In this paper, the performance characteristics of the boiler water level system are analyzed, and a fuzzy control method is used to control it based on the three-stroke water supply system. This fuzzy control method is to reason out the appropriate fuzzy control rules, design fuzzy controller, and applied to the control system, so that the system for self-adjustment of PID parameters, constitute a fuzzy PID control system. On this basis, this paper analyzes the performance, advantages and characteristics of two control systems: the traditional PID control system and the fuzzy PID control system, and simulates the parameters of the input variables for comparison and analysis.
In view of the high similarity of feature points in low texture environment, this paper proposes an interactive method of manual selection of feature points based on stereo vision under the condition that automatic modeling cannot meet the requirement of 3D environment.Firstly, the model of binocular stereo vision camera with parallel optical axis is designed, then the camera calibration is carried out, and the 3D ranging system of interactive manual selection of feature point pairs is developed.In order to verify the effectiveness of the system, this paper uses corridor floor tiles with fewer texture features to carry out experimental tests. By verifying the three-dimensional coordinates of the measured feature point pairs, and comparing with the actual measured values, it is found that the measurement error is less than 1%.
The past two decades of research on UAVs has revealed that about seventy percent of it had been published in the previous four years. To serve the exponentially increasing role of UAVs in multi-disciplinary research, the choice for most suitable path planning algorithms is presented in this work. The extent of autonomy in path planning for a UAV primarily depends upon the capabilities of its algorithm. Hence, a comprehensive survey study was proposed and conducted. This article presents a summary of the survey and suggests most suitable path planning algorithms for a UAV application. A collective consciousness was also developed while going through the process and presented on how the research work on intelligent robots should be categorized to cater future needs.
With the development of deep learning, target detection has become one of the research directions of many scholars. As one of the more mature algorithms, the single-stage YOLO algorithms have been widely used in real life. Combining the development history of the YOLO algorithm, this article focuses on the main framework and main content of the current latest YOLOv5 algorithm, and uses the YOLOv5s model to identify and detect multi-target. The test results show that YOLOv5s algorithm has good detection effect and wide application meaning in real life.
This device is designed for the phenomenon that people often ignore the potted plants at home and lead to the death of potted plants. The intelligent flowerpot can make potted plants survive and grow better without supervision. It is a smart home product based on Internet of things technology. STM32 single chip microcomputer is used to collect the data of temperature sensor, humidity sensor, soil humidity sensor, harmful gas sensor, photosensitive sensor and other sensors, and it is used with intelligent tracking system composed of four DC motors, automatic irrigation system and mobile phone app; Through machine learning, potted plants can adapt to a variety of potted plants, so as to achieve the purpose of potted cultivation, beautification and improvement of living environment. Aiming at the disadvantages of artificial cultivation and potted plants in traditional family life, the maintenance of scientific intelligence is realized. We designed this smart flowerpot. This flowerpot not only solves the problem of life, but also adds green to the homes of those who have no time or ability to raise flowers, even the disabled.
In recent years, the technology of the Internet of Things (IoT) has developed rapidly and has been successfully used in different fields. Moreover, the application context of the IoT will be extended more widely. This work applies the IoT technology to forestry management, including: 1. Transmission of sensing data about forest information using wireless network communication technology of Low Power Wide Area Network (LPWAN) such as LoRa and NB-IoT; 2. Apply different sensing technologies to survey resource of forest and monitor the microclimate changes in forest. In order to verify the proposed LPWAN communication technology, sensors, and sensor deployment, we built LoRa and NB-IoT communication equipment (including repeat equipment) and various sensors to transmit the real-time sensing data in the Fushan Botanical Garden with the most diverse and complex terrain in Taiwan. The returned data also proves the successful operation of various communication devices and sensors.
This paper proposes a new robust attitude control architecture for microsatellites. Based on deep learning fault detection method, Cerebellar Model Articulation Controller (CMAC) is used as fault-tolerant control. Using the image recognition function of Generation Adversarial Networks (GAN), the microsatellite actuator fault wavelet spectrum is used as the basis of training generator and discriminator for real-time fault diagnosis and classification. When the system fault diagnosis determines that the fault occurs, the cerebellar neural network participates in the fault-tolerant control. Using the Gan learning ability of generating confrontation network, the problems of insufficient sample data and insufficient sample labeling are solved respectively. As a kind of local learning network, CMAC has the advantages of strong generalization ability, fast convergence speed and simple hardware and software implementation. The simulation results show that, compared with the traditional methods, the fault detection and fault-tolerant control of GAN method combined with CMAC has higher accuracy and robustness.
The main purpose of this paper is to use the image recognition function of LabVIEW to construct a mobile robot with various functions, and make it applicable to the industry having web monitoring applications. The core of the robot is the KNRm controller which is suitable for beginners, and can be connected to DC servo motor, RC servo motor, infrared, ultrasonic and camera to achieve various functions of the robot. The structure of the robot uses metal parts sold by Studica company, which can be in accordance with the desired function to assemble the robot. Since the company is a designated equipment sponsor company for World Skills competitions, it can also be in line with international standards. Finally, PID control and sensors are added to make the robot movement and position more accurately.
The purpose of this thesis is to show that isolated pixel filtering-based image inpainting methods for drawing robots. For watercolor painting, HSI color space is used to improve the effect of color simplification such that the recognition of image processing results is enhanced, firstly. Second, that less-affected isolated point color is replaced with the surrounding color via isolated pixel filtering methods. Third, we use image inpainting technology to reduce the distortion caused by the isolated pixel filtering. Besides, we adjusted the path planning as well as reduced isolated points to dramatically reduce drawing time. For sketch painting, through the image resolution adjustment as well as the shortening of the spacing of the drawing lines, the robot can draw more detailed pictures in the same size of drawing space. To allow LabVIEW to directly issue commands to control the drawing robot, the communication function has been added. The measured results confirm that the application of the technology in this paper can shorten the drawing time by about 57% to 59% on the drawing robot system.
This study integrates the previous cross-cultural literature and aims to construct an analysis model of
cross-national culture with multiple dimensions from three important cultural dimension theoretical
models commonly used in cross-cultural studies: Hofstede, Global Leadership and Organizational
Effectiveness (GLOBE) and World Values Survey (WVS). Traditional statistical analysis seems to be
unable to solve the problem of the integration of relevant scales and units in different dimensions of
cultural analysis. Therefore, this study uses a self-organizing map (SOM) as an analysis method to
integrate 17 cultural variables from this multicultural dimension for cluster analysis and explains the
cultural types in 26 countries based on the results. This study explores the differences and similarities of
different countries in different cultural dimension analyses and provides a comparative model of
multicultural analysis. This study takes samples from three cross-cultural analysis databases as data
sources and employs the self-organizing map for analysis based on a neural network algorithm that can be
used for type discrimination, map analysis, process monitoring, and error analysis. The results identify the
cross-cultural groups of 26 countries and reveal their key cultural similarities and differences. We also
elaborate upon the findings of these cultural characteristics and multi-cultural dimensions. The
signification of this study is presented as a reference for subsequent studies of transnational and
cross-cultural analysis and its applications.