We explore the feasibility of H I galaxy redshift surveys with the Five-hundred-meter Aperture Spherical Telescope(FAST) and its proposed Core Array interferometry.Using semi-analytical simulations,we compare the perf...We explore the feasibility of H I galaxy redshift surveys with the Five-hundred-meter Aperture Spherical Telescope(FAST) and its proposed Core Array interferometry.Using semi-analytical simulations,we compare the performance of the FAST single-dish and Core Array modes in drift scan (DS) and on-the-fly (OTF) observations across different redshifts.Our results show that the FAST single-dish mode enables significant H I detections at low redshifts (z■0.35) but is limited at higher redshifts due to shot noise.The Core Array interferometry,with higher sensitivity and angular resolution,provides robust H I galaxy detections up to z~1,maintaining a sufficient number density for power spectrum measurements and BAO constraints.At low redshifts (z~0.01–0.08),both configurations perform well,though cosmic variance dominates uncertainties.At higher redshifts (z>0.35),the Core Array outperforms the single-dish mode,while increasing the survey area has little impact on single-dish observations due to shot noise limitations.The DS mode efficiently covers large sky areas but is constrained by Earth’s rotation,whereas the OTF mode allows more flexible deep-field surveys at the cost of operational overhead.Our findings highlight the importance of optimizing survey strategies to maximize FAST’s potential for H I cosmology.The Core Array is particularly well-suited for high-redshift H I galaxy surveys,enabling precise constraints on large-scale structure and dark energy.展开更多
Due to the fast-modeling speed and high accuracy,deep learning has attracted great interest in the field of fault diagnosis in building energy systems in recent years.However,the black-box nature makes deep learning m...Due to the fast-modeling speed and high accuracy,deep learning has attracted great interest in the field of fault diagnosis in building energy systems in recent years.However,the black-box nature makes deep learning models generally difficult to interpret.In order to compensate for the poor interpretability of deep learning models,this study proposed a fault diagnosis method based on interpretable graph neural network(GNN)suitable for building energy systems.The method is developed by following three main steps:(1)selecting NC-GNN as a fault diagnosis model for building energy systems and proposing a graph generation method applicable to the model,(2)developing an interpretation method based on InputXGradient for the NC-GNN,which is capable of outputting the importance of the node features and automatically locating the fault related features,(3)visualizing the results of model interpretation and validating by matching with expert knowledge and maintenance experience.Validation was performed using the public ASHRAE RP-1043 chiller fault data.The diagnosis results show that the proposed method has a diagnosis accuracy of over 96%.The interpretation results show that the method is capable of explaining the decision-making process of the model by identifying fault-discriminative features.For almost all seven faults,their fault-discriminative features were correctly identified.展开更多
The available modelling data shortage issue makes it difficult to guarantee the performance of data-driven building energy prediction(BEP)models for both the newly built buildings and existing information-poor buildin...The available modelling data shortage issue makes it difficult to guarantee the performance of data-driven building energy prediction(BEP)models for both the newly built buildings and existing information-poor buildings.Both knowledge transfer learning(KTL)and data incremental learning(DIL)can address the data shortage issue of such buildings.For new building scenarios with continuous data accumulation,the performance of BEP models has not been fully investigated considering the data accumulation dynamics.DIL,which can learn dynamic features from accumulated data adapting to the developing trend of new building time-series data and extend BEP model's knowledge,has been rarely studied.Previous studies have shown that the performance of KTL models trained with fixed data can be further improved in scenarios with dynamically changing data.Hence,this study proposes an improved transfer learning cross-BEP strategy continuously updated using the coarse data incremental(CDI)manner.The hybrid KTL-DIL strategy(LSTM-DANN-CDI)uses domain adversarial neural network(DANN)for KLT and long short-term memory(LSTM)as the Baseline BEP model.Performance evaluation is conducted to systematically qualify the effectiveness and applicability of KTL and improved KTL-DIL.Real-world data from six-type 36 buildings of six types are adopted to evaluate the performance of KTL and KTL-DIL in data-driven BEP tasks considering factors like the model increment time interval,the available target and source building data volumes.Compared with LSTM,results indicate that KTL(LSTM-DANN)and the proposed KTL-DIL(LSTM-DANN-CDI)can significantly improve the BEP performance for new buildings with limited data.Compared with the pure KTL strategy LSTM-DANN,the improved KTL-DIL strategy LSTM-DANN-CDI has better prediction performance with an average performance improvement ratio of 60%.展开更多
Deep learning(DL),especially convolutional neural networks(CNNs),has been widely applied in air handling unit(AHU)fault diagnosis(FD).However,its application faces two major challenges.Firstly,the accessibility of ope...Deep learning(DL),especially convolutional neural networks(CNNs),has been widely applied in air handling unit(AHU)fault diagnosis(FD).However,its application faces two major challenges.Firstly,the accessibility of operational state variables for AHU systems is limited in practical,and the effectiveness and applicability of existing DL methods for diagnosis require further validation.Secondly,the interpretability performance of DL models under various information scenarios needs further exploration.To address these challenges,this study utilized publicly available ASHRAE RP-1312 AHU fault data and employed CNNs to construct three FD models under three various information scenarios.Furthermore,the layer-wise relevance propagation(LRP)method was used to interpret and explain the effects of these three various information scenarios on the CNN models.An R-threshold was proposed to systematically differentiate diagnostic criteria,which further elucidates the intrinsic reasons behind correct and incorrect decisions made by the models.The results showed that the CNN-based diagnostic models demonstrated good applicability under the three various information scenarios,with an average diagnostic accuracy of 98.55%.The LRP method provided good interpretation and explanation for understanding the decision mechanism of CNN models for the unlimited information scenarios.For the very limited information scenario,since the variables are restricted,although LRP can reveal key variables in the model’s decision-making process,these key variables have certain limitations in terms of data and physical explanations for further improving the model’s interpretation.Finally,an in-depth analysis of model parameters—such as the number of convolutional layers,learning rate,βparameters,and training set size—was conducted to examine their impact on the interpretative results.This study contributes to clarifying the effects of various information scenarios on the diagnostic performance and interpretability of LRP-based CNN models for AHU FD,which helps provide improved reliability of DL models in practical applications.展开更多
基金the support of the National SKA Program of China (Nos.2022SKA0110200 and 2022SKA0110203)the National Natural Science Foundation of China (NSFC,Nos.12473091 and 12473001),and 111 Project (No.B16009)the support of the Fundamental Research Funds for the Central Universities (No.N2405008)。
文摘We explore the feasibility of H I galaxy redshift surveys with the Five-hundred-meter Aperture Spherical Telescope(FAST) and its proposed Core Array interferometry.Using semi-analytical simulations,we compare the performance of the FAST single-dish and Core Array modes in drift scan (DS) and on-the-fly (OTF) observations across different redshifts.Our results show that the FAST single-dish mode enables significant H I detections at low redshifts (z■0.35) but is limited at higher redshifts due to shot noise.The Core Array interferometry,with higher sensitivity and angular resolution,provides robust H I galaxy detections up to z~1,maintaining a sufficient number density for power spectrum measurements and BAO constraints.At low redshifts (z~0.01–0.08),both configurations perform well,though cosmic variance dominates uncertainties.At higher redshifts (z>0.35),the Core Array outperforms the single-dish mode,while increasing the survey area has little impact on single-dish observations due to shot noise limitations.The DS mode efficiently covers large sky areas but is constrained by Earth’s rotation,whereas the OTF mode allows more flexible deep-field surveys at the cost of operational overhead.Our findings highlight the importance of optimizing survey strategies to maximize FAST’s potential for H I cosmology.The Core Array is particularly well-suited for high-redshift H I galaxy surveys,enabling precise constraints on large-scale structure and dark energy.
基金supported by the Opening Fund of Key Laboratory of Low-grade Energy Utilization Technologies and Systems(Chongqing University),Ministry of Education of China(LLEUTS202305)the National Natural Science Foundation of China(51906181)+4 种基金the Opening Fund of State Key Laboratory of Green Building in Western China(LSKF202316)the open Foundation of Anhui Province Key Laboratory of Intelligent Building and Building Energy-saving(IBES2022KF11)“The 14th Five Year Plan”Hubei Provincial advantaged characteristic disciplines(groups)project of Wuhan University of Science and Technology(2023D0504)the Wuhan University of Science and Technology Postgraduate Innovation and Entrepreneurship Fund(JCX2022016)the 2021 Construction Technology Plan Project of Hubei Province(2021-83).
文摘Due to the fast-modeling speed and high accuracy,deep learning has attracted great interest in the field of fault diagnosis in building energy systems in recent years.However,the black-box nature makes deep learning models generally difficult to interpret.In order to compensate for the poor interpretability of deep learning models,this study proposed a fault diagnosis method based on interpretable graph neural network(GNN)suitable for building energy systems.The method is developed by following three main steps:(1)selecting NC-GNN as a fault diagnosis model for building energy systems and proposing a graph generation method applicable to the model,(2)developing an interpretation method based on InputXGradient for the NC-GNN,which is capable of outputting the importance of the node features and automatically locating the fault related features,(3)visualizing the results of model interpretation and validating by matching with expert knowledge and maintenance experience.Validation was performed using the public ASHRAE RP-1043 chiller fault data.The diagnosis results show that the proposed method has a diagnosis accuracy of over 96%.The interpretation results show that the method is capable of explaining the decision-making process of the model by identifying fault-discriminative features.For almost all seven faults,their fault-discriminative features were correctly identified.
基金jointly supported by the Opening Fund of Key Laboratory of Low-grade Energy Utilization Technologies and Systems of Ministry of Education of China(Chongqing University)(LLEUTS-202305)the Opening Fund of State Key Laboratory of Green Building in Western China(LSKF202316)+4 种基金the open Foundation of Anhui Province Key Laboratory of Intelligent Building and Building Energy-saving(IBES2022KF11)“The 14th Five-Year Plan”Hubei Provincial advantaged characteristic disciplines(groups)project of Wuhan University of Science and Technology(2023D0504,2023D0501)the National Natural Science Foundation of China(51906181)the 2021 Construction Technology Plan Project of Hubei Province(2021-83)the Science and Technology Project of Guizhou Province:Integrated Support of Guizhou[2023]General 393.
文摘The available modelling data shortage issue makes it difficult to guarantee the performance of data-driven building energy prediction(BEP)models for both the newly built buildings and existing information-poor buildings.Both knowledge transfer learning(KTL)and data incremental learning(DIL)can address the data shortage issue of such buildings.For new building scenarios with continuous data accumulation,the performance of BEP models has not been fully investigated considering the data accumulation dynamics.DIL,which can learn dynamic features from accumulated data adapting to the developing trend of new building time-series data and extend BEP model's knowledge,has been rarely studied.Previous studies have shown that the performance of KTL models trained with fixed data can be further improved in scenarios with dynamically changing data.Hence,this study proposes an improved transfer learning cross-BEP strategy continuously updated using the coarse data incremental(CDI)manner.The hybrid KTL-DIL strategy(LSTM-DANN-CDI)uses domain adversarial neural network(DANN)for KLT and long short-term memory(LSTM)as the Baseline BEP model.Performance evaluation is conducted to systematically qualify the effectiveness and applicability of KTL and improved KTL-DIL.Real-world data from six-type 36 buildings of six types are adopted to evaluate the performance of KTL and KTL-DIL in data-driven BEP tasks considering factors like the model increment time interval,the available target and source building data volumes.Compared with LSTM,results indicate that KTL(LSTM-DANN)and the proposed KTL-DIL(LSTM-DANN-CDI)can significantly improve the BEP performance for new buildings with limited data.Compared with the pure KTL strategy LSTM-DANN,the improved KTL-DIL strategy LSTM-DANN-CDI has better prediction performance with an average performance improvement ratio of 60%.
基金supported by the Opening Fund of Key Laboratory of Low-grade Energy Utilization Technologies and Systems of Ministry of Education of China(Chongqing University)(No.LLEUTS-202305)the National Natural Science Foundation of China(No.51906181)+4 种基金the Youth Innovation Technology Project of Higher School in Shandong Province(No.2022KJ204)“The 14th Five Year Plan”Hubei Provincial advantaged characteristic disciplines(groups)project of Wuhan University of Science and Technology(No.2023D0504,No.2023D0501)the Opening Fund of State Key Laboratory of Green Building in Western China(No.LSKF202316)Hubei Undergraduate Training Program for Innovation and Entrepreneurship(No.S202210488076)the Wuhan University of Science and Technology Postgraduate Innovation and Entrepreneurship Fund(JCX2023026).
文摘Deep learning(DL),especially convolutional neural networks(CNNs),has been widely applied in air handling unit(AHU)fault diagnosis(FD).However,its application faces two major challenges.Firstly,the accessibility of operational state variables for AHU systems is limited in practical,and the effectiveness and applicability of existing DL methods for diagnosis require further validation.Secondly,the interpretability performance of DL models under various information scenarios needs further exploration.To address these challenges,this study utilized publicly available ASHRAE RP-1312 AHU fault data and employed CNNs to construct three FD models under three various information scenarios.Furthermore,the layer-wise relevance propagation(LRP)method was used to interpret and explain the effects of these three various information scenarios on the CNN models.An R-threshold was proposed to systematically differentiate diagnostic criteria,which further elucidates the intrinsic reasons behind correct and incorrect decisions made by the models.The results showed that the CNN-based diagnostic models demonstrated good applicability under the three various information scenarios,with an average diagnostic accuracy of 98.55%.The LRP method provided good interpretation and explanation for understanding the decision mechanism of CNN models for the unlimited information scenarios.For the very limited information scenario,since the variables are restricted,although LRP can reveal key variables in the model’s decision-making process,these key variables have certain limitations in terms of data and physical explanations for further improving the model’s interpretation.Finally,an in-depth analysis of model parameters—such as the number of convolutional layers,learning rate,βparameters,and training set size—was conducted to examine their impact on the interpretative results.This study contributes to clarifying the effects of various information scenarios on the diagnostic performance and interpretability of LRP-based CNN models for AHU FD,which helps provide improved reliability of DL models in practical applications.
