Search

Studying representation learning and generative modelling has been at the core of the 3D learning domain. By leveraging the generative adversarial networks and convolutional neural networks for point‐cloud representations, we propose a novel framework, which can directly generate 3D objects represented by point clouds. The novelties of the proposed method are threefold. First, the generative adversarial networks are applied to 3D object generation in the point‐cloud space, where the model learns object representation from point clouds independently. In this work, we propose a 3D spatial transformer network, and integrate it into a generation model, whose ability for extracting and reconstructing features for 3D objects can be improved. Second, a point‐wise approach is developed to reduce the computational complexity of the proposed network. Third, an evaluation system is proposed to measure the performance of our model by employing various categories and methods, and the error, considered as the difference between synthesized objects and raw objects are quantitatively compared, is less than 2.8%. Extensive experiments on benchmark dataset show that this method has a strong ability to generate 3D objects in the point‐cloud space, and the synthesized objects have slight differences with man‐made 3D objects.

Background and Purpose: Whether imaging parameters would independently predict stroke recurrence in low-risk minor ischemic stroke (MIS) or transient ischemic attack (TIA) according to traditional score system (such as ABCD 2 score, which was termed on the basis of the initials of the five factors: age, blood pressure, clinical features, duration, diabetes) remains unclear. We sought to evaluate the association between imaging parameters and 1-year stroke recurrence in patients with TIA or MIS in different risk stratum stratified by ABCD 2 score. Methods: We included patients with TIA and MIS (National Institutes of Health Stroke Scale score ≤3) with complete baseline vessel and brain imaging data from the Third China National Stroke Registry III. Patients were categorized into different risk groups based on ABCD 2 score (low risk, 0–3; moderate risk, 4–5; and high risk, 6–7). The primary outcome was stroke recurrence within 1 year. Multivariable Cox proportional-hazards regression models were used to assess whether imaging parameters (large artery stenosis, infarction number) were independently associated with stroke recurrence. Results: Of the 7140 patients included, 584 patients experienced stroke recurrence within 1 year. According to the ABCD 2 score, large artery stenosis was associated with higher stroke recurrence in both low-risk (adjusted hazard ratio, 1.746 [95% CI, 1.200–2.540]) and moderate-risk group (adjusted hazard ratio, 1.326 [95% CI, 1.042–1.687]) but not in the high-risk group ( P >0.05). Patients with multiple acute infarctions or single acute infarction had a higher risk of recurrent stroke than those with no infarction in both low- and moderate-risk groups, but not in the high-risk group. Conclusions: Large artery stenosis and infarction number were independent predictors of 1-year stroke recurrence in low-moderate risk but not in high-risk patients with TIA or MIS stratified by ABCD 2 score. This finding emphasizes the importance of early brain and vascular imaging evaluation for risk stratification in patients with TIA or MIS.

With the exacerbation of global environmental concerns, manufacturing industries need to consider the impact of carbon emissions from manufacturing processes. The selection of the parameters in the machining process greatly influences on carbon emissions and machining efficiency. Hence dynamically optimizing the machining process parameters is a significant means to reduce carbon emissions according to the real-time perception of the machining conditions. In the paper, a method of cutting parameter optimization is presented on basis of the construction the digital twin of a CNC machine tool. In this method, an ontology on CNC machining process is established to be used as a communication bridge for understanding the semantic of the real-time interaction between the physical machine and the virtual twin. And a dynamic optimization method on cutting parameters is presented according to the simulation and optimization of the virtual twin with the dynamic perception of the machining conditions of the physical machine. At last, a case study is presented to validate this method for effectively optimizing the cutting parameters and decreasing carbon emissions.

Peng Ju Liu,1 Hui Ping Lou,2 Yan Ning Zhu3 1Department of Clinical Nutrition, Peking Union Medical College Hospital, China Academic Medical Science and Peking Union Medical College, Beijing, People’s Republic of China; 2Medical Examination Center, Peking Union Medical College Hospital, China Academic Medical Science and Peking Union Medical College, Beijing, People’s Republic of China; 3Department of Obstetrics and Gynecology, Peking Union Medical College Hospital, China Academic Medical Science and Peking Union Medical College, Beijing, People’s Republic of ChinaCorrespondence: Peng Ju LiuDepartment of Clinical Nutrition, Peking Union Medical College Hospital, China Academic Medical Science and Peking Union Medical College, #1 Shuaifuyuan, Dongcheng District, Beijing, 100730, People’s Republic of ChinaTel +86 10-69155550Fax +86 10-69155551Email lpjjia@126.comBackground: The hypertriglyceridemic waist phenotype (HWP) has exhibited a strong association with metabolic syndrome, a condition closely linked with nonalcoholic fatty liver disease (NAFLD). However, no study has investigated whether the HWP can accurately predict NAFLD among premenopausal and postmenopausal women or whether alternative anthropometric indexes could replace waist circumference (WC) in the HWP. We examined the power of phenotypes combining triglyceride (TG) levels with anthropometric indexes such as body mass index (BMI), WC, waist-to-hip ratio, waist-to-height ratio, and percent body fat, to detect NAFLD among premenopausal and postmenopausal women.Methods: We conducted a cross-sectional study of 1125 premenopausal women and 654 postmenopausal women who had received an annual health checkup. For all the participating women, we measured both anthropometric and biochemical indexes, such as serum lipid levels. NAFLD diagnoses were made on the basis of abdominal ultrasonography findings. The receiver operating characteristic curve and area under the curve (AUC) were used to evaluate the indicators’ ability to detect NAFLD.Results: Among the indicators of hepatic steatosis, the combined phenotypes of TG level (≥ 1.50 mmol/L) and BMI (≥ 24.0 kg/m2) exhibited the largest AUC (0.841, 95%confidence interval [CI] 0.812– 0.871, P< 0.001) for premenopausal women, whereas WC alone exhibited the highest predictive potential (0.765, 95% CI 0.729– 0.801, P< 0.001) for postmenopausal women.Conclusion: Out of all the phenotypes combining a single anthropometric index with TG level or WC and TG level, the combination of TG level and BMI was the best indicator of NAFLD for premenopausal women. For screening NAFLD in postmenopausal women, WC alone was superior to all other indicators.Keywords: nonalcoholic fatty liver disease, hepatic steatosis, anthropometric index, hypertriglyceridemic waist phenotype, menopause

With the development of information and network technology, a new type of manufacturing paradigm, known as a service-oriented Cloud Manufacturing (CMfg), is emerged. In the CMfg paradigm, geographically distributed various manufacturing resources authorized by different companies are encapsulated as different manufacturing services (MSs) supported by the enabling technologies, such as cloud computing, Industrial Internet of Things, virtualization technologies, etc. MSs are provided according to the demands of manufacturing tasks (MTs) presented by various customers via the IoT (Internet of Things) in CMfg paradigm. Generally, one MS may complete one MT, but mostly one MT needs more MSs to complete it cooperatively. Furthermore, these MSs are perhaps controlled and managed by different enterprises. As an autonomous entity, each MS generally makes decision in light of its own interests, and their own interests generally have conflicts with the others' and the collective ones. To solve the conflicts through MSs' cooperation is an efficient and low-cost method to maximize both individual and collective interests. Hence, the influences of individual decision-making behaviors on cooperation are explored and discussed in CMfg paradigm. The evolutionary game theory and agent-based modeling and simulating method are employed to model and simulate individual behaviors of MSs during the process of forming the coalition for completing MTs. In addition, the learning mechanism of MSs is discussed in the decision-making process. The simulation results show that decision behaviors of MSs are positively influenced by the information transparency of the CMfg environment and the learning mechanism of MSs effects on the cooperative emergence.

Security logs in cloud environment like intrusion detection system (IDS) logs, firewall logs, and system logs provide historical information describing potential security risks. However, the use of logs for cyber intrusion detection relies heavily on expert knowledge. It is very difficult for the non-expert to identify these intrusion behaviors. This paper proposes a new method for mining association rules from multi-source logs to detect various intrusion behaviors in the cloud computing platform. In this method, a rule base is constructed to detect cyber intrusion. An adaptive approach is used to speed up the calculation of the association rule mining, in which the decision depends on the time complexity of the algorithm. Various cyber-attacks are simulated in the verification experiments which show the calculation speed of the proposed method is faster than other algorithms. Furthermore, compared with other methods, the performance of the proposed intrusion detection method is better than others in term of precision, recall, and f-measure.

With the development of lean manufacturing and economic globalization, supply networks increasingly become complex and large-scale, within which thousands of firms inter-depend with each other. Due to these increasing inter-dependencies, disruption of a quite few critical suppliers, namely bottleneck suppliers, can induce high loss to a supply network and even make the whole network dysfunction. Identification of bottleneck suppliers is significantly important for supply network risk management. Thus, in this article, a method based on a memetic algorithm with local neighborhood search (MALNS) is proposed to identify bottleneck suppliers in a two-stage supply network. Firstly, a model based on multipartite network is designed to describe the product supply-demand relations between multiple manufacturers and suppliers, which considers the different roles of manufacturer and supplier and differentiates the products that suppliers supply. To assess the loss caused by supplier disruptions, two performance metrics of supply networks, average product availability rate and manufacturer functioning rate, are presented. Then, a MALNS-based method is proposed to identify bottleneck suppliers, i.e., suppliers whose disruption will decrease both performance metrics most greatly. Finally, a case study based on a real automobile supply network is presented to validate the applicability and effectiveness of the proposed method.

As a key equipment of manufacturing, the intelligence of CNC machine tools affects the development and progress of intelligent manufacturing. At the same time, the rapid development of various technologies in recent years, such as cloud computing and edge computing, has brought new methods to improve the intelligence of CNC machine tools. This article proposes a new architecture of intelligent machine tools based on edge-cloud collaboration (IMT-ECC). The hierarchical structure of IMT-ECC is introduced and consists of three layers, data acquisition, network communication and edge-cloud collaboration. Combining the real-time characteristic of edge computing and complex problem processing ability of cloud computing, the edge-cloud collaboration is designed to improve the intelligence of machine tools through data collaboration, information collaboration and knowledge collaboration. Finally, the feasibility of the new intelligent machine tool architecture based on edge-cloud collaboration is verified by experiments with gantry heavy-duty CNC machine tools.

The thermal interaction of continuously welded rails with railway bridges has attracted the wide attention of researchers. In this paper, the model of a continuously welded rail and a bridge with longitudinal nonlinear stiffness has been considered. The detailed mechanics equation of the rail on the bridge and the embankment with longitudinal nonlinear stiffness has been presented using the finite element analysis. The validity of the presented model and the compiled program is illustrated. The influences of nonlinear stiffness, span number of the bridge, constant longitudinal restoring force, bridge bearing arrangement, and the span length of the bridge on the additional longitudinal stress and displacement of rails are investigated for multispan simply supported bridges. The results show that (1) the responses of rails for the nonlinear stiffness are less than those for the linear stiffness; (2) when the bridge span reaches a certain number, the maximum additional longitudinal stress and the displacement of the rail tend to be constant; (3) with the increase of the value of the constant longitudinal restoring stress, the maximum additional longitudinal stress and the displacement of the rail increase; (4) the maximum additional longitudinal stress of the rail on multispan simply supported bridges can be reduced by using alternate bearings on one pier; and (5) the maximum additional longitudinal stress and displacement of the rail increase with the increase of the span length of the bridge.

Thermal error is one of the main factors that influence the machining accuracy of computer numerical control (CNC) machine tools. It is usually reduced by thermal error compensation. Temperature field monitoring and key temperature measurement point (TMP) selection are the bases of thermal error modeling and compensation for CNC machine tools. Compared with small- and medium-sized CNC machine tools, heavy-duty CNC machine tools require the use of more temperature sensors to measure their temperature comprehensively because of their larger size and more complex heat sources. However, the presence of many TMPs counteracts the movement of CNC machine tools due to sensor cables, and too many temperature variables may adversely influence thermal error modeling. Novel temperature sensors based on fiber Bragg grating (FBG) are developed in this study. A total of 128 FBG temperature sensors that are connected in series through a thin optical fiber are mounted on a heavy-duty CNC machine tool to monitor its temperature field. Key TMPs are selected using these large-scale FBG temperature sensors by using the density-based spatial clustering of applications with noise algorithm to reduce the calculation workload and avoid problems in the coupling of TMPs for thermal error modeling. Back propagation neural network thermal error prediction models are established to verify the performance of the proposed TMP selection method. Results show that the number of TMPs is reduced from 128 to 5, and the developed model demonstrates good prediction effects and strong robustness under different working conditions of the heavy-duty CNC machine tool.

In this paper, a high-speed train–CRTS III slab track–subgrade coupled dynamic model is established. With the model, the influence of vehicle number on the dynamic characteristics of a train–CRTS III slab track–subgrade coupled system with smooth and random track irregularity conditions for conventional and vibration-reduction CRTS III slab tracks are theoretically studied and analyzed. Some conclusions are drawn from the results: (1) the largest dynamic responses of the coupled system for all items and cases are no longer changed when the vehicle number exceeds three, and three vehicles are adequate to guarantee the simulation precision to investigate the dynamic responses of the coupled system. (2) The acceleration of the car body has almost no relation with the vehicle number, and only one vehicle is needed to study the vehicle dynamics using the train–CRTS III slab track–subgrade coupled dynamic model. (3) For the conventional CRTS III slab track on a subgrade, the vehicle number has a negligible influence on the accelerations of the rail, slab, and concrete base, the positive and negative bending moments of the rail, the compressive force of the fastener, and the positive bending stress of slab, but it has a large influence on the tension force of the fastener, and the negative bending stresses of the slab and concrete base. Only one vehicle is needed to study track dynamics without considering the tension force of the fastener, the negative bending stresses of the slab and concrete base, otherwise, two or more vehicles are required. (4) For vibration reduction of the CRTS III slab track on a subgrade, the number of vehicles has some influence on the dynamic responses of all track components, and at least two vehicles are required to investigate the track dynamics.

The efficient recycling of waste electronic 3C products depends on the development of automatic disassembly process, including the robust vision detection system. Here we choose laptop parts as the target object, and build a dataset that contains 620 images. Our work focused on parts detection at disassembly scenario and implemented a universal and extensible laptop parts detector that can be applied to disassembly pipeline which based on a light and improved Mask R-CNN. After generating the mask images of parts, a rotary rectangle fitting method for parts was performed to predict the parts’ rotation angle, and apply specific rules based on quantity and space constraints to improve the accuracy.

Aiming at the problem that the screwdriver cannot be precisely embedded in the screw groove area during automatic screw removal, we propose an image semantic segmentation model fused with a lightweight convolutional neural network. Based on the classic DeeplabV3 model, a lightweight MobileNetV2 structure is used to replace original feature extractor, and its unique spatial pyramid structure is used for multi-scale fusion of the convolution feature of screw head image, and adding a dual attention module to extract the high-dimensional feature to reduce the loss of detail in segmentation. Finally, deconvolution is used to restore the resolution through the improved decoding network. By comparing our method with the state-of-the-art semantic segmentation network, It turns out that our method has better segmentation performance, with the mIoU up to 94.6%, and the testing time of a picture is 0.12ms, which can meet the demand of real-time task.

Predicting the crystal structures of novel quaternary compounds can be challenging, as there are only a few stable structures among numerous possible ones. Using a recently developed particle swarm optimization-based crystal structure prediction method and the first-principles calculation method, we discover a new crystal family of quaternary GaNGeC compounds, including six direct band gap semiconductors (denoted as S-1, S-2, S-3, S-4, S-5 and S-6) and two metals (denoted as S-7 and S-8); these compounds can potentially be employed in optoelectronic and energy applications. S-1, S-2, S-3, S-4, S-5 and S-6 exhibit high optical absorption coefficients in the visible region. Moreover, S-1, S-2, S-3, S-4 and S-5 possess band edge positions of the valence band maximum and conduction band minimum that are suitable for photocatalytic overall water splitting in the visible region.

Sleep disorder (SD) has a high incidence and seriously affects quality of life, mental health and even the manifestation of physical diseases. The combination of Pinellia ternata (Chinese name: banxia) and Prunella vulgaris (Chinese name: xiakucao), known as the Banxia–Xiakucao Chinese herb pair (BXHP), is a proven Chinese herbal medicine that has been used to treat SD for thousands of years due to its significant clinical effects. However, its active pharmacological components and sedative–hypnotic mechanisms have not been fully elucidated. Thus, the present study used a systematic pharmacological approach to develop pharmacokinetic screens and target predictions via construction of a protein–protein interaction network and annotation database for SD-related and putative BXHP-related targets. Visualization, screening and integrated discovery enrichment analyses were conducted. The BXHP chemical database contains 166 compounds between the two herbal ingredients, and of these, 22 potential active molecules were screened by pharmacokinetic evaluation. The targets of 114 of the active molecules were predicted, and 34 were selected for further analysis. Finally, gene ontology and Kyoto Encyclopedia of Genes and Genomes pathway analyses suggested that BXHP can reduce inflammatory responses. and mediate immune-related and central nervous system neurotransmitters via regulation of multiple targets and pathways. The use of a systematic pharmacology-based approach in the present study further elucidated the mechanisms of action underlying BXHP for the treatment of SD from a holistic perspective and sheds light on the systemic mechanisms of action of Chinese herbal medicines in general.

Recent methods of multi-person pose estimation focus on different aspects to increase the accuracy of keypoints localization. Although fusing the multi-scale feature maps to improve the recognition accuracy has achieved great results, there still have some space to promote. In this paper, we present two novel modules to enhance the multi-scale feature and increase the range of receptive fields by constructing hierarchical residual-like connections. First, the channel shuffle unit and Res2 block are combined to fuse the different level of features in pyramid feature maps, which prompts feature information communication. Second, a new residual block is built to fuse both spatial and channel-wise information within local receptive fields at each layer, and the residual block used in original basic network structure is replaced. The experiment have been evaluated on the COCO keypoint benchmark, which shows that our approach achieves better results than the other state-of-the-arts.

Recent research achievements in learning from demonstration (LfD) illustrate that the reinforcement learning is effective for the robots to improve their movement skills. The current challenge mainly remains in how to generate new robot motions automatically to perform new tasks, which have a similar preassigned performance indicator but are different from the demonstration tasks. To deal with the abovementioned issue, this article proposes a framework to represent the policy and conduct imitation learning and optimization for robot intelligent trajectory planning, based on the improved locally weighted regression (iLWR) and policy improvement with path integral by dual perturbation (PI2-DP). Besides, the reward-guided weight searching and basis function’s adaptive evolving are performed alternately in two spaces, i.e., the basis function space and the weight space, to deal with the abovementioned problem. The alternate learning process constructs a sequence of two-tuples that join the demonstration task and new one together for motor skill transfer, so that the robot gradually acquires motor skill, from the task similar to demonstration to dissimilar tasks with different performance metrics. Classical via-points trajectory planning experiments are performed with the SCARA manipulator, a 10-degree of freedom (DOF) planar, and the UR robot. These results show that the proposed method is not only feasible but also effective.

In order to study the axial compression performance of the T-shaped multi-cavity concrete-filled steel tube shear wall, first, three specimens were designed to perform the axial compression test. Then three-dimensional finite element analysis by the ABAQUS software was used to obtain the axial bearing capacity of the shear wall with different parameters. According to the results of the finite element model, the computational diagram in the limit state was obtained. The diagram was simplified into the core concrete in the non-enhanced area that was not constrained by the steel tube and the core concrete in the enhanced area that was uniformly constrained by the steel tube. Finally, a new practical equation for calculating the axial bearing capacity of a multi-cavity concrete-filled steel tubular shear wall was deduced and proposed based on the theory of ultimate equilibrium. The calculation results of the proposed equation were in good agreement with the finite element results, and the proposed equation can be used in practical engineering design.

Peng Ju Liu,1 Hui Ping Lou,2 Yan Ning Zhu3 1Department of Clinical Nutrition, Peking Union Medical College Hospital, China Academic Medical Science and Peking Union Medical College, Beijing, People’s Republic of China; 2Department of Medical Examination Center, Peking Union Medical College Hospital, China Academic Medical Science and Peking Union Medical College, Beijing, People’s Republic of China; 3Department of Obstetrics and Gynecology, Peking Union Medical College Hospital, China Academic Medical Science and Peking Union Medical College, Beijing, People’s Republic of ChinaCorrespondence: Peng Ju Liu Tel +86-10-69155550Fax +86-10-69155551Email lpjjia@126.comBackground: It has been suggested that hypertriglyceridemic waist (HW) phenotype is strongly associated with metabolic syndrome (MetS); however, there are very limited studies integrating triglyceride (TG) and waist circumference (WC) into a continuous variable to investigate the predictive power of this phenotype. Inspired from the triglyceride glucose index (TyG), we developed an integrated continuous index termed waist-triglyceride index (WTI) which was calculated as Ln [TG (mg/dl) WC (cm)/2].Objective: We aimed to examine the potential of WTI in screening for MetS by comparing this quantitative index with the qualitative HW phenotype and other frequently used indices.Methods: A cross-sectional study was conducted in a total of 3460 non-diabetic adults who participated in an annual health checkup. MetS was defined by the update National Cholesterol Education Program/Adult Treatment Panel ш criteria for Asian Americans. Receiving operating characteristic (ROC) curve and areas under the curve (AUC) were employed to evaluate the performance of the involved indices in screening for MetS. Statistical differences among the AUC values of the indices were compared.Results: In both genders, the AUC value of WTI, TyG or HW phenotype was markedly larger than that of each anthropometric index alone. In men, there were no statistical differences in the AUC values among WTI, TyG and HW phenotype, whereas in women, the AUC value of WTI was significantly larger than that of HW phenotype [difference between area (DBA): 0.042, 95% CI: 0.0224– 0.0617, P < 0.0001] and was nominally and significantly smaller than that of TyG (DBA: 0.00646, 95% CI: 0.000903– 0.012, P = 0.0227).Conclusion: Our results suggest that there are discriminatory performance between the WTI and HW phenotype in the detection of MetS in women rather than in men. Appropriate markers for screening MetS in population study should be considered according to the genders.Keywords: metabolic syndrome, hypertriglyceridemic, waist circumference, triglyceride glucose index, hypertriglyceridemic waist phenotype

Thermal error caused by the thermal deformation is one of the most significant factors influencing the accuracy of the machine tool. Complicated working condition lead to difficulties in data collection. Compare to the processing state, it is relatively easier to collect the data of the rest and idling states. The difficulty of data collection results in a large amount of data collected in resting and idling conditions, and a small amount of data in processing conditions. To overcome the limitation of data imbalance during the thermal error modeling of CNC machine tools, the paper proposed a transfer learning thermal error modeling method and performs similarity analysis on imbalanced experimental data by calculating the maximum mean difference. Through experiments, we conclude that the proposed method with insufficient data volume is superior to traditional machine learning methods in terms of prediction accuracy and model training efficiency.

This paper presents an integrated procedure for dynamic impact predictions and an experimental verification of rubber–metal bonded components with fluid to be used as a potential application in rail vehicle suspensions. There are three steps involved in the procedure. First, a quasi-static analysis was performed to verify the elastic properties of the rubber material using hyperelastic models. Second, a dynamic impact evaluation on selected hydro-mounts without fluid was conducted using the Natural Frequency Region (NFR) approach. Finally, a coupled NFR (with Fluid-Structural-Interaction) approach, different from the usual viscoelastic methods, was initiated to predict the dynamic impact responses of these components with the fluid in time domain. All the analyses have been validated with experimental data. The first two stages have been briefly described and the third stage is detailed in this paper. It should be noted that a powerful computer with multi-central processing units is essential to obtain a reasonable result within an acceptable time frame. It took approximately 40 h wall-clock time to complete the analysis using a workstation with 10 central processing units. It has been suggested that the natural frequency region–fluid–structure interaction methodology is reliable and could be used at the design stage and for engineering applications.

Cloud manufacturing (CMfg) is an innovative manufacturing paradigm in which geographically distributed various manufacturing resources are encapsulated into manufacturing services (MSs), and also these MSs can provide users with various services. Users can find and choose qualified MSs to form cliques to help them complete their manufacturing tasks via Internet. Trust makes cooperative endeavors happen. Hence, it is an important problem to evaluate the trustworthiness of MSs in CMfg. In this paper, we present a comprehensive assessment approach to evaluate the trustworthiness of a MS in CMfg. The approach evaluates a MS from both objective and subjective perspectives, named as credit assessment and reliability assessment, respectively. Multinomial logistic regression analysis is presented to assess the credit of a MS, while fuzzy analytic hierarchy process is used to assess its reliability. Finally, a case study is presented and the results show the comprehensive assessment approach is efficacious at the trustworthiness evaluation of a MS.

As one kind of significant manufacturing equipment, computer numerical control (CNC) machine tools have to be endowed with new functions to meet the requirements of processing devices in the era of “Industry 4.0.”Inter-connection and intelligence are the fundamental characteristics of CNC machine tools in this era. To make CNC machine tools be more accessible and promote them to a higher level of intelligence, this paper presents a new architecture of CNC machine tools based on a cyberphysical system and fog computing, named as a fog computing-based cyber-physical machine tool system (FC-CPMTS). The definition, functions, and hierarchical structure of the FC-CPMTS are described respectively. CNC machine tools, cyber space, and human beings are connected closely through sensing, computing, communicating, and controlling in the FC-CPMTS. The application of fog computing enhances autonomy and collaboration of CNC machine tools. It also reduces network traffic and calculation workload of the cloud platform in the FC-CPMTS. To demonstrate the rationality and feasibility of the FC-CPMTS, an FC-CPMTS for a heavy-duty CNC machine tool is taken as a case study. The result shows that autonomy, intelligence, interconnection, and interoperability of the CNC machine tool are improved.

Industrial cloud robotics (ICRs), which is proposed to integrate the distributed industrial robots (IRs) resources to provide ICRs services at any place, has been attracted great attention due to the characteristics of convenient access, cheaper computing cost, more convenient network resources, etc. Meanwhile, in manufacturing industry, the energy-efficient issue, which means minimize the amount of energy resources to achieve a given output level in manufacturing process, is also gradually paid great attention by academia, industry and government. Currently, ICRs plays a crucial role in production. The implementation of energy-efficient manufacturing for ICRs will significantly decrease the energy consumption on the premise of normal production process, and also have remarkable effect on energy-saving and emission-reduction in manufacturing industry. In this context, the energy condition perception and big data analysis of ICRs are the essential procedure to achieve the aforementioned goals. A novel system architecture which mainly focuses on distributed energy condition perception and big data analysis for ICRs is built. Based on the perceptive data of ICRs related to energy consumption, a big data analysis model combined with the manufacturing status of ICRs is proposed, and the relationship between the big data and the analysis model is presented. Through the data analysis model, we can analyze the energy consumption fluctuation characteristic of ICRs operating state, count the energy consumption of the product related to different production phases, predict the health status of ICRs, as well as the trend of energy consumption associated with their operations. A case study is implemented to demonstrate the effectiveness of the proposed system and approaches.

Condition sensing and understanding for CNC machine tools is an effective means to find hidden faults and to make their diagnosis. In this paper, an intelligent perception system of CNC machine tools is designed and implemented based on human-machine collaboration. With the application of wearable and mobile smart devices, such as Google Glasses and mobile phones, the system makes the information acquisition and data analysis capabilities of site-operator improved further more. A light deep learning model MobileNetV2 is used in this system, which can identify the key parts of the machine tools observed by the site-operator with the Google Glass. The various sensing data of the machine tools can be displayed visually via the screen of the Google Glass, so that site-operator can monitor them more conveniently. Finally, a fault response method for CNC machine tools based on human-machine collaboration is presented. The method improves the sensing capability and responding speed of site-operator by the collaboration of the smart glasses.

Cloud manufacturing is a new kind of manufacturing paradigm, in which geographically distributed various manufacturing resources belonging to different enterprises are encapsulated as manufacturing services (service providers) for providing users (service consumers) with services and users are able to find, select, and trade with MSs via Networks on a cloud manufacturing platform. To solve the trust issues between service providers and service consumers, a trust mechanism based on blockchain(BC) for services' information was proposed. Based on the decentralized, distributed storage and non-tamperable of BC, using public BC and consortium BC to construct a trusted mechanism for cloud manufacturing service platforms. Public BC is high credible, consortium BC is efficient and has larger capacity. The trusted mechanism can ensure that the source and storage of the service information is trusted, to solve the problem that the cloud manufacturing platform service data is untrustworthy and easily falsified. It can provide trusted choices to service consumers while operating efficiently and at low cost.

The cloud service platform is an open platform designed to provide various users with application services. The reliability of the platform is threatened by anomalous access behaviors such as resource abuse, DDoS attacks etc. Detecting anomalous behaviors to access the cloud service platform is an essential task. In this paper, an anomaly detection method based on Max-min distance and Support vector data description (MMD-SVDD) is proposed. The method identifies anomalous user access behaviors using CPU/memory/disk/network related system resource metrics. It firstly uses MMD to divide servers in the cloud service platform into multi-clusters. The servers in each of the clusters have similar running environment and can share an anomaly detection model. This process can effectively reduce the detection scale and system resource consumption. Then, aiming at the problem of incomplete abnormal data samples, the anomaly detection models are built based on SVDD algorithm, which utilizes normal data samples to construct a hypersphere for each cluster. Finally, the anomalous behavior is identified via judging whether the target data falls outside the hypersphere. The method is applied in cloud service platform and the result shows that it can accurately identity anomalies with lower system resource consumption.

Thermal error is one of the main factors that affect the machining precision of heavy CNC machine tools. Through the establishment of thermal error model based on temperature field monitoring, the compensation of thermal error is an effective method to improve the machining precision. Because the mechanism of the thermal error is complex, now a data driven modeling method is usually used to establish a thermal error model. However, traditional data driven modeling methods need to choose different key temperature points according to different working conditions to model in order to improve prediction accuracy and generalization. Therefore, it is difficult to get the thermal error model with strong generalization in different working conditions. Convolution neural network is a kind of deep neural network that can automatically extract feature of input data without artificial construction. A thermal error prediction model based on convolution neural network is proposed and the generalization is improved. The experimental results show that this method can accurately predict the thermal error of the Z axis in different working conditions, and validate the effectiveness of the modeling method.

The dynamic model for the vehicle-CRTS III slab track system is established subjected to uniform seismic excitation, and the calculation program with MATLAB is compiled and verified. The influences of track parameters, seismic intensity, and running speed of the vehicle on the dynamic responses of the system and the vehicle running safety are analyzed. The results show that (1) the track parameters have certain influence on the dynamic responses of the system, and the seismic intensity and the running speed of the vehicle have important influence on the vehicle running safety; (2) the derailment coefficient is highly sensitive to seismic intensity, and the wheel load reduction rate is also highly sensitive to the running speed of the vehicle.

Battery lifetime prediction is a promising direction for the development of next-generation smart energy storage systems. However, complicated degradation mechanisms, different assembly processes, and various operation conditions of the batteries bring tremendous challenges to battery life prediction. In this work, charge/discharge data of 12 solid-state lithium polymer batteries were collected with cycle lives ranging from 71 to 213 cycles. The remaining useful life of these batteries was predicted by using a machine learning algorithm, called symbolic regression. After populations of breed, mutation, and evolution training, the test accuracy of the quantitative prediction of cycle life reached 87.9%. This study shows the great prospect of a data-driven machine learning algorithm in the prediction of solid-state battery lifetimes, and it provides a new approach for the batch classification, echelon utilization, and recycling of batteries.

The recent application of computer vision to disassembly and remanufacturing has pushed forward this field significantly. In disassembling the laptop, we find that the existing positioning screw methods such as hough transform and template matching were not suitable for black laptops, so we propose a new method to solve this problem. We use RCF network to locate the screw hole contour, and make two improvements according to the characteristics of small screw hole size: 1. A feature integration module is added to RCF network to increase multi-scale features.2. A modulating factor is added to the loss function to enhance the attention to the indistinguishable pixels. Our approach has shown good results on black laptops and has higher ODS and OIS than the original RCF network and the existing method.

Linear programming method is presented for calculation of the Buckling critical load of the pile in nonlinear soils. Matlab programming for buckling stability analysis of pile in nonlinear soils is...

ObjectiveWaist-to-height ratio (WHtR) has been reported to be more strongly associated with cardiometabolic risk factors among non-obese individuals than BMI and waist circumference (WC). A body shape index (ABSI) and body roundness index (BRI) have been proposed recently to assess obesity-related disorders or mortalities. Our aim was to compare the ability of ABSI and BRI with that of WHtR to identify cardiometabolic risk factors in Chinese adults with normal BMI and WC.DesignReceiver-operating characteristic curves and areas under the curve (AUC) were employed to evaluate the ability of the indices (WHtR, BRI, ABSI) to identify metabolic risk factors and to determine the indices’ optimal cut-off values. The value of each index that resulted in maximization of the Youden index (sensitivity + specificity – 1) was defined as optimal. Differences in the AUC values between the indices were also evaluated.SettingIndividuals attending a voluntary health check-up in Beijing, China, July–December 2015, were recruited to the study.SubjectsNon-obese adults (n 1596).ResultsAmong both genders, ABSI exhibited the lowest AUC value for identifying each risk factor among the three indices; the AUC value of BRI for identifying each risk factor was very close to that of WHtR, and no significant differences were observed between the AUC values of the two new indices.ConclusionsWhen evaluating cardiometabolic risk factors among non-obese adults, WHtR was a simple and effective index in the assessment of cardiometabolic risk factors, BRI could be used as an alternative body index to WHtR, while ABSI could not.

A mixed two- and three-dimensional model is developed to simulate the dynamic track-tunnel-soil interaction in underground railway with ballastless track taking into account the moving train comprising a number of carriages, the track irregularities, and interaction among various components of the system. The effects of different track irregularities on the environmental vibration generated by underground railway with direct fixation and floating slab tracks are investigated. The results show that random track irregularities have large effects on the environmental vibration compared with perfectly smooth track condition. For direct fixation tracks, the environmental vibration induced by the irregularity of short wavelength is more significant than that induced by the irregularity of medium wavelength. However, for floating slab tracks, the environmental vibration induced by the irregularity of short wavelength is less significant than that induced by the irregularity of medium wavelength. The track irregularity samples measured by track geometry measuring car should therefore be used together with the short-wavelength random track irregularity for accurate prediction of the environmental vibration induced by underground railway with direct fixation track.

Background/Aims: Diabetes mellitus and pre-diabetes are closely associated with visceral obesity. Visceral adiposity index (VAI) is a novel sex-specific index, indirectly expressing visceral adipose function. Our aim was to determine the associations of VAI with dysglycemia (the combination of diabetes and pre-diabetes) and to compare the predictive ability for dysglycemia between VAI and traditional obesity indices. Methods: We performed a cross-sectional analysis of the data of 2,754 Chinese community-dwelling people who participated in the health checkup. Sex-specific VAI tertile cut-off points were used as follows: 1.70, 2.77 in males and 0.98, 1.75 in females. Binary logistic regression models were performed to estimate the association of the higher values of all the obesity indices with pre-diabetes and diabetes. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was applied to compare the predictive potential for dysglycemia among the obesity indices. Results: VAI was the only index significantly associated with both pre-diabetes and diabetes in both sexes after adjusting for potential confounders. The results of ROC analysis and AUC showed that VAI possessed the largest AUC, followed by other obesity indices. Conclusions: Higher VAI values are positively associated with the presence of pre-diabetes and diabetes in Chinese adults.

Due to the rail-bridge thermal interaction, the high additional axial force in continuously welded rails on continuous bridges may lead to rail buckling or breaking. However, there is little research on the influence of the location of the fixed bearing of continuous beam on the additional force of rail. In order to study the influence of bridge bearing arrangement on the additional longitudinal force of CWR, the thermal interaction model is established for rail, and simple and continuous beams considering nonlinear stiffness and the methods are proposed to determine the locations of fixed bearings of continuous beams corresponding to the maximum additional forces in rail reaching minimum values. Multiple continuous beams with several different lengths and simple beams with three types of bearing arrangements are taken into account to find the effect laws of the locations of the fixed bearings of continuous beams on the maximum additional forces in rail. The results show that as long as the same number of continuous beams, the ratios of the distances of adjacent two fixed bearings to the distance between the two fixed bearings of the simple beams neighbour to the first and last continuous beams respectively are approximately equal to each other. Furthermore the appropriate locations of the fixed bearings of continuous beams are recommended. The results can guide designing the location of the fixed bearing of continuous railway bridge while reducing the additional axial force in continuously welded rails due to bridge thermal effect.

Due to the temperature change of bridges, there is a great additional force in continuously welded rails on continuous bridges. Laying rail expansion regulators is an effective measure to reduce the additional force. The nonlinear finite element model is presented for a continuously welded rail track with a rail expansion regulator resting on the embankment and simple and continuous beams, considering the temperature change of the bridge. Then, a method is proposed to determine the locations of the rail expansion regulator and the fixed bearing of the continuous beam, corresponding to the maximum additional forces of rail reaching minimum values. Their appropriate matching locations are recommended based on the obtained influence laws of any locations of the rail expansion regulator and the fixed bearing of the continuous beam on the maximum additional forces of rail. The results can provide the theoretical basis for the design of the rail expansion regulator and the fixed bearing of long-span continuous bridges.

With the increasingly fierce market competition, manufacturing enterprises have to continuously improve their competitiveness through their collaboration and labor division with each other, i.e. forming manufacturing enterprise collaborative network (MECN) through their collaboration and labor division is an effective guarantee for obtaining competitive advantages. To explore the topology and evolutionary process of MECN, in this paper we investigate an empirical MECN from the viewpoint of complex network theory, and construct an evolutionary model to reproduce the topological properties found in the empirical network. Firstly, large-size empirical data related to the automotive industry are collected to construct an MECN. Topological analysis indicates that the MECN is not a scale-free network, but a small-world network with disassortativity. Small-world property indicates that the enterprises can respond quickly to the market, but disassortativity shows the risk spreading is fast and the coordinated operation is difficult. Then, an evolutionary model based on fitness preferential attachment and entropy-TOPSIS is proposed to capture the features of MECN. Besides, the evolutionary model is compared with a degree-based model in which only node degree is taken into consideration. The simulation results show the proposed evolutionary model can reproduce a number of critical topological properties of empirical MECN, while the degree-based model does not, which validates the effectiveness of the proposed evolutionary model.

At present, rail transit is developing rapidly in the world, and this means new and changing requirements for the training of talents in railway engineering experiments. Given the current problems of limited laboratory/field instruments for railway engineering experimentsand the safety/administrative difficulties of going to the frontline of railway lines to teach railway engineering experiemnts in the field, the Department of Railway Engineering of Central South University tried to introduce virtual reality (VR) technology to teach students experiments in the field of railway engineering. Through the virtualized experimental methods, students can carry out railway engineering experiments such as; vehicle wheel pair off-axis experiments, track geometry and position detection, etc by immersive means. It was observed that after performing virtual simulation experiments, students appeared conversant in subsequent field experiments. Thus, VR greatly improves the teaching efficiency of railway engineering experiments.

Thermal error of CNC machine tools is one of the main factors affecting the machining accuracy. The data-driven method for thermal error modeling is an effective and efficient, but they have some flaws, such as poor accuracy, bad robustness, and etc. because of having no quite enough data set and imbalanced data set. In this paper, a new method based on transfer learning for thermal error modeling is presented for solving the issue of imbalanced data set. The dataset of monitoring the temperature field of the machine tools includes monitoring data of three kinds of operating conditions, namely stopping, idling, and machining. When the fewer idling data is used to train a model, the larger stopping data are introduced as train aids. Transfer learning is adopted to fully learn the common characteristics of the two different working conditions, which can effectively solve the problem of imbalanced dataset. The experimental results prove that our method have better performance than other methods trained only with limited idling data.

Aims: A pilot survey shows that primary nocturnal enuresis (PNE) prevalence has increased significantly during the past decade in Mainland China. Whether it is related to the delay of elimination communication (EC) is unclear. This study retrospectively investigated the influence of delayed EC on the PNE prevalence in children and adolescents in mainland China. Methods: A cross-sectional study of PNE prevalence was performed by distributing 19 500 anonymous self-administered questionnaires to parents in five provinces of mainland China from July 2017 to October 2017. The questionnaires included sociodemographic data, family caregivers’ information, and details about the disposable diapers (DD) usage, EC commencement date, psychological disorders, lower urinary tract symptoms, and family history of PNE in children and adolescents. The 2017 PNE prevalence was compared with that of 2006 in Mainland China. Results: The total response rate was 97.04% (18 631 of 19 500) and 92.39% (18 016 of 19 500) qualified for statistical analysis. The PNE prevalence in 2017 has increased significantly compared to that of 2006 (7.30% vs 4.07%, P < 0.001). The PNE prevalence in children with EC starting before 6 months of age was significantly lower than those who start after 12 months of age. The longer DD were used and the later the beginning of EC, the higher the PNE prevalence was found. Conclusions: The PNE prevalence in Mainland China has increased significantly during the past 10 years. A longer use of DD and later onset of EC may be risk factors for PNE.

The joint moment provides specific information of human motion. It plays an important role as an advanced interfacing technology in robot assistant systems for elderly and disabled people. The surface electromyography (sEMG) signals are usually affected by the adjacent muscles. And muscle tendon units in the same muscle show different activation characteristics with different movement patterns. It is significant to calculate the contribution degree of signals from multi-channels to different movements. In this paper, the wrist joint moment, in particular the flexion and extension of wrist (WFE), is estimated by a novel approach that combines muscle synergy theory with musculoskeletal model. sEMG signal and joint angle of WFE were collected and input to the estimation model to calculate the joint moment. Experiments on five healthy subjects have demonstrated that, the estimation result of the proposed approach is more accurate with higher average correlation coefficient (CC) and lower normalized root-mean-square error (NRMSE) between estimated moment and reference moment.

With the advent and swift development of advanced network and information technology, various advanced manufacturing paradigms are rapidly emerged. A new kind of service-oriented network manufacturing paradigm, named Cloud Manufacturing (CMfg) is paid attraction by industries and academia. In this CMfg environment, the different kinds of manufacturing resources are encapsulated as manufacturing services (MSs), which are able to provide users with various machining/producing services and also can independently make decisions by themselves. Hence users can select different manufacturing services to help them finish their tasks together. In this paper, two different preferential selection mechanisms are used to select MSs, namely the local preferential and the global preferential selection. Therefore, there are two different relationship structures between tasks and MSs to be formed and a bipartite network is used to describe this relationship structures. For exploring the effect of the relationship structures on cooperative behaviors, the Stag Hunt game is used to describe their behavioral strategies in the processing of their repeated interactions. Lastly the agent-based modeling and simulating are used to analyze the cooperative behaviors of MSs in the process of repeated game with Repast. The simulating and analyzing result shows that different relationship structures are influenced on the emergence of cooperative behaviors in the CMfg environment.

Recently, a kind of service-oriented network manufacturing, cloud manufacturing (CMfg), has been emerged. In a CMfg environment, geographically distributed various manufacturing resources are encapsulated as different manufacturing services with the capability of independent making-decision, which are able to provide users with various services to help them to finish manufacturing tasks. Usually one manufacturing task needs several manufacturing services to work together. Apparently mutual cooperation between manufacturing services plays a crucial part in a CMfg environment. It can ensure service quality and reduce the interaction costs between manufacturing services in the process of collaborative manufacturing. Thus, the building of cooperative relations is an important issue of CMfg. In this paper, to promote the establishment of cooperative relations between manufacturing services and make manufacturing services get the high profit, a behavior learning mechanism is proposed to support the action selection of manufacturing services during the process of repeated interaction. The results show that the relationship of cooperation between manufacturing services can be established by using this mechanism. Moreover, the willingness of cooperation (WOC) of manufacturing services and the profit that is generated by behaviors have an effect on the emergence of cooperative behaviors of manufacturing services.

The classic job shop scheduling problem mainly focuses on one kind of manufacturing resources, such as machine tools, and etc. But the job shop scheduling in practical production activities always needs to consider the constraints of different manufacturing resources. In this paper, a double-resource flexible job shop scheduling problem (DFJSSP) is presented. Both machines and workers are considered in the process of job shop scheduling in this DFJSSP. And a genetic algorithm (GA) is used to solve this problem, in which a new well designed three-layer chromosome encoding method has been adopted and some effective crossover and mutation operators are designed. Finally, a case study is used to validate the method.

Cyber-Physical System (CPS) is a combination of closely integrated physical processes, network and computation. It has been widely used in manufacturing because of its advantages in connecting cyber world and physical world. Computer numerical control (CNC) machine tools play a vital role in modern manufacturing, and their machining accuracy is greatly affected by thermal errors. In this paper, a thermal error compensator based on CPS for CNC machine tools is designed and developed. According to the requirements of a CPS, the compensator is developed on an embedded system, which can speedily collect data from sensors, precisely predict thermal errors, and effectively communicate with CNC system as well as cloud service platform. The compensator is applied in a heavy-duty CNC machine tool and the result shows that it produces intended effect in different machining conditions.

In online temperature monitoring system for CNC machine tools, the temperature detecting data of CNC machine tools sensed by Fiber Bragg Grating (FBG) temperature sensors directly affect the reconstruction of the temperature field. Analysis on the temperature detecting data can provide important information regarding the thermal error of the CNC machine tools indeed. In this paper, a method of the outlier detection is presented. The method uses the image morphology to detect the outlier online. Firstly, the sliding window is adopted to guarantee online performance. Then outliers are detected by applying opening and closing operations and sequential filter based on image morphology. Finally, the proposed method is applied to handle actual data collected by FBG temperature sensors on CNC machine tools. The results show that the method is valid.

Thermal error caused by the thermal deformation of computer numerical control (CNC) machine tools is one of the main factors to affect the machining accuracy. With monitoring data of the temperature field, establishing data-driven thermal error model is considered as a more convenient, effective and cost-efficient way to reduce the thermal error. As a matter of fact, it is very difficult to develop a thermal error model with perfect generalization adapting to different working conditions of machining tools. In this paper, a method of an ensemble modeling (EM) based on Convolution Neural Network (CNN) and Back Propagation (BP) Neural Network for modeling thermal error is presented. This ensemble model takes full advantages of two different neural networks, namely CNN having self-extracting feature to solve collinear problem in temperature field and BP can process heat source to thermal error by mapping nonlinear function, then combined into a EM. To demonstrate the effectiveness of the proposed model, an experiment platform was set up based on a heavy-duty CNC machine tool. The results show that the proposed model achieves better accuracy and strong robustness in comparison with only with BP network and CNN network respectively.