Accurate detection of smoke and fire sources is critical for early fire warning and environmental monitoring.However,conventional detection approaches are highly susceptible to noise,illumination variations,and comple...Accurate detection of smoke and fire sources is critical for early fire warning and environmental monitoring.However,conventional detection approaches are highly susceptible to noise,illumination variations,and complex environmental conditions,which often reduce detection accuracy and real-time performance.To address these limitations,we propose Lightweight and Precise YOLO(LP-YOLO),a high-precision detection framework that integrates a self-attention mechanism with a feature pyramid,built upon YOLOv8.First,to overcome the restricted receptive field and parameter redundancy of conventional Convolutional Neural Networks(CNNs),we design an enhanced backbone based on Wavelet Convolutions(WTConv),which expands the receptive field through multifrequency convolutional processing.Second,a Bidirectional Feature Pyramid Network(BiFPN)is employed to achieve bidirectional feature fusion,enhancing the representation of smoke features across scales.Third,to mitigate the challenge of ambiguous object boundaries,we introduce the Frequency-aware Feature Fusion(FreqFusion)module,in which the Adaptive Low-Pass Filter(ALPF)reduces intra-class inconsistencies,the offset generator refines boundary localization,and the Adaptive High-Pass Filter(AHPF)recovers high-frequency details lost during down-sampling.Experimental evaluations demonstrate that LP-YOLO significantly outperforms the baseline YOLOv8,achieving an improvement of 9.3%in mAP@50 and 9.2%in F1-score.Moreover,the model is 56.6%and 32.4%smaller than YOLOv7-tiny and EfficientDet,respectively,while maintaining real-time inference speed at 238 frames per second(FPS).Validation on multiple benchmark datasets,including D-Fire,FIRESENSE,and BoWFire,further confirms its robustness and generalization ability,with detection accuracy consistently exceeding 82%.These results highlight the potential of LP-YOLO as a practical solution with high accuracy,robustness,and real-time performance for smoke and fire source detection.展开更多
Ultrafine austenite grains with average size of 2μm were successfully obtained by combining thermo-mechanical control process followed by reheating in a vanadium microalloyed steel.The mixed microstructure transforme...Ultrafine austenite grains with average size of 2μm were successfully obtained by combining thermo-mechanical control process followed by reheating in a vanadium microalloyed steel.The mixed microstructure transformed from pancaked austenite formed during controlled rolling has a higher density of high angle boundaries,compared to that transformed from equiaxial austenite.It contributes to increasing nucleation density of austenite grain during the reheating process.A certain volume fraction of undissolved nano-sized（Ti,V）C particles,which are formed during the controlled rolling process and/or the reheating process,effectively inhibit austenite grain growth and consequently refine austenite grain size significantly.The critical grain size of austenite calculated by Gladman model agrees well with the experimental result.展开更多
Dynamic strain-induced transformation of the low carbon steel Q（235） at 770℃ and 850℃ leads to fine ferrite grains. The microstructure characterization and mechanism of the fine ferrite grain were studied by scann...Dynamic strain-induced transformation of the low carbon steel Q（235） at 770℃ and 850℃ leads to fine ferrite grains. The microstructure characterization and mechanism of the fine ferrite grain were studied by scanning electron microscopy （SEM）, transmission electron microscopy （TEM） and electron backscattered diffraction （EBSD） technique. The results show that strain-induced microstructure is the mixed microstructure of ferrite and pearlite, with cementite randomly distributed on ferrite grain boundaries and the grains interiors. EBSD images of grain boundaries demonstrate that high angle grain boundaries （HAGBs） are dominant in both of the deformation induced microstructures occurring below and above A（e3） , with only a few low angle grain boundaries （LAGBs） existing in the grain interiors. It implies that the dynamic strain-induced transformation （DSIT） happens above and below A（e3） temperature and has the same phase transition mechanisms. The refinement of ferrite is the cooperative effect of DSIT and continuous dynamic recrystallization （CDRX） of ferrite. Besides, DSIT is deemed as an incomplete carbon diffusion phase transition through the analysis of microstructure and the previous simulated results. The strengths of the Q（235） steel with refined ferrite and pearlite structure get doubled than the initial state without treated by DSIT and the residual stress in the refined structure is partly responsible for the ductility loss.展开更多
The lattice Boltzmann method （LBM） has gained increasing popularity in the last two decades as an alternative numerical approach for solving fluid flow problems. One of the most active research areas in the LBM is i...The lattice Boltzmann method （LBM） has gained increasing popularity in the last two decades as an alternative numerical approach for solving fluid flow problems. One of the most active research areas in the LBM is its application in particle-fluid systems, where the advantage of the LBM in efficiency and parallel scalability has made it superior to many other direct numerical simulation （DNS） techniques. This article intends to provide a brief review of the application of the LBM in particle-fluid systems. The numerical techniques in the LBM pertaining to simulations of particles are discussed, with emphasis on the advanced treatment for boundary conditions on the particle-fluid interface. Other numerical issues, such as the effect of the internal fluid, are also briefly described. Additionally, recent efforts in using the LBM to obtain closures for particle-fluid drag force are also reviewed.展开更多
基金supported by the National Natural Science Foundation of China(No.62203163)the Scientific Research Project of Hunan Provincial Education Department(No.24A0519)+1 种基金the Hunan Provincial Natural Science Foundation(No.2025JJ60407)the Postgraduate Scientific Research Innovation Project of Hunan Province(No.CX2024100).
文摘Accurate detection of smoke and fire sources is critical for early fire warning and environmental monitoring.However,conventional detection approaches are highly susceptible to noise,illumination variations,and complex environmental conditions,which often reduce detection accuracy and real-time performance.To address these limitations,we propose Lightweight and Precise YOLO(LP-YOLO),a high-precision detection framework that integrates a self-attention mechanism with a feature pyramid,built upon YOLOv8.First,to overcome the restricted receptive field and parameter redundancy of conventional Convolutional Neural Networks(CNNs),we design an enhanced backbone based on Wavelet Convolutions(WTConv),which expands the receptive field through multifrequency convolutional processing.Second,a Bidirectional Feature Pyramid Network(BiFPN)is employed to achieve bidirectional feature fusion,enhancing the representation of smoke features across scales.Third,to mitigate the challenge of ambiguous object boundaries,we introduce the Frequency-aware Feature Fusion(FreqFusion)module,in which the Adaptive Low-Pass Filter(ALPF)reduces intra-class inconsistencies,the offset generator refines boundary localization,and the Adaptive High-Pass Filter(AHPF)recovers high-frequency details lost during down-sampling.Experimental evaluations demonstrate that LP-YOLO significantly outperforms the baseline YOLOv8,achieving an improvement of 9.3%in mAP@50 and 9.2%in F1-score.Moreover,the model is 56.6%and 32.4%smaller than YOLOv7-tiny and EfficientDet,respectively,while maintaining real-time inference speed at 238 frames per second(FPS).Validation on multiple benchmark datasets,including D-Fire,FIRESENSE,and BoWFire,further confirms its robustness and generalization ability,with detection accuracy consistently exceeding 82%.These results highlight the potential of LP-YOLO as a practical solution with high accuracy,robustness,and real-time performance for smoke and fire source detection.
基金Sponsored by National Basic Research Program of China(2010CB630805)
文摘Ultrafine austenite grains with average size of 2μm were successfully obtained by combining thermo-mechanical control process followed by reheating in a vanadium microalloyed steel.The mixed microstructure transformed from pancaked austenite formed during controlled rolling has a higher density of high angle boundaries,compared to that transformed from equiaxial austenite.It contributes to increasing nucleation density of austenite grain during the reheating process.A certain volume fraction of undissolved nano-sized（Ti,V）C particles,which are formed during the controlled rolling process and/or the reheating process,effectively inhibit austenite grain growth and consequently refine austenite grain size significantly.The critical grain size of austenite calculated by Gladman model agrees well with the experimental result.
基金support from the National Natural Science Foundation of China (NSFC) under Grantb No. 50871109
文摘Dynamic strain-induced transformation of the low carbon steel Q（235） at 770℃ and 850℃ leads to fine ferrite grains. The microstructure characterization and mechanism of the fine ferrite grain were studied by scanning electron microscopy （SEM）, transmission electron microscopy （TEM） and electron backscattered diffraction （EBSD） technique. The results show that strain-induced microstructure is the mixed microstructure of ferrite and pearlite, with cementite randomly distributed on ferrite grain boundaries and the grains interiors. EBSD images of grain boundaries demonstrate that high angle grain boundaries （HAGBs） are dominant in both of the deformation induced microstructures occurring below and above A（e3） , with only a few low angle grain boundaries （LAGBs） existing in the grain interiors. It implies that the dynamic strain-induced transformation （DSIT） happens above and below A（e3） temperature and has the same phase transition mechanisms. The refinement of ferrite is the cooperative effect of DSIT and continuous dynamic recrystallization （CDRX） of ferrite. Besides, DSIT is deemed as an incomplete carbon diffusion phase transition through the analysis of microstructure and the previous simulated results. The strengths of the Q（235） steel with refined ferrite and pearlite structure get doubled than the initial state without treated by DSIT and the residual stress in the refined structure is partly responsible for the ductility loss.
文摘The lattice Boltzmann method （LBM） has gained increasing popularity in the last two decades as an alternative numerical approach for solving fluid flow problems. One of the most active research areas in the LBM is its application in particle-fluid systems, where the advantage of the LBM in efficiency and parallel scalability has made it superior to many other direct numerical simulation （DNS） techniques. This article intends to provide a brief review of the application of the LBM in particle-fluid systems. The numerical techniques in the LBM pertaining to simulations of particles are discussed, with emphasis on the advanced treatment for boundary conditions on the particle-fluid interface. Other numerical issues, such as the effect of the internal fluid, are also briefly described. Additionally, recent efforts in using the LBM to obtain closures for particle-fluid drag force are also reviewed.
