A systematic review of deep transfer learning for machinery fault diagnosis

Neurocomputing, Год журнала: 2020, Номер 407, С. 121 - 135

Опубликована: Май 12, 2020

Язык: Английский

---

Evolving Deep Echo State Networks for Intelligent Fault Diagnosis

IEEE Transactions on Industrial Informatics, Год журнала: 2019, Номер 16(7), С. 4928 - 4937

Опубликована: Сен. 9, 2019

Echo state network (ESN) is a fast recurrent neural with remarkable generalization performance for intelligent diagnosis of machinery faults. When dealing high-dimensional signals mixed much noise, however, the deep ESN still highly affected by random selection input weights and reservoir weights, resulting in optimal design architecture, which an open issue. For this reason, hybrid evolutionary algorithm featuring competitive swarm optimizer combined local search proposed article. An indirect encoding method designed based on characteristics to make process computationally economical. A layerwise optimization strategy subsequently introduced evolving ESNs. The results two experimental cases show that approach has promising identifying different faults reliably accurately comparing other fault approaches.

Язык: Английский

---

Collaborative multidepot electric vehicle routing problem with time windows and shared charging stations

Expert Systems with Applications, Год журнала: 2023, Номер 219, С. 119654 - 119654

Опубликована: Фев. 4, 2023

Язык: Английский

---

Multi-objective metaheuristics for discrete optimization problems: A review of the state-of-the-art

Applied Soft Computing, Год журнала: 2020, Номер 93, С. 106382 - 106382

Опубликована: Май 7, 2020

Язык: Английский

---

Attitude data-based deep hybrid learning architecture for intelligent fault diagnosis of multi-joint industrial robots

Journal of Manufacturing Systems, Год журнала: 2020, Номер 61, С. 736 - 745

Опубликована: Сен. 8, 2020

Язык: Английский

---

Metaheuristics for solving the vehicle routing problem with the time windows and energy consumption in cold chain logistics

Applied Soft Computing, Год журнала: 2020, Номер 95, С. 106561 - 106561

Опубликована: Июль 18, 2020

Язык: Английский

---

The Vehicle Routing Problem: State-of-the-Art Classification and Review

Applied Sciences, Год журнала: 2021, Номер 11(21), С. 10295 - 10295

Опубликована: Ноя. 2, 2021

Transportation planning has been established as a key topic in the literature and social production practices. An increasing number of researchers are studying vehicle routing problems (VRPs) their variants considering real-life applications scenarios. Furthermore, with rapid growth processing speed memory capacity computers, various algorithms can be used to solve increasingly complex instances VRPs. In this study, we analyzed recent published between 2019 August 2021 using taxonomic framework. We reviewed research according models solutions, divided into three categories customer-related, vehicle-related, depot-related models. classified solution exact, heuristic, meta-heuristic algorithms. The main contribution our study is classification table that available online Appendix A. This should enable future find relevant easily provide readers trends methodologies field VRPs some well-known variants.

Язык: Английский

---

QMOEA: A Q-learning-based multiobjective evolutionary algorithm for solving time-dependent green vehicle routing problems with time windows

Information Sciences, Год журнала: 2022, Номер 608, С. 178 - 201

Опубликована: Июнь 17, 2022

Язык: Английский

---

A systematic literature review for the tourist trip design problem: Extensions, solution techniques and future research lines

Operations Research Perspectives, Год журнала: 2022, Номер 9, С. 100228 - 100228

Опубликована: Янв. 1, 2022

The tourism sector represents an opportunity for economic growth in countries with potential. However, new trends global require efficiency supply chain management. One of the main changes is trend personalized tourism, which includes management itineraries by tourist. tourist trip design problem associated design. This has been modeled field Operations Research different ways, being Orienteering Problem most widely applied specialized literature. objective this paper to carry out a systematic review contributions made problem. A taxonomy proposed analyze variants, objectives, and solution techniques. Also, future research lines are analyzed enrich literature provide solutions real problems.

Язык: Английский

---

Generative Adversarial Networks Selection Approach for Extremely Imbalanced Fault Diagnosis of Reciprocating Machinery

IEEE Access, Год журнала: 2019, Номер 7, С. 70643 - 70653

Опубликована: Янв. 1, 2019

At present, countless approaches to fault diagnosis in reciprocating machines have been proposed, all considering that the available machinery dataset is equal proportions for conditions. However, when application closer reality, problem of data imbalance increasingly evident. In this paper, we propose a method creation diagnoses consider an extreme data. Our approach first processes vibration signals machine using wavelet packet transform-based feature-extraction stage. Then, improved generative models are obtained with dissimilarity-based model selection artificially balance dataset. Finally, Random Forest classifier created address diagnostic task. This methodology provides considerable improvement 99% over other reported literature, showing performance similar balanced set

Язык: Английский

---