The heating process of the blast furnace is a complex and huge controlled object, which has the characteristics of nonlinear, multivariable, distributed parameters, fast and slow processes intertwined. It is impossibl...
详细信息
We introduce a three-stage framework for designing an optimal controller. First, we apply offline black-box optimization algorithms to find optimal controller parameters based on a heuristically chosen setpoint profil...
详细信息
Cybersecurity plays an increasingly vital role in contemporary times, particularly as large companies face escalating threats and substantial losses, with ransomware attacks standing out as one of the more sophisticat...
详细信息
Federated learning is a collaborative machine learning approach that allows multiple parties to train a model without exchanging sensitive data. In manufacturing, where different parties may have proprietary or sensit...
详细信息
ISBN:
(纸本)9783031381645;9783031381652
Federated learning is a collaborative machine learning approach that allows multiple parties to train a model without exchanging sensitive data. In manufacturing, where different parties may have proprietary or sensitive data that cannot be shared, this is especially useful. However, traditional federated learning approaches (as proposed by McMahan et al.) do not consider the differences in data and computing resources across different parties, leading to sub-optimal model performance. Personalized federated learning addresses this issue by allowing each party to contribute to the model training according to its specific data and resources. Furthermore, most common approaches only consider a limited set of data and a short period of time, without considering the system's long-term usefulness. It is important to consider the integration of new clients and the continuous change of data, which could result in the addition of new classes. This paper will explore the potential of federated learning in manufacturing and present a flexible and expandable approach, focusing on mapping newcomer clients based on activation strength of weights.
In Switzerland, about 40 % (90 TWh) of the energy needs are due to buildings and about 70 % of these needs come from heating. Therefore, improving the efficiency of buildings has a high potential for energy savings. T...
详细信息
Internet of Things (IoT) enables connectivity and interoperability between users' devices, systems, services, networks, and especially control systems. Smart video surveillance is an IOT application as it uses the...
详细信息
As Programmable Logic controllers (PLCs) become more integrated into complex industrial systems and networks, their software components face increased security vulnerabilities. Fuzz testing, which uses unexpected inpu...
详细信息
ISBN:
(数字)9798331520960
ISBN:
(纸本)9798331520977
As Programmable Logic controllers (PLCs) become more integrated into complex industrial systems and networks, their software components face increased security vulnerabilities. Fuzz testing, which uses unexpected inputs to find vulnerabilities, has been used to enhance PLC security but is primarily focused on communication protocols, often overlooking control logic. This paper presents a fuzzing framework for PLC control logic programs. The framework is designed to handle control logic’s unique execution process, which may involve translating PLC languages into general-purpose languages. It generates structurally valid test cases and is platform-independent. We implement our prototype around the OpenPLC environment and expand our experiments to a Wago PLC image to evaluate the feasibility of our method on real-world devices. Our approach exhibits strong performance in terms of code coverage, test case pass rate, and crash detection, while ensuring high time efficiency.
With the rapid increase of aging population in China, more and more power-assisted devices need to be used. In this paper, aiming at the walking problem of the elderly or the disabled, a lower limb exoskeleton assiste...
详细信息
The power prediction, state estimation and fault diagnosis methods based on deep learning are introduced. Take the cloud platform of electric power automation as the analysis object to study its architecture. The modi...
详细信息
To automate the material handling duties in industries the Autonomous Industrial Rovers (AIRs) with the emerging techniques like Collaborative robots (COBOTS), indoor localization techniques, and Light Detection and R...
详细信息
ISBN:
(数字)9798331525439
ISBN:
(纸本)9798331525446
To automate the material handling duties in industries the Autonomous Industrial Rovers (AIRs) with the emerging techniques like Collaborative robots (COBOTS), indoor localization techniques, and Light Detection and Ranging (LIDAR) plays a vital role. COBOTS can communicate and collaborate with human workers, adjusting to changes in the environment in real time. The indoor localization technology establishes precise location within a space. LIDAR allows the rovers to map their environments in real time, detecting obstacles and navigating with extreme precision. The robots can detect and avoid impairments because LIDAR can create 3D maps of the surroundings. This ensures smooth operations even in congested regions or when they experience unanticipated changes in their surroundings, clients, and environment. The Master-Slave configurations of these robots enable them to work synchronized and uniform. This AIR provides enhanced efficiency, accuracy and safety by lowering reliance on human operators for repetitive, physically taxing activities.
暂无评论