To investigate whether the sleeve armature, induction coil armature, and direct fed coil armature of three electromagnetic emitters have the same control law, the McKinney analysis method was used to establish the con...
详细信息
Mountain tunnel excavation has two problems, which are a shortage of skilled engineers and frequent industrial accidents. automation of mountain tunnel excavation is progressing to solve these problems. However, loadi...
详细信息
ISBN:
(纸本)9798350355376;9798350355369
Mountain tunnel excavation has two problems, which are a shortage of skilled engineers and frequent industrial accidents. automation of mountain tunnel excavation is progressing to solve these problems. However, loading explosives in mountain tunnel excavation is difficult to automate because this task requires a sense of force. Motion reproduction is an expected method to automate the process of loading explosives that takes the sense of force into account. It uses bilateral control to save and reproduce motions and has the advantage of being able to reproduce forces and teach human skills to manipulators. On the other hand, motion reproduction cannot succeed in saved tasks when the relative position of the loading hole and manipulator or the direction of the loading hole changes from the saving phase. Therefore, this paper proposes a method to compensate for variations in relative position and direction by image processing based on depth information in motion reproduction for automation of loading explosives. Experiments showed the effectiveness of the proposed method through the successful reproduction of the insertion motion despite variations in relative position and direction.
The capacity of the rural power system is small. When it is disturbed dramatically, the frequency and voltage are no longer constant, but a dynamic process. to analyze the transition process of rural power systems, th...
详细信息
The scope of the paper is focused on the development of a stand for learning object regulation for the didactics of control systems in the power industry. The test system, based on the executive part in the form of a ...
详细信息
ISBN:
(纸本)9798350350708;9798350350715
The scope of the paper is focused on the development of a stand for learning object regulation for the didactics of control systems in the power industry. The test system, based on the executive part in the form of a fan and a damper, and the measuring part (anemometer) will provide the possibility of manual and automatic control of the selected actuator in order to achieve the set value. The stand will allow to get acquainted with the actual electric diagram of the control cabinet, the construction and application of individual components, and to provide insight on current data from all its elements. The obtained samples will enable the identification of the object, build a model and develop a successful control strategy, e.g. by selecting PID controller settings. Ultimately, the bench can provide a platform for testing the application of more advancedcontrol systems, such as neural networks, by expanding the number of process variables and introducing a number of disturbances. Due to the versatility of the solutions used, it is possible to adapt the stand to various levels of user advancement, from engineers who want to learn selected tools of the automation work, up to advanced professionals. The main purpose is explanation of possibilities for collaboration between future technologists and automation experts.
This paper introduces the development of a virtual sensor utilizing machine learning algorithms in response to challenges observed with physical sensors in grinding controlprocesses, such as calibration issues, commu...
详细信息
ISBN:
(纸本)9798350355291;9798350355284
This paper introduces the development of a virtual sensor utilizing machine learning algorithms in response to challenges observed with physical sensors in grinding controlprocesses, such as calibration issues, communication failures, and frequent disconnections. To enhance automationprocess reliability, we propose employing estimators based on Random Forest Regression (RFR), Multilayer Perceptron (MLP), and one-dimensional Convolutional Neural Networks (CNN-1D) with kernel filters. The performance of these models is evaluated within an advancedcontrol loop incorporating OPC protocol communication with a PLC. This evaluation identifies the most robust algorithm across diverse operational conditions.
To improve the automation for the startup process of a pressurizer water reactor (PWR) nuclear power plant (NPP), reduce the work intensity of the reactor operator, shorten the startup time, and improve the correctnes...
详细信息
ISBN:
(纸本)9780791888315
To improve the automation for the startup process of a pressurizer water reactor (PWR) nuclear power plant (NPP), reduce the work intensity of the reactor operator, shorten the startup time, and improve the correctness and standardization of the process, the automatic control of NPP startup process is studied in this paper. First, the control scope and the requirements of automatic startup control system are analyzed and studied based on the characteristics and the operation management process of PWR NPP. Aiming at the current manual control tasks, three realization control methods are proposed, including sequence control, traditional closed loop control and advanced algorithm. A simulation platform for automatic startup system of typical PWR NPP was established based on 3KeyMaster, Relap5, and MATLAB/Simulink. Two typical manual controlprocesses in state 3 for the startup process are selected to design the automatic control system based on PI controller and fuzzy controller respectively, and the simulation tests are carried out. The simulation results show that the designed control systems can realize the automatic control of the processes. Compared with the manual control, the control performance is improved, and the operation steps and work burden of operator are reduced. This study can provide a reference for the design of automatic startup and shutdown control system, and it is of great significance for improving the automation of startup and shutdown process of PWR NPP.
In this paper, a newly developed author's vision system allowing identification of packages moving on the conveyor belt and their classification is presented. An important aspect is that the mentioned objects move...
详细信息
ISBN:
(纸本)9798350362350;9798350362343
In this paper, a newly developed author's vision system allowing identification of packages moving on the conveyor belt and their classification is presented. An important aspect is that the mentioned objects move at relatively high speeds, which is challenging for any vision system. The methodology used in the plant is based on a hybrid combination of algorithmic determination of the features of a given object with artificial neural networks performing the classification process. An essential aspect of the work is using the advanced camera, which provides three-dimensional image analysis. The obtained verification results confirm the system's usefulness not only for research purposes but even for implementing industrial automation tasks.
This research explores the optimization of modeling and control strategies for a cement mill using advanced Artificial Intelligence (AI) techniques. Neural Nonlinear AutoRegressive with eXogenous input (NNARX) models ...
详细信息
ISBN:
(纸本)9783031782657;9783031782664
This research explores the optimization of modeling and control strategies for a cement mill using advanced Artificial Intelligence (AI) techniques. Neural Nonlinear AutoRegressive with eXogenous input (NNARX) models are employed to capture the nonlinear, multivariable dynamics of the cement grinding process. The Levenberg-Marquardt algorithm demonstrated superior training performance, achieving high accuracy in predicting key process parameters like inlet chamber fill and main drive current. The study also presents a neural control approach based on inverse modeling, enabling precise input predictions to maintain desired output conditions, stabilizing product quality and minimizing energy usage. Comparisons of neural network configurations suggest that simpler models are effective, with only slight benefits from more complex networks.
This paper systematically analyzes the general modeling process of hydraulic servo system, points out the simplified conditions of its approximation as a linear model, and makes clear the shortcomings of its control a...
详细信息
Interest in integrating wireless communication capabilities into industrial Cyber-Physical Systems (CPS) has surged recently. Driven by advantages like ease of deployment, reduced maintenance costs, and asset mobility...
详细信息
ISBN:
(纸本)9798350355376;9798350355369
Interest in integrating wireless communication capabilities into industrial Cyber-Physical Systems (CPS) has surged recently. Driven by advantages like ease of deployment, reduced maintenance costs, and asset mobility, CPSs now employ wireless communication for manufacturing control, logistics tracking, processcontrol, and heavy machinery management. While wireless technologies such as IEEE 802.11, 5G cellular networks, and redundant IEEE 802.15.4 networks offer possible solutions, the challenge to the adoption of these solutions for control systems lies in ensuring reliable and deterministic data delivery. Software-based private 5G implementations emerge as an intriguing solution, offering architectural flexibility, potential cost-effectiveness, and adaptability for diverse traffic types. We present a novel software-based 5G industrial wireless testbed with precision wireless channel measurement and control to support measurement-based research in the application of private 5G networks to these operational scenarios.
暂无评论