In modern industries, machine health monitoring systems (MHMS) have been applied wildly with the goal of realizing predictive maintenance including failures tracking, downtime reduction, and assets ...preservation. In the era of big machinery data, data-driven MHMS have achieved remarkable results in the detection of faults after the occurrence of certain failures (diagnosis) and prediction of the future working conditions and the remaining useful life (prognosis). The numerical representation for raw sensory data is the key stone for various successful MHMS. Conventional methods are the labor-extensive as they usually depend on handcrafted features, which require expert knowledge. Inspired by the success of deep learning methods that redefine representation learning from raw data, we propose local feature-based gated recurrent unit (LFGRU) networks. It is a hybrid approach that combines handcrafted feature design with automatic feature learning for machine health monitoring. First, features from windows of input time series are extracted. Then, an enhanced bidirectional GRU network is designed and applied on the generated sequence of local features to learn the representation. A supervised learning layer is finally trained to predict machine condition. Experiments on three machine health monitoring tasks: tool wear prediction, gearbox fault diagnosis, and incipient bearing fault detection verify the effectiveness and generalization of the proposed LFGRU.
In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring ...approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM) has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks(LSTMs) are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods.
In the process of metal cutting, the effective monitoring of tool wear is of great significance to ensure the machining quality of parts. Aiming at the problem of tool wear monitoring, a tool wear ...recognition and prediction method based on stack sparse self-coding network is proposed. This method can simplify the establishment process of monitoring model, monitor the tool wear according to different task requirements, and guide the tool replacement in the actual cutting process. Firstly, unsupervised K-means clustering is used to divide the tool wear stage, and the feature set is marked. Secondly, the parameters of stack sparse self-coding network layer are determined by trial, and the sensitive features that can reflect the tool wear process are obtained. Finally, the tool wear identification model of stack sparse self-encoder and the tool wear prediction model of BP neural network are established respectively, and the smoothing correction method is used to further improve the prediction accuracy. The experimental results show that the established tool wear identification and prediction model can accurately monitor the tool wear state and wear amount, and has a certain reference value for efficient tool change in the actual metal cutting process.
•A tool wear recognition and prediction method based on stack sparse self-coding network is proposed.•K-means clustering is used to divide the tool wear state, which avoids the subjective error in artificial division.•The self-coding network layer is used to encode and decode the original feature set.•The establishment process of tool wear identification and prediction model is simplified.
A low-cost Co-based alloy was employed to fabricate friction stir welding (FSW) tools to weld TA5 alloy under different welding speeds. The tool wear characteristics, tool degradation mechanisms and ...effects of tool wear behavior on the microstructure and mechanical properties of joints were investigated in detail. Results reveal that the heat input near weld root decreases with the increase of welding speed and the tool wears more extensively under lower heat input when the deterioration rates of tool sizes are considered. Furthermore, the tool wears out mainly by mechanical abrasion near pin tip, leading to a large number of tool particles in mixed regions accompanied by severe material loss. The tool wears less severely near pin root and shoulder, since the adhesion layer caused by adhesive and diffusional wear mechanisms is the main cross-sectional wear morphology, and the interlayer rich in W and Cr between adhesion layer and intact part of tool may protect the tool from serious diffusional wear.
The foreign β-stable tool compositions were introduced to the weld, reducing the transus temperature. Therefore, transformed acicular α and retained β phases were detected in contaminated zone (CZ) inside stir zone (SZ) compared with the untransformed equiaxed α grains in non-contaminated zone (NCZ). In addition, the acicular α and β phases result in much higher strength and microhardness than base material (BM).
•Friction stir welding (FSW) tools fabricated from Co-based alloy were employed to weld TA5 alloy.•Tool wear characteristics and mechanisms were investigated in detail.•Foreign β-stable tool compositions in weld resulted in phase transformation.•Transformed microstructures in contaminated zone bear much higher strength and hardness than base material.
•Established a generic tool flank wear model with adjustable coefficients.•Identified the relationship of the critical times to the adjustable coefficients in the model.•Defined a method to predicate ...tool life with the wear model.•Compared and validated milling forces per tooth obtained both from the model and the experimental data.
Tool wear is an important factor that influence machining precision and part quality in high speed milling, and it is essential to seek a convenient method to monitor and predict tool conditions. A generic wear model with adjustable coefficients is proposed and validated in this study. In this model, three wear zones of an entire tool life are divided by critical times considering the nature of different wear stages. Additionally, the intrinsic amplitude and growth frequencies in earlier and later milling stages are explicated and elaborated to determine the tool flank wear over whole milling process. The relationship between milling force against tool flank wear is studied and identified, which provides a technical foundation for online force modeling and wear monitoring. It is shown that with inclusion of the wear factor the milling force can be predicted accurately, with 98.5% agreement with the instantaneous force model. In addition, tool life can be predicted conveniently based on the wear model. Due to adjustability of coefficients in the model, it can be generalized to various machining types and conditions.
•The KPCA_IRBF technique is firstly proposed for feature fusion.•A novel tool wear assessment technique based on KPCA_IRBF and GPR is developed.•GPR performs better than ANN and SVM in prediction ...accuracy.•The KPCA_IRBF technique helps to compress and smooth the confidence interval of GPR.
To realize and accelerate the pace of intelligent manufacturing, this paper presents a novel tool wear assessment technique based on the integrated radial basis function based kernel principal component analysis (KPCA_IRBF) and Gaussian process regression (GPR) for real-timely and accurately monitoring the in-process tool wear parameters (flank wear width). The KPCA_IRBF is a kind of new nonlinear dimension-increment technique and firstly proposed for feature fusion. The tool wear predictive value and the corresponding confidence interval are both provided by utilizing the GPR model. Besides, GPR performs better than artificial neural networks (ANN) and support vector machines (SVM) in prediction accuracy since theGaussiannoises can be modeled quantitatively in the GPR model. However, the existence of noises will affect the stability of the confidence interval seriously. In this work, the proposed KPCA_IRBF technique helps to remove the noises and weaken its negative effects so as to make the confidence interval compressed greatly and more smoothed, which is conducive for monitoring the tool wear accurately. Moreover, the selection of kernel parameter in KPCA_IRBF can be easily carried out in a much larger selectable region in comparison with the conventional KPCA_RBF technique, which helps to improve the efficiency of model construction. Ten sets of cutting tests are conducted to validate the effectiveness of the presented tool wear assessment technique. The experimental results show that the in-process flank wear width of tool inserts can be monitored accurately by utilizing the presented tool wear assessment technique which is robust under a variety of cutting conditions. This study lays the foundation for tool wear monitoring in real industrial settings.
Tool wear affects tool life, dimensions, etc. However, tool wear mechanism was mainly studied by the relevant references in the sharp wear stage, and tool wear morphology and mechanism were not ...completely understood in the initial and steady wear stage. Tool wear investigation of coated carbide tool is carried out during turning GH4169 in dry cutting. Tool wear microscopic morphology, tool wear curve, tool cutting force and tool wear mechanism are studied during turning GH4169 in the initial, steady and sharp wear stage. Tool wear mechanism in the sharp wear stage is further investigated by SEM, EDS, XPS and XRD. Doing so helps to test and improve the quality of the tool coating and substrate material, helps to gain a deep understanding of the difficult-to-machine characteristics of GH4169, and helps to guarantee the dimensional accuracy and surface quality of the workpiece. Results show that serious abrasive wear, tool nose wear and adhesive wear occurred in the whole wear stage. The tool wear rate of turning superalloy GH4169 is much faster, the cutting force increases, the tool substrate material was worn seriously. The main tool wear mechanisms are abrasive wear, adhesive wear, oxidation wear and diffusion wear. Severe abrasive wear occurred between the large amount of hard abrasive carbides in the workpiece material and the tool rake and flank faces. Ni, Fe, Cr, etc are mainly distributed in the relevant wear areas. WO3, Co3O4, Ni2O3, Fe2O3, etc indicate that oxidation wear occurred, Ni, Fe, Cr, Nb and Mo are detected across the cross-section, which means that diffusion wear has occurred.
•Abrasive wear and adhesive wear are discovered in the initial and steady wear stage.•Tool wear curve and cutting force are obtained during tool wear process.•Oxides of W, Co, Ti, Al, Ni, Fe and Cr are found by EDS, XPS and XRD.•Diffusion wear is observed across the cross-section by SEM and EDS.
Additive manufacturing (AM) is chosen for its ability to streamline production processes and design freedom. This reduces material waste, enables rapid prototyping, and facilitates intricate ...geometries, ultimately offering cost-effective and customizable solutions for manufacturing complex components in diverse industries. Overlapping melting trajectories result in a low-quality surface (Ra=∼13.34 µm) in the laser metal deposition (LMD) of the Ti64 alloy. Therefore, post-processing is often essential for AMed parts for engineering applications. Milling trials were conducted on AMed specimens under four environmental conditions: dry, flood, minimum quantity lubrication (MQL), and cryogenic medium. The machinability was evaluated in terms of the cutting temperature, machined surface roughness, tool wear, chip morphology, and microhardness. The flank wear under cryogenic CO2 condition is 52.78–54.29 % lower than dry condition, 33.86–36.24 % lower than flood cutting, and 23.64–26.86 % lower than MQL. The outcomes show that cryogenic cooling augments the tool life and the surface integrity of milling LMD parts. Moreover, the hardness under cryogenic CO2 was higher, indicating dimensional stability and maintenance of shape integrity under applied loads.
Tool condition monitoring (TCM) has become essential to achieve high-quality machining as well as cost-effective production. Identification of the cutting tool state during machining before it ...reaches its failure stage is critical. This paper presents a novel big data approach for tool wear classification based on signal imaging and deep learning. By combining these two techniques, the approach is able to work with the raw data directly, avoiding the use of statistical pre-processing or filter methods. This aspect is fundamental when dealing with large amounts of data that hold complex evolving features. The imaging process serves as an encoding procedure of the sensor data, meaning that the original time series can be re-created from the image without loss of information. By using an off-the-shelf deep learning implementation, the manual selection of features is avoided, thus making this novel approach more general and suitable when dealing with large datasets. The experimental results have revealed that deep learning is able to identify intrinsic features of sensory raw data, achieving in some cases a classification accuracy above 90%.
The present study investigates the impact of micro-EDM based texturing techniques where various patterns are fabricated on the rake faces of turning inserts with and without adding WS2 nanoparticles ...in the dielectric medium. It was observed from experimental analysis that the nanoparticle-assisted groove textured tools recorded the highest reduction in average flank wear widths, tool chip contact lengths, and surface roughness values by (40–59%), (11–19%) and (34–46%) respectively while machining Ti6Al4V under dry lubrication conditions. At the same time, WS2-assisted dimple textured tools recorded the maximum decrease in chip curl diameter values by (38–55%) compared to the non-textured tools.
Display omitted
•WS2 incorporated dielectric was used for fabricating tool textures by micro-EDM process.•Surface alloyed nanoparticles facilitate nano-lubricating effects across the textures.•Maximum decrease in flank wear widths and tool chip contact lengths were 59% and 19%, respectively.•Highest reduction in roughness and curl diameter values were 46% and 55%, respectively.