In this paper,an online tracking simulation system for the 660 MW ultra-supercritical circulating fluidized bed(USCFB)boiler is established,and a tracking simulation test is conducted for the cold start-up process of ...In this paper,an online tracking simulation system for the 660 MW ultra-supercritical circulating fluidized bed(USCFB)boiler is established,and a tracking simulation test is conducted for the cold start-up process of the boiler.The system comprises two parts:the USCFB boiler model and a tracking mechanism based on sliding mode control algorithm.The USCFB boiler model includes a water-steam system,an air-flue gas system,a material supply system,and an ash circulation system.The online tracking simulation system receives the same control signal as the plant and runs synchronously in digital space.The tracking mechanism updates model parameters to eliminate deviations between simulation values and measured values.The SMC-based multi-input,multi-output algorithm is based on a state-space model,providing two distinct advantages.Firstly,it enables more efficient elimination of deviations;secondly,it exhibits robustness against uncertainties associated with simulation model behavior and measurement noise.Finally,this paper conducts tracking simulation research on the cold start-up process of the boiler.展开更多
Roadside cameras play a crucial role in road traffic,serving as an indispensable part of integrated vehicleroad-cloud systems due to their extensive visibility and monitoring capabilities.Nevertheless,these cameras fa...Roadside cameras play a crucial role in road traffic,serving as an indispensable part of integrated vehicleroad-cloud systems due to their extensive visibility and monitoring capabilities.Nevertheless,these cameras face challenges in continuously tracking targets across perception domains.To address the issue of tracking vehicles across nonoverlapping perception domains between cameras,we propose a cross-camera vehicle tracking method within a Vehicle–Road–Cloud system that integrates visual and spatiotemporal information.A Gaussian model with microlevel traffic features is trained using vehicle information obtained through online tracking.Finally,the association of vehicle targets is achieved through the Gaussian model combining time and visual feature information.The experimental results indicate that the proposed system demonstrates excellent performance.展开更多
针对室外街道的行人检测与跟踪,提出一种改进YOLOv3与简单在线实时跟踪(simple online and real-time tracking,SORT)算法相结合的检测及跟踪方法。首先,引入距离和比例交并比(distance and proportional-IOU,DPIOU)损失,将原有的损失...针对室外街道的行人检测与跟踪,提出一种改进YOLOv3与简单在线实时跟踪(simple online and real-time tracking,SORT)算法相结合的检测及跟踪方法。首先,引入距离和比例交并比(distance and proportional-IOU,DPIOU)损失,将原有的损失函数中的均方误差(mean square error,MSE)部分进行变化,从而得到更精确的检测框;其次,将网络结构中的RestNet进行优化,改变下采样区域,增加池化层,进而减少特征信息的丢失;最后将检测结果输入SORT算法进行建模和匹配。实验结果表明,在室外街道的场景下,改进的算法与YOLOv3相比较,损失值收敛更快,平均准确率高出4.85%,跟踪准确率上升3.4%,同时,模型的速度有所提高,最快可达14.39 FPS。展开更多
文摘In this paper,an online tracking simulation system for the 660 MW ultra-supercritical circulating fluidized bed(USCFB)boiler is established,and a tracking simulation test is conducted for the cold start-up process of the boiler.The system comprises two parts:the USCFB boiler model and a tracking mechanism based on sliding mode control algorithm.The USCFB boiler model includes a water-steam system,an air-flue gas system,a material supply system,and an ash circulation system.The online tracking simulation system receives the same control signal as the plant and runs synchronously in digital space.The tracking mechanism updates model parameters to eliminate deviations between simulation values and measured values.The SMC-based multi-input,multi-output algorithm is based on a state-space model,providing two distinct advantages.Firstly,it enables more efficient elimination of deviations;secondly,it exhibits robustness against uncertainties associated with simulation model behavior and measurement noise.Finally,this paper conducts tracking simulation research on the cold start-up process of the boiler.
基金the National Natural Science Foundation of China(52172389)Natural Science Foundation of Guangdong Province(2022A1515012080)Tsinghua-Toyota Joint Research Institute Interdisciplinary Program.
文摘Roadside cameras play a crucial role in road traffic,serving as an indispensable part of integrated vehicleroad-cloud systems due to their extensive visibility and monitoring capabilities.Nevertheless,these cameras face challenges in continuously tracking targets across perception domains.To address the issue of tracking vehicles across nonoverlapping perception domains between cameras,we propose a cross-camera vehicle tracking method within a Vehicle–Road–Cloud system that integrates visual and spatiotemporal information.A Gaussian model with microlevel traffic features is trained using vehicle information obtained through online tracking.Finally,the association of vehicle targets is achieved through the Gaussian model combining time and visual feature information.The experimental results indicate that the proposed system demonstrates excellent performance.
文摘针对室外街道的行人检测与跟踪,提出一种改进YOLOv3与简单在线实时跟踪(simple online and real-time tracking,SORT)算法相结合的检测及跟踪方法。首先,引入距离和比例交并比(distance and proportional-IOU,DPIOU)损失,将原有的损失函数中的均方误差(mean square error,MSE)部分进行变化,从而得到更精确的检测框;其次,将网络结构中的RestNet进行优化,改变下采样区域,增加池化层,进而减少特征信息的丢失;最后将检测结果输入SORT算法进行建模和匹配。实验结果表明,在室外街道的场景下,改进的算法与YOLOv3相比较,损失值收敛更快,平均准确率高出4.85%,跟踪准确率上升3.4%,同时,模型的速度有所提高,最快可达14.39 FPS。
