Lei Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lei Xu has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Yan-Hong Bao
School of Civil Engineering, Qinghai University, Xining, China
3 shared publicationsJiepeng Liu
2 shared publicationsKai Huang
2 shared publicationsWen-Da Wang
Lanzhou University of Technology
2 shared publicationsBaiyuan Xu
School of Civil and Architectural Engineering, Liaoning University of Technology, Jinzhou 121001, China
1 shared publication- Delei Zou
School of Civil Engineering, Dalian Minzu University, Dalian, China
1 shared publication
Latest Publications
- 23 April 2025
- Published by Elsevier in Structures
- Vol. 76
The collapse mechanism and paths of steel frame structures under designed fire scenarios
- 23 April 2025
- Published by Elsevier in Structures
- Vol. 76
The collapse mechanism and paths of steel frame structures under designed fire scenarios
- Open Access
Predict Future Transient Fire Heat Release Rates Based on Fire Imagery and Deep Learning
The fire heat release rate (HRR) is a crucial parameter for describing the combustion process and its thermal effects. In recent years, some studies have employed fire scene images and deep learning algorithms to predict real-time fire HRR, which has led to the advancement of HRR prediction in terms of both lightweightness and real-time monitoring. Nevertheless, the development of an early-stage monitoring system for fires and the ability to predict future HRR based on current moment data represents a crucial foundation for evaluating the scale of indoor fires and enhancing the capacity to prevent and control such incidents. This paper proposes a deep learning model based on continuous fire scene images (containing both flame and smoke features) and their time-series information to predict the future transient fire HRR. The model (Att-BiLSTM) comprises three bi-directional long- and short-term memory (Bi-LSTM) layers and one attention layer. The model employs a bidirectional feature extraction approach, followed by the introduction of an attention mechanism to highlight the image features that have a critical impact on the prediction results. In this paper, a large-scale dataset is constructed by collecting 27,231 fire scene images with instantaneous HRR annotations from 40 different fire trials from the NIST database. The experimental results demonstrate that Att-BiLSTM is capable of effectively utilizing fire scene image features and temporal information to accurately predict future transient HRR, including those in high-brightness fire environments and complex fire source situations. The research presented in this paper offers novel insights and methodologies for fire monitoring and emergency response.
Open AccessPredict Future Transient Fire Heat Release Rates Based on Fire Imagery and Deep Learning
The fire heat release rate (HRR) is a crucial parameter for describing the combustion process and its thermal effects. In recent years, some studies have employed fire scene images and deep learning algorithms to predict real-time fire HRR, which has led to the advancement of HRR prediction in terms of both lightweightness and real-time monitoring. Nevertheless, the development of an early-stage monitoring system for fires and the ability to predict future HRR based on current moment data represents a crucial foundation for evaluating the scale of indoor fires and enhancing the capacity to prevent and control such incidents. This paper proposes a deep learning model based on continuous fire scene images (containing both flame and smoke features) and their time-series information to predict the future transient fire HRR. The model (Att-BiLSTM) comprises three bi-directional long- and short-term memory (Bi-LSTM) layers and one attention layer. The model employs a bidirectional feature extraction approach, followed by the introduction of an attention mechanism to highlight the image features that have a critical impact on the prediction results. In this paper, a large-scale dataset is constructed by collecting 27,231 fire scene images with instantaneous HRR annotations from 40 different fire trials from the NIST database. The experimental results demonstrate that Att-BiLSTM is capable of effectively utilizing fire scene image features and temporal information to accurately predict future transient HRR, including those in high-brightness fire environments and complex fire source situations. The research presented in this paper offers novel insights and methodologies for fire monitoring and emergency response.
- 3 November 2022
- Published by Springer Nature in Fire Technology
- Vol. 60 (5) , 3059-3089
Numerical Simulation of the Fire Response of a Frame with Concrete-Filled Steel Tube Columns
- 3 November 2022
- Published by Springer Nature in Fire Technology
- Vol. 60 (5) , 3059-3089
Numerical Simulation of the Fire Response of a Frame with Concrete-Filled Steel Tube Columns
- 6 September 2022
- Published by Elsevier in Journal of Building Engineering
- Vol. 61
Intelligent planning of fire evacuation routes using an improved ant colony optimization algorithm
- 6 September 2022
- Published by Elsevier in Journal of Building Engineering
- Vol. 61
Intelligent planning of fire evacuation routes using an improved ant colony optimization algorithm
- Open Access
- 23 February 2022
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2022, 1-10
Hybrid Model of Machine Learning Refractory Data Prediction Based on IoT Smart Cities
With the advent of the digital age in recent years, the application of artificial intelligence in urban Internet of Things (IoT) systems has become increasingly important. The concept of smart cities has gradually formed, and smart firefighting under the smart city system has also become important. The method of machine learning is now applied in various fields, but seldom to the data prediction of smart firefighting. Various types of applications including data applications of machine learning algorithms in smart firefighting have yet to be explored. In this article, we propose using machine learning algorithms to predict building fire-resistance data, aiming to provide more theoretical and technical support for IoT smart cities. This article adopts the fire-resistance data of building beam components in a real fire environment, using three integrated machine learning algorithms, Extreme random Tree (ET), AdaBoost, and Gradient Boosting Machine (GBM), and the grey wolf optimization algorithm to optimize. We improve the grey wolf algorithm and combine the grey wolf algorithm with the machine learning model. The algorithm constitutes three machine learning hybrid models: GWO-ET, GWO-AdaBoost, and GWO-GBM. Compared with traditional grid tuning, particle swarm optimization (PSO), and genetic algorithm (GA) optimization, the robustness and accuracy of the three optimization algorithms and the machine learning hybrid algorithm on the data set are compared and analyzed. Performance is measured through various performance comparisons and experimental result comparisons. For various building beam component data sets under real fires, the optimization and comparison show that the mean square error (MSE) of the proposed algorithm is extremely small. The results indicate that the GWO machine learning hybrid model is superior to other models and has a smaller prediction error.
- 23 February 2022
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2022, 1-10
Open AccessHybrid Model of Machine Learning Refractory Data Prediction Based on IoT Smart Cities
With the advent of the digital age in recent years, the application of artificial intelligence in urban Internet of Things (IoT) systems has become increasingly important. The concept of smart cities has gradually formed, and smart firefighting under the smart city system has also become important. The method of machine learning is now applied in various fields, but seldom to the data prediction of smart firefighting. Various types of applications including data applications of machine learning algorithms in smart firefighting have yet to be explored. In this article, we propose using machine learning algorithms to predict building fire-resistance data, aiming to provide more theoretical and technical support for IoT smart cities. This article adopts the fire-resistance data of building beam components in a real fire environment, using three integrated machine learning algorithms, Extreme random Tree (ET), AdaBoost, and Gradient Boosting Machine (GBM), and the grey wolf optimization algorithm to optimize. We improve the grey wolf algorithm and combine the grey wolf algorithm with the machine learning model. The algorithm constitutes three machine learning hybrid models: GWO-ET, GWO-AdaBoost, and GWO-GBM. Compared with traditional grid tuning, particle swarm optimization (PSO), and genetic algorithm (GA) optimization, the robustness and accuracy of the three optimization algorithms and the machine learning hybrid algorithm on the data set are compared and analyzed. Performance is measured through various performance comparisons and experimental result comparisons. For various building beam component data sets under real fires, the optimization and comparison show that the mean square error (MSE) of the proposed algorithm is extremely small. The results indicate that the GWO machine learning hybrid model is superior to other models and has a smaller prediction error.
- 18 March 2021
- Published by SAGE Publications in Advances in Structural Engineering
- Vol. 24 (11) , 2413-2426
Experimental study on the fire resistance of concrete filled steel tube reinforced concrete (CFSTRC) column-RC beam frames
To reveal the temperature characteristics and mechanical properties of frame structures with concrete filled steel tube reinforced concrete (CFSTRC) columns under fire, the fire resistance of four planar frames consisting of CFSTRC columns and reinforced concrete (RC) beams subjected to ISO-834 standard fire was tested in this study. The test parameters included the column fire load ratio, beam fire load ratio, and beam-to-column linear stiffness ratio. In the test, the temperatures of the column, beam, and slab cross-sections in the joint and nonjoint zones were measured, and the fire resistance, beam and column deformation curves, and failure modes of the frame were investigated. The experimental results showed that the concrete volume was the main factor affecting the temperature distribution on each typical cross-section of the frame: the temperatures at the measuring points of the beam and column in the joint zone were significantly lower than the temperatures at the corresponding points in the nonjoint zone, and the concrete outside the steel tube significantly slowed the propagation of temperature to the steel tube and its concrete core. Hence, there was only a small loss of the bearing capacity of steel tube and the core concrete inside the steel tube. The column fire load ratio, beam fire load ratio, and beam-to-column linear stiffness ratio have obvious influences on the fire resistance: the larger the column fire load ratio or beam fire load ratio, the smaller the fire resistance; and the larger the beam-to-column linear stiffness ratio, the larger the fire resistance.
- 18 March 2021
- Published by SAGE Publications in Advances in Structural Engineering
- Vol. 24 (11) , 2413-2426
Experimental study on the fire resistance of concrete filled steel tube reinforced concrete (CFSTRC) column-RC beam frames
To reveal the temperature characteristics and mechanical properties of frame structures with concrete filled steel tube reinforced concrete (CFSTRC) columns under fire, the fire resistance of four planar frames consisting of CFSTRC columns and reinforced concrete (RC) beams subjected to ISO-834 standard fire was tested in this study. The test parameters included the column fire load ratio, beam fire load ratio, and beam-to-column linear stiffness ratio. In the test, the temperatures of the column, beam, and slab cross-sections in the joint and nonjoint zones were measured, and the fire resistance, beam and column deformation curves, and failure modes of the frame were investigated. The experimental results showed that the concrete volume was the main factor affecting the temperature distribution on each typical cross-section of the frame: the temperatures at the measuring points of the beam and column in the joint zone were significantly lower than the temperatures at the corresponding points in the nonjoint zone, and the concrete outside the steel tube significantly slowed the propagation of temperature to the steel tube and its concrete core. Hence, there was only a small loss of the bearing capacity of steel tube and the core concrete inside the steel tube. The column fire load ratio, beam fire load ratio, and beam-to-column linear stiffness ratio have obvious influences on the fire resistance: the larger the column fire load ratio or beam fire load ratio, the smaller the fire resistance; and the larger the beam-to-column linear stiffness ratio, the larger the fire resistance.
- 31 December 2017
- Published by Springer Nature in International Journal of Steel Structures
- Vol. 17 (4) , 1561-1581
Numerical analysis on mechanical property of concrete filled steel tube reinforced concrete (CFSTRC) columns subjected to ISO-834 standard fire
- 31 December 2017
- Published by Springer Nature in International Journal of Steel Structures
- Vol. 17 (4) , 1561-1581
Numerical analysis on mechanical property of concrete filled steel tube reinforced concrete (CFSTRC) columns subjected to ISO-834 standard fire
- 31 December 2017
- Published by Springer Nature in International Journal of Steel Structures
- Vol. 17 (4) , 1515-1528
Numerical analysis on structural behaviors of concrete filled steel tube reinforced concrete (CFSTRC) columns subjected to 3-side fire
- 31 December 2017
- Published by Springer Nature in International Journal of Steel Structures
- Vol. 17 (4) , 1515-1528
Numerical analysis on structural behaviors of concrete filled steel tube reinforced concrete (CFSTRC) columns subjected to 3-side fire
- 13 March 2015
- Published by Springer Nature in Journal of Central South University
- Vol. 22 (3) , 800-805
Activated flux tungsten inert gas welding of 8 mm-thick AISI 304 austenitic stainless steel
- 13 March 2015
- Published by Springer Nature in Journal of Central South University
- Vol. 22 (3) , 800-805
Activated flux tungsten inert gas welding of 8 mm-thick AISI 304 austenitic stainless steel