您的检索：
学者姓名：王普
精炼检索结果：
年份
成果类型
收录类型
来源
综合
曾用名
合作者
语言
清除所有精炼条件
摘要 ：
一种基于改进Levenberg‑Marquardt的径向基神经网络优化方法，属于参数优化技术领域。主要包括三个部分，即“典型样本选取”，“改进Levenberg‑Marquardt的参数优化”和“多步更新规则”。“典型样本选取”步骤：典型样本可以用来近似样本整体，利用样本之间的最小距离来表示多样性构建典型样本集，可以在网络稳定性和快速响应之间取得较好平衡。“改进的LM参数优化”步骤：利用模型参数组合重新定义学习率，消除了奇异点，保证了模型的有效稳定。“多步更新规则”步骤：通过计算典型样本集中的Hessian矩阵和梯度，使用多步更新规则以减少单个样本引入的样本误差，加速了网络收敛。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 杨彦霞 , 王普 , 高学金 . 一种基于改进Levenberg-Marquardt的径向基神经网络优化方法 : CN202111433963.7[P]. | 2021-11-29 . |
| MLA | 杨彦霞 等. "一种基于改进Levenberg-Marquardt的径向基神经网络优化方法" : CN202111433963.7. | 2021-11-29 . |
| APA | 杨彦霞 , 王普 , 高学金 . 一种基于改进Levenberg-Marquardt的径向基神经网络优化方法 : CN202111433963.7. | 2021-11-29 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明公开了一种基于自动聚类结合偏最小二乘的间歇过程质量预测方法。针对间歇过程的多阶段性特征，目前已有的阶段划分方法很少考虑质量相关变量对阶段划分结果的影响。本发明在划分阶段前利用典型相关分析(canonical correlation analysis，CCA)对间歇过程数据进行特征选择，在保证其过程变量以及质量相关变量之间相关关系最大时找到其最优的线性表示。该过程不仅可以实现数据降维，同时考虑质量相关变量对划分结果的影响。最终，在DBSCAN划分阶段内建立基于MPLS的质量预测模型。将该算法在青霉素发酵仿真实验平台进行了实验验证，实验结果证明了本方法的可行性和有效性。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 王雨 , 王普 , 高学金 et al. 一种基于自动聚类结合偏最小二乘的间歇过程质量预测方法 : CN202110258605.0[P]. | 2021-03-09 . |
| MLA | 王雨 et al. "一种基于自动聚类结合偏最小二乘的间歇过程质量预测方法" : CN202110258605.0. | 2021-03-09 . |
| APA | 王雨 , 王普 , 高学金 , 高慧慧 , 韩华云 . 一种基于自动聚类结合偏最小二乘的间歇过程质量预测方法 : CN202110258605.0. | 2021-03-09 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Fault monitoring can find out-of-control conditions of equipment operation in a timely manner, which is essential for eliminating faults and for stable operation of industrial systems in batch processes. Many conventional data-driven fault detection methods focus less on the non-Gaussian and Multi-stage characteristics of batch process data, which may result in degradation of monitoring performance. In this paper, a Multi-stage Fourth Order Moment Staked Autoencoder (M-FOM-SAE) is designed to solve the above problems. The proposed method firstly automatically determines the number of clusters and divides the batch process into multiple stages. After that, the FOM-SAE model is established in each sub-stage, which can not only effectively learn the nonlinear features of process data, but also extract the non-Gaussian information. The proposed strategy is applied to real-world industrial processes. Experimental results indicate that it can better capture the non-Gaussian and Multi-stage characteristics of process data, and improve the ability to monitor abnormalities.
关键词 ：
Fault monitoring Fault monitoring Stacked Autoencoder Stacked Autoencoder Multi-stage Multi-stage non-Gaussian non-Gaussian Batch process Batch process
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Chen, Jin , Pu, Wang , Kai, Wang . Batch Process Monitoring Based on Multi-stage Fourth Order Moment Stacked Autoencoder [C] . 2020 : 721-728 . |
| MLA | Chen, Jin et al. "Batch Process Monitoring Based on Multi-stage Fourth Order Moment Stacked Autoencoder" . (2020) : 721-728 . |
| APA | Chen, Jin , Pu, Wang , Kai, Wang . Batch Process Monitoring Based on Multi-stage Fourth Order Moment Stacked Autoencoder . (2020) : 721-728 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Aiming at nonlinearity and multimodal batch trajectories in semiconductor manufacturing processes, principal component analysis and k nearest neighbor (kNN)-related methods were previously presented. However, these methods require data unfolding and are not capable of extracting crucial features, which affects the performance of fault detection. In this paper, an automated fault detection method using convolutional auto encoder (CAE) and k nearest neighbor rule is proposed. Firstly, data collected in one batch is considered as a two-dimensional gray-scale image, and is input to CAE for feature unsupervised learning, with no need of data preprocessing and data labels. Secondly, kNN rule is incorporated into CAE to construct the monitoring index and perform fault detecting. Finally, the effectiveness of the proposed method is verified with a benchmark semiconductor manufacturing process.
关键词 ：
convolutional auto encoder convolutional auto encoder fault detection fault detection k nearest neighbor k nearest neighbor semiconductor manufacturing process semiconductor manufacturing process
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Zhang, Haili , Wang, Pu , Gao, Xuejin et al. Automated Fault Detection Using Convolutional Auto Encoder and k Nearest Neighbor Rule for Semiconductor Manufacturing Processes [C] . 2020 : 83-87 . |
| MLA | Zhang, Haili et al. "Automated Fault Detection Using Convolutional Auto Encoder and k Nearest Neighbor Rule for Semiconductor Manufacturing Processes" . (2020) : 83-87 . |
| APA | Zhang, Haili , Wang, Pu , Gao, Xuejin , Gao, Huihui , Qi, Yongsheng . Automated Fault Detection Using Convolutional Auto Encoder and k Nearest Neighbor Rule for Semiconductor Manufacturing Processes . (2020) : 83-87 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
We demonstrated MIR-pump NIR-probe photothermal spectroscopy with the first harmonic (PTS-1f) detection of formaldehyde, one of the most common volatile organic compounds (VOCs), in a silica hollow-core negative curvature fiber (HC-NCF). The photothermal gas sensor adopts a mid-infrared interband cascade pump laser at 3.6 mu m and a near-infrared fiber probe laser at 1.56 mu m. At the optimal modulation frequency (8 kHz) and modulation index (1.8) of the pump laser, we obtained a normalized noise equivalent absorption (NNEA) coefficient of 4 x 10(-9) cm(-1)WHz(-1/)2. The use of HC-NCF with an inner diameter of 65 mu m enables the sensitive photothermal detection even for a very low pump power of micro-watts. The background-free PTS-1f detection was observed to enhance the sensitivity by a factor of 2.4 compared to the second harmonic (2f) detection. A theoretical model was established in this work to interpret the experimental results.
关键词 ：
gas sensor gas sensor hollow core fiber hollow core fiber optical fiber sensor optical fiber sensor Photothermal spectroscopy Photothermal spectroscopy
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Yao, Chenyu , Gao, Shoufei , Wang, Yingying et al. MIR-Pump NIR-Probe Fiber-Optic Photothermal Spectroscopy With Background-Free First Harmonic Detection [J]. | IEEE SENSORS JOURNAL , 2020 , 20 (21) : 12709-12715 . |
| MLA | Yao, Chenyu et al. "MIR-Pump NIR-Probe Fiber-Optic Photothermal Spectroscopy With Background-Free First Harmonic Detection" . | IEEE SENSORS JOURNAL 20 . 21 (2020) : 12709-12715 . |
| APA | Yao, Chenyu , Gao, Shoufei , Wang, Yingying , Wang, Pu , Jin, Wei , Ren, Wei . MIR-Pump NIR-Probe Fiber-Optic Photothermal Spectroscopy With Background-Free First Harmonic Detection . | IEEE SENSORS JOURNAL , 2020 , 20 (21) , 12709-12715 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
A visual-inertial odometer is used to fuse the image information obtained by a vision sensor with the data measured by an inertial sensor and recover the motion track online in a global frame. However, in an indoor environment, geometric transformation, sparse features, illumination changes, blurring, and noise will occur, which will either cause a reduction in or failure of the positioning accuracy. To solve this problem, a map matching algorithm based on an indoor plane structure map is proposed to improve the positioning accuracy of the system; this algorithm was implemented using a conditional random field model. The output of the attitude information from the visual-inertial odometer was used as the input of the conditional random field model. The feature function between the attitude information and the expected value was established, and the maximum probabilistic value of the attitude was estimated. Finally, the closed-loop feedback correction of the visual-inertial system was carried out with the probabilistic attitude value. A number of experiments were designed to verify the feasibility and reliability of the positioning method proposed in this paper.
关键词 ：
conditional random field conditional random field indoor positioning system indoor positioning system map matching map matching visual-inertial odometer visual-inertial odometer
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Meng, Juan , Ren, Mingrong , Wang, Pu et al. Improving Positioning Accuracy via Map Matching Algorithm for Visual-Inertial Odometer [J]. | SENSORS , 2020 , 20 (2) . |
| MLA | Meng, Juan et al. "Improving Positioning Accuracy via Map Matching Algorithm for Visual-Inertial Odometer" . | SENSORS 20 . 2 (2020) . |
| APA | Meng, Juan , Ren, Mingrong , Wang, Pu , Zhang, Jitong , Mou, Yuman . Improving Positioning Accuracy via Map Matching Algorithm for Visual-Inertial Odometer . | SENSORS , 2020 , 20 (2) . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Ultrasensitive mid-infrared absorption spectroscopy is demonstrated by the use of a novel silica-based hollow-core negative curvature fiber (HC-NCF). The HC-NCF used in this article consists of a single ring of six nontouching cladding capillaries around the hollow core, thus forming a unique core boundary with a negative curvature. Such a silica HC-NCF enables the broadband single-mode transmission in the mid-infrared. By using the HC-NCF as a compact gas cell, a proof-of-principle experiment is conducted to detect the N2O line at 2778.37 cm(-1) with a distributed-feedback interband cascade laser emitting at 3.6 mu m. A minimum detectable absorbance of 3 x 10(-5) is achieved for a fiber length of 120 cm, corresponding to a noise equivalent absorption (NEA) coefficient of 2.5 x 10(-7) cm(-1). Silica HC-NCFs offer a new opportunity of developing sensitive and compact gas sensors using mid-infrared absorption spectroscopy.
关键词 ：
hollow core fiber hollow core fiber mid-infrared absorption spectroscopy mid-infrared absorption spectroscopy Gas sensor Gas sensor microstructured optical fiber microstructured optical fiber optical fiber sensor optical fiber sensor
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Yao, Chenyu , Gao, Shoufei , Wang, Yingying et al. Silica Hollow-Core Negative Curvature Fibers Enable Ultrasensitive Mid-Infrared Absorption Spectroscopy [J]. | JOURNAL OF LIGHTWAVE TECHNOLOGY , 2020 , 38 (7) : 2067-2072 . |
| MLA | Yao, Chenyu et al. "Silica Hollow-Core Negative Curvature Fibers Enable Ultrasensitive Mid-Infrared Absorption Spectroscopy" . | JOURNAL OF LIGHTWAVE TECHNOLOGY 38 . 7 (2020) : 2067-2072 . |
| APA | Yao, Chenyu , Gao, Shoufei , Wang, Yingying , Wang, Pu , Jin, Wei , Ren, Wei . Silica Hollow-Core Negative Curvature Fibers Enable Ultrasensitive Mid-Infrared Absorption Spectroscopy . | JOURNAL OF LIGHTWAVE TECHNOLOGY , 2020 , 38 (7) , 2067-2072 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
High-precision indoor localization plays a vital role in various places. In recent years, visual inertial odometry (VIO) system has achieved outstanding progress in the field of indoor localization. However, it is easily affected by poor lighting and featureless environments. For this problem, we propose an indoor localization algorithm based on VIO system and three-dimensional (3D) map matching. The 3D map matching is to add height matching on the basis of previous two-dimensional (2D) matching so that the algorithm has more universal applicability. Firstly, the conditional random field model is established. Secondly, an indoor three-dimensional digital map is used as a priori information. Thirdly, the pose and position information output by the VIO system are used as the observation information of the conditional random field (CRF). Finally, the optimal states sequence is obtained and employed as the feedback information to correct the trajectory of VIO system. Experimental results show that our algorithm can effectively improve the positioning accuracy of VIO system in the indoor area of poor lighting and featureless.
关键词 ：
map matching map matching visual inertial odometry visual inertial odometry conditional random field conditional random field three-dimensional three-dimensional indoor localization indoor localization
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Zhang, Jitong , Ren, Mingrong , Wang, Pu et al. Indoor Localization Based on VIO System and Three-Dimensional Map Matching [J]. | SENSORS , 2020 , 20 (10) . |
| MLA | Zhang, Jitong et al. "Indoor Localization Based on VIO System and Three-Dimensional Map Matching" . | SENSORS 20 . 10 (2020) . |
| APA | Zhang, Jitong , Ren, Mingrong , Wang, Pu , Meng, Juan , Mu, Yuman . Indoor Localization Based on VIO System and Three-Dimensional Map Matching . | SENSORS , 2020 , 20 (10) . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明公开一种基于双核t分布随机近邻嵌入的过程监测可视化方法。包括离线建模和在线监测两个步骤。离线建模利用标准t‑SNE方法对历史正常数据降维；计算输入核矩阵到特征核矩阵的映射参数矩阵；利用PCA将特征核矩阵降至两维，然后计算平方马氏距离作为统计量并求控制限。在线监测计算采集到的数据与建模数据之间的核函数；将得到的核向量与映射参数矩阵相乘获得映射后的特征核向量；利用PCA对映射后的特征核向量降维，得到用于可视化的二维特征；绘制特征的散点图并观察是否在椭圆控制限范围内。相比于现有技术，本发明保留标准t‑SNE方法数据降维优势的同时，将其应用于工业过程故障监测可视化，降低了工业过程监测的误报和漏报率。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 张海利 , 王普 , 高学金 et al. 一种基于双核t分布随机近邻嵌入的过程监测可视化方法 : CN202010550245.7[P]. | 2020-06-16 . |
| MLA | 张海利 et al. "一种基于双核t分布随机近邻嵌入的过程监测可视化方法" : CN202010550245.7. | 2020-06-16 . |
| APA | 张海利 , 王普 , 高学金 , 高慧慧 . 一种基于双核t分布随机近邻嵌入的过程监测可视化方法 : CN202010550245.7. | 2020-06-16 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
一种基于CL‑RNN的出水氨氮软测量方法属于质量预测技术领域。首先将采集到的数据进行标准化处理，然后通过注意向量对原始输入进行调制，增强重要元素的影响，同时抑制不重要元素的影响，使得网络具有注意性能；之后通过连接隐含层和输出层神经元，将全局递归和局部递归嵌入到传统网络中。最后，利用权值更新策略实现污水NH4‑N的软测量，并用污水处理厂实际数据验证了所提方法的有效性。本发明使得递归神经网络在获取内部状态信息的同时捕获输出信号，可有效利用训练数据中的特征信息；其次，在外部反馈层中加入改进的注意力机制，对输入信号进行细粒度调制，使递归神经元具有注意能力，大大提高了出水NH4‑N的测量准确度。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 杨彦霞 , 王普 , 高学金 et al. 一种基于CL-RNN的出水氨氮软测量方法 : CN202011271414.X[P]. | 2020-11-14 . |
| MLA | 杨彦霞 et al. "一种基于CL-RNN的出水氨氮软测量方法" : CN202011271414.X. | 2020-11-14 . |
| APA | 杨彦霞 , 王普 , 高学金 , 高慧慧 , 韩华云 . 一种基于CL-RNN的出水氨氮软测量方法 : CN202011271414.X. | 2020-11-14 . |
| 导入链接 | NoteExpress RIS BibTex |
导出
| 数据： |
选中 到 |
| 格式： |
