The cement clinker firing system is complex, with interdependent indicators, making it challenging to optimize decision-making. Furthermore, the traditional static single-objective or multi-objectiveoptimization meth...
详细信息
The cement clinker firing system is complex, with interdependent indicators, making it challenging to optimize decision-making. Furthermore, the traditional static single-objective or multi-objectiveoptimization methods are inadequate in adapting to the dynamic changes of complex working conditions. To address these issues, this paper proposes a dynamic multi-objective optimization method for the production index of the cement clinker firing process. The way first establishes a data-driven dynamic multi-objective optimization model, the content of free calcium oxide (f-CaO) in clinker and the coal consumption of the sintering system as optimizationobjectives, numerous operational indicators as decision variables, considers dynamic factors and constraints during manufacturing. Then a dynamicmulti-objective evolutionary algorithm based on a collaborative prediction strategy (CPS-DMOEA) is designed to solve the model. Experimental results for some benchmark test problems show a significant improvement in dynamicoptimization performance with CPS-DMOEA. Furthermore, experiments using actual cement production data show that the proposed method outperforms traditional static multiobjectiveoptimization methods.
In recent years, many dynamic multi-objective optimization algorithms (DMOAs) have been proposed to address dynamic multi-objective optimization problems (DMOPs). Most existing DMOAs treat all decision variables unifo...
详细信息
In recent years, many dynamic multi-objective optimization algorithms (DMOAs) have been proposed to address dynamic multi-objective optimization problems (DMOPs). Most existing DMOAs treat all decision variables uniformly and respond to them in an identical manner. This paper proposes a dynamic multi-objective optimization algorithm based on the classification response of decision variables (CRDV-DMO). Firstly, CRDV-DMO categorizes the decision variables into convergence variables and diversity variables. Different decision variables adopt distinct response strategies. The response strategy of diversity variable (RSDV) uses Latin hypercube sampling to generate the diversity variables of the new environment. For each dimensional convergence variable, the response strategy of convergence variable (RSCV) first evaluates whether the basic center prediction strategy (CPS) yields positive feedback or negative feedback, further determining the predictability of that dimensional convergence variable. RSCV then decides to either use the basic CPS to generate the convergence variable for that dimension or to retain that dimensional convergence variable from the current environment, based on the predictability of that dimensional convergence variable. The proposed algorithm is extensively studied through comparison with several advanced DMOAs, demonstrating its effectiveness in dealing with the benchmark DMOPs and the parameter-tuning problem of the PID controller on a dynamic system.
With the special porous structure and super-long carbon sequestration characteristic, the biochar has shown to have potential in improving soil fertility, reducing carbon emissions and increasing soil carbon sequestra...
详细信息
With the special porous structure and super-long carbon sequestration characteristic, the biochar has shown to have potential in improving soil fertility, reducing carbon emissions and increasing soil carbon sequestration. However, the biochar technology has not been applied on a large scale, due to the complex structure, long transportation distance of raw materials, and high cost. To overcome these issues, the brazier-type gasification and carbonization furnace is designed to carry out dry distillation, anaerobic carbonization and have a high carbonization rate under high-temperature conditions. To improve the operation and maintenance efficiency, we formulate the operation of the brazier-type gasification and carbonization furnace as a dynamic multi-objective optimization problem (DMOP). Firstly, we analyze the dynamic factors in the work process of the brazier-type gasification and carbonization furnace, such as the equipment capacity, the operating conditions, and the biomass treated by the furnace. Afterward, we select the biochar yield and carbon monoxide emission as the dynamicobjectives and model the DMOP. Finally, we apply three dynamicmultiobjective evolutionary algorithms to solve the optimization problem so as to verify the effectiveness of the dynamicoptimization approach in the gasification and carbonization furnace.
In contrast to traditional recommender systems which usually pay attention to users' general and long-term preferences, sequential recommendation (SR) can model users' dynamic intents based on their behaviour ...
详细信息
In contrast to traditional recommender systems which usually pay attention to users' general and long-term preferences, sequential recommendation (SR) can model users' dynamic intents based on their behaviour sequences and suggest the next item(s) to them. However, most of existing sequential models learn the ranking score of an item only based on its relevance property, and the personalized user demands in terms of different learning objectives, such as diversity, tail novelty or recency, which have been played essential roles in multi-objective recommendation (MOR), are often neglected in SR. In this paper, we first discuss the importance of considering multiple different objectives within a learning model for recommender system. Next, to capture users' objective-level preferences by utilizing interactive information in the sequential context, we propose a novel dynamicmulti-objective Recommendation (DMORec) framework with interactive evolution for SR. In particular, DMORec formulates a dynamic multi-objective optimization task to simultaneously optimize more than two varying objectives in an interactive recommendation process. Moreover, to resolve this optimization task in SR, we develop an evolutionary algorithm with supervised learning approach to obtain the Pareto-optimal solutions of the formulated problem. Comprehensive experiments on four real-world datasets demonstrate the effectiveness of the proposed DMORec for dynamicmulti-objective recommendation in sequential recommender systems.
In this paper, the conventional lion group algorithm is improved and used to solve dynamic multi-objective optimization Problems (DMOPs). An environment change detection strategy is adopted to determine whether the en...
详细信息
ISBN:
(纸本)9798350385113;9798350385106
In this paper, the conventional lion group algorithm is improved and used to solve dynamic multi-objective optimization Problems (DMOPs). An environment change detection strategy is adopted to determine whether the environment changes by calculating the average difference in fitness values of the hunting lions. Furthermore, the algorithm constructs a time series by recording the positions of the lion king at times t 1 and t to predict the lion king's position at time t + 1 to adapt to the changing environment. The performance of the proposed algorithm is studied by comparing it with four state-ofthe-art dynamicoptimization algorithms. The experimental results show that the proposed algorithm outperforms other peer algorithms in most benchmark functions.
The catalytic esterification of -butyl propionate in a semi-batch reactor is examined using dynamic, nonlinear programming-based optimization. To solve the conflicting bi-objective of minimizing the final time t(f) an...
详细信息
The catalytic esterification of -butyl propionate in a semi-batch reactor is examined using dynamic, nonlinear programming-based optimization. To solve the conflicting bi-objective of minimizing the final time t(f) and maximizing the conversion X-c, the epsilon-constraint, weighted sum, and NSGA-II (non-dominated sorting genetic algorithm II) techniques were implemented. By computing performance measurements like hypervolume, pure diversity, and spacing, these multi-objectiveoptimization techniques were compared to the characteristics of the Pareto solution. Each Pareto solution point comprises a unique combination of optimal feed flow rate and temperature trajectories. These solutions provide various options for evaluating trade-offs while establishing the best operating strategy.
The design of optimal energy systems is vital to achieving global environmental and economic targets. In the design of solar-geothermal multi-generation systems, most pre-vious investigations have relied on the static...
详细信息
The design of optimal energy systems is vital to achieving global environmental and economic targets. In the design of solar-geothermal multi-generation systems, most pre-vious investigations have relied on the static multi-objectiveoptimization approach (SMOA), which may leave considerable room for improvement under certain conditions. In this numerical study, the optimal condition at which to operate a solar-geothermal multi -generation system -which can simultaneously produce hydrogen, fresh water, electricity, and heat, along with storing energy -is determined via a dynamicmulti-objective opti-mization approach (DMOA). optimization is performed using a combination of NSGA-II and TOPSIS, and the results are benchmarked against those of SMOA. The decision variables include the solar area, geothermal water extraction mass flow, and hydrogen storage pressure. The objective functions include the production of electricity, heat, hydrogen, and fresh water, along with the exergy and energy efficiencies and the payback period. It is found that when compared with SMOA, DMOA can significantly improve all the objective functions. The annual production of electricity, heat, hydrogen, and fresh water increases by 14.4, 16.1, 13.5, and 14.3%, respectively, while the average annual exergy and energy efficiencies increase by 5.2 and 3.0%, respectively. The use of DMOA also reduces the payback period from 5.56 to 4.43 years, with a 4.4% reduction in hydrogen storage pressure. This shows that compared with a static approach such as SMOA, DMOA can improve the exergy and energy efficiencies, economic viability, and safety of a solar-geothermal multi -generation system. (c) 2022 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.
dynamic integrated timetabling and vehicle scheduling (D-ITVS) is essential for mitigating the negative impacts of service disruptions arising from the stochastic nature of traffic flow and passenger demand fluctuatio...
详细信息
dynamic integrated timetabling and vehicle scheduling (D-ITVS) is essential for mitigating the negative impacts of service disruptions arising from the stochastic nature of traffic flow and passenger demand fluctuations in public transit. Existing optimization approaches for the D-ITVS problem typically conduct optimization independently at each rescheduling stage. In contrast, this paper proposes a novel dynamic multi-objective optimization approach that considers evolving patterns across different rescheduling stages from a holistic perspective. This approach formulates the optimization problem for all rescheduling stages during a day's operation as a dynamic multi-objective optimization problem, modeled using a dynamic time-space network flow framework. To leverage these evolving patterns for achieving optimal solutions throughout, a dynamic multi-objective optimization approach for the D-ITVS problem (DMO-TVS) is introduced. The DMO-TVS approach learns the evolving patterns, and incorporates a dynamic solution representation alongside three key mechanisms: (1) change detection mechanism, (2) change response mechanism, and (3) multi-objectiveoptimization mechanism. These mechanisms work in tandem to dynamically adjust the initial solution set at each rescheduling stage based on predicted optimal solutions derived from learned evolving patterns, balance conflicting objectives in the DITVS problem, and select optimal solutions with diversity throughout the optimization process. Experimental results demonstrate that the dynamic multi-objective optimization approach is capable of generating timetables and vehicle schedules with reduced costs, enhanced robustness, and improved convergence and diversity across all rescheduling stages. By balancing operational costs and passenger service quality, these improvements benefit transit operators, and during daily operations, passengers enjoy reduced travel costs and enhanced service reliability.
Terahertz metamaterial sensors (TMS) playa key role in the highly sensitive detection of trace substances, especially in label-free, real-time, and in-situ measurements for disease, microbial, and pesticide residue di...
详细信息
Terahertz metamaterial sensors (TMS) playa key role in the highly sensitive detection of trace substances, especially in label-free, real-time, and in-situ measurements for disease, microbial, and pesticide residue diagnostics. To obtain excellent performance, the sensitivity of TMS is closely related to the resonance characteristics of the metamaterial, which depends on the optimal structural units. However, a desirable sensor often relies on experience and theory, and the design is gradually optimized through extensive manual calculations and simulations. Under the premise of ensuring the performance of terahertz devices, the use of algorithm to quickly generate customized device designs that meet specific needs has attracted widespread attention. Herein, we propose a strategy for designing multi-resonance TMS with high Q-factors and resonance depth based on dynamic multi-objective optimization (DMO). By introducing DMO, we designed high-Q TMS with 2-5 resonances simultaneously, saving about 122 min of design time compared with the traditional multi- objective strategy. To better demonstrate the performance of the sensor, we have characterized the 3-resonance TMS. The Q-factors of the optimized TMS can reach up to 301, 465, and 201, respectively. During the refractive index sensing process, the sensitivities of the three resonances (369, 376, and 387 GHz/RIU) have been achieved in the range of 0.9-1.7 THz. With the covered 2,4-D and thiabendazole analytes, the transmission spectra of the TMS demonstrate different "fingerprint peak"related characteristics. The proposed method can be used for dynamic multi-objective optimization challenges in various metamaterial device scenarios and provides a promising solution for designing multiple high-Q TMS.
The primary challenge in addressing dynamic multi-objective optimization problems (DMOPs) is the rapid tracking of optimal solutions. Although methods based on transfer learning have shown remarkable performance in ta...
详细信息
The primary challenge in addressing dynamic multi-objective optimization problems (DMOPs) is the rapid tracking of optimal solutions. Although methods based on transfer learning have shown remarkable performance in tackling DMOPs, most existing methods overlook the potential relationships between individuals within the population and those from historical environments. Consequently, they fail to adequately exploit historical information. To this end, this study proposes a dynamic multi-objective optimization algorithm based on probability-driven prediction and correlation-guided individual transfer (PDP&CGIT), which consists of two strategies: probability-driven prediction (PDP) and correlation-guided individual transfer (CGIT). Specifically, the PDP strategy analyzes the distribution of population characteristics and constructs a discriminative predictor based on a probability-annotation matrix to classify high-quality solutions from numerous randomly generated solutions within the decision space. Moreover, from the perspective of individual evolution, the CGIT strategy analyzes the correlation between current elite individuals and those from the previous moment. It learns the dynamic change pattern of the individuals and transfers this pattern to new environments. This is to maintain the diversity and distribution of the population. By integrating the advantages of these two strategies, PDP&CGIT can efficiently respond to environmental changes. Extensive experiments were performed to compare the proposed PDP&CGIT with five state-of-the-art algorithms across the FDA, F, and DF test suites. The results demonstrated the superiority of PDP&CGIT.
暂无评论