Search

To simultaneously predict tool wear and surface roughness accurately during machining, this paper develops a multi-target predictive model that leverages a novel two-step feature-integration approach and Multi-kernel Gaussian process autoregressive regression (MK-GPAR). Compared with the traditional Gaussian process autoregressive regression (GPAR) models, the MK-GPAR demonstrates an enhanced capability in capturing detailed structures within heterogeneous data originating from various sources or disparate data forms. The weight coefficients of the kernel functions in MK-GPAR are typically assigned a value of 1 to minimize their influence on the predictive model. Furthermore, when compared to conventional multi-target predictive models like Gradient Boosting, Support Vector Regression (SVR), and K-Nearest Neighbors (KNN), the GPAR not only delivers higher-accuracy predictions for tool wear and surface roughness but also provides corresponding confidence intervals (CI). However, the CI of predictions for tool wear and surface roughness provided by MK-GPAR are inconsistent, which will seriously affect the reliability of the evaluation of the prediction results. The proposed two-step feature-integration approach is employed to enhance signal features effectively, reduce noise, and mitigate its adverse impact, thus enhancing the consistency and smoothness of the CI. The two-step feature-integration approach integrates principal component analysis (PCA) and orthogonal neighborhood preserving projections (ONPP) to merge force and vibration signal features obtained from the fixture's monitoring signals. Following the two-step feature-integration (first PCA, then ONPP) process, the MK-GPAR is utilized to build a multi-target predictive model for tool wear and surface roughness prediction. The impact of the proposed two-step feature-integration method on the prediction performance of the MK-GPAR is demonstrated revealed milling experiments. The experimental findings indicate that the proposed two-step feature-integration method significantly enhances the accuracy of predictions and the consistency of CI of the MK-GPAR. This research lays the foundation for implementing the multi-target predictive model in real industrial environments to predict tool wear and surface roughness. [ABSTRACT FROM AUTHOR]

This paper proposes a novel tool wear predicting method based on a weighted multi-kernel relevance vector machine (WMKRVM) and the integrated radial basis function–based probabilistic kernel principal component analysis (PKPCA_IRBF). The proposed WMKRVM model is constructed using the optimized standard single kernel RVM and its weight parameters. As a new dimension increment technique, PKPCA_IRBF can extract the noise information of the cutting force signal feature and incorporate the noise information into the model. Moreover, PKPCA_IRBF is first proposed to fuse the cutting force signal feature to improve the confidence interval provided by the WMKRVM model. Compared to the traditional PKPCA_RBF method, PKPCA_IRBF has a broader range of kernel parameter selection intervals and higher model accuracy. The cutting experiment is carried out to validate the effectiveness of the proposed tool wear predicting technique. Experimental results show that the proposed tool wear predicting technique can accurately monitor the tool wear width with strong robustness under various cutting conditions, laying the foundation for application in the industrial field. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) are extensively deployed to collect various data. Due to harsh environments and limitation of computing and communication capabilities of sensor nodes, the quality and reliability of sensor data are compromised by outliers. With the advent of 5G, sensors tend to generate increasingly more complex data. When faced with big data, traditional outlier detection methods relied on sensor nodes and remote cloud are unable to accord satisfactory performance in terms of delay and energy consumption. To address this problem, we propose a mobile edge–cloud collaboration outlier detection framework. Outlier detection is performed by edge nodes between the remote cloud and the underlying WSNs, while the training and updating of detection model are conducted on the cloud. A fast angle‐based outlier detection method is developed to obtain training data. The detection model is constructed based on support vector data description. An on‐line learning‐based iterative optimization scheme is devised to update the detection model. Besides, a fuzzy concept is incorporated into the detection model to alleviate the problem of loose decision boundary. Extensive experiments are conducted on real‐world data set. Simulation results show that our model is superior to three popular methods in terms of delay and energy consumption. In addition, when the percentage of operational nodes is 60%, our proposal prolongs the network lifetime by 14.2% to 69.8% compared to the three methods. [ABSTRACT FROM AUTHOR]

Based on the morphology of carbon microspheres and stable capacitance characteristic of dual material composite, it has great research significance in the preparation of electrode materials for supercapacitor. In this work, cottonseed shell/carbon nanospheres composite (CSPC@G) was prepared with cottonseed shell and glucose through hydrothermal carbonization and KOH activation. The structural features and electrochemical properties of the composites have been studied using physical representation and electrochemical tests. CSPC@G has the large specific surface area of 2281.39 m2 g−1 with obvious nanospheres on the surface of the material. In a three-electrode system with a 6 M KOH electrolyte, CSPC@G offers a high specific capacitance of 308.8 F g−1 at 0.5 A g−1 and the specific capacitance is reduced by only 18.2% even at 20 A g−1. The cyclic stability is maintained at 92.9% after 5000 cycles of charge and discharge. A symmetric double-layer capacitive device assembled with CSPC@G exhibits an energy density of 4.5 Wh kg−1 at 1246 W kg−1. This paper provides a new approach to prepare electrode materials for supercapacitors from cottonseed shell and glucose, and to broaden the applications of cottonseed shell. Formation process of glucose carbon microspheres. [Display omitted] • Porous carbon composite was obtain from cottonseed shell and glucose through hydrothermal and KOH activation. • The porous carbon possesses a large surface area of 2281.39 m2 g−1. • The porous carbon offers a high specific capacitance of 308.8 F g−1 at 0.5 A g−1. • The symmetrical capacitor with the porous carbon reaches high power density of 1246 W kg−1 at 4.5 Wh kg−1. [ABSTRACT FROM AUTHOR]

• A novel Multi-kernel GPR is developed for tool wear monitoring. • Multi-kernel GPR outperforms original GPR models in prediction accuracy. • Adam is effective in determining the hyper-parameters of Multi-kernel GPR. • Stacked Multilayer Denoising AutoEncoders improve Multi-kernel GPR's performance. To improve product quality and realize accurate monitoring of cutting tool wear in the cutting process, the monitoring of cutting tool wear is presented based on the Multi-kernel Gaussian Process Regression (GPR) and the Stacked Multilayer Denoising AutoEncoders techniques. In this paper, a Multi-kernel GPR is constructed for the drawback of the original GPR in difficulty capturing the structure of non-homogeneous data from multiple data sources or different data types. The weight coefficients of the kernel function of the Multi-kernel GPR are set to 1 to eliminate the impact of the weight coefficients on the monitoring model and optimize its hyper-parameter using the Adaptive Moment Estimation algorithm (Adam). However, compressing the confidence interval (CI) of GPR to improve the GPR's predicted accuracy leads to incomplete coverage of the test points. As a novel feature representation learning approach, Stacked Multilayer Denoising AutoEncoders are trained locally to denoise corrupted versions of their inputs to yield significantly lower predicted error. The fused features learned by Stacking Multilayer Denoising AutoEncoders are able to zero in on more useful structure in force signal feature data, thereby improving predicted accuracy and maintaining CI stability. Twelve sets of cutting tests confirmed the reliability of the proposed tool wear monitoring technique. The experimental results show that Stacked Multilayer Denoising AutoEncoders can reduce the mean square error (MSE) of Multi-kernel GPR by>40% while maintaining CI stability. This research establishes the groundwork for monitoring tool wear in real industrial settings. [ABSTRACT FROM AUTHOR]

In order to realize real-time and precise monitoring of the tool wear in the milling process, this paper presents a tool wear predictive model based on the stacked multilayer denoising autoencoders (SMDAE) technique, the particle swarm optimization with an adaptive learning strategy (PSO-ALS), and the least squares support vector machine (LSSVM). Cutting force and vibration information are adopted as the monitoring signals. Three steps make up the unique feature extraction and fusion method: multi-domain features extraction, principal component analysis (PCA)-based dimension reduction, and SMDAE-based dimension increment. As a novel feature representation learning approach, the SMDAE technique is utilized to fuse the PCA-based fusion features to enrich the effective information by increasing the dimension, thus helping polish up the predictive performance of the proposed model. PSO-ALS is used to obtain the optimal parameters for LSSVM, simplifying the problem and increasing the population diversity. Twelve sets of milling experiments are conducted to demonstrate the reliable performance of the proposed model. The experimental results show that the presented model is superior to models such as PSO-LSSVM in predictive performance, and the SMDAE technique effectively improves the prediction accuracy of the established model. The findings of this paper offer theoretical guidelines for monitoring milling tool wear in real industrial situations. [ABSTRACT FROM AUTHOR]

In many real networks, temporary and fluctuant high load on nodes does not always lead to the complete failure of them. The recovery of nodes' traffic function and the corresponding cascading congestion phenomenon can be observed. In this paper, we quantitatively associate local node capacity with external network load, and reveal the cascading congestion phenomenon of networks by modeling the traffic recovery behavior of nodes under fluctuant load. A hard traffic recovery model describing the general traffic recovery behavior of nodes and an adaptive traffic recovery model containing a local flow-adjusting strategy are proposed. We apply the two models to artificial networks and real networks. The network cascading congestion process and the limitation of network delivery ability under given node capacity are revealed. A hierarchical and load-dependent distribution of accepting probability is proved to be beneficial for the adaptive traffic recovery model in enhancing the network robustness against cascading congestion. Moreover, the critical node capacity corresponding to the maximal network load can be determined by our models. This function of our models is significant for obtaining the maximal network delivery ability with the lowest cost of node buffer in real applications. • Node traffic recovery behavior and network cascading congestion are modeled. • Network robustness is enhanced by an adaptive traffic recovery model. • The critical node capacity allows for maximal network load is determined. • The performance of our model is tested on BA networks and real networks. [ABSTRACT FROM AUTHOR]

One of the key factors to improve electrochemical properties is to find exceptional electrode materials. In this work, the nickel-cobalt layered double hydroxide (CNT@CoS/NiCo-LDH) with the structure of a hollow nanocage was prepared by etching CNT@CoS with zeolitic imidazolate framework-67 (ZIF-67) as a template. The results show that the addition of nickel has a great influence on the structure, morphology and chemical properties of materials. The prepared material CNT@CoS/NiCo-LDH-100 (C@CS/NCL-100) inherited the rhombic dodecahedral shape of ZIF-67 well and the CNTs were evenly interspersed among the rhombic dodecahedrons. The presence of CNTs improved the conductivity and surface area of the samples. The C@CS/NCL-100 demonstrates a high specific capacitance of 2794.6 F·g−1 at 1 A·g−1. Furthermore, as an assemble device, the device of C@CS/NCL-100 as a positive electrode exhibits a relatively high-energy density of 35.64 Wh·kg−1 at a power density of 750 W·kg−1 Further, even at the high-power density of 3750 W·kg−1, the energy density can still retain 26.38 Wh·kg−1. Hence, the superior performance of C@CS/NCL-100 can be ascribed to the synergy among CNTs, CoS and NiCo LDH, as well as the excellent three-dimensional structure obtained by used ZIF-67 as a template. [ABSTRACT FROM AUTHOR]

Failure in real interdependent networks can be induced by temporal and fluctuant overload on nodes. Moreover, failure of nodes will lead to loss of flow to some extent due to the decline of system delivery ability. In this paper, we propose a cascading failure model of interdependent networks based on mutual traffic redistribution under fluctuant load. In the model, the flow loss that is correlated with network existing resource is considered by defining a traffic loss parameter. The interdependence between coupled layers is realized by mutual traffic redistribution. Different types of artificial interdependent networks and a Bus-Metro network example are investigated. The results show larger node tolerance and larger traffic loss parameter can lead to higher network robustness. Moreover, cascading time synchronization of different layers induced by mutual traffic redistribution is observed. Although the interdependence usually makes the entire systems fragile, the optimal mutual flow redistribution rules that are beneficial to the whole network robustness can be obtained by our model. The model and results in this paper can provide some references on robust traffic flow assignment and network topology design for real interdependent systems. • A cascading failure model based on mutual traffic redistribution is proposed. • Synchronization of final cascading times of network layers is observed. • Network robustness is enhanced by optimization of flow redistribution. • Different types of artificial networks and a real example are investigated. [ABSTRACT FROM AUTHOR]