资源类型

期刊论文 232

会议视频 6

年份

2023 32

2022 33

2021 21

2020 28

2019 29

2018 9

2017 11

2016 5

2015 4

2014 8

2013 4

2012 2

2011 5

2010 9

2009 7

2008 1

2007 3

2006 3

2005 2

2004 2

展开 ︾

关键词

深度学习 15

人工智能 8

岩爆 5

关键技术 4

机器学习 4

冲刷防护 2

勘探开发 2

基础研究 2

天然气水合物 2

扬矿管 2

深井开采 2

深度神经网络 2

深海 2

深海采矿 2

深部裂缝带 2

高含硫 2

6G；广域覆盖信令小区；多维资源分配；深度Q网络（DQN） 1

COVID-19 1

Deep metal mining 1

展开 ︾

检索范围：

排序： 展示方式：

Development and deep-sea exploration of the Haidou-1

《工程管理前沿（英文）》   页码 546-549 doi: 10.1007/s42524-023-0260-6

摘要： Development and deep-sea exploration of the Haidou-1

关键词： hadal zone     autonomous and remotely-operated vehicle     integrated exploration operation     deep dive exceeding 10000 meters    

HTML PDF 收藏

RETRACTED ARTICLE: Using a Newton-type technique for smart meters estimation frequency of electric power

Tanveer AHMAD,Qadeer UI HASAN

《能源前沿（英文）》 2016年 第10卷 第4期   页码 489-489 doi: 10.1007/s11708-016-0395-9

HTML PDF 收藏

Effect of harmonic distortion on electric energy meters of different metrological principles

Illia DIAHOVCHENKO, Vitalii VOLOKHIN, Victoria KUROCHKINA, Michal ŠPES, Michal KOSTEREC

《能源前沿（英文）》 2019年 第13卷 第2期   页码 377-385 doi: 10.1007/s11708-018-0571-1

摘要： This paper deals with the errors of electric energy metering devices as a result of distortions in the shape of the curves of voltage and current load. It is shown and proved that the errors in energy measurements depend on the design and the algorithms used in electricity meters. There are three main types of metering devises having different principles: inductive (electro-mechanical), electronic static, and digital electronic (microprocessor). Each of these types has its measuring features. Some devices take into account all the harmonic distortions and the constant component which occur in the network while others measure the power and energy values of the fundamental harmonic only. Such traits lead to the discrepancies in the readings of commercial electric energy meters of different types. Hence, the violations in the measurement system unity occur, and a significant error can be observed in the balance of transmitted/consumed electric energy.

关键词： current     distortion     electric energy meter     harmonics     power quality    

HTML PDF 收藏

DSM in an area consisting of residential, commercial and industrial load in smart grid

Balasubramaniyan SARAVANAN

《能源前沿（英文）》 2015年 第9卷 第2期   页码 211-216 doi: 10.1007/s11708-015-0351-0

摘要： With the latest introduction of the demand side management (DSM) in smart grids, the power distribution units are able to modify the load schedules of the consumers. This involves a co-operative interaction of the utility and the consumers so as to achieve customer load modifications in which the customer, utility and society all are benefited. The interaction is performed with the help of the devices known as the smart meter. This paper shows the use of game theory and logical mathematical expressions in order to achieve the objectives. The objectives are to minimize the peak to average ratio (PAR) and the energy cost. The outcome of the game between supplier and customers helps to shape the load profile. The design proposed in this paper is very user-friendly and is based on simple logarithmic programming computations. In this paper, residential, commercial and industrial types of loads are taken into account. A basic 24 h load schedule along with the fluctuating prices at each hour of the day is forecasted by the supplier of the various shiftable and non-shiftable loads and then that schedule is conveyed to the user. The users are encouraged to shift their high load devices to off-peak hours which will not only reduce their electricity costs but also substantially reduce the PAR in the load demand.

关键词： demand side management (DSM)     smart grids     peak to average ratio (PAR)     smart meters and logarithmic price function    

HTML PDF 收藏

Digital image correlation-based structural state detection through deep learning

《结构与土木工程前沿（英文）》 2022年 第16卷 第1期   页码 45-56 doi: 10.1007/s11709-021-0777-x

摘要： This paper presents a new approach for automatical classification of structural state through deep learning. In this work, a Convolutional Neural Network (CNN) was designed to fuse both the feature extraction and classification blocks into an intelligent and compact learning system and detect the structural state of a steel frame; the input was a series of vibration signals, and the output was a structural state. The digital image correlation (DIC) technology was utilized to collect vibration information of an actual steel frame, and subsequently, the raw signals, without further pre-processing, were directly utilized as the CNN samples. The results show that CNN can achieve 99% classification accuracy for the research model. Besides, compared with the backpropagation neural network (BPNN), the CNN had an accuracy similar to that of the BPNN, but it only consumes 19% of the training time. The outputs of the convolution and pooling layers were visually displayed and discussed as well. It is demonstrated that: 1) the CNN can extract the structural state information from the vibration signals and classify them; 2) the detection and computational performance of the CNN for the incomplete data are better than that of the BPNN; 3) the CNN has better anti-noise ability.

关键词： structural state detection     deep learning     digital image correlation     vibration signal     steel frame    

HTML PDF 收藏

Dynamic prediction of moving trajectory in pipe jacking: GRU-based deep learning framework

《结构与土木工程前沿（英文）》   页码 994-1010 doi: 10.1007/s11709-023-0942-5

摘要： The moving trajectory of the pipe-jacking machine (PJM), which primarily determines the end quality of jacked tunnels, must be controlled strictly during the entire jacking process. Developing prediction models to support drivers in performing rectifications in advance can effectively avoid considerable trajectory deviations from the designed jacking axis. Hence, a gated recurrent unit (GRU)-based deep learning framework is proposed herein to dynamically predict the moving trajectory of the PJM. In this framework, operational data are first extracted from a data acquisition system; subsequently, they are preprocessed and used to establish GRU-based multivariate multistep-ahead direct prediction models. To verify the performance of the proposed framework, a case study of a large pipe-jacking project in Shanghai and comparisons with other conventional models (i.e., long short-term memory (LSTM) network and recurrent neural network (RNN)) are conducted. In addition, the effects of the activation function and input time-step length on the prediction performance of the proposed framework are investigated and discussed. The results show that the proposed framework can dynamically and precisely predict the PJM moving trajectory during the pipe-jacking process, with a minimum mean absolute error and root mean squared error (RMSE) of 0.1904 and 0.5011 mm, respectively. The RMSE of the GRU-based models is lower than those of the LSTM- and RNN-based models by 21.46% and 46.40% at the maximum, respectively. The proposed framework is expected to provide an effective decision support for moving trajectory control and serve as a foundation for the application of deep learning in the automatic control of pipe jacking.

关键词： dynamic prediction     moving trajectory     pipe jacking     GRU     deep learning    

HTML PDF 收藏

A new automatic convolutional neural network based on deep reinforcement learning for fault diagnosis

《机械工程前沿（英文）》 2022年 第17卷 第2期 doi: 10.1007/s11465-022-0673-7

摘要： Convolutional neural network (CNN) has achieved remarkable applications in fault diagnosis. However, the tuning aiming at obtaining the well-trained CNN model is mainly manual search. Tuning requires considerable experiences on the knowledge on CNN training and fault diagnosis, and is always time consuming and labor intensive, making the automatic hyper parameter optimization (HPO) of CNN models essential. To solve this problem, this paper proposes a novel automatic CNN (ACNN) for fault diagnosis, which can automatically tune its three key hyper parameters, namely, learning rate, batch size, and L2-regulation. First, a new deep reinforcement learning (DRL) is developed, and it constructs an agent aiming at controlling these three hyper parameters along with the training of CNN models online. Second, a new structure of DRL is designed by combining deep deterministic policy gradient and long short-term memory, which takes the training loss of CNN models as its input and can output the adjustment on these three hyper parameters. Third, a new training method for ACNN is designed to enhance its stability. Two famous bearing datasets are selected to evaluate the performance of ACNN. It is compared with four commonly used HPO methods, namely, random search, Bayesian optimization, tree Parzen estimator, and sequential model-based algorithm configuration. ACNN is also compared with other published machine learning (ML) and deep learning (DL) methods. The results show that ACNN outperforms these HPO and ML/DL methods, validating its potential in fault diagnosis.

关键词： deep reinforcement learning     hyper parameter optimization     convolutional neural network     fault diagnosis    

HTML PDF 收藏

Multiclass classification based on a deep convolutional

Ying CAI,Meng-long YANG,Jun LI

《信息与电子工程前沿（英文）》 2015年 第16卷 第11期   页码 930-939 doi: 10.1631/FITEE.1500125

摘要： Head pose estimation has been considered an important and challenging task in computer vision. In this paper we propose a novel method to estimate head pose based on a deep convolutional neural network (DCNN) for 2D face images. We design an effective and simple method to roughly crop the face from the input image, maintaining the individual-relative facial features ratio. The method can be used in various poses. Then two convolutional neural networks are set up to train the head pose classifier and then compared with each other. The simpler one has six layers. It performs well on seven yaw poses but is somewhat unsatisfactory when mixed in two pitch poses. The other has eight layers and more pixels in input layers. It has better performance on more poses and more training samples. Before training the network, two reasonable strategies including shift and zoom are executed to prepare training samples. Finally, feature extraction filters are optimized together with the weight of the classification component through training, to minimize the classification error. Our method has been evaluated on the CAS-PEAL-R1, CMU PIE, and CUBIC FacePix databases. It has better performance than state-of-the-art methods for head pose estimation.

关键词： Head pose estimation     Deep convolutional neural network     Multiclass classification    

HTML PDF 收藏

Hybrid deep learning model for risk prediction of fracture in patients with diabetes and osteoporosis

《医学前沿（英文）》 2022年 第16卷 第3期   页码 496-506 doi: 10.1007/s11684-021-0828-7

摘要： The fracture risk of patients with diabetes is higher than those of patients without diabetes due to hyperglycemia, usage of diabetes drugs, changes in insulin levels, and excretion, and this risk begins as early as adolescence. Many factors including demographic data (such as age, height, weight, and gender), medical history (such as smoking, drinking, and menopause), and examination (such as bone mineral density, blood routine, and urine routine) may be related to bone metabolism in patients with diabetes. However, most of the existing methods are qualitative assessments and do not consider the interactions of the physiological factors of humans. In addition, the fracture risk of patients with diabetes and osteoporosis has not been further studied previously. In this paper, a hybrid model combining XGBoost with deep neural network is used to predict the fracture risk of patients with diabetes and osteoporosis, and investigate the effect of patients’ physiological factors on fracture risk. A total of 147 raw input features are considered in our model. The presented model is compared with several benchmarks based on various metrics to prove its effectiveness. Moreover, the top 18 influencing factors of fracture risks of patients with diabetes are determined.

关键词： XGBoost     deep neural network     healthcare     risk prediction    

HTML PDF 收藏

Stability analysis on Tingzikou gravity dam along deep-seated weak planes during earthquake

Weiping HE, Yunlong HE

《结构与土木工程前沿（英文）》 2012年 第6卷 第1期   页码 69-75 doi: 10.1007/s11709-012-0146-x

摘要： The stability of a gravity dam against sliding along deep-seated weak planes is a universal and important problem encountered in the construction of dams. There is no recommended method for stability analysis of the dam on deep-seated weak planes under earthquake condition in Chinese design codes. Taking Tingzikou dam as an example, the research in this paper is focused on searching a proper way to evaluate the seismic safety of the dam against sliding along deep-seated weak planes and the probable failure modes of dam on deep-seated weak planes during earthquake. It is concluded that there are two probable failure modes of the dam along the main weak geological planes in the foundation. In the first mode, the concrete tooth under the dam will be cut and then the dam together with part foundation will slide along the muddy layer; in the second mode, the dam together with part foundation will slide along the path consist of the weak rock layer under the tooth and the muddy layer downstream the tooth. While there is no geological structure planes to form the second slip surface, the intersection of the main and the second slip surface is 40 to 80 m downstream from dam toe, and the angle between the second slip surface and the horizontal plane probably be 25 to 45 degrees.

关键词： gravity dam     deep-seated weak planes     stability against sliding     earthquake    

HTML PDF 收藏

对公路桥梁剩余寿命评估时可变荷载取值的研究

索清辉,钱永久,张方

《中国工程科学》 2004年 第6卷 第5期   页码 52-55

摘要：

文章以现行公路桥梁设计荷载为基础，采用后继服役期超越评估荷载的概率等于设计使用期超越设计荷载概率的原则，给出了现有公路桥梁结构可靠性评估时可变荷载取值的修正系数；利用时变安全可靠度理论，对现有结构的剩余寿命进行评估，提出了对可变荷载取值进行修正的方法。

关键词： 桥梁结构     可变荷载     等超越概率     时变可靠度     后继服役期    

HTML PDF 收藏

Survey on deep learning for pulmonary medical imaging

Jiechao Ma, Yang Song, Xi Tian, Yiting Hua, Rongguo Zhang, Jianlin Wu

《医学前沿（英文）》 2020年 第14卷 第4期   页码 450-469 doi: 10.1007/s11684-019-0726-4

摘要： As a promising method in artificial intelligence, deep learning has been proven successful in several domains ranging from acoustics and images to natural language processing. With medical imaging becoming an important part of disease screening and diagnosis, deep learning-based approaches have emerged as powerful techniques in medical image areas. In this process, feature representations are learned directly and automatically from data, leading to remarkable breakthroughs in the medical field. Deep learning has been widely applied in medical imaging for improved image analysis. This paper reviews the major deep learning techniques in this time of rapid evolution and summarizes some of its key contributions and state-of-the-art outcomes. The topics include classification, detection, and segmentation tasks on medical image analysis with respect to pulmonary medical images, datasets, and benchmarks. A comprehensive overview of these methods implemented on various lung diseases consisting of pulmonary nodule diseases, pulmonary embolism, pneumonia, and interstitial lung disease is also provided. Lastly, the application of deep learning techniques to the medical image and an analysis of their future challenges and potential directions are discussed.

关键词： deep learning     neural networks     pulmonary medical image     survey    

HTML PDF 收藏

Advanced finite element analysis of a complex deep excavation case history in Shanghai

Yuepeng DONG, Harvey BURD, Guy HOULSBY, Yongmao HOU

《结构与土木工程前沿（英文）》 2014年 第8卷 第1期   页码 93-100 doi: 10.1007/s11709-014-0232-3

摘要： The construction of the North Square Shopping Center of the Shanghai South Railway Station is a large scale complex top-down deep excavation project. The excavation is adjacent to several current and newly planned Metro lines, and influenced by a neighboring Exchange Station excavation. The highly irregular geometry of this excavation greatly increases the complexity in 3D Finite Element modeling. The advanced numerical modeling described in this paper includes detailed structural and geotechnical behavior. Important features are considered in the analysis, e.g., 1) the small-strain stiffness of the soil, 2) the construction joints in the diaphragm wall, 3) the shrinkage in the concrete floor slabs and beams, 4) the complex construction sequences, and 5) the shape effect of the deep excavation. The numerical results agree well with the field data, and some valuable conclusions are generated.

关键词： advanced finite element analysis     deep excavations     case history     small-strain stiffness    

HTML PDF 收藏

Theoretical and technological exploration of deep

Heping XIE, Yang JU, Shihua REN, Feng GAO, Jianzhong LIU, Yan ZHU

《能源前沿（英文）》 2019年 第13卷 第4期   页码 603-611 doi: 10.1007/s11708-019-0643-x

摘要： Mining industries worldwide have inevitably resorted to exploiting resources from the deep underground. However, traditional mining methods can cause various problems, e.g., considerable mining difficulty, environmental degradations, and frequent disastrous accidents. To exploit deep resources in the future, the concept of mining must be reconsidered and innovative new theories, methods, and technologies must be applied. To effectively acquire coal resources deeper than 2000 m, new theoretical and technological concepts about deep fluidized mining are required. The limits of mining depth need to be broken to acquire deep-coal resources in an environmentally friendly, safe, and efficient manner. This is characterized by ‘There are no coal on the ground and no men in the coal mine’. First, this paper systematically explains deep fluidized coal mining. Then, it presents a new theoretical concept, including the theories of mining-induced rock mechanics, three-field visualization, multi-physics coupling for transformation, and mining, transformation and transport. It also presents key technological concepts, including those of intelligent, unmanned, and fluidized mining. Finally, this paper presents a strategic roadmap for deep fluidized coal mining. In summary, this paper develops new theoretical and technological systems for accomplishing groundbreaking innovations in mining technologies of coal resources in the deep underground.

关键词： coal resource     deep in situ     fluidized mining     theoretical system     key technologies     strategic roadmap    

HTML PDF 收藏

标题 作者 时间 类型 操作

Development and deep-sea exploration of the Haidou-1

期刊论文

RETRACTED ARTICLE: Using a Newton-type technique for smart meters estimation frequency of electric power

Tanveer AHMAD,Qadeer UI HASAN

期刊论文

Effect of harmonic distortion on electric energy meters of different metrological principles

Illia DIAHOVCHENKO, Vitalii VOLOKHIN, Victoria KUROCHKINA, Michal ŠPES, Michal KOSTEREC

期刊论文

DSM in an area consisting of residential, commercial and industrial load in smart grid

Balasubramaniyan SARAVANAN

期刊论文

智能控制——超越世纪的目标——国际自动控制联合会第14次代表大会报告

宋健

期刊论文

Digital image correlation-based structural state detection through deep learning

期刊论文

Dynamic prediction of moving trajectory in pipe jacking: GRU-based deep learning framework

期刊论文

A new automatic convolutional neural network based on deep reinforcement learning for fault diagnosis

期刊论文

Multiclass classification based on a deep convolutional

Ying CAI,Meng-long YANG,Jun LI

期刊论文

Hybrid deep learning model for risk prediction of fracture in patients with diabetes and osteoporosis

期刊论文

Stability analysis on Tingzikou gravity dam along deep-seated weak planes during earthquake

Weiping HE, Yunlong HE

期刊论文

对公路桥梁剩余寿命评估时可变荷载取值的研究

索清辉,钱永久,张方

期刊论文

Survey on deep learning for pulmonary medical imaging

Jiechao Ma, Yang Song, Xi Tian, Yiting Hua, Rongguo Zhang, Jianlin Wu

期刊论文

Advanced finite element analysis of a complex deep excavation case history in Shanghai

Yuepeng DONG, Harvey BURD, Guy HOULSBY, Yongmao HOU

期刊论文

Theoretical and technological exploration of deep

Heping XIE, Yang JU, Shihua REN, Feng GAO, Jianzhong LIU, Yan ZHU

期刊论文