Search results

Bolted joint is the most important connection method in aircraft composite/metal stacked connections due to its large load transfer capacity and high manufacturing reliability. Aircraft components are subjected to complex hybrid variable loads during service, and the mechanical properties of composite/metal bolted joint directly affect the overall safety of aircraft structures. Research on composite/metal bolted joint and their mechanical properties has also become a topic of general interests. This article reviews the current research status of aeronautical composite/metal bolted joint and its mechanical properties and looks forward to future research directions.

This article reviews the research progress on static strength failure and fatigue failure of composite/metal bolted joint, focusing on exploring failure analysis and prediction methods from the perspective of the theoretical models. At the same time, the influence and correlation mechanism of hole-making quality and assembly accuracy on the mechanical properties of their connections are summarized from the hole-making processes and damage of composite/metal stacked structures.

The progressive damage analysis method can accurately analyze and predict the static strength failure of composite/metal stacked bolted joint structures by establishing a stress analysis model combined with composite material performance degradation schemes and failure criteria. The use of mature metal material fatigue cumulative damage models and composite material fatigue progressive damage analysis methods can effectively predict the fatigue of composite/metal bolted joints. The geometric errors such as aperture accuracy and holes perpendicularity have the most significant impact on the connection performance, and their mechanical responses mainly include ultimate strength, bearing stiffness, secondary bending effect and fatigue life.

Current research on the theoretical prediction of the mechanical properties of composite/metal bolted joints is mainly based on ideal fits with no gaps or uniform gaps in the thickness direction, without considering the hole shape characteristics generated by stacked drilling. At the same time, the service performance evaluation of composite/metal stacked bolted joints structures is currently limited to static strength and fatigue failure tests of the sample-level components and needs to be improved and verified in higher complexity structures. At the same time, it also needs to be extended to the mechanical performance research under more complex forms of the external loads in more environments.

The mechanical performance of the connection structure directly affects the overall structural safety of the aircraft. Many scholars actively explore the theoretical prediction methods for static strength and fatigue failure of composite/metal bolted joints as well as the impact of hole-making accuracy on their mechanical properties. This article provides an original overview of the current research status of aeronautical composite/metal bolted joint and its mechanical properties, with a focus on exploring the failure analysis and prediction methods from the perspective of theoretical models for static strength and fatigue failure of composite/metal bolt joints and looks forward to future research directions.

The paper is aimed to avoid the situation that historical relics are encroached, isolated and fragmented because of cities in the rapid urban process. Taking the environment around the Qinglong Temple in Xi'an city as an example and based on the characteristics of urban patterns in the history, this paper explores the spatial connection relationship between historical relics and surrounding villages as well as the connection between metro traffic and commercial bodies. At the end of the paper, the improvement strategy is put forward, namely the design concepts of “stepwise style” and “landscape style”, which can be achieved by the demand of ecological restoration and the relationship between urban axis. To be noted, the research shows, by restructuring new connection space, the city can promote the urban memory to be restored, the urban appearance to be reshaped, and the urban patterns in the history to be respected and displayed.

Textual information about restaurants, such as online reviews and food categories, is essential for consumer purchase decisions. However, previous restaurant recommendation studies have failed to use textual information containing essential information for predicting consumer preferences effectively. This study aims to propose a novel restaurant recommendation model to effectively estimate the assessment behaviors of consumers for multiple restaurant attributes.

The authors collected 1,206,587 reviews from 25,369 consumers of 46,613 restaurants from Yelp.com. Using these data, the authors generated a consumer preference vector by combining consumer identity and online consumer reviews. Thereafter, the authors combined the restaurant identity and food categories to generate a restaurant information vector. Finally, the nonlinear interaction between the consumer preference and restaurant information vectors was learned by considering the restaurant attribute vector.

This study found that the proposed recommendation model exhibited excellent performance compared with state-of-the-art models, suggesting that combining various textual information on consumers and restaurants is a fundamental factor in determining consumer preference predictions.

To the best of the authors’ knowledge, this is the first study to develop a personalized restaurant recommendation model using textual information from real-world online restaurant platforms. This study also presents deep learning mechanisms that outperform the recommendation performance of state-of-the-art models. The results of this study can reduce the cost of exploring consumers and support effective purchasing decisions.

关于餐厅的文本信息, 如在线评论和食品分类, 对于消费者的购买决策产生至关重要。然而, 先前的餐厅推荐研究未能有效利这些文本信息去预测消费者喜好。本研究提出了一种新颖的餐厅推荐模型, 以有效估计消费者对多个餐厅属性的评估行为。

我们从 Yelp.com 收集了来自25,369名消费者对 46,613 家餐厅的 1,206,587 条评论。利用这些数据, 我们通过结合消费者身份和在线消费者评论生成了消费者偏好向量。然后, 我们结合了餐厅身份和食品分类来生成餐厅信息向量。最后, 考虑到餐厅属性向量, 本研究调查了消费者偏好和餐厅信息向量之间的非线性交互关系。

我们发现, 所提出的推荐模型相比于之前最先进的模型表现出更优秀的性能, 这表明结合消费者和餐厅的各种文本信息是预测消费者喜好的基本因素。

据我们所知, 这是第一项利用来自真实在线餐厅平台的文本信息开发个性化餐厅推荐模型的研究。本研究还提出了胜过最先进模型的深度学习机制。本研究的结果可以降低探索消费者行为的成本并支持有效的购买决策。

The objective of this study is to develop an automated tool condition monitoring scheme for PCB drilling.

Vibration signals are used to distinguish micro drill wear stages with proper features extraction and classifier design. Then a tool condition monitoring system is built up through a back propagation neural network (BPNN).

Experimental results show that BPNN is a practical method of modeling tool wear, and with this method a tool condition monitoring system is built up using energy ratio, root mean square (RMS) and kurtosis coefficient that transformed by vibration signals.

In the further investigation, more signal samples should be computed as monitoring features for BPNN modeling. In addition, in order to build the best monitoring model, it is necessary to evaluate the performance of the BPNN model in advance, and optimize the process.

The paper provides a method and a system for PCB drill wear monitoring. The method and system can achieve on‐line monitoring of PCB drill condition.

Grinding may generate high temperature along the arc of grinding zone, especially during the grinding process of difficult‐to‐machine materials. It can cause thermal damage to the ground surface and poor surface integrity. Conventional cooling methods based on large amounts of water‐oil emulsions can be both ineffective and environmentally unacceptable. The purpose of this paper is to offer a new high efficiency cooling method – cryogenic pneumatic mist jet cooling (CPMJ) to enhance heat transfer in the grinding zone during grinding of difficult‐to‐machine materials.

CPMJ equipment is a set up, which can produce water mist of −5°C with jet velocity above 150 m/s and mean particle size below 20 μm at the impingement distance of 10‐40 mm on the symmetry axis. To validate the cooling efficiency of CPMJ equipment, heat transfer experiments were carrying out on it. Finally, CPMJ was applied to the grinding of titanium alloy to verify its cooling effects.

With high penetrative power and water mist of −5°C, CPMJ can greatly improve heat transfer efficiency in the grinding zone. Experimental results, including heat transfer experiments and grinding experiments, indicate that CPMJ has strong cooling ability and can offer better cooling effects compared with cold air jet and traditional flood cooling method. With CPMJ cooling method, grinding zone temperature can be effectively reduced and good surface quality can be achieved during grinding of titanium alloy.

CPMJ cooling method is an effective and pollution‐free way to solve the thermal problems during grinding of difficult‐to‐machine materials.

The purpose of this paper is to investigate the cutting mechanism of drilling printed circuit board (PCB) and to optimize the drilling parameters for decreasing burr size and thrust force.

An experimental study was carried out to investigate the effect of drilling parameters on thrust force and burr formation. The drilling process of PCB was divided by the variation of drilling force signals. Analysis of variance (ANVONA) was carried out for burr size and thrust force. Desirability function method was used in multiple response optimization, to find the best drilling parameters.

Enter burr and exit burr have different morphologies and types. The generation of enter burr is mainly caused by burr bending which can be observed in micrographs, whereas the generation of exit burr is more complicated than enter burr; both burr breakup and burr bending are observed in exit burrs. In the selected area, the optimized spindle speed and feed rate for drilling PCB is 12 krev/min and 6 mm/s, respectively.

In this paper, hole wall roughness and tool wear were not considered in the optimization of drilling parameters. The future research work should consider them.

This paper investigates the mechanism of burr formation and thrust force in drilling PCB and then optimizes the drilling parameters to decrease the burr formation and thrust force.

The purpose of this study was to compare machining performance between chemical vapor deposition (CVD)- and physical vapor deposition (PVD)-coated cutting tools to obtain the optimal cutting parameters based on different types of tools for machining titanium alloy (Ti-6Al-4V).

The design of the experiment was constructed using the response surface methodology (RSM) with the Box–Behnken method. Two types of round-shaped tungsten carbide inserts were used in this experiment, namely, PVD TiAlN/AlCrN insert tool and CVD TiCN/Al₂O₃ insert tool. The titanium alloy (Ti-6Al-4V) material was used throughout this experiment. The tool wear and microstructure analysis were measured using a tool maker microscope, an optical microscope and a scanning electron machine.

The PVD TiAlN/AlCrN insert tool produces the lowest tool wear that significantly prolongs the cutting tool life compared to the CVD TiCN/Al₂O₃ insert tool. In addition, depth of cut was the main factor affecting the tool life, followed by cutting speed and feed rate.

This study was conducted to compare machining performance between CVD- and PVD-coated cutting tools to obtain the optimal cutting parameters based on different types of tools for machining titanium alloy (Ti-6Al-4V). In addition, the information presented in this paper helps reduce the manufacturing cost and setup time for machining titanium alloy. Finally, tool wear comparison between PVD- and CVD-coated titanium alloys was also presented for future improvement for tool manufacturing application.

Most previous studies predicting review helpfulness ignored the significance of deep features embedded in review text and instead relied on hand-crafted features. Hand-crafted and deep features have the advantages of high interpretability and predictive accuracy. This study aims to propose a novel review helpfulness prediction model that uses deep learning (DL) techniques to consider the complementarity between hand-crafted and deep features.

First, an advanced convolutional neural network was applied to extract deep features from unstructured review text. Second, this study used previous studies to extract hand-crafted features that impact the helpfulness of reviews and enhance their interpretability. Third, this study incorporated deep and hand-crafted features into a review helpfulness prediction model and evaluated its performance using the Yelp.com data set. To measure the performance of the proposed model, this study used 2,417,796 restaurant reviews.

Extensive experiments confirmed that the proposed methodology performs better than traditional machine learning methods. Moreover, this study confirms through an empirical analysis that combining hand-crafted and deep features demonstrates better prediction performance.

To the best of the authors’ knowledge, this is one of the first studies to apply DL techniques and use structured and unstructured data to predict review helpfulness in the restaurant context. In addition, an advanced feature-fusion method was adopted to better use the extracted feature information and identify the complementarity between features.

大多数先前预测评论有用性的研究忽视了嵌入在评论文本中的深层特征的重要性, 而主要依赖手工制作的特征。手工制作和深层特征具有高解释性和预测准确性的优势。本研究提出了一种新颖的评论有用性预测模型, 利用深度学习技术来考虑手工制作特征和深层特征之间的互补性。

首先, 采用先进的卷积神经网络从非结构化的评论文本中提取深层特征。其次, 本研究利用先前研究中提取的手工制作特征, 这些特征影响了评论的有用性并增强了其解释性。第三, 本研究将深层特征和手工制作特征结合到一个评论有用性预测模型中, 并使用Yelp.com数据集对其性能进行评估。为了衡量所提出模型的性能, 本研究使用了2,417,796条餐厅评论。

广泛的实验验证了所提出的方法优于传统的机器学习方法。此外, 通过实证分析, 本研究证实了结合手工制作和深层特征可以展现出更好的预测性能。

据我们所知, 这是首个在餐厅评论预测中应用深度学习技术, 并结合了结构化和非结构化数据来预测评论有用性的研究之一。此外, 本研究采用了先进的特征融合方法, 更好地利用了提取的特征信息, 并识别了特征之间的互补性。