Szczegóły publikacji
Opis bibliograficzny
Utilizing artificial intelligence for energy-efficient route planning in hyperloop low-pressure capsule transit: a study in alignment with sustainable development goals / Rafał RUMIN, Jerzy DUDA, Jędrzej BLAUT, Dawid Pękała, Thomas Merolla // Scientific Papers of Silesian University of Technology [Dokument elektroniczny]. — Czasopismo elektroniczne ; ISSN 2720-751X. Organization & Management ; ISSN 2720-751X. — 2024 — no. 204, s. 541–552. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 551–552, Abstr. — W pełnym tekście błędnie podany rok wydania 2023
Autorzy (5)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 156536 |
|---|---|
| Data dodania do BaDAP | 2024-12-17 |
| Tekst źródłowy | URL |
| DOI | 10.29119/1641-3466.2024.204.32 |
| Rok publikacji | 2024 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Creative Commons | |
| Czasopismo/seria | Zeszyty Naukowe Politechniki Śląskiej = Scientific Journal of Silesian University of Technology, Organizacja i Zarządzanie = Organization & Management |
Abstract
Purpose: The purpose of this paper is to explore the integration of reinforcement learning with simulation software to optimize Hyperloop transportation systems, aiming to enhance operational efficiency, reduce departure timetable variability, and improve station operations through dynamic dispatch prioritization. Design/methodology/approach: The research utilizes reinforcement learning combined with discrete-event simulation to model and optimize Hyperloop system operations, focusing on departure schedules, delay reduction, and dispatch prioritization. Findings: The research demonstrates that reinforcement learning significantly enhances Hyperloop system performance by optimizing departure schedules, reducing delays, and improving dispatch prioritization, leading to more efficient and reliable operations. Research limitations/implications: The study's limitations include the reliance on simulated data and hypothetical scenarios, which may not fully capture real-world complexities, and future research should focus on testing the proposed methods in actual Hyperloop environments and addressing potential scalability issues. Practical implications: The research identifies enhanced diagnostic methods for Hyperloop systems that could lead to more efficient and reliable operations, potentially reducing maintenance costs and downtime. The adoption of these methods can improve the safety and performance of Hyperloop services, thereby boosting commercial viability and economic benefits for businesses involved in the development and operation of this high-speed transportation technology. Social implications: This research on Hyperloop diagnostics could significantly influence public attitudes towards the acceptance and adoption of high-speed vacuum transportation, highlighting its safety and efficiency. Improved diagnostic methods will enhance the reliability of Hyperloop systems, promoting sustainable and environmentally friendly transportation alternatives. Additionally, the findings could inform public and industry policy, encouraging investment in advanced transportation infrastructure, ultimately improving quality of life through reduced travel times and lower emissions. Originality/value: This paper presents novel diagnostic methods tailored for the unique conditions of Hyperloop systems, such as high-speed vacuum environments. It offers valuable insights for engineers, researchers, and policymakers involved in the development and implementation of advanced transportation technologies.
