Long short-term memory (LSTM) has been widely applied to real-time automated natural gas leak detection and localization. However, LSTM approach could not provide the interpretation that this leak position is localized instead of other positions. This study proposes a leakage detection and localization approach by integrating the attention mechanism (AM) with the LSTM network. In this hybrid network, a fully-connected neural network behaving as AM is first applied to assign initial weights to time-series data. LSTM is then used to discover the complex correlation between the weighted data and leakage positions. A labor-scale pipeline leakage experiment of an urban natural gas distribution network is conducted to construct the benchmark dataset. A comparison between the proposed approach and the state-of-the-arts is also performed. The results demonstrate our proposed approach exhibits higher accuracy with AUC = 0.99. Our proposed approach assigns a higher attention weight to the sensor close to the leakage position, indicating the variation of data from the sensor has a significant influence on leakage localization. It corresponds that the closer to the leakage position, the larger variation of monitoring pressure after leakage, which enhances the detection results’ trustiness. This study provides a transparent and robust alternative for real-time automatic pipeline leak detection and localization, which contributes to constructing a digital twin of emergency management of urban pipeline leakage.@en

Deep learning has been widely applied to automated leakage detection and location of natural gas pipe networks. Prevalent deep learning approaches do not consider the spatial dependency of sensors, which limits leakage detection performance. Graph deep learning is a promising alternative to prevailing approaches as it can model spatial dependency. However, the challenge of collecting real-world anomaly data for training limits the accuracy and robustness of currently used graph deep learning approaches. This study proposes a deep probabilistic graph neural network in which attention-based graph neural network is built to model spatial sensor dependency. Variational Bayesian inference is integrated to model the posterior distribution of sensor dependency so that the leakage can be localized. An urban natural gas pipe network experiment is employed to construct the benchmark dataset, in which normal time-series data is applied to develop our proposed model while anomaly leakage data is used for performance comparison between our model and other state-of-the-art models. The results demonstrate that our model exhibits competitive detection accuracy (AUC) = 0.9484, while the additional uncertainty interval provides more comprehensive leakage detection information compared to state-of-the-art deep learning models. In addition, our model's posterior distribution enhances the leakage localization with the accuracy of positioning (PAc) = 0.8, which is higher than that of other state-of-the-art graph deep learning models. This study provides a comprehensive and robust alternative for subsequent decision-making to mitigate natural gas leakage from pipe networks.@en

The ‘travelling fire’ models have been used to describe the localised and travelling burning of uniform fuel bed in large open-plan building space. However, fuel is typically distributed non-uniformly in the built environment, leading to complex fire spread behaviours. This paper investigates the effect of non-uniform fuel load distribution on fire development in a sufficiently-ventilated space. A series of fire tests up to 3.5 MW with different wood crib layouts are categorised into two types, i.e., non-uniform and continuous, and non-uniform and discontinuous. The leading and trailing edges of the flame, height of flame, and fire spread rates are estimated using visual evidence. The non-uniform fuel load distribution fundamentally changes the spreading behaviour of fire. On a continuous wood crib, the fire spread rate and fire size are generally proportional to the fuel load density when the arrangement of the wood crib is similar. However, when wood cribs are discontinuous, the fire dynamics depend more on the localised burning size and gaps between fuels. Furthermore, very distinct fire behaviours were observed for fuel loads with different porosity. This work reveals the possible under-estimation of fire hazards of assuming evenly distributed fuel load and suggests considering design fire scenarios of non-uniform fuel load distribution in the performance-based fire safety design.

@en

This study analyses the structural response of an aluminium reticulated roof structure that is constructed at Sichuan Fire Research Institute (Sichuan, China), and to be tested in fire. The structural fire behaviour under 960 localised fire scenarios is considered first, and then used to construct a database for training a modular artificial intelligence (AI) system for real-time forecasting. The system consists of several AI models, each of which predicts the displacement at a specific monitoring point. These individual predictions are then combined to generate a comprehensive forecast of the global structural-fire behaviour. The individual AI model utilized is a Long Short-Term Memory Recurrent Neural Network (LSTM RNN). The modular design allows different models to be modified or added as needed, making the system flexible and adaptable, and improving the accuracy and reliability of the predictions. The results demonstrate the effectiveness of the modular AI approach in accurately forecasting fire-induced structural collapses as indicated by the sensitivity the local models can have. The key objective of this research is to help to make informed decisions and prioritize efforts to minimize the risk of structural collapse in fire.

@en

Large open-plan compartment fires in modern buildings may exhibit a local burning region travelling across the floor plan as a ‘travelling fire’. This phenomenon has been found in the forensic investigations of fire accidents and in the large compartment fire tests. The fire impact in a large compartment is spatially non-uniform and time-variant, which can cause severe local damage to structural components. Advanced from the previous models assuming constant travelling, the natural fire model established in this paper comprises time-variant and test-based travelling behaviour models and localised fire models of various modes. It is demonstrated with the fast-spread Veselí fire test and the slow-spread Malveira fire test. A generic structural model is set up within OpenSees for fire to examine the thermal impact on structural members under various travelling fire scenarios of different travelling parameters, fire travelling directions, and beam sizes. Locally much higher thermal responses are represented after introducing behaviour models while adopting the same design fire load. Based on the work in this paper, a library of design fire models can be potentially enabled to examine the fire safety performance of structures regarding the realistic fire load and fire impact aiming for discovering unknown worse fire scenarios.

@en

In performance-based structural fire engineering, “travelling fires” is being gradually accepted as an important fire boundary condition. However, its application is still limited by uncertainties in the selection of different design travelling fire parameters, resulting from the lack of relevant experimental data and corresponding validated structural finite element models which can be used with advanced travelling fire methodologies, e.g. the Extended Travelling Fire Methodology (ETFM) framework. This paper aims to fill this gap through modelling a prototype steel-composite floor structure (representing a “slice” of a large open-plan office), to investigate its true structural response under a wide range of travelling fire scenarios, with an emphasis on considering the effect of concrete slab in a 3D finite element model, using LS-DYNA. To ensure the credibility of this numerical study, the model was first validated against the experimental data of the structural response from the Veselí Travelling Fire Test. In the parametric studies, 32 cases were examined to investigate the thermal and structural response, related to the selection of key design parameters for travelling fires (i.e. fire spread rates, fuel load densities and inverse opening factors (IOF)); fire protection (i.e. different fire protection schemes and required fire resistance rating (FRR)), and the effect of slab specification (i.e. thicknesses and steel reinforcements). It was found that solely satisfying the critical temperature and deflection criteria for the structural members might not guarantee a sufficient structural design for travelling fire scenarios, and it is suggested that the steel stress utilisation should also be examined. Compared with the IOF, it appears that the selection of fire spread rates and fuel load densities are likely to be more critical in identifying the worst travelling fire scenario for the structural response with fire protection. Moreover, the global structural response under travelling fire is also affected by the combination of fire protection (i.e. equivalent FRR in this paper) and fire spread rate. Under a “slow” travelling fire (e.g. 0.5 mm/s) with increasing FRR, the failure of structural elements during the cooling phase was prevented effectively; however, under a relatively “fast” travelling fire (e.g. 2.5 mm/s, 12.5 mm/s), increasing FRR may not always improve the fire performance of the structure. This work also indicates that steel reinforcement ratio has a greater influence on structural response than slab thickness under travelling fires. Furthermore, the 3D finite element model is very important for structural fire analysis, not only due to the more conservative internal force captured by the 3D model (i.e. reduced by over 80 % on the 2D model in our case) thereby reproducing the collapse triggered by the failure of the connection under fire in general, but also the 3D model was able to better represent the deflection and the “internal force reversal” caused by travelling fires.

@en