As the volume and scale of urban expressways continue to increase, renewal remains a concern for urban development. The renewal and decision-making of an urban expressway need to be endowed with new concepts to adapt to the rapid development of cities. Nevertheless, in addition to considering road factors such as facility conditions, driving conditions, and environmental protection, the existing evaluation system lacks comprehensive consideration of factors that improve resilience and adapt to future urban development, and it lacks a quantifiable general update evaluation system. Thus, the establishment of a comprehensive renewal indicator system and a mixed evaluation framework is a challenge. This study proposes an evaluation framework of expressway renewal indicators that integrates the three dimensions of macro, meso, and micro based on the fuzzy Delphi method, the fuzzy AHP method, and the TOPSIS method. A q-rung orthopair fuzzy linguistic set was used to handle expert uncertainty information in the process of conducting fuzzy evaluations. The indicators were refined into general and quantifiable evaluation indicators to improve their versatility. Moreover, the renewal value of expressways was measured and calculated using the TOPSIS method, and four renewal intervals were divided according to the calculation results. As a result, 28 renewal indicators were screened out, and the five factors with the greatest impact on renewal were the demand for transport development, the renewal of facility and service functions, the upgrading of institutional resilience, structural renewal, and economic development. The model was applied to eight expressways in Shanghai to calculate the renewal degree value and divide the renewal status. The model could identify the renewal needs of each road to guide the renewal decision. This study proposes an evaluation model to measure urban expressway renewal studies and provides a reference for urban renewal in the area of sustainable development
As an important element of urban infrastructure renewal, urban expressway renewal is of great significance to improve the commuting efficiency of cities (especially metropolitan cities), strengthen the service capacity of urban road facilities, and enhance the quality of cities. Considering the advantages of a knowledge graph in the integration of multi-source data and assisted decision-making based on knowledge reasoning, this paper provides assisted decision support for urban expressway renewal with the help of a knowledge graph. In this paper, we sorted out the concepts related to road renewal from road maintenance standards, designed an ontology concept matching algorithm to extract relevant concepts in existing ontologies, constructed concept models, and built a knowledge graph of expressway renewal with ontology as the carrier. Then, based on road maintenance standards and road properties, this work proposes a knowledge reasoning rule combined with case similarity for an expressway renewal strategy. The final experimental results verified the feasibility of the expressway renewal strategy based on the knowledge graph.
Shield tunneling must satisfy safety requirements while maintaining efficiency, but the dynamic interactions among subsystems and continuously evolving ground conditions make manual coordination unreliable. To address this challenge, this study proposes the Counterfactual Reinforcement Learning-Based Shield Multi-Subsystem Collaborative Optimization (CRL-SMSCO), a multi-agent reinforcement learning framework with a centralized critic and decentralized actors. CRL-SMSCO performs counterfactual credit assignment to quantify each subsystem’s marginal contribution to global tunneling outcomes and jointly optimizes subsystem parameters. Safety is enforced by a safety-oriented action masking unit that restricts the feasible action space in real time, together with a hierarchical reward that prioritizes safety over efficiency. These features enable CRL-SMSCO to achieve interpretable subsystem coordination and rigorous safety enforcement. In the Nanjing Metro case study, experiments show that CRL-SMSCO improves average training reward by 3.9% over multi-agent deep deterministic policy gradient (MADDPG) and by 3.5% over multi-agent proximal policy optimization (MAPPO), while also yielding lower variance and higher minimum rewards on the held-out test segment. In the engineering application, relative to experience-based manual operation under similar geology, CRL-SMSCO increases average tunneling speed by 13.2%, reduces equipment loads over 1.7%, and decreases ground deformation by 82%, with all indicators maintained within permissible limits. These results demonstrate that CRL-SMSCO provides significant practical value in shield tunneling, offering an effective framework for managing other safety-critical coupled systems.