A bi-objective deep reinforcement learning approach for low-carbon-emission high-speed railway alignment design

He, Qing; Gao, Tianci; Gao, Yan; Li, Huailong; Schonfeld, Paul; Zhu, Ying; Li, Qilong; Wang, Ping

doi:10.1016/j.trc.2022.104006

Cited by 6 publications

(3 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This framework was based on the deep reinforcement learning (DRL) approach for a single objective and focused on optimizing a policy function to guide the agent's actions in the environment. Subsequently, they proposed a biobjective optimization method built on the concept of reinforcement learning (He et al., 2023). These models can perform strategy selection and learn like humans during railway alignment optimization.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Through the proposed method, multiobjective values are optimized to achieve a coherent and efficient alignment within the entire preference space of the domain while adhering to the corresponding optimal policy. To accomplish this, a Pareto front (PF) is sought during the optimization process (He et al., 2023).…”

Section: Adp‐based Railway Alignment Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

Biobjective optimization for railway alignment fine‐grained designs with parallel existing railways

Gao,

Zhang,

Zhu

et al. 2024

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

Urban high‐speed railway construction is complex due to limited land resources, high population density, and potential construction risks, especially when new tracks are parallelly aligned to operational railways. Addressing a gap in current literature on fine optimization of manual alignment in such scenarios, this paper introduces a biobjective approximate fine‐grained optimization model for railway alignments (BA‐FORA). Utilizing an approximate dynamic programming (ADP) method, BA‐FORA effectively searches the feasible region to approach a global optimum, overcoming the dimensionality challenges inherent in standard dynamic programming (DP). This paper presents a biobjective optimization framework that takes into account both construction cost and construction risk adjacent to existing operating railways (CRAEOR), offering a method for the fine‐grained design of new railways adjacent to existing railways. Finally, the proposed BA‐FORA framework is applied to practical cases, demonstrating its superior optimization performance. The findings indicate that the BA‐FORA model can autonomously investigate and enhance railway alignment. It generates cost‐effective and low‐risk solutions exceeding manual efforts, ensuring alignment constraint compliance.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Adp‐based Railway Alignment Optimizationmentioning

confidence: 99%

Biobjective optimization for railway alignment fine‐grained designs with parallel existing railways

Gao,

Zhang,

Zhu

et al. 2024

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…Through engineering data collection, research and analysis, case references, relevant literature [1,2,[20][21][22][23], and current standards, and from the perspectives of the external influence and internal structure, the key elements and characteristic indicators of internal and external system's interactions and coercive relationships are systematically screened (Table 1). Among these, external elements are the key elements constraining route selection in the resource environment along the railway, including natural environment, ecological environment, resource, and socio-economic environment elements.…”

Section: The Interactive Impact Mechanism Of the "Alignment Design-re...mentioning

confidence: 99%

The Coupling Mechanism between Railway Alignment Design and Resource Environment in the Southwestern Mountainous Areas of China

Wan,

Bao,

2024

Sustainability

View full text Add to dashboard Cite

Faced with the characteristics of multifactor coupling and interweaving along the railway lines in the southwestern mountainous areas of China, researching the coupling mechanism and optimizing the collaborative development path between alignment designs and the resource environment is conducive to promoting the green and sustainable development of railways in these southwestern mountainous areas. In this study, first, regarding the environmental characteristics of engineering along the railway lines in the southwestern mountainous area, the key elements of the interaction and coercion between the alignment design (internal system) and the resource environment (external system) are identified, and the interactive impact mechanism of the “alignment design–resource environment” complex is revealed. Accordingly, a nonlinear coupling mechanism between the alignment design system and the resource environment system is established using the deviation coefficient coupling degree model. Second, from a methodological perspective, following a technical path of “analyzing the coercive effects of internal and external factors–identifying coupling relationships–discovering coupling laws–screening driving factors–proposing optimization plans–achieving collaborative development goals”, we propose an overall optimization plan to solve the problem. Finally, the Chengdu Changdu section of the X railway, which is located in a southwestern mountainous area, is taken as an example for this study. The results indicate that if the state of the external system of the KL scheme is continuously improved through the regulation of the u22 (crossing the ecological protection red line length), u23 (biodiversity impact), and u24 (ecosystem impact) indicators and that the internal structure of the line design is improved by optimizing the l12 (total length of bridges and tunnels) and l13 (number of stations) indicators, effectively driving the improvement in the u31 (land resource occupation) and u43 (land development intensity) indicators, the alignment design and resource environment will exhibit a mutually reinforcing coupling evolution trend and ultimately achieve an “alignment design–resource environment” composite system with higher quality coupling.

show abstract

Reinforcement learning based approach for the optimization of mechanical properties of additively manufactured specimens

Mishra

Jatti

2023

Int J Interact Des Manuf

View full text Add to dashboard Cite

A bi-objective deep reinforcement learning approach for low-carbon-emission high-speed railway alignment design

Cited by 6 publications

References 68 publications

Biobjective optimization for railway alignment fine‐grained designs with parallel existing railways

Biobjective optimization for railway alignment fine‐grained designs with parallel existing railways

The Coupling Mechanism between Railway Alignment Design and Resource Environment in the Southwestern Mountainous Areas of China

Reinforcement learning based approach for the optimization of mechanical properties of additively manufactured specimens

Contact Info

Product

Resources

About