检索结果-内蒙古大学图书馆

Simulation model optimization for bonnet polishing considering consistent contact area response

Frontiers of mechanical engineering 2024年第4期19卷 87-105页

作者： Yanjun HAN Haiyang ZHANG Menghuan YU Jinzhou YANG Linmao QIAN School of Mechanical Engineering Southwest Jiaotong UniversityChengdu 610031China Institute of Data Science Maastricht UniversityMaastricht 6229ENthe Netherlands

Simulation model optimization plays a crucial role in the accurate prediction of material removal function in bonnet polishing processes,but model complexity often poses challenges to the practical implementation and efficiency of these *** paper presents an innovative method for optimizing simulation model parameters,focusing on achieving consistent contact area and the accurate prediction of the material removal function while preventing increase in model ***,controllable and uncontrollable factors in bonnet simulations are analyzed,and then a simplified contact model is developed and applied under constant force *** characterize the bonnet's contact performance,a contact area response curve is introduced,which can be obtained through a series of single spot contact ***,a rubber hyperelastic parameter optimization model based on a neural network is proposed to achieve optimal matching of the contact area between simulation and *** average deviation of the contact area under different conditions was reduced from 22.78%before optimization to 3.43%after optimization,preliminarily proving the effectiveness of the proposed simulation optimization ***,orthogonal experiments are further conducted to validate the proposed *** comparison between the experimental and predicted material removal functions reveals a high consistency,validating the accuracy and effectiveness of the proposed optimization method based on consistent contact *** research provides valuable insights into enhancing the reliability and effectiveness of bonnet polishing simulations with a simple and practical approach while mitigating the complexity of the model.

关键词： bonnet polishing simulation contact area tool influence function optimization

来源：评论

学校读者我要写书评

暂无评论

On the Consistency of Kernel Methods with Dependent Observations 41

On the Consistency of Kernel Methods with Dependent Observat...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Massiani, Pierre-François Trimpe, Sebastian Solowjow, Friedrich Institute for Data Science in Mechanical Engineering RWTH Aachen University Aachen Germany

The consistency of a learning method is usually established under the assumption that the observations are a realization of an independent and identically distributed (i.i.d.) or mixing process. Yet, kernel methods such as support vector machines (SVMs), Gaussian processes, or conditional kernel mean embeddings (CKMEs) all give excellent performance under sampling schemes that are obviously non-i.i.d., such as when data comes from a dynamical system. We propose the new notion of empirical weak convergence (EWC) as a general assumption explaining such phenomena for kernel methods. It assumes the existence of a random asymptotic data distribution and is a strict weakening of previous assumptions in the field. Our main results then establish consistency of SVMs, kernel mean embeddings, and general Hilbert-space valued empirical expectations with EWC data. Our analysis holds for both finite- and infinite-dimensional outputs, as we extend classical results of statistical learning to the latter case. In particular, it is also applicable to CKMEs. Overall, our results open new classes of processes to statistical learning and can serve as a foundation for a theory of learning beyond i.i.d. and mixing. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Feedforward Controllers from Learned Dynamic Local Model Networks with Application to Excavator Assistance Functions 63

Feedforward Controllers from Learned Dynamic Local Model Net...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Greiser, Leon Demir, Ozan Hartmann, Benjamin Hose, Henrik Trimpe, Sebastian Robert Bosch GmbH Stuttgart Germany Institute for Data Science in Mechanical Engineering Rwth Aachen University Germany

ISBN: (纸本)9798350316339

Complicated first principles modelling and controller synthesis can be prohibitively slow and expensive for high-mix, low-volume products such as hydraulic excavators. Instead, in a data-driven approach, recorded trajectories from the real system can be used to train local model networks (LMNs), for which feedforward controllers are derived via feedback linearization. However, previous works required LMNs without zero dynamics for feedback linearization, which restricts the model structure and thus modelling capacity of LMNs. In this paper, we overcome this restriction by providing a criterion for when feedback linearization of LMNs with zero dynamics yields a valid controller. As a criterion we propose the bounded-input bounded-output stability of the resulting controller. In two additional contributions, we extend this approach to consider measured disturbance signals and multiple inputs and outputs. We illustrate the effectiveness of our contributions in a hydraulic excavator control application with hardware experiments. To this end, we train LMNs from recorded, noisy data and derive feedforward controllers used as part of a leveling assistance system on the excavator. In our experiments, incorporating disturbance signals and multiple inputs and outputs enhances tracking performance of the learned controller. A video of our experiments is available at https://***/lrrWBx2ASaE. © 2024 IEEE.

关键词： Excavators

来源：评论

学校读者我要写书评

暂无评论

Optimizing mechanical strength and thermal stability of sisal fiber-plastic composites by high-temperature treatment

引用

Interactions 2025年第1期246卷 1-15页

作者： Mungle, Nischal P. Jadhav, Varsha D. Kulkarni, Sumant Khanderao D.S.Vijayan Saminathan, Rajasekaran Satishkumar, P. Department of Mechanical Engineering Yeshawantrao Chavan College of Engineering Maharashtra Wanadongari Nagpur India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Technology Maharashtra Pune India School of Civil Engineering REVA University Rukmini Knowledge Park Karnataka Kattigenahalli Bengaluru India Tamilnadu Chennai India Department of Mechanical Engineering College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of Mechanical Engineering Rathinam Technical Campus Tamilnadu Coimbatore India

In this experiment, high-temperature polyethylene terephthalate (PT) was mixed with epoxy resin (ER) that had been thinned with acetone. Sisal fibers were coated with the resulting product. Composites of Coated treated sisal fibre-reinforced PT (CTSF-PT) were made using a constant fiber loading of 10 wt% and processing temperatures of 230, 250, and 270ºC. The fibers were treated with NaOH. These composites were then characterized for thermal, mechanical and morphological performances. When comparing findings obtained at 250 and 270ºC, the optimal processing temperature was found to be 230ºC. This temperature resulted in the best thermal and mechanical properties, and excellent interfacial adhesion among the coated fibers and the PT. In comparison to the uncoated SF, the coated composites showed a 9.5% reduction in degradation onset temperature and a 13% improvement in decomposition temperature following resin coating, according to thermogravimetric analysis. The CSF-PT composites surpassed the uncoated composites by 2.18% and 2.8% in terms of glass transition (Tg) and melting temperature (Tm) measured by differential scanning calorimetry (DSC), with peak values at 122.2 °C and 265.1 °C, respectively. Coated Sisal-reinforced PT (CSF-PT) and coated-treated PT (CTSF-PT) composites outperformed raw Sisal (SF-PT) composites in terms of overall qualities and morphological properties, regardless of processing temperature. Applying resin to natural fibers enhances their heat resistance and the bond between the coated fibers and the plastic matrix, making them better suited for engineering plastic composites. Applications involving high temperatures, such as construction and automotive industries are well-suited to the resulting composites. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Smart Resume Analyser 15

Smart Resume Analyser

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Rane, Milind Zanwar, Harsh Wagh, Kunal Wakode, Suhani Yadav, Avishkar Kulkarni, Atul Department of Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune India Department of Mechanical Engineering Vishwakarma Institute of Information Technology Pune India

ISBN: (纸本)9798331300579

Every time job recruiters (HR) have to go through a huge pile of resumes submitted by applicants. which becomes a very burdensome task, with Python, NumPy, and Pandas, a resume parser is to be created as part of the project. A structured format will be used to store the data that the parser extracts from resumes, including name, contact information, education, work experience, and abilities. Pandas will be used to store the data in a data frame, and NumPy will be used to manipulate the data. The parser will recognise and extract pertinent information from resumes using methods of natural language processing, improving the accuracy and efficiency of the procedure. By swiftly extracting pertinent information from resumes, the initiative will assist in automating the hiring process and save time for recruiters and HR personnel. © Grenze Scientific Society, 2024.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Early Landslide Detection Using Multi-Sensor data and IoT-Based Alert Mechanism 8

Early Landslide Detection Using Multi-Sensor Data and IoT-Ba...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Rajas, Neha Kandare, Kalash Bhadre, Ajay Talele, Ekant Gurav, Aarti Wani, Himanshu Vishwakarma Institute of Technology Artificial Intelligence and Data Science Pune India Vishwakarma Institute of Technology Mechanical Engineering Pune India ReLVishwakarma Institute of Technology Pune India

ISBN: (纸本)9798350367904

The 'Early Landslide Detection System' utilizes IoT to monitor and detect landslide risks in real-time. An artificial rain setup simulates rainfall on a model mountain, with a rain sensor, soil moisture sensors, and vibration sensors tracking rainfall, soil saturation, and ground movement. data is logged on ThingSpeak, and once significant vibrations are detected, the system alerts users through the Blynk app via mobile notifications and emails. This system provides an efficient, cost-effective solution for early landslide detection, enhancing disaster preparedness and minimizing potential damage. © 2024 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

DocBot Connect: A Conversational Search System Powered by Large Language Models

DocBot Connect: A Conversational Search System Powered by La...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Patil, Ratna Buchkul, Sandesh Ashok Mohite, Ritesh Sanjay Borase, Jayesh Samadhan Khandelwal, Anuj Rawandale, Shitalkumar Vishwakarma Institute of Information Technology Department of Artificial Intelligence and Data Science Pune India Primpri Chinchwad College of Engineering Department of Mechanical Engineering Pune India

ISBN: (纸本)9798350378092

DocBot Connect revolutionizes document retrieval by enabling users to have a natural conversation to search through multiple PDFs. This user-centric system leverages the power of large language models (LLMs) and cutting-edge information retrieval *** Connect boasts a user-friendly interface where users can upload their PDFs and ask questions in plain English. To unlock the deeper meaning within these documents, the system utilizes Google PaLM embeddings. These embeddings capture the essence of the text, allowing for a richer understanding. A critical step involves text segmentation, which meticulously divides the document content into manageable chunks. These segmented portions are then processed by Google PaLM, resulting in a robust embedded representation. This embedded representation forms the foundation for efficient retrieval using a FAISS vector store, enabling lightning-fast information retrieval. To ensure a seamless and contextually aware conversation, DocBot Connect incorporates a ConversationBufferMemory component. This component meticulously stores the conversation history, allowing the system to maintain a coherent dialogue flow. Finally, a ConversationalRetrievalChain, powered by the formidable capabilities of Google PaLM, retrieves relevant information from the vector store. This retrieval process is not solely driven by the user's query but also meticulously considers the established conversational context. DocBot Connect transcends traditional document retrieval systems, offering an intuitive and efficient gateway to access and comprehend information within a multitude of PDFs. This user-friendly approach fosters a more interactive and engaging experience for those navigating the ever-expanding world of document exploration. © 2024 IEEE.

关键词： Gateways (computer networks)

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Weld Quality Prediction

引用

Journal of Dynamics, Monitoring and Diagnostics 2024年第4期3卷 237-245页

作者： Shubhranil Chakraborty Sayani Guha Debasish Mishra Surjya K.Pal Department of Electronics and Communication Engineering Jalpaiguri Government Engineering CollegeIndia Data Science and Information Systems IFMR GSBKrea UniversityIndia Department of Mechanical Engineering Indian Institute of Technology KharagpurIndia

This study introduces a monitoring system that can accurately predict the quality of friction stir *** study involved four different sets of welding experiments using varying materials and tool *** goal was to create a universal monitoring system capable of predicting weld quality across these diverse experimental ***-time welding data was collected using instruments such as load cells and a power *** processing methods were then used to analyze this data and extract essential information about welding ***,federated learning(FL)was used to develop the universal monitoring *** method involves collective learning and model training,leading to a global model trained on decentralized data from the different experimental *** approach proved to be effective in forecasting weld quality,achieving a mean absolute error(MAE)of 10.44 for all welding ***,it offered benefits such as reduced latency and enhanced user data protection,while maintaining the accuracy of the global *** artificial neural network model was also developed for comparison with FL,achieving a MAE of 13.85 for the welding ***,this study demonstrates the effectiveness of training global and more reliable models,with multiple devices sharing their knowledge bases to train the global model effectively.

关键词： deep learning federated learning friction stir welding Industry 4.0 manufacturing neural network quality

来源：评论

学校读者我要写书评

暂无评论

IoT-Driven Mushroom Farm Automation Using Neural Turing Machines (NTM) 4

IoT-Driven Mushroom Farm Automation Using Neural Turing Mach...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Manoj Kumar, S. Monica, C.L. Sunith Babu, L. Manikandan, V. Subramani, Dinesh Malik, Subhash Madanapalle Institute of Technology & Science Department of Mechanical Engineering Angallu India V.R.Siddhartha Engineering College Department of Environmental Science Vijayawada India M. S. Ramaiah Institute of Technology Department of Mechanical Engineering Bengaluru India Department of Computer Science and Engineering Bengaluru India Department of Artificial Intelligence and Data Science Erode India Maharishi Markendeshwar Engineering College Department of Mechanical Engineering Mullana India

ISBN: (纸本)9798350352931

Mushroom cultivation leads global agriculture due to its impact on worldwide trade. One of the main challenges in this area is optimal weather, especially temperature and humidity. Unfortunately, traditional farming's inability to achieve these conditions often leads to low yields. The recommended procedure involves collecting sensor data, constructing the model, and training it. Preprocessing includes spectral smoothing, normalization, and reflectance calibration. Sensors measure motion, temperature, light, and soil moisture. Photo feature extraction uses edge detection to identify objects. The model is trained using NTM. The suggested NTM-based model beats top-tier models like Random Forest (RF) and Support Vector Machine (SVM) with 92.35 percent accuracy. This increasing accuracy shows the model's mushroom production optimization. This proposed uses sensor data and current image processing techniques to improve mushroom farming conditions. NTM-based mushroom cultivation is more efficient and yields more than conventional methods. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Mobile Malware Attacks, Classification, Propagation, Analysis, Detection, Challenges and Future Directions – A Survey 14

Mobile Malware Attacks, Classification, Propagation, Analysi...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Senthilkumar, B. Sujithra, M. Mani Barathi, S.P.S. Department of Mechanical Engineering Kumaraguru College of Technology India Department of Computing – Data Science Coimbatore Institute of Technology India

Number of Smartphone users are increasing day by day and mobiles have become an integral part of the society. This is because of the rich variety of mobile devices and essential applications provided by its manufacturers. The increasing number of mobile devices invite skilled developers and hackers to develop malware that invades personal and business information in a very efficient manner. Therefore, mobile devices are an ideal target for various security issues and data privacy threats in a mobile ecosystem. Threats posed by malwares include leaking of private information, financial loss to users, system damage. For better protection on computers, researchers and manufacturers making great efforts to produce anti-malware systems with effective detection methods why the most targeted platform for the malware developers is Android and why and how and when malwares propagate into the mobile system with how they are detected, and protection mechanism is discussed in this paper. © Grenze Scientific Society, 2023.

关键词： Personal computing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：