Fault detection and diagnosis are essential to the air conditioning system of the data center for elevating reliability and reducing energy consumption.This study proposed a convolutional neural network(CNN)based data...Fault detection and diagnosis are essential to the air conditioning system of the data center for elevating reliability and reducing energy consumption.This study proposed a convolutional neural network(CNN)based data-driven fault detection and diagnosis model considering temporal dependency for composite air conditioning system that is capable of cooling the high heat flux in data centers.The input of fault detection and diagnosis model was an unsteady dataset generated by the experimentally validated transient mathematical model.The dataset concerned three typical faults,including refrigerant leakage,evaporator fan breakdown,and condenser fouling.Then,the CNN model was trained to construct a map between the input and system operating conditions.Further,the performance of the CNN model was validated by comparing it with the support vector machine and the neural network.Finally,the score-weighted class mapping activation method was utilized to interpret model diagnosis mechanisms and to identify key input features in various operating modes.The results demonstrated in the pump-driven heat pipe mode,the accuracy of the CNN model was 99.14%,increasing by around 8.5%compared with the other two methods.In the vapor compression mode,the accuracy of the CNN model achieved 99.9%and declined the miss rate of refrigerant leakage by at least 61%comparatively.The score-weighted class mapping activation results indicated the ambient temperature and the actuator-related parameters,such as compressor frequency in vapor compression mode and condenser fan frequency in pump-driven heat pipe mode,were essential features in system fault detection and diagnosis.展开更多
Hybrid excitation synchronous motor has the advantages of uniform and adjustable electromagnetic field, wide speed range and high power density. It has broad application prospects in new energy electric vehicles, wind...Hybrid excitation synchronous motor has the advantages of uniform and adjustable electromagnetic field, wide speed range and high power density. It has broad application prospects in new energy electric vehicles, wind power generation and other fields. This paper introduces the basic structure of hybrid excitation motor with modular stator, and analyzes the operation principle of hybrid excitation motor. The cooling structure of the water-cooled plate is designed, and the effects of the thickness of the water-cooled plate and the number of water channels in the water-cooled plate on the heat dissipation capacity of the water-cooled plate are analyzed by theoretical and computational fluid dynamics methods. The effects of different water cooling plate structures on water velocity, pressure drop, water pump power consumption and heat dissipation capacity were compared and analyzed. The influence of different inlet flow velocity on the maximum temperature rise of each part of the motor is analyzed, and the temperature of each part of the motor under the optimal water flow is analyzed. The influence of the traditional spiral water jacket cooling structure and the water-cooled plate cooling structure on the maximum temperature rise of the motor components is compared and analyzed. The results show that the water-cooled plate cooling structure is more suitable for the modular stator motor studied in this paper. Based on the water-cooled plate cooling structure, the air-water composite cooling structure is designed, and the effects of the air-water composite cooling structure and the water-cooled plate cooling structure on the maximum temperature rise of each component of the motor are compared and analyzed. The results show that the maximum temperature rise of each component of the motor is reduced under the air-water composite cooling structure.展开更多
Smog chambers are the effective tools for studying formation mechanisms of air pollution.Simulations by traditional smog chambers differ to a large extent from real atmospheric conditions,including light,temperature a...Smog chambers are the effective tools for studying formation mechanisms of air pollution.Simulations by traditional smog chambers differ to a large extent from real atmospheric conditions,including light,temperature and atmospheric composition.However,the existing parameters for mechanism interpretation are derived from the traditional smog chambers.To address the gap between the traditional laboratory simulations and the photochemistry in the real atmosphere,a vehicle-mounted indoor-outdoor dual-smog chamber(JNUVMDSC)was developed,which can be quickly transferred to the desired sites to simulate quasi-realistic atmosphere simultaneously in both chambers using“local air”.Multiple key parameters of the smog chamber were characterized in the study,demonstrating that JNUVMDSC meets the requirements of general atmospheric chemistry simulation studies.Additionally,the preliminary results for the photochemical simulations of quasi-realistic atmospheres in Pearl River Delta region and Nanling Mountains are consistent with literature reports on the photochemistry in this region.JNU-VMDSC provides a convenient and reliable experimental device and means to study the mechanism of atmospheric photochemical reactions to obtain near-real results,and will make a great contribution to the control of composite air pollution.展开更多
基金the support from the National Natural Science Foundation of China(Grant number 52176180)the support from“the open competition mechanism to select the best candidates”key technology project of Liaoning(Grant 2022JH1/10800008).
文摘Fault detection and diagnosis are essential to the air conditioning system of the data center for elevating reliability and reducing energy consumption.This study proposed a convolutional neural network(CNN)based data-driven fault detection and diagnosis model considering temporal dependency for composite air conditioning system that is capable of cooling the high heat flux in data centers.The input of fault detection and diagnosis model was an unsteady dataset generated by the experimentally validated transient mathematical model.The dataset concerned three typical faults,including refrigerant leakage,evaporator fan breakdown,and condenser fouling.Then,the CNN model was trained to construct a map between the input and system operating conditions.Further,the performance of the CNN model was validated by comparing it with the support vector machine and the neural network.Finally,the score-weighted class mapping activation method was utilized to interpret model diagnosis mechanisms and to identify key input features in various operating modes.The results demonstrated in the pump-driven heat pipe mode,the accuracy of the CNN model was 99.14%,increasing by around 8.5%compared with the other two methods.In the vapor compression mode,the accuracy of the CNN model achieved 99.9%and declined the miss rate of refrigerant leakage by at least 61%comparatively.The score-weighted class mapping activation results indicated the ambient temperature and the actuator-related parameters,such as compressor frequency in vapor compression mode and condenser fan frequency in pump-driven heat pipe mode,were essential features in system fault detection and diagnosis.
基金supported by the National Natural Science Foundation of China (51907129)Project Supported by Department of Science and Technology of Liaoning Province (2021-MS-236)。
文摘Hybrid excitation synchronous motor has the advantages of uniform and adjustable electromagnetic field, wide speed range and high power density. It has broad application prospects in new energy electric vehicles, wind power generation and other fields. This paper introduces the basic structure of hybrid excitation motor with modular stator, and analyzes the operation principle of hybrid excitation motor. The cooling structure of the water-cooled plate is designed, and the effects of the thickness of the water-cooled plate and the number of water channels in the water-cooled plate on the heat dissipation capacity of the water-cooled plate are analyzed by theoretical and computational fluid dynamics methods. The effects of different water cooling plate structures on water velocity, pressure drop, water pump power consumption and heat dissipation capacity were compared and analyzed. The influence of different inlet flow velocity on the maximum temperature rise of each part of the motor is analyzed, and the temperature of each part of the motor under the optimal water flow is analyzed. The influence of the traditional spiral water jacket cooling structure and the water-cooled plate cooling structure on the maximum temperature rise of the motor components is compared and analyzed. The results show that the water-cooled plate cooling structure is more suitable for the modular stator motor studied in this paper. Based on the water-cooled plate cooling structure, the air-water composite cooling structure is designed, and the effects of the air-water composite cooling structure and the water-cooled plate cooling structure on the maximum temperature rise of each component of the motor are compared and analyzed. The results show that the maximum temperature rise of each component of the motor is reduced under the air-water composite cooling structure.
基金supported by the National Natural Science Foundation of China(NSFC)(Nos.41877370 and 42077190)the China Postdoctoral Science Foundation(No.2021M691229)+2 种基金the fund of Creative Research Groups of NSFC(No.42121004)the Science and Technology Planning Project of Guangdong Province of China(No.2019B121202002)the Guangdong Innovative and Entrepreneurial Research Team Program(No.2016ZT06N263).
文摘Smog chambers are the effective tools for studying formation mechanisms of air pollution.Simulations by traditional smog chambers differ to a large extent from real atmospheric conditions,including light,temperature and atmospheric composition.However,the existing parameters for mechanism interpretation are derived from the traditional smog chambers.To address the gap between the traditional laboratory simulations and the photochemistry in the real atmosphere,a vehicle-mounted indoor-outdoor dual-smog chamber(JNUVMDSC)was developed,which can be quickly transferred to the desired sites to simulate quasi-realistic atmosphere simultaneously in both chambers using“local air”.Multiple key parameters of the smog chamber were characterized in the study,demonstrating that JNUVMDSC meets the requirements of general atmospheric chemistry simulation studies.Additionally,the preliminary results for the photochemical simulations of quasi-realistic atmospheres in Pearl River Delta region and Nanling Mountains are consistent with literature reports on the photochemistry in this region.JNU-VMDSC provides a convenient and reliable experimental device and means to study the mechanism of atmospheric photochemical reactions to obtain near-real results,and will make a great contribution to the control of composite air pollution.
