated with plastic deformation. The observed AE decay time constants following insert entry decreased with cutting speed, consistent with thermal models of the cutting process. Whereas the results of this study alone would not constitute an independent means of tool wear monitoring, they could provide a diagnosis of tool wear when supplemented with other AE measures and with knowledge of the specific cutting process.

TOOL WEAR MONITORING OF TURNING OPERATIONS BY NEURAL NETWORK AND EXPERT SYSTEM CLASSIFICATION OF A FEATURE SET GENERATED FROM MULTIPLE SENSORS

Feature extraction and decision-making is a matter of considerable interest for condition monitoring of complex phenomena with multiple sensors. In tool wear monitoring, the extraction of subtle aspects of signals from a range of transient and static events offers a special challenge for diagnostic and control systems due to the broad range of information in the signal. Features based on frequency spectra and statistical transformations of a number of sensor signals were studied in an attempt to obtain a reliable indication of the evolution of tool wear. Two neural networks and an expert system using Taylor's tool life equation were used to classify the tool wear state. Despite the complexity of the data and subsequent testing by the removal of two of the most clearly systematic features, a reproducible diagnosis of tool wear was obtained.