Search

This study investigates the deformation and mechanical behavior of metallic hollow spheres (MHSs) under quasi-static compression. Quasi-static axial compression simulations on aluminum alloy MHSs of varying diameters and wall thicknesses were conducted using ANSYS. The effects of diameter, wall thickness, and density on deformation modes, mechanical properties, and energy absorption characteristics were analyzed. The results indicate that MHSs experience three deformation stages during quasi-static compression, exhibiting both symmetric and asymmetric indentation modes. With a constant thickness-to-diameter ratio (T/D), MHSs demonstrate consistent deformation patterns and compressive strength, with load-bearing capacity influenced by both diameter and wall thickness. For a fixed diameter, wall thickness becomes the key factor determining compressive strength. Increasing wall thickness significantly enhances shell stiffness and load-bearing capacity, while reducing the risk of sidewall instability. Notably, at a T/D value of 0.03, MHSs display enhanced structural strength due to distinctive structural transformations during compression. Additionally, at a given density, MHSs with larger diameters exhibit higher load-bearing capacity, although this improvement tends to level off when density exceeds a certain threshold. The study also reveals that the initial peak load, average compression load, and energy absorption capacity of MHSs are influenced by both diameter and wall thickness, whereas energy absorption efficiency is primarily determined by the interaction between these parameters. This research provides essential theoretical support for the design and performance optimization of MHSs and offers valuable insights for applications in energy-absorbing structural design. [ABSTRACT FROM AUTHOR]

Humans excel at learning and recognizing objects, swiftly adapting to new concepts with just a few samples. However, current studies in computer vision on few-shot learning have not yet achieved human performance in integrating prior knowledge during the learning process. Humans utilize a hierarchical structure of object categories based on past experiences to facilitate learning and classification. Therefore, we propose a method named n-Hierarchy SEmantic Guided Attention (nHi-SEGA) that acquires abstract superclasses. This allows the model to associate with and pay attention to different levels of objects utilizing semantics and visual features embedded in the class hierarchy (e.g., house finch-bird-animal, goldfish-fish-animal, rose-flower-plant), resembling human cognition. We constructed an nHi-Tree using WordNet and Glove tools and devised two methods to extract hierarchical semantic features, which were then fused with visual features to improve sample feature prototypes. [ABSTRACT FROM AUTHOR]

Sleep position recognition plays a crucial role in enhancing individual sleep quality and addressing sleep-related disorders. However, the conventional non-invasive technology for recognizing sleep positions tends to be limited in its widespread application due to high production and computing costs. To address this issue, an enhanced stacking model is proposed based on a specific air bag mattress. Firstly, the hyperparameters of the candidate base model are optimized using the Bayesian optimization algorithm. Subsequently, the entropy weight method is employed to select extreme gradient boosting (XGBoost), support vector machine (SVM), and deep neural decision tree (DNDT) as the first layer of the enhanced stacking model, with logistic regression serving as the meta-learner in the second layer. Comparative analysis with existing machine learning techniques demonstrates that the proposed enhanced stacking model achieves higher classification accuracy and applicability. [ABSTRACT FROM AUTHOR]

The flexible job shop scheduling problem (FJSP) is a classic NP-hard problem, and the quality of its scheduling solution directly affects the operational efficiency of the manufacturing system. However, the traditional scheduling algorithms suffer from poor generalization when solving FJSP; there are problems such as long computational time and dimensional disasters, especially as the scale of FJSP increases. Therefore, an effective deep actor-critic reinforcement learning (DACRL) method is proposed for solving FJSP. Firstly, the FJSP is modeled as a multi-agent Markov decision process (MMDP), the state space, action space, and reward function in the MMDP are designed. Secondly, a DACRL model is constructed to solve FJSP. The actor network is responsible for choosing the most suitable scheduling rule in different states, while the critic network is responsible for outputting the value function of the actions and providing feedback to the actor network to better adjust the scheduling strategy. Finally, the proposed DACRL method is validated on benchmark FJSP instances of different scales. The experimental results show that the proposed method significantly outperforms the heuristic scheduling rules and double deep Q-network (DDQN) in terms of solution quality. Compared with the meta-heuristic algorithms and the self-learning genetic algorithm (SLGA), the proposed method has higher solution efficiency with the same solution quality. [ABSTRACT FROM AUTHOR]

Downhole turbine generators (DHTG) installed within drill-string are susceptible to internal and external excitation during the drilling process, causing significant dynamic loads on bearings, and thereby reducing the bearing's service life. In this study, a finite element model of an unbalanced rotor-bearing system (RBS) of DHTG with multi-frequency excitations, based on the Lagrangian motion differential equation, is established. The responses of the RBS under different drill-string excitations in terms of time-domain response, whirl orbit, and spectrum are analyzed. For a constant rotor speed, lateral harmonic translational and lateral oscillation both transform the whirl orbit to quasi-periodic, while axial rotation only changes the response amplitude. Changing the duration of pulse excitation leads to different response forms. Then, the dynamic characteristics of the RBS supported by a squeeze film damper (SFD) are investigated. The results indicate that SFD effectively reduces the displacement response amplitude and bearing force near the critical speed. As the axial rotation angular velocity of the drill-string increases, the first critical speed and displacement response decrease, while the variation of lateral oscillation frequency and amplitude has limited impact on them. The established model provides a means for analyzing the dynamic characteristics of DHTG's RBS under drill-string excitations during the design stage. [ABSTRACT FROM AUTHOR]

In response to global climate change, China has committed to peaking carbon emissions by 2030 and achieving carbon neutrality by 2060, commonly known as the "30–60 Dual Carbon". Under the background of "30–60 Dual Carbon", this article takes the electric power industry, which is the main industry contributing to China's carbon emission, as the research object, explores the time and peak value of the carbon peak of the electric power industry, and analyzes whether carbon neutrality can be realized under the peak method, so as to get the carbon neutrality path of the electric power industry and serve as the theoretical basis for the formulation of relevant policies. The Environmental Kuznets Curve inspection and the relationship analysis are carried out, then the system dynamics model is constructed, the carbon emissions from 2020 to 2040 are simulated, and the peak time is predicted. Three different scenarios are set to explore the path of electricity carbon neutralization under the premise of a fixed peak. It is shown that Gross Domestic Product per capita index factors have the largest positive contribution, and thermal power share index factors have the largest negative contribution to electricity carbon emissions. Based on the current efforts of the new policy, carbon emissions can achieve the peak carbon emissions' target before 2030, and it is expected to peak in 2029, with a peak range of about 4.95 billion tons. After the power industry peaks in 2029, i.e., Scenario 3, from coal 44%, gas 9% (2029) to coal 15%, gas 7% (2060), where the CCUS technology is widely used, this scenario can achieve carbon neutrality in electricity by 2060. Adjusting the power supply structure, strictly controlling the proportion of thermal power, optimizing the industrial structure, and popularization of carbon capture, utilization, and storage technology will all contribute to the "dual carbon" target of the power sector. [ABSTRACT FROM AUTHOR]

Currently, the research on the predictions of remaining useful life (RUL) of rotating machinery mainly focuses on the process of health indicator (HI) construction and the determination of the first prediction time (FPT). In complex industrial environments, the influence of environmental factors such as noise may affect the accuracy of RUL predictions. Accurately estimating the remaining useful life of bearings plays a vital role in reducing costly unscheduled maintenance and increasing machine reliability. To overcome these problems, a health indicator construction and prediction method based on multi-featured factor analysis are proposed. Compared with the existing methods, the advantages of this method are the use of factor analysis, to mine hidden common factors from multiple features, and the construction of health indicators based on the maximization of variance contribution after rotation. A dynamic window rectification method is designed to reduce and weaken the stochastic fluctuations in the health indicators. The first prediction time was determined by the cumulative gradient change in the trajectory of the HI. A regression-based adaptive prediction model is used to learn the evolutionary trend of the HI and estimate the RUL of the bearings. The experimental results of two publicly available bearing datasets show the advantages of the method. [ABSTRACT FROM AUTHOR]

Alloy composition design at the atomic scale is one of the key strategies for Ni-based single crystal superalloys (Ni-SCSs). In this article, the site preference of co-alloying elements Re-M (M: Cr, Mo, W or Re) in Ni3Al system and the strengthening effects of co-alloying elements on the shear deformation resistance of Ni3Al system are investigated using the first-principles method. It is found that the atom pairs of co-alloying elements prefer Al–Al site and the site preference of alloying elements is not affected by paired atoms. And co-alloying atom pairs occupying Ni–Ni site have a strong mutual interaction, which can be responsible for the formation of Re clusters and segregation of alloying elements. The ideal shear strength (ISS) of the quaternary Ni3Al system enhanced greatly by co-alloying elements is at least higher 11.9% than that of any Ni3Al system doped with single alloying elements, which indicates there are common effect among the co-alloying elements. The result of electronic structures shows that the strong interaction between the alloy atoms and their common the first nearest neighbors (FNN) Ni atoms is the common strengthening mechanism. The present article provides valuable guidelines for improving the mechanical strength of Ni-SCSs via alloy composition design. [ABSTRACT FROM AUTHOR]

In the process of the continuous development of subway construction, the safe evacuation of subway passengers has been paid much attention to. As the subway itself has the characteristics of limited space and high passenger density, once a fire emergency occurs, it can cause huge losses only by passive rescue. Therefore, it is important to actively plan for evacuation to reduce life and property losses due to fires in subways. This study aims to develop a fault tree analysis method for identifying scenarios that lead to evacuation failure in subways due to impassability incurred by fires. First, a virtual evacuation model is established using an agent modeling technique, with collected passenger characteristics to calibrate local evacuation behaviors. Then, fire impassability scenarios (e.g. fire(s) in the escalator(s), in emergency stairs, or the combination) are evaluated using the established agent model. Eventually, a fault tree analysis is constructed to identify scenarios that lead to evacuation failures. The research results show that the passability of escalator(s) is critical for subway fire resilience. It is important to use stationary escalator(s) as evacuation pathways for more evacuation capacity. Fire risk management around escalator(s) should be stricter. Passengers and staff are advised to learn how to stop a running escalator to avoid evacuation failures. [ABSTRACT FROM AUTHOR]

The time-series data generated by turbofan engines has a great degree of complexity and dynamics. At present, recurrent neural networks are commonly used to model and forecast the remaining useful life (RUL). The relationship of the sample data is not taken into account, and there are issues such as gradient explosion. In view of this, a spatio-temporal attention model is proposed, which comprehensively relates to the temporal association of data features and the hidden state of data features in space. At the same time, position coding is performed on the temporal relationship, avoiding the use of recurrent neural networks. Experimental results show that by combining the two dimensions, the predictive performance of the model is significantly improved. Compared with different methods on the four data sets of the commercial modular aerospace propulsion system simulation (C-MAPSS), the stability and prediction accuracy of the spatio-temporal attention model are better than that of alternative methods. [ABSTRACT FROM AUTHOR]

Closed-cell metal syntactic foam is a new material consisting of hollow spheres embedded in metal matrix syntactic foams. These foams have good physical and mechanical properties and are increasingly used worldwide in industrial and high-tech fields. Magnesium matrix syntactic foams containing hollow Al2O3 spheres ((Al2O3hs)/AZ91D) were successfully fabricated by hot press sintering at different temperatures. The fabrication of Al2O3hs/AZ91D and the effect of sintering temperature on the microstructure and properties are reported in this paper. Additionally, sandwiched magnesium matrix syntactic foams were prepared by placing magnesium plates on both sides of the syntactic foam. Some Al2O3hs particles became filled with matrix particles during preparation. Thus, the actual density was greater than the theoretically calculated value and increases with increasing sintering temperature. Above 723 K, a brittle phase MgAl2O4 formed in Al2O3hs/AZ91D. The quasistatic and dynamic compressive strengths of Al2O3hs/AZ91D first increased and then decreased with increasing sintering temperature, and the maximums were 162 MPa and 167.87 MPa, respectively. Thus, this paper reports a new strategy for the controlled preparation of metal matrix syntactic foams with predetermined porosity. The results show that this strategy improved the performance of lightweight and high-strength syntactic foam materials and shows potential for further research. [ABSTRACT FROM AUTHOR]

Perfluorinated isobutyronitrile (C4F7N) is favored in electrical engineering because it is an environmentally friendly gas-insulating medium with a low greenhouse effect. Unfortunately, under the influence of electricity and over-heating, its decomposition results in the deterioration of its insulating properties, which potentially leads to partial discharge or even gas breakdown. In this paper, the adsorption behavior of C4F7N gas and its toxic decomposition product, acetonitrile (C2N2), on MoS2 surfaces doped with small copper clusters was investigated by calculating the adsorption energy and density of states, etc. The effects of multiple initial adsorption positions as well as externally applied electric fields were also taken into account. The results depict that the maximum adsorption energy of C4F7N on the Cuγ (γ = 1–3)-MoS2 surface gradually decreases with the increase in γ. The Cu3-modified MoS2 is most suitable for use as a resistive-based gas-sensitive sensor substrate. This paper provides the theoretical foundation for the maintenance of future power equipment with environmentally friendly insulating gas. [ABSTRACT FROM AUTHOR]

Aiming at the problems of low fault diagnosis accuracy caused by insufficient samples and unbalanced data sample distribution in bearing fault diagnosis, this paper proposes a fault diagnosis method for rolling bearings referencing conditional deep convolution adversarial generative networks (C−DCGAN) for efficient data augmentation. Firstly, the concept of conditional constraints is used to guide and improve the sample generation process of the original generative adversarial network, and specific constraints are added to the data generation model to perform a balanced expansion of muti-category fault data for small sample data sets. Secondly, aiming at the phenomena of training instability, gradient disappearance and gradient explosion in the imbalanced sample set, it is proposed to optimize the structure of the generative network by using the structure of self-defined skip connections and spectral normalization, while using the Wasserstein distance with penalty term instead of cross entropy. The function is used as the loss function of the generative adversarial network to improve the stable feature extraction ability of the generative network and the effect of the training process; in this way, simulation sample data with only a small variation from the real data distribution can be generated. Finally, the complete fault data set (after mixing the original data with sufficient fault category and sample number) and the generated data are input into the one-dimensional convolution neural network for fault diagnosis of rolling bearing. The experiment's results show that the diagnosis method in this paper can improve the fault classification effect of rolling bearings by generating balanced and sufficient sample data. [ABSTRACT FROM AUTHOR]

This study aimed to investigate the effect of sintering temperature on microstructures and properties of AA6061 reinforced with SiC particles composites fabricated by Ultra high-pressure sintering. Results show that little agglomeration exists in AA6061 reinforced with SiC particles with the method of SiC particles coated by nano-aluminum powders. Al4C3 formed at the interface between AA6061Al and SiCp in the composite sintered above 600 °C. In the sintering temperature range of 450 ∼ 650 °C, the maximum relative density and highest hardness could reach 99.58% and 52 HRA, and the wear resistance is also the best for the AA6061 reinforced with SiC particles sintered at 600 °C. [ABSTRACT FROM AUTHOR]

In turbofan engine datasets, to address problems, such as noise interference, diverse data types, large data volumes, complex feature extraction, inability to effectively describe degradation trends, and poor remaining useful life (RUL) prognosis effects, a remaining useful life prognosis model combining an improved stack sparse autoencoder (imSSAE) and an improved echo state network (imESN) is proposed in this paper. First, the 3-sigma criterion is adopted to remove the noise and reconstruct the data, and then the deep features of the engine are extracted by using an imSSAE and fused into health indicator (HI) curves describing the engine degradation trend. Finally, an attention mechanism is introduced into an imESN to adaptively process different types of data and obtain the RUL. The experimental results based on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset show that compared with the other popular RUL prediction models, the combined model proposed in this paper has higher prediction accuracy, and the evaluation indices also show the effectiveness and superiority of the model. [ABSTRACT FROM AUTHOR]

In turbofan engine datasets, to address problems, such as noise interference, diverse data types, large data volumes, complex feature extraction, inability to effectively describe degradation trends, and poor remaining useful life (RUL) prognosis effects, a remaining useful life prognosis model combining an improved stack sparse autoencoder (imSSAE) and an improved echo state network (imESN) is proposed in this paper. First, the 3-sigma criterion is adopted to remove the noise and reconstruct the data, and then the deep features of the engine are extracted by using an imSSAE and fused into health indicator (HI) curves describing the engine degradation trend. Finally, an attention mechanism is introduced into an imESN to adaptively process different types of data and obtain the RUL. The experimental results based on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset show that compared with the other popular RUL prediction models, the combined model proposed in this paper has higher prediction accuracy, and the evaluation indices also show the effectiveness and superiority of the model. [ABSTRACT FROM AUTHOR]

Garbage classification is a social issue related to people's livelihood and sustainable development, so letting service robots autonomously perform intelligent garbage classification has important research significance. Aiming at the problems of complex systems with data source and cloud service center data transmission delay and untimely response, at the same time, in order to realize the perception, storage, and analysis of massive multisource heterogeneous data, a garbage detection and classification method based on visual scene understanding is proposed. This method uses knowledge graphs to store and model items in the scene in the form of images, videos, texts, and other multimodal forms. The ESA attention mechanism is added to the backbone network part of the YOLOv5 network, aiming to improve the feature extraction ability of the network, combining with the built multimodal knowledge graph to form the YOLOv5-Attention-KG model, and deploying it to the service robot to perform real-time perception on the items in the scene. Finally, collaborative training is carried out on the cloud server side and deployed to the edge device side to reason and analyze the data in real time. The test results show that, compared with the original YOLOv5 model, the detection and classification accuracy of the proposed model is higher, and the real-time performance can also meet the actual use requirements. The model proposed in this paper can realize the intelligent decision-making of garbage classification for big data in the scene in a complex system and has certain conditions for promotion and landing. [ABSTRACT FROM AUTHOR]

In this paper, the mechanical properties of nano-silica modified insulating paper under the combined action of mechanical vibration and temperature conditions are studied. Unmodified and nano-silica modified cellulose insulating paper with 2 wt% and 4 wt% were prepared, respectively, and a series of mechanical-thermal synergy experiments were carried out. With the same mechanical stress and temperature, and with the same aging duration of 144 h (6d), the tensile strength of modified insulating paper with 4 wt% nano-silica, increased 0.99 kN/m and 0.55 kN/m, respectively, compared with those of the unmodified and the 2 wt% nano-silica modified insulating paper. The experiments indicate that the nano-silica modification can effectively improve the mechanical properties of insulating paper. In this work, the modified mechanism of nano-silica is analyzed from the interface effect of modified polymer and the quantum effect of the modified polymer interface two aspects. It is shown that the interface formed in the modified insulating paper can transfer the mechanical stress acted on the insulating paper and prevent the cracks formed in the aging process of the test sample from further expansion, while the quantum effect discretizes the electron energy level, which can restrict the motion of the molecular chain segment to some extent. The conclusion can be used for reference to improve the performance of insulating paper. [ABSTRACT FROM AUTHOR]

The structure stability, mechanical properties and electronic structures of B2-FeAl intermetallics and the influence of La/Ce doping were investigated by first-principles density functional theory calculations. Several models were established. The total energies, cohesive energies, lattice constants, elastic constants, electronic density of states of Fe8Al8 and Fe8Al7X (X = La, Ce) were analyzed. The stability of alloy systems were determined according to the cohesive energy results. The calculated lattice constants of Fe8Al7X (X = La, Ce) were found to be related to the atomic radii of the alloy elements. The calculation and analysis of the elastic constants showed that ductility of B2-FeAl can be improved by the addition of La or Ce, the order of the ductility was as follows: Fe8Al7Ce > Fe8Al7La > Fe8Al8. The results of electronic structures showed that the brittleness of B2-FeAl was mainly due to the orbital hybridization of the d orbital of Fe and p orbital of Al, showing typical characteristics of a valent bond. Specifically, the mechanism for improving the ductility of B2-FeAl is that d orbital of La/Ce is mainly involved in the hybridization of B2-FeAl. [ABSTRACT FROM AUTHOR]

The Internet has become one of the important channels for users to obtain information and knowledge. It is crucial to work out how to acquire personalized requirement of users accurately and effectively from huge amount of network document resources. Group recommendation is an information system for group participation in common activities that meets the common interests of all members in the group. This paper proposes a group recommendation system for network document resource exploration using the knowledge graph and LSTM in edge computing, which can solve the problem of information overload and resource trek effectively. An extensive system test has been carried out in the field of big data application in packaging industry. The experimental results show that the proposed system recommends network document resource more accurately and further improves recommendation quality using the knowledge graph and LSTM in edge computing. Therefore, it can meet the user's personalized resource need more effectively. [ABSTRACT FROM AUTHOR]

Ultra high-pressure sintering (UHPS) was used to prepare AA6061/SiCp composites with different contents and the effect of sintering temperatures on microstructure and mechanical properties was investigated in this study. The results showed that a uniform distribution of nano-SiC particles (N-SiCp) is obtained by the UHPS method. With the increase in N-SiCp contents, the higher hardness and better wear resistance could be inspected. The interfacial reactions and Al4C3 phase appeared above 550 °C. The relative density of composites first increased and then decreased; with the temperature raising it reached 99.58% at 600 °C. The hardness and wear property showed the same trend with the hardness reaching 52 HRA and wear rate being 1.0 × 10−6 g/m at 600 °C. Besides, the wear mechanism of the composites is mainly composed of abrasive wear and adhesive wear. [ABSTRACT FROM AUTHOR]

The mode selection and resource allocation are important issues in Device-to-Device (D2D) communication, which have been investigated in single Base Station (BS) cellular network. However, the joint problem of the base station selection, mode selection and resource allocation is a challenging issue. Because the mode selection, base station and resource allocation are inter-coupled with each other. The joint problem of D2D User Equipments (DUEs) mode selection, base station selection, channel allocation and power allocation remains an open problem. In this paper, the scenario with multiple BSs in D2D heterogeneous networks is considered, and the joint problem of DUEs mode selection, base station selection, channel allocation and power allocation is studied. The objective is to maximize the system energy efficiency. We consider the DUEs multiplex the cellular user uplink resource. Meanwhile, the constraint of the total transmission power of the DUEs, and the constraint of the load balancing of the BSs are considered. The joint problem of mode selection, base station selection and resource allocation is formulated. The formulated problem is a non-convex mixed-integer optimization problem. In order to handle the formulated problem, a joint mode selection, base station selection and resource allocation algorithm based on particle swarm optimization is proposed. Numerical results demonstrate that the proposed algorithm can improve the system energy efficiency and obtain the desired target. [ABSTRACT FROM AUTHOR]

The SiCp/6061Al composites with volume fractions of 10%, 20%, 30% and 40% were prepared by power metallurgy method. The effects of the volume fraction of SiCp on microstructure and mechanical properties were studied by means of phase analysis, microstructure observation, hardness test, friction test, wear and tensile test. The results show that the SiC particles distribute uniformly in the matrix and the interface bonding between the matrix and the reinforcement was exceptional. With the increase of the volume fracture of SiC particles, the distribution uniformity decreases, the hardness increases, the elongation decreases, with the tensile strength and wear resistance were increasing before slowly decrease. If the volume fracture of SiC particles is 30%, the comprehensive mechanical property is best that the hardness is 97.9 HV, the tensile strength 243 MPa, the elongation is 2.9% and wear rate is 1.21 × 10–5 g/m. [ABSTRACT FROM AUTHOR]

In this paper, the 30 vol% SiCp/6061Al composites were prepared by vacuum hot pressing sintering. The effect of SiC particle size on the microstructure mechanical properties and wear behaviour of SiCp/6061Al composites was studied. From the results, it is shown that the SiC particle distribution increases firstly and then decreases with the increase of the particle sizes, the relative density, microhardness, elongation, and wear rate increase firstly and then slightly decrease. If the SiC particle size is 16 μm, the comprehensive properties of the composite are the best. [ABSTRACT FROM AUTHOR]

Graphite/6061 aluminum (G/6061Al) composites with different content of graphite were ultra-high pressure (UHP)-sintered and hot pressing (HP)-sintered, respectively. The result shows that homogeneous dispersion of graphite flakes in the 6061Al matrix can be achieved using graphite flakes coated by nano-Al particles, both in the UHP-sintered and in the HP-sintered composite. Due to the comprehensive effects of ultra-high pressure, high temperature and formation of Al4C3, the UHP-sintered composites endowed with higher relative density, higher hardness, stronger tensile strength and better wear resistance than the HP-sintered composite. The highest tensile strength of the UHP-sintered with 5 vol.% graphite is 183 MPa. Wear test reveals that the wear rate of the UHP sintered with 10 vol.% G/6061Al decreases drastically when the sintering temperature is 650 °C or higher, which is one to three orders of magnitude lower than that of the HP-sintered. The lowest wear rate of the UHP sintered with 10 vol.% graphite is 0.15 × 10−5 g/mm, while that of the HP-sintered composite is 133 × 10−5 g/mm. [ABSTRACT FROM AUTHOR]

A novel Si-Al alloy prepared by spray forming process investigated in this paper. Experimental results show that fine and homogeneous grain structure is obtained in as-deposited alloy. In addition, hot pressing process can eliminate the porosities formed at deposition process. Microstructure analysis show that the primary silicon fractured at a given stress and the particles congregated in microzone with increasing of the stress. After hot pressing, the alloy exhibits well physical and mechanical characteristics, the density is 2.514 g·cm3, the coefficient of thermal expansion is 10.3 × 10−6 K−1 at the range from room temperature to 100 °C, the thermal conductivity can reach 132 W·m−1·K−1, the ultimate compressive strength and Brinell hardness is 97.2 MPa and 130 HB, respectively. [ABSTRACT FROM AUTHOR]

Three kinds of SiCp/Al-Si-Mg composites, containing 20%, 40% and 60% volume fraction of silicon carbide particles (SiCp) were respectively sintered at high cubic anvil pressure, using SiC powders prepackaged by aluminum. Then microstructures of the composites were investigated, and the influences of pressure, sintering temperature and volume fraction of SiCp on the microstructures were analyzed. Results show that the composites own homogeneous microstructures, high density and few porosities. In the composites, SiCp and Al matrix were bounded to each other tightly and few agglomeration of SiCp or aluminum was observed. With the volume fraction of SiCp increased, the pinning effect of the reinforcement on the Al matrix is enhanced. With the sintering temperature and pressure increased, densities of the samples are also increased. Energy Dispersive Spectrometer (EDS) and X-ray diffraction (XRD) results show that there are transition layers and Al4C3 phases formed at the interface between SiCp and Al matrix when fabricated under pressure of 3.0GPa and temperature of 620 °C. [ABSTRACT FROM AUTHOR]

To address the problems of low recognition accuracy, slow convergence speed and weak generalization ability of traditional LeNet-5 network used in rolling-element bearing fault diagnosis, a rolling-element bearing fault diagnosis method using improved 2D LeNet-5 network is put forward. The following improvements to the traditional LeNet-5 network are made: the convolution and pooling layers are reasonably designed and the size and number of convolution kernels are carefully adjusted to improve fault classification capability; the batch normalization (BN) is adopted after each convolution layer to improve convergence speed; the dropout operation is performed after each full-connection layer except the last layer to enhance generalization ability. To further improve the efficiency and effectiveness of fault diagnosis, on the basis of improved 2D LeNet-5 network, an end-to-end rolling-element bearing fault diagnosis method based on the improved 1D LeNet-5 network is proposed, which can directly perform 1D convolution and pooling operations on raw vibration signals without any preprocessing. The results show that the improved 2D LeNet-5 network and improved 1D LeNet-5 network achieve a significant performance improvement than traditional LeNet-5 network, the improved 1D LeNet-5 network provides a higher fault diagnosis accuracy with a less training time in most cases, and the improved 2D LeNet-5 network performs better than improved 1D LeNet-5 network under small training samples and strong noise environment. [ABSTRACT FROM AUTHOR]

To effectively predict the rolling bearing fault under different working conditions, a rolling bearing fault prediction method based on quantum particle swarm optimization (QPSO) backpropagation (BP) neural network and Dempster–Shafer evidence theory is proposed. First, the original vibration signals of rolling bearing are decomposed by three-layer wavelet packet, and the eigenvectors of different states of rolling bearing are constructed as input data of BP neural network. Second, the optimal number of hidden-layer nodes of BP neural network is automatically found by the dichotomy method to improve the efficiency of selecting the number of hidden-layer nodes. Third, the initial weights and thresholds of BP neural network are optimized by QPSO algorithm, which can improve the convergence speed and classification accuracy of BP neural network. Finally, the fault classification results of multiple QPSO-BP neural networks are fused by Dempster–Shafer evidence theory, and the final rolling bearing fault prediction model is obtained. The experiments demonstrate that different types of rolling bearing fault can be effectively and efficiently predicted under various working conditions. [ABSTRACT FROM AUTHOR]