检索结果-南通市图书馆

An attention-based teacher-student model for multivariate short-term landslide displacement prediction incorporating weather forecast data

在线全文

学校读者我要写书评

暂无评论

Journal of Mountain Science 2024年第8期21卷 2739-2753页

作者： chen Jun HU wang ZHANG yu QIU Hongzhi wang Renchao Sichuan Artificial Intelligence Research Institute Yibin 644000China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China School of Architecture and Civil Engineering Chengdu UniversityChengdu 610106China

Predicting the displacement of landslide is of utmost practical importance as the landslide can pose serious threats to both human life and ***,traditional methods have the limitation of random selection in sliding window selection and seldom incorporate weather forecast data for displacement prediction,while a single structural model cannot handle input sequences of different lengths at the same *** order to solve these limitations,in this study,a new approach is proposed that utilizes weather forecast data and incorporates the maximum information coefficient(MIC),long short-term memory network(LSTM),and attention mechanism to establish a teacher-student coupling model with parallel structure for short-term landslide displacement *** MIC,a suitable input sequence length is selected for the LSTM *** investigate the influence of rainfall on landslides during different seasons,a parallel teacher-student coupling model is developed that is able to learn sequential information from various time series of different *** teacher model learns sequence information from rainfall intensity time series while incorporating reliable short-term weather forecast data from platforms such as China Meteorological Administration(CMA)and Reliable Prognosis(https://***)to improve the model’s expression capability,and the student model learns sequence information from other time *** attention module is then designed to integrate different sequence information to derive a context vector,representing seasonal temporal attention ***,the predicted displacement is obtained through a linear *** proposed method demonstrates superior prediction accuracies,surpassing those of the support vector machine(SVM),LSTM,recurrent neural network(RNN),temporal convolutional network(TCN),and LSTM-Attention *** achieves a mean absolute error(MAE)of 0.072 mm,root mean square error(RMSE)of 0.096 mm,and pearson correlation coefficients(PC

关键词： Landslide prediction MIC LSTM Attention mechanism Teacher Student model Prediction stability and interpretability

Multimodal Machine Learning Guides Low Carbon Aeration Strategies in Urban Wastewater Treatment

在线全文

学校读者我要写书评

暂无评论

Engineering 2024年第5期36卷 51-62页

作者： Hong-cheng wang yu-Qi wang Xu wang Wan-Xin Yin Ting-Chao yu chen-Hao Xue Ai-Jie wang State Key Laboratory of Urban Water Resource and Environment School of Civil and Environmental EngineeringHarbin Institute of Technology(Shenzhen)Shenzhen 518055China Key Laboratory of Drinking Water Safety and Distribution Technology of Zhejiang Province College of Civil Engineering and ArchitectureZhejiang UniversityHangzhou 310058China

The potential for reducing greenhouse gas(GHG)emissions and energy consumption in wastewater treatment can be realized through intelligent control,with machine learning(ML)and multimodality emerging as a promising ***,we introduce an ML technique based on multimodal strategies,focusing specifically on intelligent aeration control in wastewater treatment plants(WWTPs).The generalization of the multimodal strategy is demonstrated on eight ML *** results demonstrate that this multimodal strategy significantly enhances model indicators for ML in environmental science and the efficiency of aeration control,exhibiting exceptional performance and *** random forest with visual models achieves the highest accuracy in forecasting aeration quantity in multimodal models,with a mean absolute percentage error of 4.4%and a coefficient of determination of *** testing in a full-scale plant reveals that the multimodal model can reduce operation costs by 19.8%compared to traditional fuzzy control *** potential application of these strategies in critical water science domains is *** foster accessibility and promote widespread adoption,the multimodal ML models are freely available on GitHub,thereby eliminating technical barriers and encouraging the application of artificial intelligence in urban wastewater treatment.

关键词： Wastewater treatment Multimodal machine learning Deep learning Aeration control Interpretable machine learning

Pd-catalyzed intermolecular Si–O formation via Si–C activation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China Chemistry 2024年第8期67卷 2661-2669页

作者： Shuang Liu yu-Shu chen Yichen Wu Peng wang State Key Laboratory of Organometallic Chemistry Shanghai Institute of Organic ChemistryUniversity of Chinese Academy of SciencesShanghai 200032China School of Chemistry and Materials Science Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024China College of Material Chemistry and Chemical Engineering Key Laboratory of Organosilicon Chemistryand Material Technology of Ministry of EducationHangzhou Normal UniversityHangzhou 311121China

The development of efficient Si–O bond formation reaction with 100% atom-economy, excellent functional group tolerance, and broad scope under mild conditions is highly desired due to the prevalence of silanol, silyl ether, and their derivatives in synthetic chemistry and materials science. Here, we have realized the Pd-catalyzed Si–O formation reaction via a Si–C activation approach with 100% atom-economy by employing silacyclobutanes(SCBs) and various hydroxy-containing substrates, including water,alcohols, phenols, and silanols. This protocol features a broad substrate scope, remarkable functional compatibility and mild conditions, providing a series of silanols, silyl ethers in high efficiency. Notably, this protocol could also be used for selective protection of hydroxy functionalities, and for the access of a class of novel polymers containing Si–O main chain. Preliminary mechanistic studies unveiled that this reaction underwent a Pd-catalyzed concerted ring-opening mechanism.

关键词： Si–O formation Si–C activation palladium silacyclobutane silanol silyl ether

A resonant high-pressure microsensor based on a composite pressure-sensitive mechanism of diaphragm bending and volume compression

在线全文

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2024年第2期10卷 57-66页

作者： Pan Qian Zongze yu Jie yu yulan Lu Bo Xie Jian chen Deyong chen Junbo wang The State Key Laboratory of Transducer Technology Aerospace Information Research InstituteChinese Academy of SciencesBeijing100190China The School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijing100049China

In this paper,a composite pressure-sensitive mechanism combining diaphragm bending and volume compression was developed for resonant pressure microsensors to achieve high-pressure measurements with excellent *** composite mechanism was explained,and the sensor structure was designed based on theoretical analysis and finite element *** all-silicon resonant high-pressure microsensor with multiple miniaturized cavities and dual resonators was developed,where dual resonators positioned in two resonant cavities with suitably different widths are used to perform opposite characteristics in pressure and the same characteristics at different temperatures,which can improve pressure sensitivities and realize temperature self-compensation by differential frequency *** microsensor was fabricated by microfabrication,and the experimental results showed that the sensor had an accuracy of±0.015%full scale(FS)in a pressure range of 0.1~100 MPa and a temperature range of−10~50℃.The pressure sensitivity of the differential frequency was 261.10 Hz/MPa(~2523 ppm/MPa)at a temperature of 20℃,and the temperature sensitivities of the dual resonators were−1.54 Hz/℃(~−14.5 ppm/℃)and−1.57 Hz/℃(~−15.6 ppm/℃)at a pressure of 2 *** differential output had an outstanding stability within±0.02 Hz under constant temperature and ***,this research provides a convenient solution for high-pressure measurements because of its advantages,namely,large range,excellent accuracy and stability.

关键词： stability resonant bending

A hybrid physics-informed data-driven neural network for CO_(2) storage in depleted shale reservoirs

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Petroleum Science 2024年第1期21卷 286-301页

作者： Yan-Wei wang Zhen-Xue Dai Gui-Sheng wang Li chen yu-Zhou Xia yu-Hao Zhou College of Construction Engineering Jilin UniversityChangchun130026JilinChina Institute of Intelligent Simulation and Early Warning for Subsurface Environment Jilin UniversityChangchun130026JilinChina School of Energy Resources China University of GeosciencesBeijing100083China Department of Safety Environmental Protection and Quality ManagementShengli OilfieldSinopecDongying257000ShandongChina Key Laboratory of Thermo-Fluid Science and Engineering of MOE School of Energy and Power EngineeringXi'an Jiaotong UniversityXi'an710049ShaanxiChina College of Computer Science and Technology China University of Petroleum(East China)Qingdao266580ShandongChina Department of Physics University of FribourgFribourg1700Switzerland

To reduce CO_(2) emissions in response to global climate change,shale reservoirs could be ideal candidates for long-term carbon geo-sequestration involving multi-scale transport ***,most current CO_(2) sequestration models do not adequately consider multiple transport ***,the evaluation of CO_(2) storage processes usually involves laborious and time-consuming numerical simulations unsuitable for practical prediction and *** this paper,an integrated model involving gas diffusion,adsorption,dissolution,slip flow,and Darcy flow is proposed to accurately characterize CO_(2) storage in depleted shale reservoirs,supporting the establishment of a training *** this basis,a hybrid physics-informed data-driven neural network(HPDNN)is developed as a deep learning surrogate for prediction and *** incorporating multiple sources of scientific knowledge,the HPDNN can be configured with limited simulation resources,significantly accelerating the forward and inversion ***,the HPDNN can more intelligently predict injection performance,precisely perform reservoir parameter inversion,and reasonably evaluate the CO_(2) storage capacity under complicated *** validation and test results demonstrate that the HPDNN can ensure high accuracy and strong robustness across an extensive applicability range when dealing with field data with multiple noise *** study has tremendous potential to replace traditional modeling tools for predicting and making decisions about CO_(2) storage projects in depleted shale reservoirs.

关键词： Deep learning Physics-informed data-driven neural network Depleted shale reservoirs CO_(2)storage Transport mechanisms

Cardiac regeneration: Pre-existing cardiomyocyte as the hub of novel signaling pathway

在线全文

学校读者我要写书评

暂无评论

Genes & Diseases 2024年第2期11卷 747-759页

作者： Tao wang Xinzhe chen Kai wang Jie Ju Xue yu Wanpeng yu Cuiyun Liu Yin wang Institute for Translational Medicine The Affiliated Hospital of Qingdao UniversityCollege of MedicineQingdao UniversityQingdaoShandong 266023China College of Medicine Qingdao UniversityQingdaoShandong 266023China

In the mammalian heart,cardiomyocytes are forced to withdraw from the cell cycle shortly after birth,limiting the ability of the heart to regenerate and *** development of multimodal regulation of cardiac proliferation has verified that pre-existing cardiomyocyte proliferation is an essential driver of cardiac *** the continuous development of genetic lineage tracking technology,it has been revealed that cell cycle activity produces polyploid cardiomyocytes during the embryonic,juvenile,and adult stages of cardiogenesis,but newly formed mononucleated diploid cardiomyocytes also elevated sporadically during myocardial *** implied that adult cardiomyocytes have a weak regenerative capacity under the condition of ischemia injury,which offers hope for the clinical treatment of myocardial ***,the regeneration frequency and source of cardiomyocytes are still low,and the mechanism of regulating cardiomyocyte proliferation remains further *** is noteworthy to explore what force triggers endogenous cardiomyocyte proliferation and heart ***,we focused on summarizing the recent research progress of emerging endogenous key modulators and crosstalk with other signaling pathways and furnished valuable insights into the internal mechanism of heart *** addition,myocardial transcription factors,non-coding RNAs,cyclins,and cell cycle-dependent kinases are involved in the multimodal regulation of pre-existing cardiomyocyte ***,awakening the myocardial proliferation endogenous modulator and regeneration pathways may be the final battlefield for the regenerative therapy of cardiovascular diseases.

关键词： Cardiac regeneration Cell cycle re-enter Myocardial infarction Pre-existing cardiomyocyte proliferation Regenerative therapy of cardiovascular diseases

可溶性油类和溶解性有机物对砂加载混凝沉淀处理高悬浮矿井水效果的影响

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

科学技术与工程 2024年第22期24卷 9316-9323页

作者：王雨晨邸卫猛虎晓龙宋喜东郝春明刘硕中煤(北京)环保股份有限公司北京100071 国家能源集团宁夏煤业有限责任公司灵新煤矿灵武751400 华北科技学院化工安全学院三河065201 河北省地质环境监测院石家庄050011

矿井水中可溶性油类和溶解性有机物含量对石英砂加载混凝沉淀效果的影响很少有系统的研究,影响机制也不清晰。为此,选用石英砂加载混凝处理高悬浮矿井水为研究对象,分析矿井水中乳化油、浓缩液、腐殖酸(humic acid,HA)、富里酸(fulvic a... 详细信息

矿井水中可溶性油类和溶解性有机物含量对石英砂加载混凝沉淀效果的影响很少有系统的研究,影响机制也不清晰。为此,选用石英砂加载混凝处理高悬浮矿井水为研究对象,分析矿井水中乳化油、浓缩液、腐殖酸(humic acid,HA)、富里酸(fulvic acid,FA)和L-色氨酸(L-tryptophan,LA)含量对石英砂加载混凝处理高悬浮物矿井水效率的影响。分析结果表明:矿井水中乳化油、浓缩液和过量的HA含量不利于加载混凝沉淀处理的效率和沉淀速率。HA、LA和适量的FA含量并不能影响加载混凝沉淀处理高悬浮物矿井水的效率和沉降速率。响应面分析结果表明乳化油和浓缩液的浓度变化对砂加载混凝沉淀效率和过程的影响较大,而HA、FA和LA的浓度变化则对其影响较小。该结果为进一步认知砂加载混凝处理工艺,提升其处理效率,实现中国煤矿矿井水资源保护和合理化利用具有重要的意义。

关键词：乳化油浓缩液腐殖酸黄腐酸 L-色氨酸混凝沉淀

Wellbore-heat-transfer-model-based optimization and control for cooling downhole drilling fluid

在线全文

学校读者我要写书评

暂无评论

Petroleum Science 2024年第3期21卷 1955-1968页

作者： Chao wang He Liu Guo-Wei yu chen yu Xian-Ming Liu Peng Huang Yangtze University Jingzhou434023HubeiChina State Key Laboratory of Petroleum Resources and Engineering China University of Petroleum(Beijing)Beijing2249China CNPC Bohai Drilling Engineering Co. LtdTianjin300280China Exploration Development and Construction Engineering Division of PetroChina Jidong Oilfield Company Tangshan63200HebeiChin Henan University of Urban Construction Pingdingshan467036HenanChina

To address the two critical issues of evaluating the necessity of implementing cooling techniques and achieving real-time temperature control of drilling fluids underground in the current drilling fluid cooling technology,we first established a temperature and pressure coupled downhole heat transfer model,which can be used in both water-based and oil-based drilling ***,fourteen factors,which could affect wellbore temperature,were *** on the standard deviation of the downhole temperature corresponding to each influencing factor,the influence of each factor was *** influencing factors that can be used to guide the drilling fluid's cooling technology were drilling fluid thermal conductivity,drilling fluid heat capacity,drilling fluid density,drill strings rotation speed,pump rate,viscosity,ROP,and injection *** nondominated sorting genetic algorithm was used to optimize these six parameters,but the optimization process took 182 *** these eight parameters'influence rules with the nondominated sorting genetic algorithm can reduce the optimization time to 108 ***,the downhole temperature has been demonstrated to increase with the inlet temperature increasing linearly under quasi-steady *** this law and PID,the downhole temperature can be controlled,which can reduce the energy for cooling the surface drilling fluid and can ensure the downhole temperature reaches the set value as soon as possible.

关键词： Drilling Cooling Influencing factors Analysis Optimization Control

Deterministic learning-based neural output-feedback control for a class of nonlinear sampled-data systems

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第9期67卷 164-183页

作者： yu ZENG Fukai ZHANG Tianrui chen Cong wang School of Automation Science and Engineering South China University of Technology School of Control Science and Engineering Shandong University

This study investigates the deterministic learning(DL)-based output-feedback neural control for a class of nonlinear sampled-data systems with prescribed performance(PP). Specifically, first, a sampleddata observer is employed to estimate the unavailable system states for the Euler discretization model of the transformed system dynamics. Then, based on the observations and backstepping method, a discrete neural network(NN) controller is constructed to ensure system stability and achieve the desired tracking performance. The noncausal problem encountered during the controller deduction process is resolved using a command filter. Moreover, the regression characteristics of the NN input signals are demonstrated with the observed states. This ensures that the radial basis function NN, based on DL theory, meets the partial persistent excitation condition. Subsequently, a class of discrete linear time-varying systems is proven to be exponentially stable, achieving partial convergence of neural weights to their optimal/actual values. Consequently, accurate modeling of unknown closed-loop dynamics is achieved along the system trajectory from the output-feedback control. Finally, a knowledge-based controller is developed using the modeling *** controller not only enhances the control performance but also ensures the PP of the tracking error. The effectiveness of the scheme is illustrated through simulation results.

关键词： deterministic learning neural networks adaptive neural control predefined performance nonlinear sampled-data systems