检索结果-南通市图书馆

Geomaterials 2011年第3期1卷 88-94页

作者： R. G. Elenga B. Mabiala L. Ahouet j. goma-maniongui G. F. Dirras 不详

Physical properties of compressed earth blocks reinforced with plastic wastes are compared to those of nonreinforced ones. These bricks are made with two clayey soils from two deposits of Congo located in Brazzaville and Yengola. Mineralogical and geotechnical analysis revealed that the soil of Brazzaville is mainly composed of kaolinite whereas that of Yengola is a mixture of kaolinite and illite. The amounts of clay (46 and 48%, respectively) are higher than those usually recommended for bricks’ production without stabilizers. Despite this difference of mineralogical compositions, the physical properties of these soils are quite similar. The compressive strength of the resulted bricks compacted with an energy of 2.8 MPa is about 1.5 MPa, which is the lower limit value allowed for adobes. Reinforcing with polyethylene waste nets increased the strength by about 20 to 30% and slightly enhanced resistance to water, Young’s modulus and strain to failure. However, the reinforcement had no significant effect either on bricks’ curing length or on their shrinkage.

关键词： Clayey Soils Compressed Earth Block Stabilization Plastic Waste

Editorial for the Special Issue on Emerging Technology and Advanced Application of Nondestructive Detection for Power Equipment

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese j.urnal of Electrical Engineering 2024年第1期10卷 1-2页

作者： Li j. Mei H. Li S. Tianj.n University China Tsinghua Shenzhen International Graduate School China Lanzhou j.aotong University China

The rapid development of clean and renewable energy technologies represented by wind and solar energy,as well as the continuous growth of load demand,have put forward higher requirements for the safe operation of the power *** performance of power equipment based on traditional dielectric materials is often limited by various defects generated during molding,transportation,assembly,and operation,which cannot meet the reliability requirements of power systems in the new *** detection is an essential technical method in industrial development,which can detect and evaluate the defect and damage status of in-service equipment,key components,and materials without damaging the obj.ct.

关键词： service Application operation

Machine Fault Diagnosis Using Audio Sensors Data and Explainable AI Techniques-LIME and SHAP

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials and Continua 2024年第3期80卷 3463-3484页

作者： Zereen A.N. Das A. Uddin j. School of Data and Sciences Brac University Dhaka 1212 Bangladesh j. KIM College of Future Studies Endicott College Woosong University Daejeon 300-718 South Korea AI and Big Data Department Endicott College Woosong University Daejeon 300-718 South Korea

Machine fault diagnostics are essential for industrial operations, and advancements in machine learning have significantly advanced these systems by providing accurate predictions and expedited solutions. Machine learning models, especially those utilizing complex algorithms like deep learning, have demonstrated maj.r potential in extracting important information from large operational datasets. Despite their efficiency, machine learning models face challenges, making Explainable AI (XAI) crucial for improving their understandability and fine-tuning. The importance of feature contribution and selection using XAI in the diagnosis of machine faults is examined in this study. The technique is applied to evaluate different machine-learning algorithms. Extreme Gradient Boosting, Support Vector Machine, Gaussian Naive Bayes, and Random Forest classifiers are used alongside Logistic Regression (LR) as a baseline model because their efficacy and simplicity are evaluated thoroughly with empirical analysis. The XAI is used as a targeted feature selection technique to select among 29 features of the time and frequency domain. The XAI approach is lightweight, trained with only targeted features, and achieved similar results as the traditional approach. The accuracy without XAI on baseline LR is 79.57%, whereas the approach with XAI on LR is 80.28%. Copyright © 2024 The Authors. Published by Tech Science Press.

关键词： Explainable AI feature selection machine fault diagnosis machine learning

A New Method for Deriving High-Vertical-Resolution Wind Vector Data from the L-Band Radar Sounding System in China

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in Atmospheric Sciences 2024年第11期41卷 2192-2202页

作者： Yuan F. Zhou Z. Liao j. National Meteorological Information Center China Meteorological Administration Beijing 100081 China

High-vertical-resolution radiosonde wind data are highly valuable for describing the dynamics of the meso- and microscale atmosphere. However, the current algorithm used in China’s L-band radar sounding system for calculating high-vertical-resolution wind vectors excessively smooths the data, resulting in significant underestimation of the calculated kinetic energy of gravity waves compared to similar products from other countries, which greatly limits the effective utilization of the data. To address this issue, this study proposes a novel method to calculate high-vertical-resolution wind vectors that utilizes the elevation angle, azimuth angle, and slant range from L-band radar. In order to obtain wind data with a stable quality, a two-step automatic quality control procedure, including the RMSE-F (root-mean-square error F) test and elemental consistency test are first applied to the slant range data, to eliminate continuous erroneous data caused by unstable signals or radar malfunctions. Then, a wind calculation scheme based on a sliding second-order polynomial fitting is utilized to derive the high-vertical-resolution radiosonde wind vectors. The evaluation results demonstrate that the wind data obtained through the proposed method show a high level of consistency with the high-resolution wind data observed using the Vaisala Global Positioning System and the data observed by the new Beidou Navigation Sounding System. The calculation of the kinetic energy of gravity waves in the recalculated wind data also reaches a level comparable to the Vaisala observations. © Institute of Atmospheric Physics/Chinese Academy of Sciences, and Science Press 2024.

关键词： high-vertical-resolution radiosonde wind vectors L-band radar sounding system polynomial fitting quality control upper air

Importance of timely and adequate source control in sepsis and septic shock

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

j.urnal of Intensive Medicine 2024年第3期4卷 281-286页

作者： j.n j.De Waele Department of Intensive Care Medicine Ghent University HospitalGhentBelgium Department of Internal Medicine and Pediatrics Faculty of Medicine and Health SciencesGhent UniversityGhentBelgium

Source control is defined as the physical measures undertaken to eliminate the source of infection and control ongoing contamination, as well as restore anatomy and function at the site of infection. It is a key component of the management of patients with sepsis and septic shock and one of the main determinants of the outcome of infections that require source control. While not all infections may require source control, it should be considered in every patient presenting with sepsis;it is applicable and necessary in numerous infections, not only those occurring in the abdominal cavity. Although the biological rationale is clear, several aspects of source control remain under debate. The timing of source control may impact outcome;early source control is particularly relevant for patients with abdominal infections or necrotizing skin and soft tissue infections, as well as for those with more severe disease. Percutaneous procedures are increasingly used for source control;nevertheless, surgery—tailored to the patient and infection—remains a valid option for source control. For outcome optimization, adequate source control is more important than the strategy used. It should be acknowledged that source control interventions may often fail, posing a challenge in this setting. Thus, an individualized, multidisciplinary approach tailored to the infection and patient is preferable.

关键词： Sepsis Septic shock Source control Drainage Debridement

Error field penetration in j.TEXT tokamak based on two-fluid drift-MHD model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第4期33卷 545-551页

作者：王文徐涛张仪 the j.TEXT team State Key Laboratory of Advanced Electromagnetic Technology International Joint Research Laboratory of Magnetic Confinement Fusion and Plasma PhysicsSchool of Electrical and Electronic EngineeringHuazhong University of Science and TechnologyWuhan 430074China

An externally generated resonant magnetic perturbation can induce complex non-ideal MHD responses in their resonant *** have studied the plasma responses using Fitzpatrick's improved two-fluid model and program *** calculated the error field penetration threshold for *** addition,we find that the island width increases slightly as the error field amplitude increases when the error field amplitude is below the critical penetration ***,the island width suddenly j.mps to a large value because the shielding effect of the plasma against the error field disappears after the *** scanning the natural mode frequency,we find that the shielding effect of the plasma decreases as the natural mode frequency ***,we obtain the m/n=2/1 penetration threshold scaling on density and temperature.

关键词： plasma responses drift-MHD model error field penetration

Value Function Mechanism in WSNs-Based Mango Plantation Monitoring System

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials and Continua 2024年第3期80卷 3733-3759页

作者： Sung W.-T. Isa I.G.T. Hsiao S.-j. Department of Electrical Engineering National Chin-Yi University of Technology Taichung 411030 Taiwan Department of Informatics Management Politeknik Negeri Sriwijaya Palembang 30139 Indonesia Department of Information Technology Takming University of Science and Technology Taipei City 11451 Taiwan

Mango fruit is one of the main fruit commodities that contributes to Taiwan’s income. The implementation of technology is an alternative to increasing the quality and quantity of mango plantation product productivity. In this study, a Wireless Sensor Networks (“WSNs”)-based intelligent mango plantation monitoring system will be developed that implements deep reinforcement learning (DRL) technology in carrying out prediction tasks based on three classifications: “optimal,” “sub-optimal,” or “not-optimal” conditions based on three parameters including humidity, temperature, and soil moisture. The key idea is how to provide a precise decision-making mechanism in the real-time monitoring system. A value function-based will be employed to perform DRL model called deep Q-network (DQN) which contributes in optimizing the future reward and performing the precise decision recommendation to the agent and system behavior. The WSNs experiment result indicates the system’s accuracy by capturing the real-time environment parameters is 98.39%. Meanwhile, the results of comparative accuracy model experiments of the proposed DQN, individual Q-learning, uniform coverage (UC), and Naïve Bayes classifier (NBC) are 97.60%, 95.30%, 96.50%, and 92.30%, respectively. From the results of the comparative experiment, it can be seen that the proposed DQN used in the study has the most optimal accuracy. Testing with 22 test scenarios for “optimal,” “sub-optimal,” and “not-optimal” conditions was carried out to ensure the system runs well in the real-world data. The accuracy percentage which is generated from the real-world data reaches 95.45%. From the results of the cost analysis, the system can provide a low-cost system compared to the conventional system. Copyright © 2024 The Authors. Published by Tech Science Press.

关键词： deep Q-network (DQN) deep reinforcement learning (DRL) Intelligent monitoring system wireless sensor networks (WSNs)

Knowledge-Driven Possibilistic Clustering with Automatic Cluster Elimination

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials and Continua 2024年第3期80卷 4917-4945页

作者： Hu X. Tang Y. Pedrycz W. j.ang j. j.ang Y. The School of Computer Science and Engineering Southeast University Nanjing 211189 China The School of Computer and Information Hefei University of Technology Hefei 230601 China The Department of Electrical and Computer Engineering University of Alberta Edmonton T6R 2V4 AB Canada The Systems Research Institute Polish Academy of Sciences Warsaw 00-901 Poland The School of Information Engineering Nanjing University of Finance and Economics Nanjing 210023 China

Traditional Fuzzy C-Means (FCM) and Possibilistic C-Means (PCM) clustering algorithms are data-driven, and their obj.ctive function minimization process is based on the available numeric data. Recently, knowledge hints have been introduced to form knowledge-driven clustering algorithms, which reveal a data structure that considers not only the relationships between data but also the compatibility with knowledge hints. However, these algorithms cannot produce the optimal number of clusters by the clustering algorithm itself; they require the assistance of evaluation indices. Moreover, knowledge hints are usually used as part of the data structure (directly replacing some clustering centers), which severely limits the flexibility of the algorithm and can lead to knowledge misguidance. To solve this problem, this study designs a new knowledge-driven clustering algorithm called the PCM clustering with High-density Points (HP-PCM), in which domain knowledge is represented in the form of so-called high-density points. First, a new data density calculation function is proposed. The Density Knowledge Points Extraction (DKPE) method is established to filter out high-density points from the dataset to form knowledge hints. Then, these hints are incorporated into the PCM obj.ctive function so that the clustering algorithm is guided by high-density points to discover the natural data structure. Finally, the initial number of clusters is set to be greater than the true one based on the number of knowledge hints. Then, the HP-PCM algorithm automatically determines the final number of clusters during the clustering process by considering the cluster elimination mechanism. Through experimental studies, including some comparative analyses, the results highlight the effectiveness of the proposed algorithm, such as the increased success rate in clustering, the ability to determine the optimal cluster number, and the faster convergence speed. Copyright © 2024 The Authors. Published by

关键词： Fuzzy C-Means (FCM) fuzzy logic knowledge-driven machine learning optimal number of clusters possibilistic clustering

Enhancing Log Anomaly Detection with Semantic Embedding and Integrated Neural Network Innovations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials and Continua 2024年第3期80卷 3991-4015页

作者： Xu Z. Wang Z. Xu j. Shi H. Zhao H. School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China

System logs, serving as a pivotal data source for performance monitoring and anomaly detection, play an indispensable role in assuring service stability and reliability. Despite this, the maj.rity of existing log-based anomaly detection methodologies predominantly depend on the sequence or quantity attributes of logs, utilizing solely a single Recurrent Neural Network (RNN) and its variant sequence models for detection. These approaches have not thoroughly exploited the semantic information embedded in logs, exhibit limited adaptability to novel logs, and a single model struggles to fully unearth the potential features within the log sequence. Addressing these challenges, this article proposes a hybrid architecture based on a multiscale convolutional neural network, efficient channel attention and mogrifier gated recurrent unit networks (LogCEM), which amalgamates multiple neural network technologies. Capitalizing on the superior performance of robustly optimized BERT approach (RoBERTa) in the realm of natural language processing, we employ RoBERTa to extract the original word vectors from each word in the log template. In conj.nction with the enhanced Smooth Inverse Frequency (SIF) algorithm, we generate more precise log sentence vectors, thereby achieving an in-depth representation of log semantics. Subsequently, these log vector sequences are fed into a hybrid neural network, which fuses 1D Multi-Scale Convolutional Neural Network (MSCNN), Efficient Channel Attention Mechanism (ECA), and Mogrifier Gated Recurrent Unit (GRU). This amalgamation enables the model to concurrently capture the local and global dependencies of the log sequence and autonomously learn the significance of different log sequences, thereby markedly enhancing the efficacy of log anomaly detection. To validate the effectiveness of the LogCEM model, we conducted evaluations on two authoritative open-source datasets. The experimental results demonstrate that LogCEM not only exhibits excellent ac

关键词： anomaly detection Deep learning log analysis natural language processing

Effect of Processing and Cultivar on Thermo-Chemical Properties of Australian-Grown Hemp Hurd (Cannabis sativa L.)

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

j.urnal of Renewable Materials 2024年第8期12卷 1475-1493页

作者： Fehrmann j. Belleville B. Ozarska B. Ismayati M. Dwianto W. School of Agriculture Food and Ecosystem Sciences (SAFES) Faculty of Science The University of Melbourne Melbourne 3121 Australia Research Center for Biomass and Bioproducts National Research and Innovation Agency (BRIN) Jakarta 16911 Indonesia

This study explored the thermo-chemical properties of industrial hemp hurd with different provenances, maturity stages, and retting protocols. The findings were then compared to hemp hurd used in the fabrication of citric acid-bonded ultra-low-density hemp hurd particleboard. Pyrolysis-gas chromatography-mass spectrometry (Py-GC/MS), Fourier-transform infrared spectroscopy (FTIR), and thermogravimetric analysis (TGA) were employed to document the variability of the hurd and comprehend the potential impact on biobased composite applications. The choice of cultivar, maturity stage, and processing modality significantly influenced the chemical composition, presence of functional groups, and thermal stability of the hurd. Py-GC/MS revealed substantial variations in the lignin-to-carbohydrate (L/C) ratio, along with the absence of fatty acids in certain cultivars. While FTIR signals confirmed consistent functional groups, differences in peak intensities were indicative of carbohydrate variations associated with maturity and retting duration, impacting the availability of hydroxyl groups for, i.e., interparticle bonding in citric acid-based bio-composites. Furthermore, it was observed that shorter retting durations initially enhanced the thermal resistance, but prolonged retting led to accelerated degradation, significantly reducing the hurd’s residual mass. The findings indicated notable differences among the samples, emphasizing the importance of investigating variables such as provenance/cultivar, maturity,andprocessing modality. This assessment is essential to ensure effective agronomic practices that align the raw material characteristics with the specific requirements of intended applications, such as the fabrication of biobased hemp hurd composites. © 2024 The Authors.

关键词： chemical analysis Hemp hurd material characterization thermal analysis