To address the challenges posed by restricted waters, uncertain model parameters, and strong environmental disturbances such as wind and currents during the harbor navigation of underactuated ships, this paper introdu...
详细信息
ISBN:
(数字)9798350380323
ISBN:
(纸本)9798350380330
To address the challenges posed by restricted waters, uncertain model parameters, and strong environmental disturbances such as wind and currents during the harbor navigation of underactuated ships, this paper introduces a method for controlling ship heading using partial dynamic linearization, which operates without relying on any model information. Firstly, a partial dynamic linearization model is developed using the system's input-output data, and then the model is adjusted online with changing navigation conditions through pseudo-partial derivative estimation. Additionally, conventional model-free adaptive control methods applied directly to ship heading control in the body coordinate system can result in non-convergent control errors. To solve this problem, this paper introduces a model-free adaptive sliding mode control method. Finally, MATLAB simulation tests and a comparative analysis withthe traditional model-free PID control method demonstrate the effectiveness of the proposed control method and its strong robustness against environmental disturbances.
Aerospace engine blade remanufacturing technology requires intelligent adaptive techniques for support. Due to the complexity of the operating environment and the demand for intelligence, in order to maximize machinin...
详细信息
ISBN:
(数字)9798331544577
ISBN:
(纸本)9798331544584
Aerospace engine blade remanufacturing technology requires intelligent adaptive techniques for support. Due to the complexity of the operating environment and the demand for intelligence, in order to maximize machining efficiency, avoid collisions, and adapt to different blade shapes and sizes, as well as to enhance production flexibility, research emphasis should be placed on path planning. through robotic path planning, it is possible to effectively optimize the machining path, reduce the movement time of the robot during the machining process, improve machining efficiency, and reduce the machining cycle. this paper first introduces the traditional rapidly exploring random tree (RRT) algorithm and the RRT* algorithm, and proposes an improved RRT* algorithm to address the shortcomings of these two algorithms. It first introduces the improved RRT* algorithm and proposes three improvement strategies. then, it conducts simulations in two-dimensional space and validates its effectiveness in two map environments. Finally, the paper models a robotic arm on the MATLAB software platform, simulates the path smoothing planning of the robotic arm, thereby verifying the feasibility and superiority of the algorithm.
In recent years, increasing the energy efficiency of buildings has become one of the objectives of facility managers. Advanced control methods can be used to improve the efficiency of Heating, Ventilation, and Air Con...
详细信息
ISBN:
(数字)9798331541699
ISBN:
(纸本)9798331541705
In recent years, increasing the energy efficiency of buildings has become one of the objectives of facility managers. Advanced control methods can be used to improve the efficiency of Heating, Ventilation, and Air Conditioning (HVAC). However, advanced control methods cannot be effectively applied due to inconvenient commissioning. therefore, simulating and modeling the HVAC system becomes particularly important for verifying various control algorithms. Modeling and calibrating the HVAC simulation system becomes crucial for the application of various control strategies based on actual operational data, while current calibration methods are usually based on experience. In this research, a method for the calibration of an HVAC model based on Heteroscedastic Evolutionary Bayesian Optimization (HEBO) is presented. Firstly, the HVAC model is built using the Modelica language in the Dymola environment. Secondly, real operation and weather data are fed to the HVAC model to predict the energy consumption of various equipment. thirdly, the Root Mean Squared Error (RMSE) between predicted and real values is minimized by HEBO so that the optimal parameters of the equipment can be obtained. Finally, a case study is conducted to verify the effectiveness of the proposed method. the results show that the CV(RMSE) of calibrated models meets the guideline requirements of ASHRAE, IPMVP, and FEMP.
the proceedings contain 33 papers. the special focus in this conference is on Internet Computing and IoT. the topics include: Malware Detection in the IoT Home Network;IoT-Based Analysis of Environmental and Motion Da...
ISBN:
(纸本)9783031859229
the proceedings contain 33 papers. the special focus in this conference is on Internet Computing and IoT. the topics include: Malware Detection in the IoT Home Network;IoT-Based Analysis of Environmental and Motion Data for Comfort and Energy Conservation in Optimizing HVAC Systems;improving Critical Controls Using IoT and Computer Vision;A Data-Driven Driving Under the Influence (DUI) Detection, Notification and Prevention System Using Artificial Intelligence and Internet-Of-things (IoT);understanding User Interactions with IoT Process models: A Demographic Perspective;Advancing IoT Process Modeling: A Comparative Evaluation of BPMNE4IoT and Traditional BPMN on User-Friendliness, Effectiveness, and Workload;threat Detection Using MLP for IoT Network;harnessing Social robotics and the Internet of things to Reduce the Risk of Older Adults Developing Hypothermia and Dehydration;re/Imagining Smart Home automation Framework in the Era of 6G-Enabled Smart Cities;smart Roadway Monitoring: Pothole Detection and Mapping via Google Street View;Energy-Efficiency Modeling for AI Applications on Edge Computing;optimizing Wireless Sensor Network Node Placement Using Bacterial Foraging Optimization;the Vital Role of Small and Marginal Farmer in Future of Our Climate: Democratization of Machine Learning, Artificial Intelligence, and Dairy Cow Necklace Sensors in Achieving the UN Climate Change Goals (COP21) and the Paris Agreement;autonomous Driving Prototype with Raspberry Pi by Using Image Processing Technology;towards Implementation of Privacy-Preserving Federated Learning Aggregation Using Multi-key Homomorphic Encryption;advancing Nursing Education through Virtual Reality Training: A Revolutionary Approach to Ensuring Patient Safety;multiDrone Simulator An Open Source Multi-plataform Tool to Use in Tests of Optimized Flight of Group of Drones;Revolutionizing Multiplayer Gaming: A Deep Dive into VisionXO, a 3D Multiplayer Tic-Tac-Toe Game.
this paper investigates the observability of two-time-scale multi-agent systems (MASs), with particular attention to antagonistic interactions among agents. the study begins by modeling the systems, followed by defini...
详细信息
ISBN:
(数字)9798331541699
ISBN:
(纸本)9798331541705
this paper investigates the observability of two-time-scale multi-agent systems (MASs), with particular attention to antagonistic interactions among agents. the study begins by modeling the systems, followed by defining observability and establishing its conditions using singular perturbation theory. Numerical simulations are conducted to demonstrate the effectiveness of the proposed conditions.
Due to the influence of noise, the performance of crack detection methods employing a single signal is not satisfactory. In order to fully utilize both acoustic and vibration signals, a compressor blade crack detectio...
详细信息
ISBN:
(数字)9798350307535
ISBN:
(纸本)9798350307542
Due to the influence of noise, the performance of crack detection methods employing a single signal is not satisfactory. In order to fully utilize both acoustic and vibration signals, a compressor blade crack detection method based on decision-level fusion of acoustic and vibration signals is proposed. Firstly, a crack detection model using SVM is designed, which utilizes the extracted permutation entropy and energy entropy features for classification. then a convolutional neural network model that fuse multi-source homogeneous signals is designed. Finally, multiple SVM models and convolutional neural network models were trained by taking acoustic and vibration signals as inputs, respectively. the improved BP network approach performs decision-level fusion based on the results of multiple models, and realizes the compressor blade crack detection. the effectiveness of the compressor blade crack detection method is verified through experiments.
this study presents a reinforcement learning-based framework for optimizing energy efficiency in electric vehicle (EV) and grid interactions. Managing grid load, especially during peak charging times, becomes critical...
详细信息
ISBN:
(数字)9798331541699
ISBN:
(纸本)9798331541705
this study presents a reinforcement learning-based framework for optimizing energy efficiency in electric vehicle (EV) and grid interactions. Managing grid load, especially during peak charging times, becomes critical as EV adoption increases. the framework leverages short-term load forecasting with data from the Electricity Load Forecasting dataset to dynamically balance energy distribution. Experimental results show a 131.5% reduction in Peak-to-Average Load Ratio (PALR) with a GRU model, a 97.53% improvement in Charging Efficiency Index (CEI) with a CNN-LSTM model, and a lower RMSE, demonstrating the framework’s effectiveness in enhancing grid integration and EV charging efficiency.
Accurate electricity consumption forecasting is essential for efficient resource allocation and grid management, particularly with limited data. the present paper investigates how artificial intelligence techniques ca...
详细信息
ISBN:
(数字)9798331518493
ISBN:
(纸本)9798331518509
Accurate electricity consumption forecasting is essential for efficient resource allocation and grid management, particularly with limited data. the present paper investigates how artificial intelligence techniques can enhance forecasting in small datasets and addresses data quality concerns in the educational sector. It reviews challenges in traditional forecasting, explores artificial intelligence methods such as support vector machines, autoregressive integrated moving average, and long short-term memory networks, and evaluates their performance using real-world data from four educational buildings belonging to the Technical University of Cluj-Napoca. By combining theoretical insights with empirical results, the present study advances artificial intelligence-driven forecasting for electricity consumption in small datasets, offering insights for future research and industry applications in energy management and policy formulation.
the hiring process is becoming increasingly complex, as HR departments are overwhelmed with large volumes of resumes and recommendations that require in-depth analysis. this paper presents SATYA (Smart AI-driven Talen...
详细信息
ISBN:
(数字)9798331520038
ISBN:
(纸本)9798331520045
the hiring process is becoming increasingly complex, as HR departments are overwhelmed with large volumes of resumes and recommendations that require in-depth analysis. this paper presents SATYA (Smart AI-driven Talent Yield Analyzer), a comprehensive AI system that automates the resume screening process, validates recommendations, and enhances the accuracy of talent acquisition. By leveraging Natural Language Processing (NLP), Machine Learning (ML), and graph-based algorithms, SATYA assesses resumes, verifies skill claims, evaluates recommendation credibility, and generates final candidate scores. Trained on a dataset of 1000 resumes manually scored by HR experts, SATYA achieved an accuracy of 91.4%, significantly outperforming traditional resume screening methods. this paper describes the architecture of SATYA, detailing the resume scoring model, recommendation network analysis, skill validation process, and multi-objective candidate evaluation. the system's scalable design ensures that it can be integrated into existing Applicant Tracking Systems (ATS) to improve talent acquisition efficiency.
Taking a single-link flexible system driven by a DC motor as an example, the Takagi-Sugeno (T-S) fuzzy model is used to study the state and disturbance estimation methods for nonlinear systems, which are commonly pres...
详细信息
ISBN:
(数字)9798350355642
ISBN:
(纸本)9798350355659
Taking a single-link flexible system driven by a DC motor as an example, the Takagi-Sugeno (T-S) fuzzy model is used to study the state and disturbance estimation methods for nonlinear systems, which are commonly present in the field of electromechanical engineering. By analyzing the working mechanism of the system, a nonlinear model of the system is established and then expressed as a T-S fuzzy model. By utilizing system state extension, the original system is transformed into a formal generalized system to achieve both system state estimation and estimation of system output disturbances. A robust proportional-integral observer is designed to achieve system state and disturbance estimation. the solution for the observer gain matrix is obtained by solving linear matrix inequalities. the system is studied separately with and without disturbance, and the correctness and effectiveness of the proposed method are verified through simulation results.
暂无评论