Search

The digital twin (DT) for application development in specific fields or specific factors has emerged as a foundational framework for intelligent manufacturing. The increasing demand for customized and diverse production poses enormous challenges for the effective evaluation of production line processing capability (PLPC). Therefore, this paper presents a multidimensional information model-driven digital twin specifically designed for PLPC evaluation. The information model describes the characteristics of PLPC in the structural, physical, and kinematic dimensions, and it provides multidimensional information for constructing a comprehensive evaluation model in combination with the fuzzy Delphi method. An information model-driven digital twin enables more efficient extraction of processing capabilities relevant to product manufacturing and provides a digital and visual assessment of PLPC. In the case of the commutator processing industry, this paper highlights the feasibility of the digital twin model and its potential impact on forward-looking guidance for product process planning. [ABSTRACT FROM AUTHOR]

The percent global glomerulosclerosis is a key factor in determining the outcome of renal transfer surgery. At present, the rate is typically computed by pathologists, which is labour intensive and nonstandardized. With the development of Deep Learning (DL), DL-based segmentation models can be used to better identify and segment normal and sclerosed glomeruli. Based on this, we can better quantify percent global glomerulosclerosis to reduce the discard rate of donor kidneys. We used 51 whole slide images (WSIs) from different institutions that are publicly available on the internet. However, the number of sclerosed glomeruli is much smaller than that of normal glomeruli in different WSIs, which can reduce the effectiveness of Deep Learning. For better sclerosed glomerular identification and segmentation performance, we modified and trained a GAN (generative adversarial network)-based image inpainting model to obtain more synthetic sclerosed glomeruli. Our proposed inpainting method achieved an average SSIM (Structural Similarity) of 0.8086 and an average PSNR (Peak Signal-to-Noise Ratio) of 22.8943 dB in the area of generated sclerosed glomeruli. We obtained sclerosed glomerular segmentation performance improvement by adding synthetic sclerosed glomerular images and achieved the best Dice of glomerular segmentation in different test sets based on the modified Unet model. [ABSTRACT FROM AUTHOR]

Chatter is a kind of self-excited vibration, which always has a negative impact on production efficiency. In this paper, a novel online chatter detection method for milling processes is proposed. In this method, firstly, the spindle revolution period component is extracted by angular synchronous averaging (ASA) the vibration signals generated in different cutting conditions. Then, the residual part related to chatter is calculated by subtracting the periodic component. Subsequently, the filtered signal is decomposed into a set of intrinsic mode functions (IMFs) using variational mode decomposition (VMD) to obtain chatter information. Finally, the multiscale permutation entropy (MPE) and multiscale power spectral entropy (MPSE) of the selected IMFs are calculated, and Laplacian score (LS) for feature selection is applied to select the optimal sensitive scale features with generalization. Online chatter detection based on selected sensitive scale features by splitting signal up into overlapping frames in milling process. The analysis results show that the proposed method can effectively detect the chatter under stable cutting conditions and variable cutting conditions. [ABSTRACT FROM AUTHOR]

In ultra-precision flying cutting (UPFC), a vibration is a unique dynamic response due to periodic intermittent excitation of cutting forces, which has a significant impact on surface generation. In UPFC, cutting forces act on the machine tool system intermittently and periodically, which may cause a self-excited vibration. This self-excited vibration will cause chatter, which maybe occurs during machining operations and even catastrophically degrades surface quality and limits productivity. This study has been motivated by the fact that chatter occurrence is generally in relation to the tool wear, which has seldom been investigated comprehensively in literature. In this paper, a chatter model for UPFC that can account for the effects of tool wear and process damping was presented. A number of experiments with different machining conditions were conducted to investigate the effect of the tool wear on the chatter stability. These experiments proved that the stability lobe is closely related to tool wear and with the tool wear increase, which increases the tendency for chatter in UPFC. Finally, it was found that increasing the tool clearance angle and reducing the spindle speed can improve the stability limit. [ABSTRACT FROM AUTHOR]

During the testing and sorting of LED chips, traditional methods do not exclude the polycrystalline and fragmentary LED chips from the normal chips well. The purpose of this paper is to propose a new algorithm to solve this problem. The algorithm consists of three steps. Firstly, present a simple but efficient image segmentation method to get blobs. Secondly, analyze the blobs to exclude abnormal blobs and predict the pose (position and orientation) of the potential object based on the pose of the minimum enclosing rectangle (MER) of each remained blob. Finally, according to the predicted poses, locate the LED chips precisely in the originally captured image based on gradient orientation features. Experiments show that the algorithm is not only robust to illumination variation but also can locate the LED chips and exclude the polycrystalline and fragmentary chips efficiently. [ABSTRACT FROM AUTHOR]

The dynamics of the machine tool structure are significant in high-precision machining and are meaningful to be evaluated. This paper proposes a new approach based on the modal mass distribution matrix to evaluate the dynamics and identify the weak components of machine tool structure and then to investigate the various components' effects on the machining process in different frequency bands. First, the approach is developed and verified by a designed mass-spring model whose weak components are known. Then, the proposed approach is used to identify the weak components of a machine tool structure whose modal parameters are obtained by experimental modal analysis. The result shows that the same component presents different weakness levels at different modes and that the various components of the structure present different weakness levels at the same mode. Finally, a cutting experiment is then conducted to verify the identification result. The result meets the former weak components' identification result well. [ABSTRACT FROM AUTHOR]

Improving production efficiency while ensuring product surface quality is a constant focus of manufacturers. Cutting parameter optimization is an important technique for ensuring high-efficiency and high-quality production. In this paper, a novel method for cutting parameter optimization that integrates multi-agent reinforcement learning with a dual-drive virtual machining environment is proposed. First, a feature extraction, fusion and generation model for cutting simulation and experimental data is proposed to solve the problem of incomplete data acquisition in the production process. Second, a Markov decision model for optimizing cutting parameters is defined, and a virtual machining environment driven by both simulation and experimental data is constructed. Third, a novel multi-agent reinforcement learning method called Q-MIX-MATD3, in which a twin delay deep deterministic policy gradient, value function decomposition and a teacher model are combined, is proposed to explore the cutting parameter optimization policy by interacting with the virtual machining environment. Finally, the proposed method is verified on a commutator production line. Moreover, the results show that the accuracy of the virtual machining environment driven by both simulation and experiment increases by more than 5 %, response efficiency increases by 31 %, and Q-MIX-MATD3-based cutting parameter optimization method reduces time cost by 98 % and achieves the optimization effect of the classical optimization method. [ABSTRACT FROM AUTHOR]

The production requirements of multi-variety and high-quality products pose significant challenges for implementing intelligent production lines that integrate process sensing, adaptive processing, and precise decision-making. Digital twin is the key enabling technology for intelligent production lines, but it lacks the perception of multidimensional process information to enable adaptive production. Thus, this paper proposes the adaptive digital twin motivated by a knowledge model with process information interactions. First, the process information related to product quality is located, and the process information is digitally modeled to implement the virtual-real mapping. Second, multidimensional feature extraction and fusion of process information digital model are performed to form adaptive adjustment capabilities for multi-variety production. Finally, the formal modeling of the adaptive adjustment capability enables the construction of the knowledge model that drives the adaptive digital twin. In adaptive digital twin, the virtual and real mapping of process information facilitates the knowledge model to continuously update the domain knowledge, which enables the adaptive decision-making ability to dynamically adapt to different processing requirements in the physical model. As a fusion technique developed in intelligent production lines, the modeling of adaptive digital twin has been well applied and validated in commutator finishing lines. [ABSTRACT FROM AUTHOR]

• Uncertainty quantification based on Bayesian inference for SLDs was proposed. • FRFs of the tool tip during the cutting operation was considered as the prior distributions. • An advanced Morris method was used to select the most influential parameters. • An improved Ensemble MCMC algorithm was used to infer posterior distributions. To predict the stability boundary of cutting operation, it is necessary to establish process force model and dynamic mechanical behavior model. Uncertainty of model parameters may lead to significant differences between predicted and measured stability boundary. In this paper, a novel method for determining boundary of stability in milling, which performs the stability analysis on an uncertain dynamic milling model, is presented. Firstly, the input parameters of milling stability prediction model are considered as random variables. Subsequently, sensitivity analysis is used to determine the most influential parameters, the posterior distributions of all influential parameters are estimated using a Bayesian inference framework, which is built based on an improved Ensemble Markov Chain Monte Carlo (IGWMCMC) algorithm. Compared with the traditional method, IGWMCMC is not affected by affine transformations of space, which can achieve much better convergence on badly scaled problems and the computational costs are cheaper. Finally, the posterior distributions of uncertainties calculated using Bayesian inference are propagated through the computational model. The experimental results verify the reliability of the calculated boundaries of stability lobe diagrams. [ABSTRACT FROM AUTHOR]

• Two novel chatter indicators are employed as chatter detection indicators. • Angular synchronous averaging method is used to preprocess milling signals. • Gradient Tree Boostingis applied to diagnosis of the chatter severity levels. • A relative threshold is adopted under different cutting conditions. In the milling process, chatter, which results in poor surface quality, dimensional errors, reduced cutter and machine life, is one of the main limitations on performance. In this paper, a novel method of online chatter detection for milling processes is developed. In this method, first, the spindle revolution period component is obtained via angular synchronous averaging (ASA). Then, the residual part related to chatter information is calculated by subtracting the periodic component. Secondly, the multiscale permutation entropy (MPE) and multiscale power spectral entropy (MPSE) of the residual part are calculated, and the Laplacian score (LS) for feature selection is applied to select the optimal sensitive scale features with generalization. Online chatter detection that is based on selected sensitive scale features by splitting signal up into (overlapping) frames in milling process. Finally, a trained gradient tree boosting (GTB) can be used to intelligent diagnosis of the chatter severity level. The analysis results show that the proposed method can effectively detect the onset of chatter under stable cutting conditions and variable cutting conditions, which is simpler and more robust than the existing methods. [ABSTRACT FROM AUTHOR]

Chatter is a common state in milling and turning, which will reduce the machining quality of parts. For taking adequate measures to avoid chatter, chatter detection is necessary. However, chatter recognition still has many difficulties for both turning and milling. Due to the material removal effect, the chatter frequency will change. The existing frequency band extraction methods, such as ensemble empirical mode decomposition (EEMD) and wavelet packet transform, can not fully reflect the chatter information. As a result, a novel online chatter recognition method is proposed based on spectrum characteristics, which can be applied to the chatter recognition for both turning and milling under the combination of multiple cutting parameters black simultaneously. Firstly, we carried out the hammering experiment to obtain the frequency response function and modal frequency of the machining system before and after machining. The signal distribution characteristics of turning and milling signals are analyzed. Four features sensitive to chatter are extracted, including spectral standard deviation, frequency spectral expectation (FSE), spectral skewness, and relative power spectral entropy (RPE). Taking these features as inputs, a chatter recognition model is established based on an extreme gradient boosting (XGBoost) algorithm. Finally, we conducted the turning and milling tests. The experimental results show that the proposed chatter recognition model can be effective under different cutting parameters for turning and milling. Besides, results also show the chatter recognition model has extraterritorial applicability. [ABSTRACT FROM AUTHOR]

The tool tip vibration measurement has a great significance for online surface topography prediction and active vibration control. Many measurement methods have been developed. However, most of these methods are difficult to be applied in actual machining process for the following problems: the chips and cutting fluid will cause damage to the sensor or distort its measurement results and the sensor must be installed again when replacing the cutting tool. In order to overcome the above problems, this paper proposes an indirect measurement method: the vibration of the tool tip is obtained from the vibration of the measurement point on the turret. The relationship between the tool tip vibration and the turret measurement point vibration is obtained through impact tests. The vibration of the measurement point on the turret is measured via an accelerometer, which is easy to install. The measurement point is so far away from the cutting area and chip evacuation zone that the accelerometer and its measurement results will not be affected by the chips and cutting fluid. The accuracy of the measurement method is checked by comparing the calculated tool tip vibration calculated from the vibration of the turret measurement point to the directly measured results, which is measured via an accelerometer installed below the tool tip. The comparison results show that the calculated tool tip vibration at main frequencies as well as low frequencies has a high accuracy. Moreover, the effectiveness of the measurement method is verified through machined surface profile. [ABSTRACT FROM AUTHOR]

During a long-term structural health monitoring (SHM), large-scale machine tool structural response observed from various sensors show obvious big data characteristics. However, serious "data island" issues existing in traditional SHM inevitably limit the efficiencies of sensor data analysis. Besides, most existing identification methods for these diverse and complex signal data are manual methods, which are extremely time-consuming and inefficient. In this paper, a novel method based on knowledge graph (KG) was proposed to deal with the fine-grained domain knowledge modeling and multi-source sensor data integration problems in the field of machine tool SHM. With the help of KG-based querying and reasoning, it is more intelligent and convenient to retrieve and analyze sensor data. To verify the effectiveness of the proposed method, a long-term condition monitoring experiment was conducted on a CNC machine tool in an automobile factory. The dynamic properties of the machine tool structure were automatically identified based on KG, and a condition monitoring indicator based on the similarity of dynamic properties was applied to monitor the health condition of the machine tool. The final result showed the effectiveness of the KG for health monitoring of the machine tool structure. [ABSTRACT FROM AUTHOR]

A high-speed reciprocating operating mechanism with fast running and frequent stopping produces a certain vibration due to inertia. The inherent vibration of this mechanism becomes a key factor affecting positioning accuracy and time. However, the existing vibration identification method is suitable only for static or low-speed structure operations. Therefore, a method of identification for operational modal parameters based on strain response is proposed. This method combines the strain mode with the operational modal analysis method, both of which are verified under the static and operational states, respectively. First, the theoretical background of the identification method is derived. Next, the proposed approach is used to identify the displacement mode shapes and the strain mode shapes of the beam structure with modal parameters that are obtained by experimental modal analysis. These results show that the beam structure presents different displacement mode shapes and strain mode shapes under different constraints. Finally, the displacement mode shapes of the sorting arm are obtained by the method under operation. The recognition results are compared with the computational modal analysis, and the two mode shapes are found to be highly consistent, which verifies that the method is equally reliable during operation. This method expands the application scope of the classic experimental modal analysis and reduces the error because of the additional mass of the actual sensor. [ABSTRACT FROM AUTHOR]

• Assembly error transferred to carriage of a translational axis. • Volumetric error of a horizontal machine tool linked with carriage. • Combined error sensitivity for effects of assembly geometric error. • Decomposition and measurement on translational axis as base, slider and carriage. The geometric errors of a translational axis are important factors influencing the volumetric error of machine tools. Error relationship in the assembly process of a translational axis quantitatively remains an open problem. In the paper, the slide guideway, forming the translational axis, has been decomposed into three key parts as the base, slider and carriage. New error transfer relationship model has been proposed in the assembly process. Volumetric error model of the horizontal machine tool is established and influence of the assembly error parameter on the volumetric error is analyzed with the two error models. Measurement experiments for the slide guideway has been carried out and the error transfer model has been verified. The proposed error transfer relationship model, as well as the error effects analysis method, provides important theoretical guide basis to optimize manufacture and assembly of a translational axis in a scientific and reasonable way. [ABSTRACT FROM AUTHOR]

• An innovative partly explainable deep learning model has been proposed for tool wear intelligent monitoring. • The proposed Conv-PhyFormer model is a novel model driven by both physical and data. • The embedded hard physical constraint and soft physical constraint in the model make the model partially interpretable and credible. • The proposed model shows a significantly superior high prediction accuracy and robustness. • The proposed model has superior ability to learn global and local sensitive tool wear features. With the trend of lightweight in the field of intelligent electric vehicles and 3C, the demand for high precision machining of aluminum alloy parts is growing. And tool condition monitoring (TCM) is very important for quality control of parts, so intelligent high-accuracy wear prediction of aluminum alloy high precision machining tools has great industrial application value at present and in the future. This paper presents a novel TCM model (Conv-PhyFormer) of Transformer with physics informed. The model has excellent ability to capture short-term and long-term dependencies from nonlinear cutting time series data when there are few training samples. The embedded hard physical constraint and soft physical constraint in the model make the model partially interpretable. Soft physical constraint in the form of one-dimensional causal convolution can help the proposed model better learn the local context. Hard physical constraint in the form of the mathematical equation representing cutting physical knowledge are embedded, thus the model does not need to learn this knowledge from time series data from scratch. A large number of analysis results of aluminum alloy machining experimental data show that the proposed Conv-PhyFormer has significantly superior prediction accuracy and robustness compared with the current three popular deep learning models for TCM. Embedded soft and hard physical constraints can significantly reduce the training epochs of Transformer prediction model. [ABSTRACT FROM AUTHOR]

Unlabeled time series signals collected during manufacturing typically have low value density and must be labeled and intercepted according to the specific application scenario. During variable-parameter milling, particularly high-precision machining, machining parameters vary, and associated discrepancies in vibration signals are small. In this scenario, signal features that are extracted by hand or via deep learning methods cannot typically distinguish machining states via classification models. To solve this problem, a sequence labeling model developed using a stacked bidirectional long short-term memory network with a conditional random field layer (stacked-BiLSTM-CRF) is proposed in this study to automatically label and intercept vibration signals. The stacked BiLSTM receives the shallow features obtained by the short-time Fourier transform of the vibration signals and then outputs the extracted deep features to capture the before and after dependence of the signals. The stacked BiLSTM is then extended by stacking a CRF layer to explicitly model the dependence of signal labels. In a more accurate labeling scenario, the fast low-cost online semantic segmentation algorithm (FLOSS) is used to acquire more fine-grained signal boundary locations after obtaining the frame-level signal label using the stacked BiLSTM-CRF model. In addition, to evaluate model performance, a novel evaluation index for signal labeling is proposed. The feasibility and effectiveness of the proposed method are verified using the vibration signals collected from variable parameter cutting experiments, and results show that the proposed model achieves the best labeling performance of tested methods in nearly all scenarios. [ABSTRACT FROM AUTHOR]

Abstract: Environmental temperature has an enormous influence on large machine tools with regards to thermal deformation, which is different from the effect on ordinary-sized machine tools. The thermal deformation has hysteresis effects due to environmental temperature, and the hysteresis time fluctuates with seasonal weather. This paper focused on the hysteresis nonlinear characteristic, analyzing the thermal effect caused by external heat sources. Fourier synthesis, time series analysis and the Newton cooling law were combined to build a time-varying analytical model between environmental temperature and the corresponding thermal error for a large machine tool. A multiple linear regression model based on the least squares principle was used to model the internal heat source effects simultaneously. The two models were united to make up a synthetic thermal error prediction model called the environmental temperature consideration prediction model (ETCP model). A series of experiments were performed using a large gantry type machine tool to verify the accuracy and efficiency of the predicted model under random environments, random times and random machining conditions throughout an entire year. The proposed model showed high robustness and universality, with over 85% thermal error, with up to 0.2mm was predicted. The mathematical model was easily integrated into the NC system and could greatly reduce the thermal error of large machine tools under ordinary workshop conditions, especially for long-period cycle machining. [Copyright &y& Elsevier]

• A weakly supervised defect segmentation method that does not require pixel-level annotations of defects for training is proposed based on the dynamic templates generated by an improved Cycle-GAN, which can achieve significantly higher performance than other weakly supervised methods and have competitive performance with supervised methods. • A novel defect attention module is proposed in the discriminator of Cycle-GAN to better eliminate defects with weak signals, such as small region and low contrast, for more accurate template images. • A defect consistency loss is proposed by adding SSIM to the L1 loss based on grayscale and texture, respectively, for better modeling the inner structure of defects. • The proposed method has been successfully applied at an industrial site for commutator surface defect detection and has exhibited excellent detection accuracy and significantly reduced manual labeling costs. • The proposed method can also be employed as a semiautomatic annotation tool combined with active learning. Surface defect segmentation is very important for the quality inspection of industrial production and is an important pattern recognition problem. Although deep learning (DL) has achieved remarkable results in surface defect segmentation, most of these results have been obtained by using massive images with pixel-level annotations, which are difficult to obtain at industrial sites. This paper proposes a weakly supervised defect segmentation method based on the dynamic templates generated by an improved cycle-consistent generative adversarial network (CycleGAN) trained by image-level annotations. To generate better templates for defects with weak signals, we propose a defect attention module by applying the defect residual for the discriminator to strengthen the elimination of defect regions and suppress changes in the background. A defect cycle-consistent loss is designed by adding structural similarity (SSIM) to the original L1 loss to include the grayscale and structural features; the proposed loss can better model the inner structure of defects. After obtaining the defect-free template, a defect segmentation map can easily be obtained through a simple image comparison and threshold segmentation. Experiments show that the proposed method is both efficient and effective, significantly outperforms other weakly supervised methods, and achieves performance that is comparable or even superior to that of supervised methods on three industrial datasets (intersection over union (IoU) on the DAGM 2007, KSD and CCSD datasets of 78.28%, 59.43%,and 68.83%, respectively). The proposed method can also be employed as a semiautomatic annotation tool combined with active learning. [ABSTRACT FROM AUTHOR]

• A novel graph-based semi-supervised method is proposed to predict position- and speed-dependent tool tip dynamics with limited labeled data. • To avoid the over-fitting occurrence, the conventional GCN is extended by stacking a transposed GCN. • The accuracy of proposed method for predicting the milling stability is validated through chatter tests. The tool tip frequency response function (FRF), as one of the essential inputs to calculate the stability lobe diagram (SLD), varies with the position and speed of changes in the moving components within the machine tool work volume. How to predict the position- and speed-dependent tool tip dynamics accurately has become one of the most challenging tasks in obtaining SLDs while avoiding chatter. However, traditional finite element analyses or kinematic modelling-based methods are costly and time consuming. Data-driven machine learning methods require large amounts of labeled data to train a model, but labeled industrial data are limited and extremely valuable in real manufacturing industries. To minimize experimentation, an improved semi-supervised graph convolutional network (GCN) is proposed to predict position- and speed- dependent tool tip dynamics with limited labeled data. First, the inverse stability solution is applied to identify dominant modal parameters under cutting conditions to obtain labeled samples. Subsequently, both the limited labeled samples and large amounts of unlabeled samples are converted into graph data to train a GCN regression model integrated with a multilayer perceptron. To avoid overfitting under limited data conditions, the conventional GCN is extended by stacking a transposed GCN, which is utilized to reconstruct the initial node features. The results demonstrate an improved prediction performance by adding the unsupervised reconstruction error into the loss function. Compared with other machine learning methods, our proposed method has superior performance in predicting tool tip dynamics with only 20% of the labeled samples. Finally, the SLDs were reconstructed with predicted FRFs, and the accuracy of the SLDs was validated through chatter tests. [ABSTRACT FROM AUTHOR]