This research presents an advanced solar-powered cooling system seamlessly integrated with IoT functionalities offering a comprehensive solution for enhanced functionality, efficiency, and sustainability. The proposed...
详细信息
ISBN:
(数字)9798350378092
ISBN:
(纸本)9798350378108
This research presents an advanced solar-powered cooling system seamlessly integrated with IoT functionalities offering a comprehensive solution for enhanced functionality, efficiency, and sustainability. The proposed system comprises a transmitting section incorporating essential components such as a solar panel, voltage regulator, Node MCU, temperature sensor, 12V DC fan, and transmitting coil. Utilizing the temperature sensor, the system dynamically regulates the fan operation, activating it when the transmitting coil’s temperature surpasses a predefined threshold to initiate cooling. Meanwhile, in the receiving section, a diode, potentiometer, and Node MCU collaborate to facilitate seamless wireless communication, enabling remote monitoring and control of critical parameters such as coil temperature and voltage during charging cycles. The development of the user interface is a testament to modern web technologies, with HTML, CSS, and JavaScript being employed to create an intuitive and visually appealing platform for real-time data visualization and system management. Through this integration, the system optimizes energy utilization and bridges the gap between renewable energy sources and smart cooling technologies, this integrated approach not only addresses the pressing need for eco-friendly cooling solutions additionally lays the background for a more environmentally friendly and sustainable future.
Fruit recognition plays an important role in automated picking, in order to improve the accuracy and real-time picking, this study uses deep learning methods to design a fruit-picking robot visual recognition system. ...
详细信息
ISBN:
(纸本)9798350364200;9798350364194
Fruit recognition plays an important role in automated picking, in order to improve the accuracy and real-time picking, this study uses deep learning methods to design a fruit-picking robot visual recognition system. First, multiple preprocessing methods are used to expand the sample data, and the images are proportionally cropped and scaled to make the image dataset more complete;subsequently, to improve the accuracy of image recognition, a multilayer Convolutional Neural Networks (CNN) is established;and the Adam algorithm is utilized to train the model parameters several times to determine the optimal hyperparameters, thus overcoming the defects of the multilayer neural network that has a local optimal search. The experimental results show that compared with the random forest method, this system has the characteristics of high-speed recognition and high accuracy in fruit picking, and can quickly and accurately recognize fruit images, with the recognition speed of a single image taking only 0.081 seconds, and the recognition accuracy reaching more than 97.35%. The method has important theoretical and application value and provides an effective means for automatic fruit recognition.
Condition monitoring is essential for protection and scheduling maintenance of critical systems such as in biomedical research, chemical and pharmaceutical industries without any human intervention. A wireless sensor ...
详细信息
Superconductor-based magnetic levitation struggles with an inherently non-stiff and lightly damped coupling between superconductor and levitation module. This means a magnet that is levitating above a superconductor c...
Superconductor-based magnetic levitation struggles with an inherently non-stiff and lightly damped coupling between superconductor and levitation module. This means a magnet that is levitating above a superconductor can easily start oscillating if the equilibrium is disturbed. This can, for example, occur if a superconductor-based levitation module is mounted on a mechanical handling system. During motion of the handling system magnetic torques generate angular velocities of the levitation module. For production systems that may use levitation for frictionless motion this is an undesired behavior. Therefore, it is necessary to stabilize the levitation module during motion of the handling system. In this publication a feed-forward disturbance compensation control scheme is proposed using a novel parallel actuator-sensorsystem based on induced voltages from time varying magnetic fields. The proposed control law is validated experimentally. Angular velocities during motion can be reduced by around 50%, depending on performance metric, with respect to the uncontrolled case.
In order to realize the position sensorless control of brushless DC motor, a position sensorless control method of brushless DC motor based on sliding mode observer is proposed. In order to reduce the chattering of th...
详细信息
ISBN:
(纸本)9783030945541;9783030945534
In order to realize the position sensorless control of brushless DC motor, a position sensorless control method of brushless DC motor based on sliding mode observer is proposed. In order to reduce the chattering of the system, a smooth hyperbolic tangent function is introduced. Therefore, the controlsystem can obtain a smooth linear back-EMF estimate without adding a low-pass filter and a phase compensation module, thereby avoiding the phase lag of the back-EMF estimate. The estimated BLDC motor position sensorless back EMF signal corresponds to 3 virtual Hall signals, and 6 discrete commutation signals are directly obtained, thus eliminating the need for fixed phase shift circuit and phase shift angle calculation. Simulations and experiments show that the proposed method can accurately estimate the line back EMF of the position sensorless brushless DC motor, and achieve the research goal of precise control of the position sensorless brushless DC motor.
Although driving automation systems have made significant progress over recent years, human involvement is still vital, especially for Level 2 (L2) automated vehicles. This study aimed to design and evaluate an in-veh...
详细信息
ISBN:
(纸本)9781450394154
Although driving automation systems have made significant progress over recent years, human involvement is still vital, especially for Level 2 (L2) automated vehicles. This study aimed to design and evaluate an in-vehicle interface for vehicles with L2 features to help drivers understand critical situations that require intervention. This study was conducted in two phases. First, new dashboard prototypes were developed through four design iterations. Second, a between-design experimental study was conducted to test the dashboard designs' efficiency. Forty-two participants were assigned to three dashboard groups (advanced, Basic, Original) and drove through seven scenarios. Results showed that participants took back control significantly earlier (i.e., similar to 2 seconds earlier) in advanced and Basic Dashboard groups. The results indicated that providing take back control feedback helps drivers to be more aware while driving vehicles with L2 features and that additional feedback regarding road geometry can improve drivers' take back control performance.
Urbanization is increasing indoor air quality, especially in households. For the real-time monitoring and control of home air pollution via the combination of cloud computing technologies with wireless sensor networks...
详细信息
The proceedings contain 92 papers. The topics discussed include: analytical and neural processing of multispectral images for identification of water pollution;development of an algorithm for calculating the parameter...
ISBN:
(纸本)9798350340945
The proceedings contain 92 papers. The topics discussed include: analytical and neural processing of multispectral images for identification of water pollution;development of an algorithm for calculating the parameters of the primary sensor transducer fora dynamic indentation device;thermal motion equivalent method application for multicopter swarm in exploration task;radiofrequency method for measurement of interface position between two dielectric media in a reservoir independently on their dielectric permittivities;innovative surface eddy current probe for non-destructive testing;the root-mean-square velocity stabilization of swarm multicopters interacted by the thermal motion equivalent method;stereo visual system for ensuring a safe interaction of an industrial robot and a human;exploring the potential of NIR reflective and NIR absorptive materials in the manufacture of attack tools for biometric systems;and a new virtual human model based on AR-601M humanoid robot for a collaborative HRI simulation in the Gazebo environment.
This work introduces SENSOTERIC, a multi-partner project that aims at leveraging the properties of emerging Reconfigurable Field Effect Transistors (RFETs) to develop a sensor platform. RFETs will be used for a generi...
详细信息
The Internet of Things (IoT) and Machine Learning (ML) represent dynamic research fields with significant growth. IoT applications have gained popularity among technology researchers and developers, and the increasing...
详细信息
ISBN:
(纸本)9783031751691;9783031751707
The Internet of Things (IoT) and Machine Learning (ML) represent dynamic research fields with significant growth. IoT applications have gained popularity among technology researchers and developers, and the increasing deployment of IoT devices in critical infrastructures improves efficiency and reliability and raises concerns about cyber-attacks. Enterprises have effectively implemented IoT services, enabling automated production through remote and intelligent control. However, this adoption has concurrently introduced novel security vulnerabilities. Addressing the security and privacy challenges in IoT, especially considering energy limitations and scalability issues, remains a critical focus in computer security. This paper aims to prevent multiple attacks targeting sensor nodes' data manipulation. It encompasses a range of threats, such as sensing layer attacks, malfunctions, tamper attacks, false data injection, base node and clone attacks. The proposed approach involves a threat model and a pairing algorithm that utilizes machine learning to associate each sensor node with its corresponding node. To accomplish the goal, the performance of the proposed solution is compared with various machine learning models, including Decision Tree, Linear Regression, k-nearest neighbors (KNN), Random Forest, and AdaBoost. The evaluation utilized two openly accessible real-world datasets, with metrics such as accuracy in attack detection, training time, and testing time being considered. By incorporating machine learning algorithms to improve attack detection in IoT environments, the proposed approach represents a significant advancement in enhancing security and privacy. The results highlight the importance of adopting advanced techniques to safeguard IoT systems from potential threats. The proposed method achieved an impressive 96.75% accuracy rate in detecting attacks, surpassing existing solutions with nearly twice the speed in training and testing times. As the IoT landsc
暂无评论