A corrosion defect is recognized as one of the most severe phenomena for high-pressure pipelines, especially those served for a long time. Finite-element method and empirical formulas are thereby used for the strength prediction of such pipes with corrosion. However, it is time-consuming for finite-element method and there is a limited application range by using empirical formulas. In order to improve the prediction of strength, this paper investigates the burst pressure of line pipelines with a single corrosion defect subjected to internal pressure based on data-driven methods. Three supervised ML (machine learning) algorithms, including the ANN (artificial neural network), the SVM (support vector machine) and the LR (linear regression), are deployed to train models based on experimental data. Data analysis is first conducted to determine proper pipe features for training. Hyperparameter tuning to control the learning process is then performed to fit the best strength models for corroded pipelines. Among all the proposed data-driven models, the ANN model with three neural layers has the highest training accuracy, but also presents the largest variance. The SVM model provides both high training accuracy and high validation accuracy. The LR model has the best performance in terms of generalization ability. These models can be served as surrogate models by transfer learning with new coming data in future research, facilitating a sustainable and intelligent decision-making of corroded pipelines.

Purpose: Current literature presents limited measurement methods of quantifying manufacturers' performance with environmental concerns. The purpose of this paper is to construct a company performance index for benchmarking motor vehicle manufacturers (MVMs) with environmental concerns. Design/methodology/approach: Methods of constructing the index include regression analysis, a modified linear method for normalizing variables and a geometric mean for aggregating variables into a single index I_MVM (index for MVMs). A case study is conducted in 12 MVMs from 2008 to 2017. A sensitivity analysis with the simple additive weighting method is performed to analyze how different aggregation methods affect the final value. The index I_MVM is assessed through a benchmark with three existing indices. Findings: Three realistic considerations are identified from MVMs, based on which proper and transparent methods are chosen to construct the I_MVM. The construction of the index I_MVM has been assessed through a benchmark against the methodologies of three other indices. The results indicate that the new measurement is feasible and effective for MVMs to measure their company performance from an environmental perspective. Practical implications: The construction of the index I_MVM can support policymakers with accurate statistics for decision-making. As a response to current imperative climate policies, this paper raises awareness of CO₂ emissions in vehicles' production. For statistical organizations and stakeholders in the investment world, this paper provides available and reliable statistics for trend analysis of different MVMs. Originality/value: A new method is designed for constructing a company performance index for MVMs. Three environmental variables are identified based on literature, their environmental impact as well as their data availability from public documents. A ranking by manufacturer with environmental concerns is generated. This index can contribute with available statistics and useful insights toward decision-making.

This paper investigates the problem of inter-terminal movements of containers and vehicles within a port area in order to achieve an integrated and effective transport within the port and towards the hinterland. Containers from different port terminals are first moved to a rail yard and then delivered to the hinterland by rail. To provide insights for stakeholders such as port authority and terminal operators into tactical planning problems, e.g., the coordination between terminals, railway timetable and train sizes, this paper proposes an optimization model describing the movement of containers and various vehicles between and inside terminals. The model aims at improving the container delivery from container terminals to the hinterland considering both railway hinterland transport and terminal handling operations. A network inspired by a real-life port area and its hinterland is used as a test case to test different components, i.e., inter-terminal transport connections, train formation, railway timetable. A rolling horizon framework is used to improve the computation efficiency in large transport demand cases. The result of the optimization helps in identifying the most promising features, namely, that more connections between terminals and a flexible outbound railway timetable could contribute to improving the integrated container transport performance.

A wheel impact load detector is used to assess the condition of a railway wheel by measuring the dynamic forces generated by defects. This system normally measures the impact force at multiple points by exploiting multiple sensors to collect samples from different portions of the wheel circumference. The outputs of the sensors are used to estimate the dynamic force as the main indicator for detecting the presence of the defect. This method fails to identify the defect type and its severity. Recently, a data fusion method has been developed to reconstruct the wheel defect signal from the wheel–rail contact signals measured by multiple wayside sensors. The reconstructed defect signal can be influenced by different parameters such as train velocity, axle load, number of sensors, and wheel diameter. This paper aims to carry out a parametric study to investigate the influence of these parameters. For this purpose, VI-Rail is used to simulate the wheel–rail interaction and provide the required data. Then, the developed fusion method is exploited to reconstruct the defect signal from the simulated data. This study provides a detailed insight into the effects of the influential parameters by investigating the variation of the reconstructed defect signals.