Predicting the Remaining Useful Life of Supercapacitors under Different Operating Conditions

Energies, Год журнала: 2024, Номер 17(11), С. 2585 - 2585

Опубликована: Май 27, 2024

With the rapid development of new energy industry, supercapacitors have become key devices in field storage. To forecast remaining useful life (RUL) supercapacitors, we introduce a technology that integrates variational mode decomposition (VMD) with bidirectional long short-term memory (BiLSTM) neural network. Firstly, aging experiments under various temperatures and voltages were carried out to obtain data. Then, VMD was implemented decompose data, which helped eliminate disturbances, including capacity recovery test errors. hyperparameters BiLSTM adjusted, employing sparrow search algorithm (SSA) improve consistency between input data network structure. After obtaining optimal BiLSTM, decomposed into for prediction. The experimental results showed VMD-SSA-BiLSTM model proposed this paper has high prediction accuracy robustness different voltages, an average RMSE 0.112519, decrease 44.3% compared minimum 0.031426.

Язык: Английский

---

A Learning-Driven Multi-Objective cooperative artificial bee colony algorithm for distributed flexible job shop scheduling problems with preventive maintenance and transportation operations

Computers & Industrial Engineering, Год журнала: 2024, Номер 196, С. 110484 - 110484

Опубликована: Авг. 18, 2024

Язык: Английский

---

A cooperative evolutionary algorithm with simulated annealing for integrated scheduling of distributed flexible job shops and distribution

Swarm and Evolutionary Computation, Год журнала: 2024, Номер 85, С. 101467 - 101467

Опубликована: Янв. 1, 2024

Язык: Английский

---

Scheduling stochastic distributed flexible job shops using an multi-objective evolutionary algorithm with simulation evaluation

International Journal of Production Research, Год журнала: 2024, Номер unknown, С. 1 - 18

Опубликована: Июнь 4, 2024

The trend of reverse globalisation prompts manufacturing enterprises to adopt distributed structures with multiple factories for improving production efficiency, meeting customer requirements, and responding disturbance events. This study focuses on scheduling a flexible job shop random processing time achieve minimal makespan total tardiness. First, stochastic programming model is established formulate the concerned problems. Second, in accordance natures two objectives randomness, an evolutionary algorithm incorporating evaluation method designed. In it, population-based external archive-based search processes are developed searching candidate solutions, integrates simulation discrete event calculate objective values acquired solutions. Finally, mathematical optimisation solver, CPLEX, employed validate approach. A set cases solved verify performance proposed method. comparisons discussions show superiority handling problems under study.

Язык: Английский

---

Review on ensemble meta-heuristics and reinforcement learning for manufacturing scheduling problems

Computers & Electrical Engineering, Год журнала: 2024, Номер 120, С. 109780 - 109780

Опубликована: Окт. 18, 2024

Язык: Английский

---

A knowledge-based multi-objective evolutionary algorithm for solving home health care routing and scheduling problems with multiple centers

Applied Soft Computing, Год журнала: 2023, Номер 144, С. 110491 - 110491

Опубликована: Июнь 8, 2023

Язык: Английский

---

Two-Stage Adaptive Memetic Algorithm with Surprisingly Popular Mechanism for Energy-Aware Distributed Hybrid Flow Shop Scheduling Problem with Sequence-Dependent Setup Time

Complex System Modeling and Simulation, Год журнала: 2024, Номер 4(1), С. 82 - 108

Опубликована: Март 1, 2024

This paper considers the impact of setup time in production scheduling and proposes energy-aware distributed hybrid flow shop problem with sequence-dependent (EADHFSP-ST) that simultaneously optimizes makespan energy consumption. We develop a mixed integer linear programming model to describe this present two-stage adaptive memetic algorithm (TAMA) surprisingly popular mechanism. First, initialization strategy is designed based on two optimization objectives ensure convergence diversity solutions. Second, multiple population co-evolutionary approaches are proposed for global search escape from traditional cross-randomization balance exploration exploitation. Third, considering (MA) framework less efficient due randomness selection local operators, TAMA searches. The first stage accumulates more experience updating (SPA) guide second operator ensures convergence. gets rid designs an elite archive diversity. Fourth, five problem-specific operators designed, non-critical path deceleration right-shift strategies efficiency. Finally, evaluate performance algorithm, experiments performed benchmark 45 instances. experimental results show can solve effectively.

Язык: Английский

---

Integrated Scheduling of Multi-Constraint Open Shop and Vehicle Routing: Mathematical Model and Learning-Driven Brain Storm Optimization Algorithm

Applied Soft Computing, Год журнала: 2024, Номер 163, С. 111943 - 111943

Опубликована: Июль 6, 2024

Язык: Английский

---

Aggregated planning to solve multi-product multi-period disassembly line balancing problem by considering multi-manned stations: A generic optimization model and solution algorithms

Computers & Industrial Engineering, Год журнала: 2024, Номер 196, С. 110464 - 110464

Опубликована: Авг. 14, 2024

Язык: Английский

---

A Q-Learning Based Hybrid Meta-Heuristic for Integrated Scheduling of Disassembly and Reprocessing Processes Considering Product Structures and Stochasticity

Complex System Modeling and Simulation, Год журнала: 2024, Номер 4(2), С. 184 - 209

Опубликована: Июнь 1, 2024

Remanufacturing is regarded as a sustainable manufacturing paradigm of energy conservation and environment protection. To improve the efficiency remanufacturing process, this work investigates an integrated scheduling problem for disassembly reprocessing in where product structures uncertainty are taken into account. First, stochastic programming model developed to minimize maximum completion time (makespan). Second, Q-learning based hybrid meta-heuristic (Q-HMH) specially devised. In each iteration, method employed adaptively choose premium algorithm from four candidate ones, including genetic (GA), artificial bee colony (ABC), shuffled frog-leaping (SFLA), simulated annealing (SA) methods. At last, simulation experiments carried out by using sixteen instances with different scales, three state-of-the-art algorithms literature exact solver CPLEX chosen comparisons. By analyzing results average relative percentage deviation (RPD) metric, we find that Q-HMH outperforms its rivals 9.79%-26.76%. The comparisons verify excellent competitiveness solving concerned problems.

Язык: Английский

---