This paper presents a hybrid ant colony optimization algorithm for solving large-scale scheduling problems in semiconductor production, which can be represented as a Flexible Job Shop Scheduling Problem (FJSSP) with t...
详细信息
Deep learning models have been successfully developed to solve complexproblems with the main focus on high precision. Yet, accurately assessing uncertainty and prediction is essential for making informed decisions, e...
详细信息
ISBN:
(纸本)9798350332285
Deep learning models have been successfully developed to solve complexproblems with the main focus on high precision. Yet, accurately assessing uncertainty and prediction is essential for making informed decisions, especially in high-risk tasks. In this paper, we present a step towards learning reliable uncertainty quantification and high precision performance via alpha-plane based General Type-2 Fuzzy Logic systems (GT2-FLSs). To balance between accuracy and uncertainty quantification, we propose a novel composite loss function consisting of an accuracyfocused and uncertainty-focused loss term that exploits the parameters of the Secondary Membership Functions (SMFs). For the uncertainty-focused term, we use only the type-reduced set of alpha(0) = 0 plane of the GT2-FLS, i.e. the size of the SMFs, which does not contribute to the output calculation directly. In the accuracyfocused part, we present two options for the error terms. One uses the aggregated output while the other uses only the output alpha(k) = 1 plane of the GT2-FLS. In both terms, we make the SMF shape parameters responsible for learning pointwise prediction. We present statistical comparisons and demonstrate that the learned GT2-FLSs generate reliable prediction intervals while also resulting in high-precision performance. The results show the potential of the proposed approach for GT2-FLS as a promising solution for making reliable predictions in real-world applications.
complex practical problems arising in production, economic, and social systems are characterized by weak formalization, complex structure, network nature of conditions and goals, significant opacity, subjectivity, and...
详细信息
ISBN:
(数字)9798331532178
ISBN:
(纸本)9798331532185
complex practical problems arising in production, economic, and social systems are characterized by weak formalization, complex structure, network nature of conditions and goals, significant opacity, subjectivity, and dynamism. To solve such a problem, the latter must first be presented as a system of interconnected tasks. The building of such decompositions (structures) is also not a trivial task. The paper considers the concept of decomposition of a problem as a system, the concept of structure, types of structures as well as general algorithms and approaches to the decomposition.
The numerous factors affecting combustion complicate the combustion process of the power generation boiler. In supervising the combustion process of the boiler, special attention needs to be paid to the characteristic...
详细信息
Aiming at the problems of complex data distribution logic and low execution efficiency in intelligent cluster simulation, an intelligent cluster simulation system based on DDS is designed. Firstly, according to the ch...
详细信息
Aiming at the problems of complex data distribution logic and low execution efficiency in intelligent cluster simulation, an intelligent cluster simulation system based on DDS is designed. Firstly, according to the characteristics of cluster combat system, DDS is used to build the architecture of intelligent cluster simulation environment;Secondly, the specific implementation of the simulation system is described in detail from the system operation logic flow and working mode;Finally, through the hardware in the loop cluster formation simulation test, the data interaction ability, real-time and expansibility of the simulation system are verified. The test results show that this simulation system has data-efficient, high-speed interactive capabilities, and can realize cluster distributed real-time simulation.
Reinforcement learning has been intensively applied to tackle complex quantum controlproblems owing to its adaptability in dynamic environments. However, commonly used reinforcement learning algorithms are restricted...
Currently, the research and development of novel antennas that offer reduced mass and size compared to conventional antennas while maintaining high performance is a significant objective. Particularly in wideband appl...
详细信息
The paper deals with the problems of control system synthesis for nonlinear underdetermined plant, reduced to a lower triangular form and parameterized with respect to the vector of unknown parameters. Nonlinear adapt...
详细信息
Conclusions about the technical condition of automation equipment are made based on the results of measuring and monitoring a number of parameters that determine the performance of automation equipment and the system ...
详细信息
ISBN:
(纸本)9798350309126
Conclusions about the technical condition of automation equipment are made based on the results of measuring and monitoring a number of parameters that determine the performance of automation equipment and the system as a whole. Monitoring includes performance monitoring, diagnostics and other types of monitoring. Performance monitoring is carried out regularly when preparing automation equipment and entire systems for use (start-up), during maintenance and repair, as well as during storage. The main task is to determine the technical condition of the entire automation system. During the verification process, settings and adjustments are made. Diagnostic testing of automation or automation systems is carried out in order to identify malfunctions and determine their causes. One of the most important tasks of diagnostic control is the selection of a fault finding strategy (program) in such a way as to minimize the time required to detect faulty elements. Troubleshooting programs vary depending on the method used. The most common are item sequential testing, sequential group testing, and combination testing. Hydroponics is a method of growing plants in a medium containing inorganic nutrients or a nutrient solution, without the use of soil. Hydroponic controller control system design enables automation through remote monitoring and control using various microcontrollers, sensors and networking technologies using the Internet to transmit and receive information from objects and devices. Such systems receive input data from sensors and provide control actions to maintain various parameters within specified ranges. These systems are very economical, and most importantly, they are fully automated and do not require human intervention after placing sprouted plants in the system. Automatic control makes plant selection easier. There is also the aspect of creating a system that can be used by the average consumer. This means that the project will be relatively small and easy t
With the wide application of microservice architecture in industrial controlsystems, more and more security problems arise, such as unauthorized access and data leakage. For the generation of these problems, industri...
详细信息
暂无评论