In this paper,models to predict hot spot temperature and to estimate cooling air’s working parameters of racks in data centers were established using machine learning algorithms based on simulation data.First,simulat...In this paper,models to predict hot spot temperature and to estimate cooling air’s working parameters of racks in data centers were established using machine learning algorithms based on simulation data.First,simulation models of typical racks were established in computational fluid dynamics(CFD).The model was validated with field test results and results in literature,error of which was less than 3%.Then,the CFD model was used to simulate thermal environments of a typical rack considering different factors,such as servers’power,which is from 3.3 kW to 20.1 kW,cooling air’s inlet velocity,which is from 1.0 m/s to 3.0 m/s,and cooling air’s inlet temperature,which is from 16℃ to 26℃ The highest temperature in the rack,also called hot spot temperature,was selected for each case.Next,a prediction model of hot spot temperature was built using machine learning algorithms,with servers’power,cooling air’s inlet velocity and cooling air’s inlet temperature as inputs,and the hot spot temperatures as outputs.Finally,based on the prediction model,an operating parameters estimation model was established to recommend cooling air’s inlet temperatures and velocities,which can not only keep the hot spot temperature at the safety value,but are also energy saving.展开更多
Based on the analysis of heat radiation intensity from flame, a new mathematical model ofthe tube-wall temperatmp of heated tubes is developed by taking down-fired, upright-tube cylindricalfurnace for example. The pro...Based on the analysis of heat radiation intensity from flame, a new mathematical model ofthe tube-wall temperatmp of heated tubes is developed by taking down-fired, upright-tube cylindricalfurnace for example. The proposed mathematical model can be employed to indicate both the positionand size of the hot spot at fire-facing wall of heated tube of combustion chamber, and is characteristicof simplicity and efficiency If coupled with thermoelectric couple or infrared viewer, the presentedlocation method of combustion hot spot can offer engineers very valuable proposal to keep furnacerunning more safely The same is true for any other type of tubular furnaces.展开更多
热点温度是影响金属化薄膜电容器(metallized film capacitors,MFC)绝缘寿命的重要因素之一,但由于其无法直接测量,因此通常采用热仿真分析或温度反演的方法获得。该文提出了基于共轭梯度法(conjugategradient method,CG)的热点温度反...热点温度是影响金属化薄膜电容器(metallized film capacitors,MFC)绝缘寿命的重要因素之一,但由于其无法直接测量,因此通常采用热仿真分析或温度反演的方法获得。该文提出了基于共轭梯度法(conjugategradient method,CG)的热点温度反演模型,建立了内部传热过程的温度分布目标函数,采用有限差分法求解电容器温度场,再通过CG对内部温度分布进行迭代求解。同时,通过交流温升试验校核了仿真模型以及反演模型。研究结果表明:热点温升与表面温升存在线性关系,热点温度出现在MFC中央靠近芯轴处,反演模型与仿真模型最大误差为4.35%,说明该模型可实现现场工况下的温度分布、热点分布等的有效预测。展开更多
基金The authors appreciate support of the project from China Electronics Engineering Design Institute CO.,LTD.(No.SDIC2021-08)from the Beijing Natural Science Foundation(No.4212040).
文摘In this paper,models to predict hot spot temperature and to estimate cooling air’s working parameters of racks in data centers were established using machine learning algorithms based on simulation data.First,simulation models of typical racks were established in computational fluid dynamics(CFD).The model was validated with field test results and results in literature,error of which was less than 3%.Then,the CFD model was used to simulate thermal environments of a typical rack considering different factors,such as servers’power,which is from 3.3 kW to 20.1 kW,cooling air’s inlet velocity,which is from 1.0 m/s to 3.0 m/s,and cooling air’s inlet temperature,which is from 16℃ to 26℃ The highest temperature in the rack,also called hot spot temperature,was selected for each case.Next,a prediction model of hot spot temperature was built using machine learning algorithms,with servers’power,cooling air’s inlet velocity and cooling air’s inlet temperature as inputs,and the hot spot temperatures as outputs.Finally,based on the prediction model,an operating parameters estimation model was established to recommend cooling air’s inlet temperatures and velocities,which can not only keep the hot spot temperature at the safety value,but are also energy saving.
基金This project is supported by National Natural Science Foundation of China(No.50175081).
文摘Based on the analysis of heat radiation intensity from flame, a new mathematical model ofthe tube-wall temperatmp of heated tubes is developed by taking down-fired, upright-tube cylindricalfurnace for example. The proposed mathematical model can be employed to indicate both the positionand size of the hot spot at fire-facing wall of heated tube of combustion chamber, and is characteristicof simplicity and efficiency If coupled with thermoelectric couple or infrared viewer, the presentedlocation method of combustion hot spot can offer engineers very valuable proposal to keep furnacerunning more safely The same is true for any other type of tubular furnaces.
文摘热点温度是影响金属化薄膜电容器(metallized film capacitors,MFC)绝缘寿命的重要因素之一,但由于其无法直接测量,因此通常采用热仿真分析或温度反演的方法获得。该文提出了基于共轭梯度法(conjugategradient method,CG)的热点温度反演模型,建立了内部传热过程的温度分布目标函数,采用有限差分法求解电容器温度场,再通过CG对内部温度分布进行迭代求解。同时,通过交流温升试验校核了仿真模型以及反演模型。研究结果表明:热点温升与表面温升存在线性关系,热点温度出现在MFC中央靠近芯轴处,反演模型与仿真模型最大误差为4.35%,说明该模型可实现现场工况下的温度分布、热点分布等的有效预测。
