Transfer Learning for Transportation Demand Resilience Pattern Prediction Using Floating Car Data

Introduction.Industrial pipeline transportation systems are complex, potentially hazardous engineering facilities that ensure the delivery of specified amounts of a target product to consumers. The development of emergencies associated with the transition to the down state of a certain number of pipelines may result in the disconnection of some or all the product consumers from the source. If the system’s linear elements transition to the down state in a random order, such a change of the network structure is called a progressive damage. A progressive damage is especially hazardous if, in the course of maintenance activities, a part of the system or a set of process pipelines is disconnected.The Aimof the work is to identify the change patterns of pipeline system resilience when affected by progressive damage and to develop practical recommendations for ensuring the resilience of such systems in operation and during maintenance operations.Methods of research.The resilience of systems as the capability to resist progressive damage was evaluated with an indicator that represents the average fraction of pipelines whose transition into the down state causes the disconnection of all consumers from the source of the product. The resilience values were defined by means of computer simulation. The network structure and the nature of the existing intersystem communications were defined using an adjacency matrix.Results.Damage to a transportation network structure is regarded as a result of a two-stage process. At the stage of target transformation, linear elements are purposefully excluded from a full graph-based structure, bringing the network to a certain initial state. At the second stage, the original structure is transformed according to the mechanism of progressive damage. Such approach allows correctly assessing the changes in the resilience of complex network structures and their ability to resist the development of the processes of damage. The paper sets forth calculated characteristics that allow predicting the behaviour of pipeline networks affected by emergencies. The existence of limit network structures is demonstrated that prove to be very vulnerable to the development of progressive damage.Conclusions. As the process of targeted transformation goes on, the ability of newly formed network structures to resist the development of progressive damage progressively diminishes. The lowest level of pipeline system resilience against the development of the process of progressive damage can be observed as the structure of the network nears the limit state. When preparing maintenance activities with scheduled exclusion of a number of linear elements from an active pipeline system, the proximity of the newly built network structure to the limit state should be assessed along with the resilience of the restored system to possible development of progressive damage.

This paper provides the construction of a qualitative and systemic methodology to assess the resilience of rail transport systems against natural hazards. To illustrate the capabilities of the methodology, it is applied for the flood hazard. The resilience of rail transport systems is analysed through the failure mechanisms to which they are subjected under flood conditions. These mechanisms lead to numerous, complex failure scenarios and modelling these scenarios enables the identification the components in the system that are successively damaged as a result of a disruption. The first part presents the construction of the methodology. The second part proposes a perspective of the methodology by shifting from a qualitative to a quantitative approach by using a probabilistic framework based on Bayesian networks. The choice of Bayesian networks , the construction of the quantitative model and its capabilities are demonstrated.

The objective of this comprehensive review study was to compile a state-of-the-art understanding of the resilience of the transportation system due to natural and man-made disasters. This study identified resilience measurement parameters that can be used to formulate resilience quantification and improvement strategies of a transportation system. Reviewed articles were classified and summarized from two perspectives: (i) modeling based on the mode of transportation; and (ii) modeling based on the mathematical technique used to quantify resilience. One of the unique contributions of this review article is that it compiled the key resilience indices that were analyzed to quantify resilience. This review revealed that the majority of the scholarly articles on the topic of transportation system resilience published since 2006, were focused on the resilience of the roadway-based transportation system, and vulnerability was one of the most explored resilience indices in evaluating transportation system resilience. Several future research directions were identified considering the implications of emerging transportation technologies (e.g., connected and automated vehicle technology). The complex interdependency among critical infrastructure systems such as power, transportation, and communication system, as well as the cybersecurity issues in the advanced intelligent transportation system, will be vital in the resilience analysis of future transportation systems.

During the excavation of the shield tunneling machine, the performance of the existing methods for shield tunneling machine parameter prediction often require a large amount of data to train a relatively accurate prediction model, which is in great contradiction with the limited data collected when the subway line is beginning to be constructed. In this paper, a set of transfer learning model based on long short-term memory (LSTM) is designed and built to improve the prediction process of shield tunneling machine parameter when the amount of data is small. The model selects the cutterhead torque as the prediction target and uses the Pearson coefficient method to filter the input features that are highly correlated with the prediction target. During transfer learning, the pre-training of the transfer model was first performed on the Beijing subway dataset. The best transfer learning scheme was selected by freezing the pre-training models with different layers and the optimal transfer learning model was transferred to the Tianjin Metro. Comparing the results of transfer learning and directly using LSTM model training with different data volumes, the results show that the use of transfer learning can effectively improve the accuracy of the prediction model when the data volume is small.

This paper describes a study which gives insight into the size of improvement that is possible with individual in-car routing advice based on the actual traffic situation derived from floating car data (FCD). It also gives an idea about the required penetration rate of floating car data needed to achieve a certain degree of improvement. The study uses real loop detector data from the region of Amsterdam collected for over a year, a route generating algorithm for in-car routing advice, and emulated floating car data to generate the routing advice. The case with in-car routing advice has been compared to the base case, where drivers base their routing decisions on average knowledge of travel times in the network. The improvement in total delay using the in-vehicle system is dependent on penetration rate and accuracy of the floating car data and varies from 2.0% to 3.4% for 10% penetration rate. This leads to yearly savings of about 15 million euros if delay is monetarised using standard prices for value of time (VOT).

The aim of this study was to investigate the transfer of learning of professional competences from vocational colleges to the workplace context in vocational education. Concretely, the study examined the relations between the professional competences learned at school and the use and further development of those competences at the workplace during the practice module in vocational education programmes in Spain. The study analysed individual, educational design and work environment factors that facilitate or hinder transfer of learning. The study took a multidimensional approach to professional competences by observing four dimensions: hard-specific, hard-generic, interpersonal and intrapersonal. The data collection drew from a questionnaire administered to students of vocational education programmes (N = 379) after they had completed the practice module scheme. A moderation analysis was applied to observe the effect of individual, educational design and workplace factors on the relation between the competences learned at school and those used at the workplace. The findings showed that compulsory placement, school-work alignment, work-based supervisor, access to resources and task complexity are significant moderators between the competences learned at school and those used at the workplace. The study highlights the coherence between the school and workplaces and work environment characteristics as factors conducive to transfer of learning.

Estimating resilience of manufacturing plants to physical disruptions: Model and application

Wastewater treatment plants (WWTPs) must operate efficiently under varying influent conditions and rigorous regulations due to growing populations and industrial expansion. For complex processes such as nutrient removal, effluent quality, activated sludge behaviour, and aeration control, data collection is laborious, expensive, and expert-dependent, which slows machine learning and deep learning for water quality parameter prediction, fault detection, and process optimization. Transfer learning (TL) provides an efficient approach by allowing pre-trained models, developed on extensive generic or wastewater datasets, to be tailored for WWTP applications. TL enhances wastewater processes by transferring learned features that identify hydraulic patterns, pollutant indicators, reactor state transitions, and sludge characteristics, thus improving prediction accuracy in data-scarce environments. Recent studies indicate that TL improves the estimation of nutrient concentrations, sensor calibration, anomaly detection in aeration and settling units, and the early identification of sensor fouling and equipment faults. A comprehensive review focused on TL in WWTP is currently lacking, despite these benefits. Addressing this gap is crucial for informing the development and implementation of TL-based intelligent WWTP strategies. This review summarizes the framework of TL applications in WWTPs, examining previously explored pre-trained models, data sources, sensing and control modalities, computing platforms, and TL strategies. The primary challenges identified include data heterogeneity, the scarcity of benchmark datasets, model generalization, and dynamic operational conditions. Additionally, potential research directions for the integration of TL into next-generation WWTP are discussed.

Water distribution networks (WDNs) are a critical component of modern society, responsible for delivering water to local communities and industries while maintaining continuous, stable flow within the system, which carries low-grade hydropower potential. These systems are vulnerable to disruptive events, such as pipeline failures and water contamination. To mitigate the risk of disruption events, recent EU policies have focused on the digitalisation of critical infrastructure, including WDNs and wastewater treatment plants (WWTPs), through the integration of Internet of Things (IoT) technologies. Digitalisation enables system operators to collect real-time data and perform predictive maintenance, thereby improving resilience and operational efficiency. Thus, system electricity requirements will increase to support IoT and digitalisation retrofitting.This creates an opportunity to deploy energy-harvesting (EH) devices within WDNs and WWTP infrastructure that harness and utilise the resonant and kinetic energy inherent in water flow. Although the benefits of EH devices are often considered minimal and their energy outputs are low, EH devices are considered a viable power source for low-power sensors, such as pressure, contamination, and temperature sensors.This study proposes and applies a feasibility assessment framework to evaluate EH devices as an alternative, decentralised power source for IoT-enabled monitoring in WDNs. The framework includes technical performance analysis, economic viability, and environmental impact assessments, combined with probability-based resilience modelling. It uses case-specific hydraulic, operational, design, and economic data to quantify EH power outputs, assess the costs of design and deployment, evaluate the environmental footprint of the devices, determine sensor energy requirements, and assess system resilience across different deployment scenarios.Results demonstrate that the EH device has a mechanical power-generation capacity potential ranging from 0.049 to 36 watts, depending on the study location, flow conditions, and design characteristics. This EH generation capacity is sufficient to power pressure, contamination, and temperature sensors. The resilience modelling indicates that the detection probability of WDNs exhibits the most significant gains from adding sensors at low deployment levels. Thus, most of the improvement in detection levels occurs between deploying the first five to ten sensors; beyond this threshold, adding more sensors exhibits diminishing marginal returns to detection probability and system resilience. In addition, adding more sensors can significantly reduce system resilience by increasing power requirements, thereby placing excessive load on the power supply of the EH devices. Thus, it increases the risk of failure rather than enhancing resilience.Overall, the results underscore the importance of strategic sensor allocation over high-density deployment and of balancing monitoring coverage with energy availability. Furthermore, the results show that EH devices are suitable power-generation technologies for supporting the digitalisation of WDNs and informing the design of new monitoring systems and sensor placement to enhance system reliability, enable cost-effective monitoring, and maximise mitigation benefits. In addition, the proposed framework provides decision-makers with a structured approach to assessing EH integration applications for digitalised WDNs, focusing on enhancing resilience through monitoring, conducting technical performance and cost-benefit analyses, assessing environmental trade-offs, and designing monitoring strategies aligned with sustainability and resilience objectives.

Resilience engineering is a new and proactive attitude toward improving the safety and reliability of complex industrial systems such as oil and gas companies and petrochemical plants. This study aims to evaluate the effect of redundancy on a resilient system and determine which redundancy in different aspects including human resources and equipment items (hardware, software, and information) is more efficient in a resilient system through data envelopment analysis. Data collection was performed in a petrochemical plant through a questionnaire. Then, reliability of the data was calculated through Cronbach’s alpha test. Next, the effects of human redundancy and equipment redundancy on resilience engineering are examined by means of data envelopment analysis approach. The results show that efficiency of the resilient system is improved by considering both equipment redundancy and human redundancy. It is also revealed that human redundancy is more effective in resilient system performance compared to equipment redundancy. Hence, human redundancy plays a vital role in efficiency enhancement of resilient systems. This study is among the first ones that investigate the impact of the redundancy in resilient systems in different aspects including human and equipment redundancy by means of data envelopment analysis approach and highlights the gaps between managers and staff about the impact of equipment redundancy and human redundancy on resilience engineering.

Assessing seismic vulnerability of urban road networks by a Bayesian network approach

Aiming at the problems of heavy workload of basic data collection, complicated manual parameters calibration and inaccurate calibration in the traditional microscopic traffic simulation model parameter calibration, an adaptive microscopic traffic simulation model parameter calibration method based on floating car data is proposed. First, the basic data of the simulation road network were obtained by using the floating car technology. Secondly, the parameters calibration process of the microscopic traffic simulation model was constructed, and the self- adaptive orthogonal genetic was used to achieve the model parameters calibration. Finally, using the actual data of the South Ring Road main line, District Changping, Beijing to simulate and verify. The results show that the proposed method in this paper can not only reduce the workload of manual calibration, but also the model parameter calibration is more accurate, which proves the feasibility and effectiveness of the method.

Cross-condition fault diagnosis of chillers based on an ensemble approach with adaptive weight allocation

To ensure that transport infrastructure provides acceptable levels of service with respect to extreme events, the resilience of the infrastructure needs to be estimated and targets for it need to be set. In this paper, the methodology proposed in the Foresee EU research project is presented. The methodology allows managers to measure, and set targets for, the resilience of transport systems in all situations. It requires clear definition of the transport system and how the service provided and the resilience are to be measured. The methodology allows consideration of the fact that transport infrastructure managers need to estimate resilience with various degrees of accuracy depending on the specific problem to be addressed, the time frame at disposition and the expertise available. These various levels of accuracy are covered by proposing the use of (a) simulations, (b) indicators whose values are directly related to increases in expected restoration intervention costs and reductions in service, and (c) the percentage of fulfilment of indicators. Once resilience has been estimated, the methodology provides guidance on how to set resilience targets with or without cost–benefit analysis. For demonstration, the explanation of the steps of the guideline is supported by their use for a simple transport system.

Urban systems are dynamic, complex, and often involve multiple stakeholders, resulting in responses with distinct time lags. A resilient urban mobility system should be able to neutralize the effects of disruptive events (threats) while maintaining its essential state of functionality. Given the lack of studies addressing threats to urban mobility and the concurrent impacts on the urban mobility system, a holistic analysis considering key elements of transport systems and their interactions is necessary. Thus, this study aims to describe and analyze the dynamics involved in a resilient urban mobility system using qualitative system dynamics modeling. We start by identifying the main system components, threats, interrelations, and interconnections. Then, we create causal loop diagrams (CLD) of the urban mobility system under different conditions: (i) in the essential state of functionality, (ii) affected by a disruptive event and (iii) still functioning due to its resilience. Analyzing the CLDs indicated that the dynamics involved in a resilient urban mobility system have a preventive nature as it reflects the importance of transport policies considering climate change and disaster prevention policies/measures. In addition, the results showed that public opinion and incentives to use sustainable transport play an important role in balancing the system. Therefore, the negative effects of threats on the system, such as deaths, damage to transport infrastructures, and collapse of mobility performance, can be prevented. The outcomes of this study may be used to support the process of planning and building resilient cities.