With the acceleration of intelligent transformation of energy system,the monitoring of equipment operation status and optimization of production process in thermal power plants face the challenge of multi-source heter...With the acceleration of intelligent transformation of energy system,the monitoring of equipment operation status and optimization of production process in thermal power plants face the challenge of multi-source heterogeneous data integration.In view of the heterogeneous characteristics of physical sensor data,including temperature,vibration and pressure that generated by boilers,steam turbines and other key equipment and real-time working condition data of SCADA system,this paper proposes a multi-source heterogeneous data fusion and analysis platform for thermal power plants based on edge computing and deep learning.By constructing a multi-level fusion architecture,the platform adopts dynamic weight allocation strategy and 5D digital twin model to realize the collaborative analysis of physical sensor data,simulation calculation results and expert knowledge.The data fusion module combines Kalman filter,wavelet transform and Bayesian estimation method to solve the problem of data time series alignment and dimension difference.Simulation results show that the data fusion accuracy can be improved to more than 98%,and the calculation delay can be controlled within 500 ms.The data analysis module integrates Dymola simulation model and AERMOD pollutant diffusion model,supports the cascade analysis of boiler combustion efficiency prediction and flue gas emission monitoring,system response time is less than 2 seconds,and data consistency verification accuracy reaches 99.5%.展开更多
The rapid urbanization and structural imbalances in Chinese megacities have exacerbated the housing supplydemand mismatch,creating an urgent need for fine-scale diagnostic tools.This study addresses this critical gap ...The rapid urbanization and structural imbalances in Chinese megacities have exacerbated the housing supplydemand mismatch,creating an urgent need for fine-scale diagnostic tools.This study addresses this critical gap by developing the Housing Contradiction Evaluation Weighted Index(HCEWI)model,making three key contributions to high-resolution housing monitoring.First,we establish a tripartite theoretical framework integrating dynamic population pressure(PPI),housing supply potential(HSI),and functional diversity(HHI).The PPI innovatively combines mobile signaling data with principal component analysis to capture real-time commuting patterns,while the HSI introduces a novel dual-criteria system based on Local Climate Zones(LCZ),weighted by building density and residential function ratio.Second,we develop a spatiotemporal coupling architecture featuring an entropy-weighted dynamic integration mechanism with self-correcting modules,demonstrating robust performance against data noise.Third,our 25-month longitudinal analysis in Shenzhen reveals significant findings,including persistent bipolar clustering patterns,contrasting volatility between peripheral and core areas,and seasonal policy responsiveness.Methodologically,we advance urban diagnostics through 500-meter grid monthly monitoring and process-oriented temporal operators that reveal“tentacle-like”spatial restructuring along transit corridors.Our findings provide a replicable framework for precision housing governance and demonstrate the transformative potential of mobile signaling data in implementing China’s“city-specific policy”approach.We further propose targeted intervention strategies,including balance regulation for high-contradiction zones,Transit-Oriented Development(TOD)activation for low-contradiction clusters,and dynamic land conversion mechanisms for transitional areas.展开更多
As a product of the deep integration between next-generation information technology and industrial systems,digital twin technology has demonstrated significant advantages in real-time monitoring,predictive maintenance...As a product of the deep integration between next-generation information technology and industrial systems,digital twin technology has demonstrated significant advantages in real-time monitoring,predictive maintenance,and optimization decision-making for thermal power plants.To address challenges such as low equipment efficiency,high maintenance costs,and difficulties in safety risk management in traditional thermal power plants,this study developed a digital twin simulation system that covers the entire lifecycle of power generation units.The system achieves real-time collection and processing of critical parameters such as temperature,pressure,and flow rate through a collaborative architecture integrating multi-source heterogeneous sensor networks with Programmable Logic Controllers(PLCs).A three-tier processing framework handles data preprocessing,feature extraction,and intelligent analysis,while establishing a hybrid storage system combining time-series databases and relational databases to enable millisecond-level queries and data traceability.The simulation model development module employs modular design methodology,integrating multi-physics coupling algorithms including computational fluid dynamics(CFD)and thermal circulation equations.Automated parameter calibration is achieved through intelligent optimization algorithms,with model accuracy validated via unitlevel verification,system-level cascaded debugging tests,and virtual test platform simulations.Based on the modular layout strategy,the user interface and interaction module integrates 3D plant panoramic view,dynamic equipment model and multi-mode interaction channel,supports cross-terminal adaptation of PC,mobile terminal and control screen,and improves fault handling efficiency through AR assisted diagnosis function.展开更多
Fault diagnosis techniques,which are crucial in the field of industrial intelligent manufacturing,are capable of equipment performance maintenance and productivity improvement.In fault diagnosis,multi-type sensors are...Fault diagnosis techniques,which are crucial in the field of industrial intelligent manufacturing,are capable of equipment performance maintenance and productivity improvement.In fault diagnosis,multi-type sensors are commonly used for monitoring because a single data source fails to provide sufficient information to support the comprehensive analysis and accurate diagnosis.Hidden information between modes can be mined using data fusion techniques,enabling more effective decision-making and condition analysis.However,the data measured by multiple sensors are subject to issues such as varying types,an imbalanced ratio of positive to negative samples,and significant differences in data structure,making multi-source data fusion and inter-feature information acquisition challenging.To address these problems,we propose a fault diagnosis method based on dynamic convolution and polarized self-attention(DC-PSA)feature fusion networks.Given that unimodal features are not utilized comprehensively enough,we propose a dynamic convolution-based feature self-convergence model.The ability of the model is improved by attentively aggregating multiple convolution kernels,which are combined in a form dynamically adjusted according to different inputs to fully utilize the features.To enable effective feature-level integration across modalities,we establish a cross-attention-based multimodal fusion model,where each modal branch learns multiscale spatial information independently and forms cross-channel interactions in a localized manner,which can realize the information interactions between local and global channel attention.Empirical results on the Paderborn benchmark dataset validate that the proposed method captures the complementary characteristics across signal types more effectively than existing methods,leading to a notable boost in diagnostic accuracy following the fusion process.The accuracy of the proposed model reached 98.6%,representing an improvement of 8.74%compared to the baseline model.展开更多
文摘With the acceleration of intelligent transformation of energy system,the monitoring of equipment operation status and optimization of production process in thermal power plants face the challenge of multi-source heterogeneous data integration.In view of the heterogeneous characteristics of physical sensor data,including temperature,vibration and pressure that generated by boilers,steam turbines and other key equipment and real-time working condition data of SCADA system,this paper proposes a multi-source heterogeneous data fusion and analysis platform for thermal power plants based on edge computing and deep learning.By constructing a multi-level fusion architecture,the platform adopts dynamic weight allocation strategy and 5D digital twin model to realize the collaborative analysis of physical sensor data,simulation calculation results and expert knowledge.The data fusion module combines Kalman filter,wavelet transform and Bayesian estimation method to solve the problem of data time series alignment and dimension difference.Simulation results show that the data fusion accuracy can be improved to more than 98%,and the calculation delay can be controlled within 500 ms.The data analysis module integrates Dymola simulation model and AERMOD pollutant diffusion model,supports the cascade analysis of boiler combustion efficiency prediction and flue gas emission monitoring,system response time is less than 2 seconds,and data consistency verification accuracy reaches 99.5%.
基金National Natural Science Foundation of China(No.42101346)Undergraduate Training Programs for Innovation and Entrepreneurship of Wuhan University(GeoAI Special Project)(No.202510486196).
文摘The rapid urbanization and structural imbalances in Chinese megacities have exacerbated the housing supplydemand mismatch,creating an urgent need for fine-scale diagnostic tools.This study addresses this critical gap by developing the Housing Contradiction Evaluation Weighted Index(HCEWI)model,making three key contributions to high-resolution housing monitoring.First,we establish a tripartite theoretical framework integrating dynamic population pressure(PPI),housing supply potential(HSI),and functional diversity(HHI).The PPI innovatively combines mobile signaling data with principal component analysis to capture real-time commuting patterns,while the HSI introduces a novel dual-criteria system based on Local Climate Zones(LCZ),weighted by building density and residential function ratio.Second,we develop a spatiotemporal coupling architecture featuring an entropy-weighted dynamic integration mechanism with self-correcting modules,demonstrating robust performance against data noise.Third,our 25-month longitudinal analysis in Shenzhen reveals significant findings,including persistent bipolar clustering patterns,contrasting volatility between peripheral and core areas,and seasonal policy responsiveness.Methodologically,we advance urban diagnostics through 500-meter grid monthly monitoring and process-oriented temporal operators that reveal“tentacle-like”spatial restructuring along transit corridors.Our findings provide a replicable framework for precision housing governance and demonstrate the transformative potential of mobile signaling data in implementing China’s“city-specific policy”approach.We further propose targeted intervention strategies,including balance regulation for high-contradiction zones,Transit-Oriented Development(TOD)activation for low-contradiction clusters,and dynamic land conversion mechanisms for transitional areas.
文摘As a product of the deep integration between next-generation information technology and industrial systems,digital twin technology has demonstrated significant advantages in real-time monitoring,predictive maintenance,and optimization decision-making for thermal power plants.To address challenges such as low equipment efficiency,high maintenance costs,and difficulties in safety risk management in traditional thermal power plants,this study developed a digital twin simulation system that covers the entire lifecycle of power generation units.The system achieves real-time collection and processing of critical parameters such as temperature,pressure,and flow rate through a collaborative architecture integrating multi-source heterogeneous sensor networks with Programmable Logic Controllers(PLCs).A three-tier processing framework handles data preprocessing,feature extraction,and intelligent analysis,while establishing a hybrid storage system combining time-series databases and relational databases to enable millisecond-level queries and data traceability.The simulation model development module employs modular design methodology,integrating multi-physics coupling algorithms including computational fluid dynamics(CFD)and thermal circulation equations.Automated parameter calibration is achieved through intelligent optimization algorithms,with model accuracy validated via unitlevel verification,system-level cascaded debugging tests,and virtual test platform simulations.Based on the modular layout strategy,the user interface and interaction module integrates 3D plant panoramic view,dynamic equipment model and multi-mode interaction channel,supports cross-terminal adaptation of PC,mobile terminal and control screen,and improves fault handling efficiency through AR assisted diagnosis function.
基金supported by the National Key Research and Development Program of China(Grant No.2023YFB3307300)the National Natural Science Foundation of China(Grant Nos.62125301,62021003,62373014,92467205)+1 种基金the Beijing Nova Program(Grant No.20240484694)the Beijing Youth Scholar(Grant No.037)。
文摘Fault diagnosis techniques,which are crucial in the field of industrial intelligent manufacturing,are capable of equipment performance maintenance and productivity improvement.In fault diagnosis,multi-type sensors are commonly used for monitoring because a single data source fails to provide sufficient information to support the comprehensive analysis and accurate diagnosis.Hidden information between modes can be mined using data fusion techniques,enabling more effective decision-making and condition analysis.However,the data measured by multiple sensors are subject to issues such as varying types,an imbalanced ratio of positive to negative samples,and significant differences in data structure,making multi-source data fusion and inter-feature information acquisition challenging.To address these problems,we propose a fault diagnosis method based on dynamic convolution and polarized self-attention(DC-PSA)feature fusion networks.Given that unimodal features are not utilized comprehensively enough,we propose a dynamic convolution-based feature self-convergence model.The ability of the model is improved by attentively aggregating multiple convolution kernels,which are combined in a form dynamically adjusted according to different inputs to fully utilize the features.To enable effective feature-level integration across modalities,we establish a cross-attention-based multimodal fusion model,where each modal branch learns multiscale spatial information independently and forms cross-channel interactions in a localized manner,which can realize the information interactions between local and global channel attention.Empirical results on the Paderborn benchmark dataset validate that the proposed method captures the complementary characteristics across signal types more effectively than existing methods,leading to a notable boost in diagnostic accuracy following the fusion process.The accuracy of the proposed model reached 98.6%,representing an improvement of 8.74%compared to the baseline model.
