Figure - available from: The International Journal of Advanced Manufacturing Technology
This content is subject to copyright. Terms and conditions apply.
![Predicted RUL of C4 in reference [22]](publication/340994045/figure/fig4/AS:885523392524333@1588136637542/Predicted-RUL-of-C4-in-reference-22.png)
Source publication
![Predicted RUL of C4 in reference [22]](publication/340994045/figure/fig4/AS:885523392524333@1588136637542/Predicted-RUL-of-C4-in-reference-22_Q320.jpg)
Remaining useful life prediction is essential for cutting tool utilization evaluation and replacement decision-making. However, it is very difficult to build a mechanism model for the time-varying and non-linear cutting tool wear and life decreasing process. Based on big samples, artificial intelligence–based models have weak interpretability and u...
Citations
... Nevertheless, nonlinearity is prevalent in practical applications such as bearings, turbine engines, and fatigue cracks. This issue is addressed in [28,32,47], which develop a nonlinear diffusion model from which a time-space transformation is used to approximate the RUL PDF. ...
... Upon reviewing the extant research literature, it becomes evident that while some studies have attempted to resolve the strong Markovianity with uncertainty problem, each of [13,25,33,36,41] only focuses on the case with linear degeneracy. [6,12,28,32,39,42,46,47] only focuses with the nonlinear degradation case. A comprehensive stochastic degradation model that addresses three-source uncertainty and partially mitigates Markovianity has yet to be proposed by any researcher. ...
Forecasting the remaining useful life (RUL) is a crucial aspect of prognostics and health management (PHM), which has garnered significant attention in academic and industrial domains in recent decades. The accurate prediction of RUL relies on the creation of an appropriate degradation model for the system. In this paper, a general representation of diffusion process models with three sources of uncertainty for RUL estimation is constructed. According to time-space transformation, the analytic equations that approximate the RUL probability distribution function (PDF) are inferred. The results demonstrate that the proposed model is more general, covering several existing simplified cases. The parameters of the model are then calculated utilizing an adaptive technique based on the Kalman filter and expectation maximization with Rauch-Tung-Striebel (KF-EM-RTS). KF-EM-RTS can adaptively estimate and update unknown parameters, overcoming the limits of strong Markovian nature of diffusion model. Linear and nonlinear degradation datasets from real working environments are used to validate the proposed model. The experiments indicate that the proposed model can achieve accurate RUL estimation results.
... At any moment t k during the life cycle, the stochastic parameter a of the degradation model can be estimated from all the observed data y 1:k = {y 1 , y 2 , · · · , y n } before t k . According to the concept of Bayesian updating [25], the updated value of the stochastic parameter a of the degradation model of the performance of the rail circuit equipment at the moment t k is: ...
... Due to the nonlinearity of the drift coefficients, it is often difficult to derive an exact solution for the lifetime T probability density. In this paper, we adopt the approach in the literature [25], where the PDF of the amount of performance degradation {Y(t), t ⩾ 0} reaching or exceeding the failure threshold w is, under the condition that the stochastic parameters are determined: ...
... Step 5: Online remaining life prediction. The PDF of the residual life of the in-service device at any moment t k can be obtained by substituting the parameter estimation results obtained in steps 3 and 4 into equation (25). ...
Predicting the remaining useful life (RUL) of track circuits is essential to ensure the safe and reliable operation of high-speed railways. In response to the challenges faced by current machine-learning-based RUL prediction methods, which struggle to represent the uncertainty in the probability distribution of RUL predictions, this paper suggests a hybrid-driven method for estimating remaining life. Firstly, the track circuit Health Index is constructed by feature dimensionality reduction and fusion of the original multivariate monitoring data through kernel principal component analysis and Autoencoder; Secondly, the degraded state of the rail circuit is modelled using a nonlinear Wiener degradation model. Finally, the principle of first hitting time is used to derive the probability density function of the anticipated RUL. The efficacy and superiority of the approach presented in this paper are validated by experimental research on the track circuit monitoring dataset. The method enhances forecast accuracy and reduces prediction uncertainty, offering robust technical support for track circuit maintenance decision-making.
... In contrast, artificial intelligence-based models have some advantages in bearing RUL prediction. These methods analyze large amounts of bearing operational data and utilize machine learning (ML), deep learning, and other technologies to learn the complex features and underlying patterns of bearings without relying on detailed physical rules and model assumptions [9]. Therefore, they offer higher flexibility, adaptability to different equipment and environments, higher prediction accuracy, and robustness while reducing the dependence on expert knowledge [10,11]. ...
Stochastic process-based models are extensively utilized in health assessments and Remaining Useful Life (RUL) predictions of bearings. Nevertheless, bearings in actual operation undergo multiple degradation stages, each characterized by a unique trend of degradation. The application of a singular stochastic process for RUL prediction falls short of achieving optimal performance. Consequently, this paper introduces a multi-stage Wiener process-based approach for the prediction of bearings’ RUL. Initially, to address the challenge of imbalanced sample sizes across different degradation stages of bearings, an ensemble learning-based neural network, enhanced by ARIMA Residual Anomaly Detection for identifying bearing degradation stages, is proposed. Subsequently, considering the temporal, unit-to-unit, and nonlinear variabilities of the degradation process at each stage, a Wiener process-based multi-stage degradation model for bearings is developed. A method for parameter estimation and updating, utilizing Kalman filtering and Maximum Likelihood Estimation (K-M), is introduced. Finally, the proposed model is validated using both simulated data and the XJTU-SY bearing dataset. Experimental results from three RUL predictions show that the proposed method outperforms the benchmark model with root mean square error values of 3.61, 2.92 and 7.24, respectively, affirming that the proposed model can precisely classify equipment degradation stages and predict RUL with high accuracy and stability.
... He et al. [40] developed a cross-domain adaptation network with an attention mechanism to predict tool wear during the milling of AISI 1045 steel. Sun et al. [41] proposed a non-linear Wiener-based model for predicting cutting tool wear and RUL. Liu et al. [42] developed an Attention-LSTM based method for milling tool wear prediction. ...
This study proposes a cutting tool condition monitoring platform for CNC machines used in metal part manufacturing to estimate tool wear values. The PHM 2010 Dataset, along with operational and situational data from CNC machines and sensors, were analyzed using artificial intelligence algorithms to support total equipment performance with current tool wear values. The innovation lies in developing an artificial intelligence application that incorporates the Federated Learning method with artificial neural networks. This application is among the first to monitor machine cutting tools using Federated Learning. An efficient and accurate predictive tool wear estimation method is presented through the application of Federated Learning with Long-Short Term Memory models. This novel approach holds great potential for industrial applications, optimizing CNC cutting processes and reducing operational costs through enhanced tool wear prediction.
... Common statistical methods include Wiener process models, random parameter models, and Markov models [6][7][8]. For instance, Sun et al. [9] utilized the Wiener process to construct a tool RUL prediction model and updated its parameters through historical and real-time data. Liu et al. [7] proposed an improved implicit semi-Markov model to describe the relationship between tool performance degradation and time to estimate the degradation state and RUL distribution of the tool. ...
Previous studies have primarily focused on predicting the remaining useful life (RUL) of tools as an independent process. However, the RUL of a tool is closely related to its wear stage. In light of this, a multi-task joint learning model based on a transformer encoder and customized gate control (TECGC) is proposed for simultaneous prediction of tool RUL and tool wear stages. Specifically, the transformer encoder is employed as the backbone of the TECGC model for extracting shared features from the original data. The customized gate control (CGC) is utilized to extract task-specific features relevant to tool RUL prediction and tool wear stage and shared features. Finally, by integrating these components, the tool RUL and the tool wear stage can be predicted simultaneously by the TECGC model. In addition, a dynamic adaptive multi-task learning loss function is proposed for the model’s training to enhance its calculation efficiency. This approach avoids unsatisfactory prediction performance of the model caused by unreasonable selection of trade-off parameters of the loss function. The effectiveness of the TECGC model is evaluated using the PHM2010 dataset. The results demonstrate its capability to accurately predict tool RUL and tool wear stages.
... The statistical data-driven method effectively deals with the uncertainty in RUL prediction by describing the stochastic process of tool wear evolution as probability distributions [28,29]. For example, the tool RUL prediction model based on the nonlinear Wiener process not only considers the measurement error, but also uses the confidence interval to quantify the uncertainty of the prediction results, which provides effective guidance for tool replacement [30]. ...
... LetX(t)denote the tool wear VB at time t, according to the nonlinear Wiener process [30], (10) whereX(0)is the initial value of tool wear. Without losing generality, takeX(0) = 0. ...
... However, the tool wear size cannot be accurately measured in the actual cutting process, and it can only be indirectly characterized by sensor monitoring data, that is [30], ...
Accurately predicting the tool remaining useful life (RUL) is critical for maximizing tool utilization and saving machining costs. Various physical model-based or data-driven prediction methods have been developed and successfully applied in different machining operations. However, many uncertain factors affect tool RUL during the cutting process, making it challenging to create a precise physical model to characterize the degradation of tool performance. The success of the purely data-driven technique depends on the amount and quality of the training samples, it does not consider the physical law of tool wear, and the interpretability of the prediction results is poor. This paper presents a data-model linkage approach for tool RUL prediction based on deep feature fusion and Wiener process to address the above limitations. A convolutional stacked bidirectional long short-term memory network with time-space attention mechanism (CSBLSTM-TSAM) is developed in the data-driven module to fuse the multi-sensor signals collected during the cutting process and then obtain the mapping relationship between signal features and tool wear values. In the physical modeling module, a three-stage tool RUL prediction model based on the nonlinear Wiener process is established by considering the evolution law of different wear stages and multi-layer uncertainty, and the corresponding probability density function is derived. The real-time estimated tool wear of the data-driven module is used as the observed value of the physical model, and the model parameters are dynamically updated by the weight-optimized particle filter (WOPF) algorithm under a Bayesian framework, thereby realizing the data-model linkage tool RUL prediction. Milling experiments demonstrate that the proposed method not only improves RUL prediction accuracy, but also has good generalization ability and robustness for prediction tasks under different working conditions.
... the aforementioned uncertainties, combined with measurement errors in actual machining, the degradation path of the cutting tool is often not strictly monotonous. Sun et al. [26] modeled the tool wear process of a cutting tool with the Wiener process, considering the measurement variability, and then estimated the RUL of cutting tools. The gamma and inverse Gaussian processes require the degradation data to be strictly monotonic. ...
Cutting tools are one type of critical component of modern computer numerical control (CNC) machining systems. They wear out continuously during the machining process until they fail, and cutting tool failure can lead to the collapse of the entire system and even cause substantial losses. Therefore, it is of great importance to study the method for tool wear prediction. A new model for wear prediction of cutting tools is established based on a multi-stage Wiener process, where the degradation rates of cutting tools are considered to change in three stages based on the typical cutting tool wear curve model. Firstly, the degradation processes of cutting tools are divided into three stages. Secondly, the parameter estimation for each stage of the degradation processes of cutting tools is completed, respectively, by utilizing the EM (expectation–maximization) algorithm. Then, the wear of cutting tools is predicted, and the reliability of cutting tools is analyzed by using a numerical integration simulation method based on the Monte Carlo algorithm. Finally, the proposed model is illustrated and verified via the flank wear data of cutting tools, and the prediction accuracy is measured by mean squared error (MSE) and the coefficient of determination (R2). The prediction results show that the proposed model enables us to make more economical maintenance by delaying the tool replacement time with fewer degradation data. Compared to the traditional methods based on machine learning (ML), the proposed model can complete the wear prediction and reliability analysis more accurately.
... McParland et al. proposed a tool-wear prediction method for each force direction, based on a nonparametric Bayesian hierarchical Gaussian process [58]. Sun et al. developed a nonlinear Wiener process-based tool-wear prediction method on the basis of the Bayesian approach [59]. Li et al. utilized the Bayesian approach with various ML algorithms in a hybrid manner for tool condition monitoring [60]. ...
Tool wear negatively affects machined surfaces and causes surface cracking, therefore increasing manufacturing costs and degrading product quality. Titanium alloys, which are widely used because of their desirable mechanical properties, have problems associated with tool wear due to poor thermal properties, such as specific heat capacity and thermal conductivity. Therefore, the accurate prediction of tool wear is necessary during the titanium alloy end-milling process to improve product quality and ensure reliability for corrective decisions like tool replacement. To this end, uncertainty-aware tool-wear prediction should be performed. In this study, a deep learning-based tool-wear prediction model based on a Bayesian approach was proposed. First, a convolutional neural network (CNN)-based architecture that integrates multiscale information extracted from raw sensor measurement data, termed deep multiscale CNN (DMSCNN), was proposed. It used different-sized convolutional kernels in parallel to enable various receptive field sizes suitable for machining processes. Second, based on a Bayesian learning approach, DMSCNN was transformed into a probabilistic model that produced a predictive distribution for estimated tool wear. In particular, a variational inference was applied to DMSCNN parameters to provide uncertainty awareness. Experiments were conducted with data collected from an actual end-milling process under three different conditions. The results proved the effectiveness of the proposed DMSCNN for tool-wear prediction. Bayesian DMSCNN showed promising results, as it outperformed existing comparative deterministic methods as well as probabilistic methods for tool-wear prediction. The proposed method is expected to be effectively applied in smart manufacturing as well as other machining processes that require data-driven digital decisions.
... In fact, several research works have been done on the estimation of tool RUL based on stochastic processes [19][20][21]. For example, Sun et al. [19] use Wiener process to model the tool wear process to solve the problem of nonlinear cutting tool wear and RUL prediction. ...
... In fact, several research works have been done on the estimation of tool RUL based on stochastic processes [19][20][21]. For example, Sun et al. [19] use Wiener process to model the tool wear process to solve the problem of nonlinear cutting tool wear and RUL prediction. However, as the tool wear processes are generally monotonic processes with non-negative increments, Wiener process is not rigorous for modeling tool wear process. ...
The wear of cutting tools can lead to tool failures, and thus accurate remaining useful life (RUL) prediction for tools is important. Meanwhile, the wear process of tools from a same population usually present heterogeneous patterns. Therefore, this paper proposes a RUL prediction method for heterogeneous wearing cutting tools based on Inverse Gaussian (IG) process and Bayesian inference. The IG process is used to model the tool wear process. To characterize the heterogeneity among the tool wear processes, the reciprocal of tool wear rate is assumed to follow the truncated normal distribution, and its posterior distribution can be dynamically estimated based on the Bayesian method using online tool wear data. On this basis, the closed expression for the probability density function (PDF) of the tool RUL is derived. Finally, a case study is conducted to demonstrate that the proposed method can accurately predict the RUL of heterogeneous wearing tools.
... They are considered as one of the potential replacements for the large traditional CNC machine tools [3]. However, the rigidity of 6-dof industrial robots is significantly less than that of machine tools [4], which will cause self-excited vibration or even chattering more easily [5]. Severe chatter will increase the tool wear rate and decrease the surface quality of workpieces, which means enormous losses in both efficiency and quality [6]. ...
Industrial robots have great potential to machine large parts. However, the vibration or chattering induced by their inherent weak stiffness can easily damage or break the tool. Therefore, this paper introduced a novel tool wear monitoring method for robotic milling. Firstly, a multi-domain features extraction method was proposed to obtain local features. Then, a novel deep learning model with two parallel a parallel bidirectional long short-term memory networks (BiLSTM) (Vibration branch and Cutting Force branch) was introduced to fuse the multi-domain features and learn the time dependence patterns. The proposed method was verified on both based on robot milling Al7050-T7451 workpiece dataset and the 2010 prognostics health management (PHM) dataset. The experiment results showed that the proposed method acquired an excellent predication accuracy and strong adaptability to the change of cutting parameters. The results show that the average root mean square error (RMSE) for wear recognition based on the robot milling dataset is 10.61, with an average mean absolute error (MAE) of 9.104. The average RMSE for wear recognition based on the computerized numerical control (CNC) milling dataset is 7.83, with an average MAE of 6.62.
