As the artificial intelligence market develops, demand for semiconductors also increases. In order to increase the efficiency of the semiconductor production process, anomaly detection technology is needed based on se...
详细信息
ISBN:
(纸本)9798331517939;9788993215380
As the artificial intelligence market develops, demand for semiconductors also increases. In order to increase the efficiency of the semiconductor production process, anomaly detection technology is needed based on sensor values attached to process machines. In this paper, we propose an anomaly detection system that determines whether there are abnormalities in the values obtained by attaching a sensor to the actual deposition process. The attached sensors include gas, temperature, and pressure sensors. A communication module is designed and made into a database, and the presence or absence of anomalies is determined using the characteristics of multivariate time series data through transformer-based anomaly detection network. An attention module-based transformer network is used in the AI-based anomaly detection network. Through evaluation, we confirmed that the transformer-based anomaly detection network achieves the best performance in terms of accuracy relative to other anomaly detection methods.
The rapid advancements in edge computing have opened new avenues for optimizing real-time control systems in maritime environments. Traditional centralized systems face challenges such as high latency, limited scalabi...
详细信息
Centralized control of a multi-agent system improves upon distributed control especially when multiple agents share a common task e.g., sorting different materials in a recycling facility. Traditionally, each agent in...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Centralized control of a multi-agent system improves upon distributed control especially when multiple agents share a common task e.g., sorting different materials in a recycling facility. Traditionally, each agent in a sorting facility is tuned individually which leads to suboptimal performance if one agent is less efficient than the others. Centralized control overcomes this bottleneck by leveraging global system state information, but it can be computationally expensive. In this work, we propose a novel framework called Longitudinal control Volumes (LCV) to model the flow of material in a recycling facility. We then employ a Kalman Filter that incorporates local measurements of materials into a global estimation of the material flow in the system. We utilize a model predictive control algorithm that optimizes the rate of material flow using the global state estimate in real-time. We show that our proposed framework outperforms distributed control methods by 40-100% in simulation and physical experiments.
Multi-agent systems can be used in a range of applications to observe and map spatial-temporal phenomena. In this paper, we have taken the first step to develop a multi-agent environmental monitoring system for fully ...
详细信息
ISBN:
(纸本)9798350354416;9798350354409
Multi-agent systems can be used in a range of applications to observe and map spatial-temporal phenomena. In this paper, we have taken the first step to develop a multi-agent environmental monitoring system for fully autonomous exploration and mapping of an unstructured indoor GPS-denied environment. By employing the Gmapping SLAM, the agents cooperatively map a previously unknown environment and explore its entirety. At the same time, the agents are able to successfully map and characterize the temperature distribution inside the room passively using Gaussian process Regression. The system has been experimentally tested in an indoor cluttered environment, by operation of two Unmanned Ground Vehicles built fully in house. The experimental results show that the proposed system could successfully navigate and explore in the cluttered environment and estimate the spatial distribution of the environment by locating two independent heat sources. It was found that while a passive field prediction approach can approximate the temperature distribution in the room and identify the heat sources, the accuracy of the prediction greatly depends on the proximity of the trajectories that the robots traverse close to the sources.
Korea has a high proportion of high-value-added LNG ships in its shipbuilding industry. In the past, many parts of building LNG ships were done manually, but recently, due to the labor shortage, research and developme...
详细信息
ISBN:
(纸本)9798331517939;9788993215380
Korea has a high proportion of high-value-added LNG ships in its shipbuilding industry. In the past, many parts of building LNG ships were done manually, but recently, due to the labor shortage, research and development has been conducted to automate many parts. This paper describes how to automate the welding of membranes that make up the interior of an LNG cargo hold by using a mobile manipulator. The interior of a large LNG cargo hold consists of a number of basic elements: membranes. The member lanes must be joined together by laser welding. In order to automate this process using a mobile manipulator, software was developed to automate the procedure. The welding of the membranes is closely related to the quality of the weld, and the complexity of the paths means that rather than automatically generating the robot's paths, experts still manually create unit tasks by teaching the robot. The developed software uses these unit tasks to generate a working procedure for welding the entire cargo hold.
In the paper a problem related to the field of edge computing is considered. We discuss a situation where an autonomous energy charging station is used to perform the process of charging a fleet of electric vehicles. ...
详细信息
ISBN:
(纸本)9798350311075
In the paper a problem related to the field of edge computing is considered. We discuss a situation where an autonomous energy charging station is used to perform the process of charging a fleet of electric vehicles. The station consists of two modules: a computing and an executive one. The computing module is equipped with a variable speed processor, and is responsible to find a schedule of the charging jobs. We discuss the model of the system and the resulting scheduling problem, as well and we propose a few basic approaches for solving it. Some conclusions and directions for future research are given.
Efficient aero engine fault diagnosis technology can advance the warning of fault information, improve the safety of aircraft flight, and avoid unnecessary maintenance detection, reduce aircraft maintenance cost. Ther...
详细信息
ISBN:
(纸本)9798350373172;9798350373189
Efficient aero engine fault diagnosis technology can advance the warning of fault information, improve the safety of aircraft flight, and avoid unnecessary maintenance detection, reduce aircraft maintenance cost. Therefore, this paper studies the fault diagnosis algorithm based on gray AHP for aero engine gas path fault. First, an engine fault diagnosis method based on gas path performance parameters is introduced. On this basis, the Analytic Hierarchy process (AHP) is introduced to determine the sensitivity of each aerodynamic parameter to different faults, to improve the degree of differentiation between cases, and to use Gray Correlation Analysis (GRA) as an objective weighting method to analyze the relationship between parameters. Finally, the sample of PW4000 engine fault data is used to verify the results. The results show that the proposed method is reasonable and effective, and the efficiency of fault diagnosis is improved.
This discussion explores the evolution of serverless computing, highlighting its origins, rise in importance, and the challenges it presents. Serverless computing represents a significant shift from traditional, hardw...
详细信息
This discussion explores the evolution of serverless computing, highlighting its origins, rise in importance, and the challenges it presents. Serverless computing represents a significant shift from traditional, hardware-dependent environments to cloud-based, code-centric architectures. The concept of serverless emerged with the introduction of platforms like Google App Engine and AWS Lambda, freeing developers from server management concerns and enabling them to focus solely on code development. The integration of serverless computing with DevOps practices is examined, emphasizing the role of Infrastructure as Code (IaC), version control, continuous integration (CI), and continuous deployment (CD). These practices are essential for streamlining the development and deployment of serverless applications, enhancing consistency, and promoting collaboration between development and operations teams. Furthermore, the discussion addresses the specific challenge of cold starts in serverless computing and how DevOps practices can help mitigate their impact. Strategies such as proactive monitoring, scaling policies, scheduled warm-up, provisioned concurrency, performance testing, automation, and continuous optimization are presented as solutions to minimize cold start delays. Lastly, the importance of Testing automation within the CI/CD pipeline is highlighted. Through rapid feedback, comprehensive testing, consistency, regression testing, and scalability, Testing automation ensures the quality and reliability of software in a fast-paced development environment, aligning with the principles of DevOps.
The proceedings contain 95 papers. The topics discussed include: model reference based robust tuning rule for 2-DoF fractional PI controllers with robustness constraint for SOPDT process model;improved perceptual repr...
ISBN:
(纸本)9798350364293
The proceedings contain 95 papers. The topics discussed include: model reference based robust tuning rule for 2-DoF fractional PI controllers with robustness constraint for SOPDT process model;improved perceptual representation of isosurfaces from volume data using curvature-based features;a pose-free 2D-3D hybrid approach for visual servoing control systems;control and automation education: academia and industry together;on the effects of the earth’s infrared radiation pressure on orbiting satellites;algorithmic approach for audio segmentation;problem solving e-learning platform using algorithm visualization and supervised through artificial intelligence;low-cost air pollution monitoring systems;set-based actuator fault diagnosis in a two-tank plant;control structures with anticipative action for thermoenergetic processes;and exploring the use of MPLS technologies in banking transactions.
Aiming at the problems of difficult feature extraction and high real-time requirement for weak targets in space manipulation scenes, this paper designed a parallel stream HOG feature computing architecture based on mu...
详细信息
ISBN:
(纸本)9798350322514
Aiming at the problems of difficult feature extraction and high real-time requirement for weak targets in space manipulation scenes, this paper designed a parallel stream HOG feature computing architecture based on multi-cache interaction, and adopted cell stream splitting and multi-angle interval parallel computing methods to improve the degree of parallelism. The whole architecture adopts 16-bit fixed-point base calculation, transcendental function combined with polynomial expansion and table lookup method to improve the calculation accuracy. 16 detection windows at the same time, the use of parallel computing, effectively improve the response to more than 1024.1024 pixels high-definition camera real-time computing applications. After testing the data with low signal-to-noise ratio, the error from theoretical calculation is less than 3%. The experimental verification shows that compared with previous designs, the proposed method occupies the same number of resources except Block RAM, and the computational efficiency is increased by at least 57.2%.
暂无评论