针对多型传感器采样频率不统一,现有机器学习算法难以有效处理混频数据输入,无法充分挖掘混频信号中的设备故障特征的问题,首先提出一种混频数据输入下的长短时记忆网络(multi-frequency long and short term memory network,MF-LSTM)架...针对多型传感器采样频率不统一,现有机器学习算法难以有效处理混频数据输入,无法充分挖掘混频信号中的设备故障特征的问题,首先提出一种混频数据输入下的长短时记忆网络(multi-frequency long and short term memory network,MF-LSTM)架构;然后,对不同采样频率的状态数据分别进行特征提取并进行特征融合,实现混频数据输入下的电气设备的故障诊断任务;最后,利用凯斯西储大学轴承数据集对所提模型进行了算例验证,结果表明:相比于单频信号输入,混频输入平均提高故障诊断精度1.72%。该实验结果证明了所提出的基于MF-LSTM的故障诊断框架的有效性和混频数据输入的必要性。展开更多
In the microalgae harvesting process,which includes a step for dewatering the algal suspension,directly reusing extracted water in situ would decrease the freshwater footprint of cultivation systems.Among various alga...In the microalgae harvesting process,which includes a step for dewatering the algal suspension,directly reusing extracted water in situ would decrease the freshwater footprint of cultivation systems.Among various algae harvesting techniques,membrane-based filtration has shown numerous advantages.This study evaluated the reuse of permeate streams derived from Scenedesmus obliquus(S.obliquus)biomass filtration under bench-scale and pilot-scale conditions.In particular,this study identified a series of challenges and mechanisms that influence the water reuse potential and the robustness of the membrane harvesting system.In a preliminary phase of this investigation,the health status of the initial biomass was found to have important implications for the harvesting performance and quality of the permeate stream to be reused;healthy biomass ensured better dewatering performance(i.e.,higher water fluxes)and higher quality of the permeate water streams.A series of bench-scale filtration experiments with different combinations of cross-flow velocity and pressure values were performed to identify the operative conditions that would maximize water productivity.The selected conditions,2.4 m·s^(-1)and 1.4 bar(1 bar=105 Pa),respectively,were then applied to drive pilot-scale microfiltration tests to reuse the collected permeate as a new cultivation medium for S.obliquus growth in a pilot-scale photobioreactor.The investigation revealed key differences between the behavior of the membrane systems at the two scales(bench and pilot).It indicated the potential for beneficial reuse of the permeate stream as the pilot-scale experiments ensured high harvesting performance and growth rates of biomass in permeate water that were highly similar to those recorded in the ideal cultivation medium.Finally,different nutrient reintegration protocols were investigated,revealing that both macro-and micro-nutrient levels are critical for the success of the reuse approach.展开更多
针对当前大多数无中心多频时分多址(Multi Frequency Time Division Multiple Access,MF-TDMA)卫星通信系统资源分配中资源利用率低、业务匹配率低的问题,提出了一种无中心MF-TDMA卫星通信系统的帧结构及其组网和资源按需分配方法,并通...针对当前大多数无中心多频时分多址(Multi Frequency Time Division Multiple Access,MF-TDMA)卫星通信系统资源分配中资源利用率低、业务匹配率低的问题,提出了一种无中心MF-TDMA卫星通信系统的帧结构及其组网和资源按需分配方法,并通过仿真分析将其与传统资源调控算法进行比较。无中心MF-TDMA资源按需分配算法通过提高时隙资源的利用率,相比传统资源调控算法在业务匹配度、业务呼通率等参数上有明显改善。仿真结果表明,所提的资源按需分配算法能够更大程度满足动态变化的卫星通信业务的需要。展开更多
Microfiltration membrane technology has been widely used in various industries for solid-liquid separation. However, pore clogging remains a persistent challenge. This study employs (CFD) and discrete element method (...Microfiltration membrane technology has been widely used in various industries for solid-liquid separation. However, pore clogging remains a persistent challenge. This study employs (CFD) and discrete element method (DEM) models to enhance our understanding of microfiltration membrane clogging. The models were validated by comparing them to experimental data, demonstrating reasonable consistency. Subsequently, a parametric study was conducted on a cross-flow model, exploring the influence of key parameters on clogging. Findings show that clogging is a complex phenomenon affected by various factors. The mean inlet velocity and transmembrane flux were found to directly impact clogging, while the confinement ratio and cosine of the membrane pore entrance angle had an inverse relationship with it. Two clog types were identified: internal (inside the pore) and external (arching at the pore entrance), with the confinement ratio determining the type. This study introduced a dimensionless number as a quantitative clogging indicator based on transmembrane flux, Reynolds number, filtration time, entrance angle cosine, and confinement ratio. While this hypothesis held true in simulations, future studies should explore variations in clogging indicators, and improved modeling of clogging characteristics. Calibration between numerical and physical times and consideration of particle volume fraction will enhance understanding.展开更多
文摘针对多型传感器采样频率不统一,现有机器学习算法难以有效处理混频数据输入,无法充分挖掘混频信号中的设备故障特征的问题,首先提出一种混频数据输入下的长短时记忆网络(multi-frequency long and short term memory network,MF-LSTM)架构;然后,对不同采样频率的状态数据分别进行特征提取并进行特征融合,实现混频数据输入下的电气设备的故障诊断任务;最后,利用凯斯西储大学轴承数据集对所提模型进行了算例验证,结果表明:相比于单频信号输入,混频输入平均提高故障诊断精度1.72%。该实验结果证明了所提出的基于MF-LSTM的故障诊断框架的有效性和混频数据输入的必要性。
基金supported by the Politecnico di Torino and the CleanWaterCenter@PoliTo(58_DIM20TIRALB,58_DIM22TIRALB,and 01_TRIN_CI_CWC).
文摘In the microalgae harvesting process,which includes a step for dewatering the algal suspension,directly reusing extracted water in situ would decrease the freshwater footprint of cultivation systems.Among various algae harvesting techniques,membrane-based filtration has shown numerous advantages.This study evaluated the reuse of permeate streams derived from Scenedesmus obliquus(S.obliquus)biomass filtration under bench-scale and pilot-scale conditions.In particular,this study identified a series of challenges and mechanisms that influence the water reuse potential and the robustness of the membrane harvesting system.In a preliminary phase of this investigation,the health status of the initial biomass was found to have important implications for the harvesting performance and quality of the permeate stream to be reused;healthy biomass ensured better dewatering performance(i.e.,higher water fluxes)and higher quality of the permeate water streams.A series of bench-scale filtration experiments with different combinations of cross-flow velocity and pressure values were performed to identify the operative conditions that would maximize water productivity.The selected conditions,2.4 m·s^(-1)and 1.4 bar(1 bar=105 Pa),respectively,were then applied to drive pilot-scale microfiltration tests to reuse the collected permeate as a new cultivation medium for S.obliquus growth in a pilot-scale photobioreactor.The investigation revealed key differences between the behavior of the membrane systems at the two scales(bench and pilot).It indicated the potential for beneficial reuse of the permeate stream as the pilot-scale experiments ensured high harvesting performance and growth rates of biomass in permeate water that were highly similar to those recorded in the ideal cultivation medium.Finally,different nutrient reintegration protocols were investigated,revealing that both macro-and micro-nutrient levels are critical for the success of the reuse approach.
文摘针对当前大多数无中心多频时分多址(Multi Frequency Time Division Multiple Access,MF-TDMA)卫星通信系统资源分配中资源利用率低、业务匹配率低的问题,提出了一种无中心MF-TDMA卫星通信系统的帧结构及其组网和资源按需分配方法,并通过仿真分析将其与传统资源调控算法进行比较。无中心MF-TDMA资源按需分配算法通过提高时隙资源的利用率,相比传统资源调控算法在业务匹配度、业务呼通率等参数上有明显改善。仿真结果表明,所提的资源按需分配算法能够更大程度满足动态变化的卫星通信业务的需要。
文摘Microfiltration membrane technology has been widely used in various industries for solid-liquid separation. However, pore clogging remains a persistent challenge. This study employs (CFD) and discrete element method (DEM) models to enhance our understanding of microfiltration membrane clogging. The models were validated by comparing them to experimental data, demonstrating reasonable consistency. Subsequently, a parametric study was conducted on a cross-flow model, exploring the influence of key parameters on clogging. Findings show that clogging is a complex phenomenon affected by various factors. The mean inlet velocity and transmembrane flux were found to directly impact clogging, while the confinement ratio and cosine of the membrane pore entrance angle had an inverse relationship with it. Two clog types were identified: internal (inside the pore) and external (arching at the pore entrance), with the confinement ratio determining the type. This study introduced a dimensionless number as a quantitative clogging indicator based on transmembrane flux, Reynolds number, filtration time, entrance angle cosine, and confinement ratio. While this hypothesis held true in simulations, future studies should explore variations in clogging indicators, and improved modeling of clogging characteristics. Calibration between numerical and physical times and consideration of particle volume fraction will enhance understanding.
