检索范围:
排序: 展示方式:
Novel interpretable mechanism of neural networks based on network decoupling method
《工程管理前沿(英文)》 2021年 第8卷 第4期 页码 572-581 doi: 10.1007/s42524-021-0169-x
关键词: neural networks interpretability dynamical behavior network decouple
J. Sargolzaei, A. Hedayati Moghaddam
《化学科学与工程前沿(英文)》 2013年 第7卷 第3期 页码 357-365 doi: 10.1007/s11705-013-1336-3
关键词: oil recovery artificial intelligence extraction neural networks supercritical extraction
Tiago Miguel FERREIRA, João ESTÊVÃO, Rui MAIO, Romeu VICENTE
《结构与土木工程前沿(英文)》 2020年 第14卷 第3期 页码 609-622 doi: 10.1007/s11709-020-0623-6
关键词: Artificial Neural Networks seismic vulnerability masonry buildings damage estimation vulnerability curves
T. Chandra Sekhara REDDY
《结构与土木工程前沿(英文)》 2018年 第12卷 第4期 页码 490-503 doi: 10.1007/s11709-017-0445-3
关键词: artificial neural networks root mean square error SIFCON silica fume metakaolin steel fiber
S. Surender REDDY,Chan-Mook JUNG,Ko Jun SEOG
《能源前沿(英文)》 2016年 第10卷 第1期 页码 105-113 doi: 10.1007/s11708-016-0393-y
关键词: day-ahead electricity markets price forecasting load forecasting artificial neural networks load serving entities
Alireza TABARSA, Nima LATIFI, Abdolreza OSOULI, Younes BAGHERI
《结构与土木工程前沿(英文)》 2021年 第15卷 第2期 页码 520-536 doi: 10.1007/s11709-021-0689-9
关键词: unconfined compressive strength artificial neural network support vector machine predictive models regression
Yasser SHARIFI,Sajjad TOHIDI
《结构与土木工程前沿(英文)》 2014年 第8卷 第2期 页码 167-177 doi: 10.1007/s11709-014-0236-z
关键词: steel I-beams lateral-torsional buckling finite element (FE) method artificial neural network (ANN) approach
张俊艳,冯守中,刘东海
《中国工程科学》 2005年 第7卷 第10期 页码 87-90
传统回归方法对于围岩变形时程曲线存在反弯点,这种情况的模拟具有难度。提出的基于RBF神经网络的隧道围岩变形预测方法,不仅能很好地描述复杂的围岩变形时程曲线,而且比BP神经网络具有更快的收敛速度和更好的全局搜索能力。实例研究验证了该方法的有效性与可行性。
可见光波段的深度衍射神经网络 Article
陈航, 冯佳楠, 江闽伟, 王逸群, 林杰, 谭久彬, 金鹏
《工程(英文)》 2021年 第7卷 第10期 页码 1485-1493 doi: 10.1016/j.eng.2020.07.032
基于衍射光学元件的光学深度学习在并行处理、计算速度和计算效率方面有着独特优势。深度衍射神经网络(D2NN)是其中一项具有里程碑意义的研究工作。D2NN在太赫兹波段通过3D打印进行神经网络的物理固化。鉴于太赫兹波段下存在的粒子间耦合限制和材料损耗,本文将D2NN的应用波段延展至可见光波段,并提出了包括修订公式在内的一般理论,解决了工作波长、人工神经元特征尺寸和加工制备之间的矛盾。在632.8 nm的工作波长下,本文提出了一种新颖的可见光D2NN分类器,可用于原始目标(手写数字0~9)和已更改目标(被遮盖和涂改目标)的目标识别。本文获得的实验分类精度(84%)和数值分类精度(91.57%)量化了理论设计和制造系统性能之间的匹配程度。本文所提出的一般理论模型可将D2NN应用于各种实际问题或设计全新的应用场景。
Ahmad MOZAFFARI,Mahyar VAJEDI,Nasser L. AZAD
《机械工程前沿(英文)》 2015年 第10卷 第2期 页码 154-167 doi: 10.1007/s11465-015-0336-z
The main proposition of the current investigation is to develop a computational intelligence-based framework which can be used for the real-time estimation of optimum battery state-of-charge (SOC) trajectory in plug-in hybrid electric vehicles (PHEVs). The estimated SOC trajectory can be then employed for an intelligent power management to significantly improve the fuel economy of the vehicle. The devised intelligent SOC trajectory builder takes advantage of the upcoming route information preview to achieve the lowest possible total cost of electricity and fossil fuel. To reduce the complexity of real-time optimization, the authors propose an immune system-based clustering approach which allows categorizing the route information into a predefined number of segments. The intelligent real-time optimizer is also inspired on the basis of interactions in biological immune systems, and is called artificial immune algorithm (AIA). The objective function of the optimizer is derived from a computationally efficient artificial neural network (ANN) which is trained by a database obtained from a high-fidelity model of the vehicle built in the Autonomie software. The simulation results demonstrate that the integration of immune inspired clustering tool, AIA and ANN, will result in a powerful framework which can generate a near global optimum SOC trajectory for the baseline vehicle, that is, the Toyota Prius PHEV. The outcomes of the current investigation prove that by taking advantage of intelligent approaches, it is possible to design a computationally efficient and powerful SOC trajectory builder for the intelligent power management of PHEVs.
关键词: trip information preview intelligent transportation state-of-charge trajectory builder immune systems artificial neural network
Service life prediction of fly ash concrete using an artificial neural network
《结构与土木工程前沿(英文)》 2021年 第15卷 第3期 页码 793-805 doi: 10.1007/s11709-021-0717-9
关键词: concrete fly ash carbonation neural networks experimental validation service life
《环境科学与工程前沿(英文)》 2023年 第17卷 第1期 doi: 10.1007/s11783-023-1606-3
● Reducting the sampling frequency can enhance the modelling process.
关键词: HDPE Pyrolysis Kinetics Thermogravimetric ANOVA Artificial neural network
张俊艳,魏连伟,韩文秀,邵景力,崔亚丽,张建立
《中国工程科学》 2004年 第6卷 第8期 页码 74-78
水文地质参数识别问题是水文地质学上的一个难题。针对传统水文地质参数识别方法的局限性,提出了水文地质参数识别的径向基函数(RBF )神经网络方法,并通过算例验证了它的可行性与有效性,实现了水文地质参数的自动识别,提高了计算效率,比BP神经网络具有更好的参数识别效果。
关键词: 地下水 水文地质参数 径向基函数(RBF)神经网络 BP神经网络
标题 作者 时间 类型 操作
Predicting the yield of pomegranate oil from supercritical extraction using artificial neural networks
J. Sargolzaei, A. Hedayati Moghaddam
期刊论文
The use of Artificial Neural Networks to estimate seismic damage and derive vulnerability functions for
Tiago Miguel FERREIRA, João ESTÊVÃO, Rui MAIO, Romeu VICENTE
期刊论文
Predicting the strength properties of slurry infiltrated fibrous concrete using artificial neural network
T. Chandra Sekhara REDDY
期刊论文
Day-ahead electricity price forecasting using back propagation neural networks and weighted least square
S. Surender REDDY,Chan-Mook JUNG,Ko Jun SEOG
期刊论文
Unconfined compressive strength prediction of soils stabilized using artificial neural networks and support
Alireza TABARSA, Nima LATIFI, Abdolreza OSOULI, Younes BAGHERI
期刊论文
Lateral-torsional buckling capacity assessment of web opening steel girders by artificial neural networks
Yasser SHARIFI,Sajjad TOHIDI
期刊论文
immune-inspired optimum state-of-charge trajectory estimation using upcoming route information preview and neuralnetworks for plug-in hybrid electric vehicles fuel economy
Ahmad MOZAFFARI,Mahyar VAJEDI,Nasser L. AZAD
期刊论文
high-density polyethylene pyrolysis using kinetic parameters based on thermogravimetric and artificial neuralnetworks
期刊论文