资源类型

期刊论文 616

会议视频 21

年份

2023 48

2022 55

2021 60

2020 51

2019 35

2018 33

2017 43

2016 27

2015 22

2014 11

2013 27

2012 16

2011 28

2010 21

2009 26

2008 19

2007 26

2006 22

2005 11

2004 3

展开 ︾

关键词

发展趋势 21

智能制造 4

能源 4

仿真 3

地震预测 3

预测 3

CAN总线 2

人工智能 2

储层预测 2

关键技术 2

农业科学 2

发展前景 2

天然气 2

实时控制 2

实时服务 2

时间序列 2

机器学习 2

神经网络 2

颠覆性技术 2

展开 ︾

检索范围：

排序： 展示方式：

Trend detection and stochastic simulation prediction of streamflow at Yingluoxia hydrological station

Chenglong ZHANG,Mo LI,Ping GUO

《农业科学与工程前沿（英文）》 2017年 第4卷 第1期   页码 81-96 doi: 10.15302/J-FASE-2016112

摘要： Investigating long-term variation and prediction of streamflow are critical to regional water resource management and planning. Under the continuous influence of climate change and human activity, the trends of hydrologic time series are nonstationary, and consequently the established methods for hydrological frequency analysis are no longer applicable. Five methods, including the linear regression, nonlinear regression, change point analysis, wavelet analysis and Hilbert-Huang transformation, were first selected to detect and identify the deterministic and stochastic components of streamflow. The results indicated there was a significant long-term increasing trend. To test the applicability of these five methods, a comprehensive weighted index was then used to assess their performance. This index showed that the linear regression was the best method. Secondly, using the normality test for stochastic components separated by the linear regression method, a normal distribution requirement was satisfied. Next, the Monte Carlo stochastic simulation technique was used to simulate these stochastic components with normal distribution, and thus a new ensemble hydrological time series was obtained by combining the corresponding deterministic components. Finally, according to these outcomes, the streamflow at different frequencies in 2020 was predicted.

关键词： Monte Carlo     nonstationary     trend detection     streamflow prediction     decomposition and ensemble     Yingluoxia    

HTML PDF 收藏

Trend prediction technology of condition maintenance for large water injection units

Xiaoli XU, Sanpeng DENG

《机械工程前沿（英文）》 2010年 第5卷 第2期   页码 171-175 doi: 10.1007/s11465-009-0091-0

摘要： Trend prediction technology is the key technology to achieve condition-based maintenance of mechanical equipment. Large-sized water injection units are key equipment in oilfields. The traditional preventive maintenance is not economical and cannot completely avoid vicious accidents. To ensure the normal operation of units and save maintenance costs, trend prediction technology is studied to achieve condition-based maintenance for water injection units. The main methods of the technology are given, the trend prediction method based on neural network is put forward, and the expert system based on the knowledge is developed. The industrial site verification shows that the proposed trend prediction technology can reflect the operating condition trend change of the water injection units and provide technical means to achieve condition-based predictive maintenance.

关键词： water injection units     condition-based maintenance     trend prediction    

HTML PDF 收藏

Symbolic representation based on trend features for knowledge discovery in long time series

Hong YIN,Shu-qiang YANG,Xiao-qian ZHU,Shao-dong MA,Lu-min ZHANG

《信息与电子工程前沿（英文）》 2015年 第16卷 第9期   页码 744-758 doi: 10.1631/FITEE.1400376

摘要： The symbolic representation of time series has attracted much research interest recently. The high dimensionality typical of the data is challenging, especially as the time series becomes longer. The wide distribution of sensors collecting more and more data exacerbates the problem. Representing a time series effectively is an essential task for decision-making activities such as classification, prediction, and knowledge discovery. In this paper, we propose a new symbolic representation method for long time series based on trend features, called trend feature symbolic approximation (TFSA). The method uses a two-step mechanism to segment long time series rapidly. Unlike some previous symbolic methods, it focuses on retaining most of the trend features and patterns of the original series. A time series is represented by trend symbols, which are also suitable for use in knowledge discovery, such as association rules mining. TFSA provides the lower bounding guarantee. Experimental results show that, compared with some previous methods, it not only has better segmentation efficiency and classification accuracy, but also is applicable for use in knowledge discovery from time series.

关键词： Long time series     Segmentation     Trend features     Symbolic     Knowledge discovery    

HTML PDF 收藏

Physics-Informed Deep Learning-Based Real-Time Structural Response Prediction Method

Ying Zhou,Shiqiao Meng,Yujie Lou,Qingzhao Kong,

《工程（英文）》 doi: 10.1016/j.eng.2023.08.011

摘要： High-precision and efficient structural response prediction is essential for intelligent disaster prevention and mitigation in building structures, including post-earthquake damage assessment, structural health monitoring, and seismic resilience assessment of buildings. To improve the accuracy and efficiency of structural response prediction, this study proposes a novel physics-informed deep-learning-based real-time structural response prediction method that can predict a large number of nodes in a structure through a data-driven training method and an autoregressive training strategy. The proposed method includes a Phy-Seisformer model that incorporates the physical information of the structure into the model, thereby enabling higher-precision predictions. Experiments were conducted on a four-story masonry structure, an eleven-story reinforced concrete irregular structure, and a twenty-one-story reinforced concrete frame structure to verify the accuracy and efficiency of the proposed method. In addition, the effectiveness of the structure in the Phy-Seisformer model was verified using an ablation study. Furthermore, by conducting a comparative experiment, the impact of the range of seismic wave amplitudes on the prediction accuracy was studied. The experimental results show that the method proposed in this paper can achieve very high accuracy and at least 5000 times faster calculation speed than finite element calculations for different types of building structures.

关键词： Structural seismic response prediction     Physics information informed     Real-time prediction     Earthquake engineering     Data-driven machine learning    

HTML PDF 收藏

Allocation of grassland, livestock and arable based on the spatial and temporal analysis for food demand in China

Huilong LIN, Ruichao LI, Yifan LIU, Jingrong ZHANG, Jizhou REN

《农业科学与工程前沿（英文）》 2017年 第4卷 第1期   页码 69-80 doi: 10.15302/J-FASE-2017140

摘要： To explore the distribution of food demand and the projected trend in future food demand in China, this paper analyzed the change in current (1998–2012) per-capita demand for grain, grain-consuming and herbivorous livestock products, and predicted the food demand in 2020. The results indicated that in 1998–2012, the national per-capita consumption of grain ration declined by about 36.66%, and the per-capita consumption of grain-consu-ming and herbivorous livestock products increased by about 48% and 34.09%, respectively. The grain-consu-ming livestock products have become the primary source of both calories and protein for consumers. The proportion of herbivorous livestock products in consumer diets has increased steadily and there has been huge potential in substituting beef and mutton for pork in this dynamic market. The demand for food in different provinces of China is highly variable, which is important for planning grassland agriculture development and ensuring food safety. The demand for grain, and grain-consuming and herbivorous livestock products will increase by about 3.3%, 20% and 14% respectively by 2020. Based on the food demand and trend in the development of grassland agriculture, the 31 provinces in China are divided into three priority groups for grassland agriculture development.

关键词： arable land equivalent unit (ALEU)     food equivalent unit (FEU)     food security     grassland agriculture     time trend prediction    

HTML PDF 收藏

Performance prediction of switched reluctance generator with time average and small signal models

Jyoti KOUJALAGI, B. UMAMAHESWARI, R. ARUMUGAM

《能源前沿（英文）》 2013年 第7卷 第1期   页码 56-68 doi: 10.1007/s11708-012-0216-8

摘要： This paper presents the complete mathematical model and predicts the performance of switched reluctance generator with time average and small signal models. The complete mathematical model is developed in three stages. First, a switching model is developed based on quasi-linear inductance profile. Next, based on the switching behaviour, a time average model is obtained to measure the difference between the excitation and generation time in each switching cycle. Finally, to track control voltage and current wave shapes, a small signal model is designed. The effectiveness of the complete multilevel model combining electrical machine, power converter, load and control with programming language is demonstrated through simulations. A PI controller is used for controlling the voltage of the generator. The results presented show that the controller exhibits accurate tracking control of load voltage under different operating conditions. This demonstrates that the proposed model is able to perform an accurate control of the generated output voltage even in transient situations. The simulation is performed to choose the control parameters and study the performance of switched reluctance generator prior to its actual implementation. Initial experimental results are presented using NI-Data acquisition card to control the output power according to load requirements.

关键词： generator     reluctance     switching model     small signal model     time average model    

HTML PDF 收藏

Time-series prediction based on global fuzzy measure in social networks

Li-ming YANG,Wei ZHANG,Yun-fang CHEN

《信息与电子工程前沿（英文）》 2015年 第16卷 第10期   页码 805-816 doi: 10.1631/FITEE.1500025

摘要： Social network analysis (SNA) is among the hottest topics of current research. Most measurements of SNA methods are certainty oriented, while in reality, the uncertainties in relationships are widely spread to be overridden. In this paper, fuzzy concept is introduced to model the uncertainty, and a similarity metric is used to build a fuzzy relation model among individuals in the social network. The traditional social network is transformed into a fuzzy network by replacing the traditional relations with fuzzy relation and calculating the global fuzzy measure such as network density and centralization. Finally, the trend of fuzzy network evolution is analyzed and predicted with a fuzzy Markov chain. Experimental results demonstrate that the fuzzy network has more superiority than the traditional network in describing the network evolution process.

关键词： Time-series network     Fuzzy network     Fuzzy Markov chain    

HTML PDF 收藏

Short-term prediction of the influent quantity time series of wastewater treatment plant based on a chaos

LI Xiaodong, ZENG Guangming, HUANG Guohe, LI Jianbing, JIANG Ru

《环境科学与工程前沿（英文）》 2007年 第1卷 第3期   页码 334-338 doi: 10.1007/s11783-007-0057-6

摘要： By predicting influent quantity, a wastewater treatment plant (WWTP) can be well controlled. The nonlinear dynamic characteristic of WWTP influent quantity time series was analyzed, with the assumption that the series was predictable. Based on this, a short-term forecasting chaos neural network model of WWTP influent quantity was built by phase space reconstruction. Reasonable forecasting results were achieved using this method.

关键词： nonlinear     reconstruction     WWTP influent     characteristic     Reasonable forecasting    

HTML PDF 收藏

Prediction and cause investigation of ozone based on a double-stage attention mechanism recurrent neural

《环境科学与工程前沿（英文）》 2023年 第17卷 第2期 doi: 10.1007/s11783-023-1621-4

摘要：

● Used a double-stage attention mechanism model to predict ozone.

关键词： Ozone prediction     Deep learning     Time series     Attention     Volatile organic compounds    

HTML PDF 收藏

Regional seismic-damage prediction of buildings under mainshock–aftershock sequence

Xinzheng LU, Qingle CHENG, Zhen XU, Chen XIONG

《工程管理前沿（英文）》 2021年 第8卷 第1期   页码 122-134 doi: 10.1007/s42524-019-0072-x

摘要： Strong aftershocks generally occur following a significant earthquake. Aftershocks further damage buildings weakened by mainshocks. Thus, the accurate and efficient prediction of aftershock-induced damage to buildings on a regional scale is crucial for decision making for post-earthquake rescue and emergency response. A framework to predict regional seismic damage of buildings under a mainshock–aftershock (MS–AS) sequence is proposed in this study based on city-scale nonlinear time-history analysis (THA). Specifically, an MS–AS sequence-generation method is proposed to generate a potential MS–AS sequence that can account for the amplification, spectrum, duration, magnitude, and site condition of a target area. Moreover, city-scale nonlinear THA is adopted to predict building seismic damage subjected to MS–AS sequences. The accuracy and reliability of city-scale nonlinear THA for an MS–AS sequence are validated by as-recorded seismic responses of buildings and simulation results in published literature. The town of Longtoushan, which was damaged during the Ludian earthquake, is used as a case study to illustrate the detailed procedure and advantages of the proposed framework. The primary conclusions are as follows. (1) Regional seismic damage of buildings under an MS–AS sequence can be predicted reasonably and accurately by city-scale nonlinear THA. (2) An MS–AS sequence can be generated reasonably by the proposed MS–AS sequence-generation method. (3) Regional seismic damage of buildings under different MS–AS scenarios can be provided efficiently by the proposed framework, which in turn can provide a useful reference for earthquake emergency response and scientific decision making for earthquake disaster relief.

关键词： regional seismic damage prediction     city-scale nonlinear time-history analysis     mainshock–aftershock sequence     multiple degree-of-freedom (MDOF) model     2014 Ludian earthquake    

HTML PDF 收藏

Short-term prediction of influent flow rate and ammonia concentration in municipal wastewater treatment

Shuai MA, Siyu ZENG, Xin DONG, Jining CHEN, Gustaf OLSSON

《环境科学与工程前沿（英文）》 2014年 第8卷 第1期   页码 128-136 doi: 10.1007/s11783-013-0598-9

摘要： The prediction of the influent load is of great importance for the improvement of the control system to a large wastewater treatment plant. A systematic data analysis method is presented in this paper in order to estimate and predict the periodicity of the influent flow rate and ammonia (NH ) concentrations: 1) data filtering using wavelet decomposition and reconstruction; 2) typical cycle identification using power spectrum density analysis; 3) fitting and prediction model establishment based on an autoregressive model. To give meaningful information for feedforward control systems, predictions in different time scales are tested to compare the corresponding predicting accuracy. Considering the influence of the rainfalls, a linear fitting model is derived to estimate the relationship between flow rate trend and rain events. Measurements used to support coefficient fitting and model testing are acquired from two municipal wastewater treatment plants in China. The results show that 1) for both of the two plants, the periodicity affects the flow rate and NH concentrations in different cycles (especially cycles longer than 1 day); 2) when the flow rate and NH concentrations present an obvious periodicity, the decreasing of prediction accuracy is not distinct with increasing of the prediction time scales; 3) the periodicity influence is larger than rainfalls; 4) the rainfalls will make the periodicity of flow rate less obvious in intensive rainy periods.

关键词： influent load prediction     wavelet de-noising     power spectrum density     autoregressive model     time-frequency analysis     wastewater treatment    

HTML PDF 收藏

Employing electricity-consumption monitoring systems and integrative time-series analysis models: A case

Seiya MAKI, Shuichi ASHINA, Minoru FUJII, Tsuyoshi FUJITA, Norio YABE, Kenji UCHIDA, Gito GINTING, Rizaldi BOER, Remi CHANDRAN

《能源前沿（英文）》 2018年 第12卷 第3期   页码 426-439 doi: 10.1007/s11708-018-0560-4

摘要：

The Paris Agreement calls for maintaining a global temperature less than 2°C above the pre-industrial level and pursuing efforts to limit the temperature increase even further to 1.5°C. To realize this objective and promote a low-carbon society, and because energy production and use is the largest source of global greenhouse-gas (GHG) emissions, it is important to efficiently manage energy demand and supply systems. This, in turn, requires theoretical and practical research and innovation in smart energy monitoring technologies, the identification of appropriate methods for detailed time-series analysis, and the application of these technologies at urban and national scales. Further, because developing countries contribute increasing shares of domestic energy consumption, it is important to consider the application of such innovations in these areas. Motivated by the mandates set out in global agreements on climate change and low-carbon societies, this paper focuses on the development of a smart energy monitoring system (SEMS) and its deployment in households and public and commercial sectors in Bogor, Indonesia. An electricity demand prediction model is developed for each device using the Auto-Regression eXogenous model. The real-time SEMS data and time-series clustering to explore similarities in electricity consumption patterns between monitored units, such as residential, public, and commercial buildings, in Bogor is, then, used. These clusters are evaluated using peak demand and Ramadan term characteristics. The resulting energy-prediction models can be used for low-carbon planning.

关键词： electricity monitoring     electricity demand prediction     multiple-variable time-series modeling     time-series cluster analysis     Indonesia    

HTML PDF 收藏

施工现场安全危险源实时监控与安全风险预测方法研究

吴伟巍,Patrick T. I. LAM,李启明,Michael C. H. YAM,David A. S. CHEW

《中国工程科学》 2010年 第12卷 第3期   页码 68-72

摘要：

对国内外建筑业施工现场安全风险的研究进行了文献综述，针对目前研究的不足之处，提出了施工现场安全危险源实时监控和安全风险实时预测的示意性模型，并详细解释了该模型的含义和方法。研究将提供一种基于前馈信号的施工现场安全危险源实时监控和安全风险实时预测的方法；并通过将现有研究的视角引入到施工现场关键安全危险源的前馈信号上，为进一步的研究打下良好的理论基础。

关键词： 施工现场     安全风险     实时预测     前馈信号     信号检测理论    

HTML PDF 收藏

齿轮技术的创新和发展趋势

梁桂明

《中国工程科学》 2000年 第2卷 第3期   页码 1-6

摘要：

最早的齿轮是怎样发明出来的？它源于何方？用于何处？——这是近百年来人们在探索的一个谜。 两千年前，在中国、印度、希腊、罗马、埃及出土和出水的铸铁齿轮与青铜齿轮似乎解开了这个谜。其实不然， 它们只是第2代齿轮。第1代齿轮是木制齿轮。它源于四千年前，各文明古国发明水力机械中伴生。这是由于 这些文明古国聚居大河与海湾，与水有“缘分”所致。第2代齿轮的辉煌点表现在公元前200年中国的发明 ——指南车上。它在世界上第一次发明了差动机构，第一次实现半自动控制机构，第一次出现有走向功能的机 器人。1800年工业革命带来了第3代齿轮，其特征是用直刃刀具成批生产渐开线的钢制齿轮形成了现代齿轮的 技术平台。进人21世纪，以高强度复合材料代替资源匮乏的钢材，标志着新一代（第4代）齿轮的到来，它将 与知识经济共存。未来50年齿轮创新的趋势，是追求小化、净化、静化，高可靠性、高强度、高转速和低材 耗、低能耗、低重量。

关键词： 齿轮     创新     发展趋势    

HTML PDF 收藏

一种基于充电模式识别的电动汽车充电时间预测方法 Research Article

李春喜1,傅莹颖1,崔向科2,葛泉波3,4,5

《信息与电子工程前沿（英文）》 2023年 第24卷 第2期   页码 299-313 doi: 10.1631/FITEE.2200212

摘要： 电动汽车动力电池过度充电容易导致电池加速老化和严重的安全事故。因此，准确预测车辆充电时间对充电安全防护意义重大。由于电池组结构复杂，充电方式多样，传统方法因缺乏充电模式识别而预测精度不高。本文应用数据驱动和机器学习理论，提出一种新的基于充电模式识别的充电时间预测方法。首先，基于动态加权密度峰值聚类（DWDPC）和随机森林融合的智能算法对车辆充电模式进行分类；然后，采用改进的简化粒子群优化算法（ISPSO）和强跟踪滤波器（STF），对LSTM神经网络进行优化，构建了一种高性能的充电时间预测方法；最后，通过实际工程数据对所提出的ISPSO-LSTM-STF方法进行了验证。实验结果表明，该方法能够有效区分充电模式，提高了充电时间预测精度，具有实际工程意义。

关键词： 充电模式；充电时长；随机森林；长短期记忆网络（LSTM）；简化粒子群优化算法（SPSO）    

HTML PDF 收藏

标题 作者 时间 类型 操作

Trend detection and stochastic simulation prediction of streamflow at Yingluoxia hydrological station

Chenglong ZHANG,Mo LI,Ping GUO

期刊论文

Trend prediction technology of condition maintenance for large water injection units

Xiaoli XU, Sanpeng DENG

期刊论文

Symbolic representation based on trend features for knowledge discovery in long time series

Hong YIN,Shu-qiang YANG,Xiao-qian ZHU,Shao-dong MA,Lu-min ZHANG

期刊论文

Physics-Informed Deep Learning-Based Real-Time Structural Response Prediction Method

Ying Zhou,Shiqiao Meng,Yujie Lou,Qingzhao Kong,

期刊论文

Allocation of grassland, livestock and arable based on the spatial and temporal analysis for food demand in China

Huilong LIN, Ruichao LI, Yifan LIU, Jingrong ZHANG, Jizhou REN

期刊论文

Performance prediction of switched reluctance generator with time average and small signal models

Jyoti KOUJALAGI, B. UMAMAHESWARI, R. ARUMUGAM

期刊论文

Time-series prediction based on global fuzzy measure in social networks

Li-ming YANG,Wei ZHANG,Yun-fang CHEN

期刊论文

Short-term prediction of the influent quantity time series of wastewater treatment plant based on a chaos

LI Xiaodong, ZENG Guangming, HUANG Guohe, LI Jianbing, JIANG Ru

期刊论文

Prediction and cause investigation of ozone based on a double-stage attention mechanism recurrent neural

期刊论文

Regional seismic-damage prediction of buildings under mainshock–aftershock sequence

Xinzheng LU, Qingle CHENG, Zhen XU, Chen XIONG

期刊论文

Short-term prediction of influent flow rate and ammonia concentration in municipal wastewater treatment

Shuai MA, Siyu ZENG, Xin DONG, Jining CHEN, Gustaf OLSSON

期刊论文

Employing electricity-consumption monitoring systems and integrative time-series analysis models: A case

Seiya MAKI, Shuichi ASHINA, Minoru FUJII, Tsuyoshi FUJITA, Norio YABE, Kenji UCHIDA, Gito GINTING, Rizaldi BOER, Remi CHANDRAN

期刊论文

施工现场安全危险源实时监控与安全风险预测方法研究

吴伟巍,Patrick T. I. LAM,李启明,Michael C. H. YAM,David A. S. CHEW

期刊论文

齿轮技术的创新和发展趋势

梁桂明

期刊论文

一种基于充电模式识别的电动汽车充电时间预测方法

李春喜1,傅莹颖1,崔向科2,葛泉波3,4,5

期刊论文