检索结果-内蒙古大学图书馆

Adaptive Dual-Layer Sliding Mode control for Ball on Plate System Driven by Shape Memory Alloy Wire

Journal of The Institution of Engineers (India): Series B 2024年第4期105卷 989-997页

作者： Sundareswari, M. Banu Mozhi, G. Then Dhanalakshmi, K. Department of Instrumentation and Control Engineering National Institute of Technology Tamil Nadu Tiruchirappalli India

This paper describes a dual-layer adaptive sliding mode control for a ball-on-plate system propelled by shape memory alloy (SMA) wire actuators. Conventionally, hydraulic, pneumatic, and electric actuators are used to power ball-balancing systems. However, they are heavy and bulky and take up more space. SMA actuators offer a solution to these drawbacks due to their unique actuating properties. Naturally, two-dimensional ball-balancing systems exhibit nonlinearity, which is further intensified when integrated with an SMA actuator. Moreover, these systems are sensitive to external disturbances, and controlling such systems with uncertainty using conventional control strategies is difficult. These concerns motivated the design of the dual-layer sliding mode controller (SMC) for the SMA driven ball on plate system to mitigate the causes of nonlinearities. The design is then validated by experimentation using Simulink/MATLAB™. © The Institution of Engineers (India) 2024.

关键词： Robust control

来源：评论

学校读者我要写书评

暂无评论

Inspection of dynamic modelling and control of a parabolic trough solar collector

引用

Materials Today: Proceedings 2023年 80卷 92-97页

作者： Goel, Anubhav Manik, Gaurav Verma, Om Prakash Department of Polymer and Process Engineering Indian Institute of Technology Roorkee India Department of Instrumentation and Control Engineering Dr. B R Ambedkar National Institute of Technology Jalandhar India

Solar energy conversion to thermal energy has enormous potential for meeting the need for heat energy in a variety of applications. A parabolic trough solar collector (PTSC) has proven to be effective in solar to thermal conversion. Installing a PTSC to service a specific application necessitates a large setup and significant cost, so it would be beneficial if such system analytically tested and optimized beforehand. As a result, the study relating to finding the options that might assist in improving the PTSC performance becomes critical. Modelling the PTSC is one such useful way that can assess it and suggest possible changes. Thus, surveying the literature in this area becomes equally important. This study attempts to explore the potential of dynamic modelling of PTSC's and its control mechanisms. A summary of the prospects for PTSC dynamic modelling is offered, a simplified basis is given to reader by covering the fundamentals of modelling methodologies, as well as the associated research that go along with them. Further, PTSC control components and improvements are investigated. Relevant discussion about the possibilities and limitations are provided, future scopes are also included. © 2023

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Traffic sign recognition using deep learning

引用

International Journal of Vehicle Autonomous Systems 2023年第2-4期16卷 97-107页

作者： Patel, Vraj Mehta, Joy Iyer, Saurab Sharma, Ankit K. Instrumentation and Control Engineering Department Institute of Technology Nirma University Gujarat India

Recognition of traffic signs is an integral step towards achieving Advanced Driver Assistance Systems (ADAS) as distracted driving is one of the primary causes of road accidents and fatalities. This paper attempts to exploit the capabilities of Convolutional Neural Networks (CNN) to recognise traffic signs under various computational and environmental constraints. The German Traffic Sign Recognition Benchmark (GTSRB) dataset is used for the classification of images. The dataset is subjected to various image processing techniques like greyscaling, denoising, filtering, and thresholding to obtain a generalised model for the recognition of traffic signs. The neural network used here comprises three convolution layers each followed by a max pooling layer which further are followed by four fully connected dense layers. The models are trained for 100 epochs with a validation split of 20%. The model performs best with 'Adam' optimiser with a learning rate of 0.001. © 2022 Inderscience Enterprises Ltd.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Single-Sensor based CSPO Algorithm for Maximum Power Point Tracking under Dynamic Shading Conditions

引用

Journal of The Institution of Engineers (India): Series B 2024年第4期105卷 841-854页

作者： Bashista, Prateek Mishra, Anurag Kumar, Bhavnesh Tyagi, Arjun Department of Instrumentation and Control Engineering Netaji Subhas University of Technology New Delhi India Department of Electrical Engineering Faculty of Technology University of Delhi Delhi India

One of the most significant and difficult challenges in solar systems is determining the maximum power point. This process becomes more difficult when the array of solar modules is subjected to non-uniform shade. A unique hybrid maximum power point tracking (MPPT) approach is presented in this research. The suggested approach, cuckoo search–perturb observe, is created by combining the traditional perturb & observe (P&O) and cuckoo search algorithms (CSPO). A hybrid algorithm has been developed to capitalize on the benefits of both algorithms while overcoming their respective disadvantages. The proposed algorithm attempts to incorporate the most prominent aspects of both algorithms while also attempting to address the drawbacks of both algorithms and improving the accuracy of the new approach by resolving the issue of P&O getting stuck on local maxima during non-uniform irradiance and reducing the resource-intensive approach of cuckoo search by limiting its number of iterations. Furthermore, the suggested approach locates the maximum power point using just voltage sensors, decreasing sensor requirements. The simulation findings for maximum power point tracking performance are also presented. © The Institution of Engineers (India) 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Position control of a Prismatic joint for Motorized Single Link Robotic Arm Using Adaptive Super- Twisting Sliding Mode control

引用

Journal of The Institution of Engineers (India): Series B 2023年第5期104卷 1035-1042页

作者： Then Mozhi, G. Banu Sundareswari, M. Dhanalakshmi, K. Department of Instrumentation and Control Engineering National Institute of Technology Tiruchirappalli Tiruchirappalli620015 India

Design of the dual layer adaptive super-twisting sliding mode control (ASTSMC) strategy for position control of a motorized single link flexible robotic arm is presented in this *** system comprises of a cantilever beam, the robotic arm whose horizontal sliding enables positioning at the required length. Prismatic joint at the fixed extremity of the flexure is positioned at the desired point (the set length) by a linear actuation system- the DC motor and the lead-screw. The parameters and hence the model of the DC motor is determined using the nonlinear least-square (NLS) parameter estimation method. The flexible manipulator is modeled using the lumped parameter model approach. The super twisting algorithm and adaptive law are designed in combination to control the position of the robotic arm;the performance of the adaptive SMC controller is compared with that of the classical PID controller and SMC. The simulated and experimental results show that positioning accuracy is ensured and the response time is improved by the ASTSMC controller. © 2023, The Institution of Engineers (India).

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

WAVELET BASED INDEPENDENT COMPONENT FEATURES FOR CLASSIFICATION OF LOWER-LIMB MOVEMENTS FROM SURFACE EMG SIGNALS

Biomedical Sciences Instrumentation

引用

Biomedical Sciences instrumentation 2024年第1期60卷 109-115页

作者： Madan, S. Arunganesh, K. Sivakumaran, N. Karthick, P.A. Department of Instrumentation and Control Engineering National Institute of Technology Tiruchirappalli Tamilnadu India Periyar Maniammai Institute of Science and Technology Thanjavur India

Surface electromyography is a non-invasive technique of measuring the electrical activities of contracting skeletal muscles. Recently, there are several attempts have been made to actively decode these signals for the applications such as myoelectric control, rehabilitation and sports mechanics. However, the decoding of the surface EMG signals remains a challenging task for the researchers because of its randomness associated with the signal generation mechanism. Further, the stochastic nature of these signals contributes to the non-stationary and multicomponent variations in the signals and this makes the analysis highly complex. In this work an attempt has been made to develop a non-stationary signal processing framework using wavelet transform (WT) and independent component analysis (ICA) for the recognizing standing and sitting tasks from surface EMG. For this purpose, the surface EMG signals of vastus medialis recorded from fourteen untrained subjects are considered for the analysis the signals are preprocessed and subjected to wavelet transform and ICA. In addition to this, the time and frequency domain measures namely, mean average value (MAV), root-mean-square (RMS), zerocrossing (ZC), mean frequency (MNF) and median frequency (MDF) also are used to develop the classification models based on support vector machine (SVM). The models are validated using five-fold cross validation. The results show that the time, frequency and time-frequency features show considerable variations in both the tasks. All extracted features exhibits significant difference in sitting and standing tasks. The proposed SVM based WT-ICA technique is found to achieve a classification accuracy of 92.31%. The performances of time and frequency domain metrics are found to lower than timefrequency approaches. It appears that the proposed technique is capable of handling the complex non-stationary EMG effectively. It could be used for controlling external devices such as prosthetic legs. © 20

关键词： Myoelectrically controlled prosthetics

来源：评论

学校读者我要写书评

暂无评论

An ensemble transfer learning-based deep convolution neural network for the detection and classification of diseased cotton leaves and plants

引用

Multimedia Tools and Applications 2024年第36期83卷 83991-84024页

作者： Rai, Chitranjan Kumar Pahuja, Roop Department of Instrumentation and Control Engineering Dr. B R Ambedkar National Institute of Technology Punjab Jalandhar144008 India

Agriculture is important for the economy of any country, and India is considered to be an agricultural country. One of the primary goals of agriculture is to produce disease-free crops. Since ancient times, farmers and other planting specialists have had to contend with a variety of problems and current agricultural constraints, such as widespread cotton diseases. There is a great need for a rapid, efficient, economical, and reliable approach to diagnosing cotton infection in the agri-informatics area, as severe cotton disease may result in the loss of grain crops. This paper presents an advanced method that automates the detection and classification of diseased cotton leaves and plants through deep learning techniques applied to images. To address the challenge of supervised image classification, we employ a bagging ensemble technique consisting of five transfer learning models: InceptionV3, InceptionResNetV2, VGG16, MobileNet, and Xception. This ensemble approach was adopted to significantly improve the performance of each individual mode. The ETL-NET framework we introduced was thoroughly evaluated using two publicly accessible datasets. Specifically, it achieved an impressive accuracy rate of 99.48% and a sensitivity rate of 99% when applied to binary datasets. Additionally, on the multi-class dataset, the framework achieved an accuracy rate of 98.52% and a sensitivity rate of 99%. Our method outperformed the state-of-the-art techniques and displayed comparatively better results. Remarkably, our approach demonstrated even higher performance than widely used ensemble techniques, generally considered benchmarks in the field. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Knee Joint Vibroarthrographic Signal Analysis and Classification Using Wavelet Transform 4

Knee Joint Vibroarthrographic Signal Analysis and Classifica...

引用

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

作者： Durge, Gaurav Joshi, Ashutosh Jaid, Atharva Vishwakarma Institute of Technology Department of Instrumentation and Control Engineering Pune India

ISBN: (纸本)9798350352931

The knee joint is susceptible to various pathological conditions that alter its biomechanical properties, leading to changes in vibrational characteristics detectable through Vibroarthrographic (VAG) signals. VAG signals present a valuable early diagnostic tool for knee joint disorders, owing to their nonstationary and nonlinear characteristics. Although previous research has developed different time and frequency-based parameters for VAG signal assessment and classification, limited exploration has been devoted to statistical modeling methods in the spectral domain. This study seeks to contribute to the field by classifying VAG signals into normal and abnormal categories, reflecting the health condition of knee joints, through the introduction of a novel set of features derived from wavelet analysis. This study uses a comprehensive approach integrating wavelet decomposition and sub-band feature extraction to analyze VAG signals. It focuses on spectral domain transformations using wavelet transform to extract statistical characteristic features like Energy, Shannon Entropy, Kurtosis, Skewness, and Standard Deviation, which capture fluctuations in VAG signals. The classification task is then performed by using a Support Vector Machine (SVM) and Random Forest algorithms. The proposed system achieves an impressive overall classification accuracy of 93.33% for the Random Forest classifier. This novel approach, leveraging wavelet analysis and statistical features, demonstrates the promising potential for accurate screening, with an ability to effectively classify more than 90% of subjects. © 2024 IEEE.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Patients Privacy in Healthcare Records with Blockchain technology 15

Enhancing Patients Privacy in Healthcare Records with Blockc...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Chaudhari, Archana Kedar Mahajan, Prasad Prabhakar Jadhav, Viraj Anil Kudtarkar, Raj Rajaram Vishwakarma Institute of Technology Department of Instrumentation and Control Engineering Pune India

ISBN: (纸本)9798350370249

Healthcare record administration faces many obstacles, including data manipulation, security vulnerabilities, and the risks associated with centralized storage. To securely store and manage health records, we provide an innovative system that uniquely combines blockchain technology with the Interplanetary File System (IPFS). In contrast to conventional methods, our strategy makes use of a private blockchain network that was created in collaboration with Ganache to establish a decentralized ledger that guarantees data integrity and immutability for each and every transaction through cryptographic security. This system is unique in that it uses IPFS for decentralized file storage, which makes it possible to distribute and retrieve big medical records quickly and efficiently while safeguarding sensitive data from single-point failures. Our front-end interface, created with Bootstrap, HTML, CSS, and JavaScript, offers a user-friendly experience for both patients and healthcare professionals. Furthermore, the blockchain network and IPFS are smoothly integrated into our ***-built backend. The shortcomings of traditional health record management systems are addressed by this special combination, which improves security, accessibility, and transparency. Our technology protects the security and confidentiality of sensitive medical data while promoting interoperability and collaboration among healthcare stakeholders. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Classification of Sonic Log using Multiresolution Features 5

Classification of Sonic Log using Multiresolution Features

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Patankar, Sanika Hursad, Akash Ambekar, Harsh Ijmulwar, Jatin Donge, Aditya Vishwakarma Institute of Technology Department of Instrumentation and Control Engineering Pune India

ISBN: (纸本)9798331504403

This research work proposes a novel approach to sonic log prediction in the oil and gas industry, emphasizing the importance of accurate DTC (Compressional Sonic Transit Time) and DTS (Shear Sonic Transit Time) values for reservoir characterization. The methodology combines machine learning and signal processing, specifically Wavelet transformation, to enhance prediction accuracy. The process involves dataset preprocessing, Wavelet transformation on seismic signals, feature extraction, and machine learning model training. Results demonstrate an impressive 89 percent accuracy, surpassing other algorithms. The dataset utilized is comprehensive and diverse, ensuring the model's robustness across various geological scenarios. The proposed approach significantly contributes to accurate wave velocity estimation, boosting confidence in reservoir characterization. Overall, the study offers a practical and effective solution for improving sonic log predictions, benefiting hydrocarbon exploration and decision-making in the petroleum industry. © 2024 IEEE.

关键词： Petroleum industry

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：