Steel, being a widely utilized material in industrial production, holds a pivotal role in ensuring product safety and longevity. Hence, the exploration and implementation of steel surface defect detection technology c...
详细信息
This paper presents a new approach for real-time anomaly detection and visualization of dynamic network data using Wireshark, known as the most widely used network analysis tool. As the complexity and volume of networ...
详细信息
Underwater target detection is an important method for detecting marine organisms. However, due to the image occlusion of underwater targets, blurred water quality, poor lighting conditions, small targets, and complex...
详细信息
Rapid urbanization and industrialization have led to the increased generation of electronic waste (E-waste) throughout the world, and the proper management of this hazardous E-waste is of utmost challenge nowadays. Ba...
详细信息
Dear Editor,H∞This letter develops a new framework for the robust stability and performance conditions as well as the relevant controller synthesis with respect to uncertain robot *** often exist model uncertainties ...
详细信息
Dear Editor,H∞This letter develops a new framework for the robust stability and performance conditions as well as the relevant controller synthesis with respect to uncertain robot *** often exist model uncertainties between the nominal model and the real robot manipulator and disturbances. Hence, dealing with their effects plays a crucial role in leading to high tracking performances, as discussed in [1]–[5].
Deep reinforcement learning(DRL) has demonstrated significant potential in industrial manufacturing domains such as workshop scheduling and energy system ***, due to the model's inherent uncertainty, rigorous vali...
详细信息
Deep reinforcement learning(DRL) has demonstrated significant potential in industrial manufacturing domains such as workshop scheduling and energy system ***, due to the model's inherent uncertainty, rigorous validation is requisite for its application in real-world tasks. Specific tests may reveal inadequacies in the performance of pre-trained DRL models, while the “black-box” nature of DRL poses a challenge for testing model behavior. We propose a novel performance improvement framework based on probabilistic automata,which aims to proactively identify and correct critical vulnerabilities of DRL systems, so that the performance of DRL models in real tasks can be improved with minimal model ***, a probabilistic automaton is constructed from the historical trajectory of the DRL system by abstracting the state to generate probabilistic decision-making units(PDMUs), and a reverse breadth-first search(BFS) method is used to identify the key PDMU-action pairs that have the greatest impact on adverse outcomes. This process relies only on the state-action sequence and final result of each trajectory. Then, under the key PDMU, we search for the new action that has the greatest impact on favorable results. Finally, the key PDMU, undesirable action and new action are encapsulated as monitors to guide the DRL system to obtain more favorable results through real-time monitoring and correction mechanisms. Evaluations in two standard reinforcement learning environments and three actual job scheduling scenarios confirmed the effectiveness of the method, providing certain guarantees for the deployment of DRL models in real-world applications.
Photovoltaic(PV)arrays are usually installed in open areas;hence,they are vulnerable to lightning strikes that can result in cell degradation,complete damage,service disruption,and increased maintenance *** a result,i...
详细信息
Photovoltaic(PV)arrays are usually installed in open areas;hence,they are vulnerable to lightning strikes that can result in cell degradation,complete damage,service disruption,and increased maintenance *** a result,it is imperative to develop an effective and efficient lightning protection system by evaluating the transient behaviour of PV arrays during lightning *** aim is to evaluate the transient analysis of large-scale PV systems when subjected to lightning strikes using the finite difference time domain(FDTD)*** overvoltages are calculated at various points within the mounting *** optimise the FDTD method's execution time and make it more suitable for less powerful hardware,a variable cell size approach is ***,larger cell dimensions are used in the earthing system and smaller cell dimensions are used in the mounting *** FDTD method is utilised to calculate the temporal variation of transient overvoltages for large-scale PV systems under different scenarios,including variations in the striking point,soil resistivity,and the presence of a metal *** results indicate that the highest transient overvoltages occur at the striking point,and these values increase with the presence of a PV metal frame as well as with higher soil ***,a comparison is performed between the overvoltage results obtained from the FDTD approach and the partial element equivalent circuit(PEEC)method at the four corner points of the mounting systems to demonstrate the superior accuracy of the FDTD ***,a laboratory experiment is conducted on a small-scale PV system to validate the simulation *** calculated overvoltages obtained from the FDTD and PEEC methods are compared with the measured values,yielding a mean absolute error of 5%and 11%for the FDTD and PEEC methods,respectively,thereby confirming the accuracy of the FDTD simulation model.
This paper introduces 'SmogMaster: Your Smart Driving Companion, ' the Visual Editorial Quality Assurance, an intelligent Smart Driving Assistant System (SDAS) in areas with high foggy weather affected by heav...
详细信息
Several cutting-edge modern technologies, including hologram technology, have emerged due to the tremendous advancements of our era. The science of holography is used to make holograms, which are 3D images with lifeli...
详细信息
The depletion in non-renewable energy sources and a fast-growing population in Bangladesh are exacerbating the already existing energy scarcity,highlighting the need for an efficient and robust renewable-energy supply...
详细信息
The depletion in non-renewable energy sources and a fast-growing population in Bangladesh are exacerbating the already existing energy scarcity,highlighting the need for an efficient and robust renewable-energy supply *** primary goal of this study is to evaluate the most optimized renewable-energy supply chain based on natural resource availability and government policies of *** the present study,four renewable energy resources,including solar,biomass,wind and hydropower,are studied and nine subcriteria are defined under four primary criteria for each supply *** for Order Preference by Similarity to Ideal Solution(TOPSIS)and VIseKriterijumska Optimizacija I Kompromisno Resenje(VIKOR)are multicriteria decision-making approaches used in this study to compare and choose the best renewable-energy supply *** relative significance of four supply-chain criteria for primary renewable energy in this study,namely energy procurement,production,operations and maintenance costs,and social and environmental impact,is gathered via a *** results of this research,supported by a comprehensive sensitivity analysis,indicate that hydropower is the best renewable-energy supply chain,followed by wind as a compromise solution,biomass and *** study also demonstrates that no energy source can satisfy all supply-chain criteria alone;each resource is better for a specific criterion-solar is better for procurement,hydropower is significant for production and wind is remarkable for operations and social ***,to maximize output,renewable energy sources must be *** Bangladesh’s perspective,for the first time,by using TOPSIS and VIKOR together,this study offers significant insights to establish an efficient and sustainable renewable-energy supply chain for practitioners,academics and policymakers.
暂无评论