期刊:
Thermal Science and Engineering Progress,2023年44:102070 ISSN:2451-9049
通讯作者:
Yuan, ZP
作者机构:
[Yang, Hanqian; Chen, Zhichao; Yuan, Zhipeng; Ding, Chenyi] Cent South Univ Forestry & Technol, Coll Mech & Elect Engn, Changsha 410004, Peoples R China.;[Xia, Yan] Hunan Prov Inst Prod & Goods Qual Inspect, Changsha 410007, Peoples R China.;[Fu, Jianqin] Hunan Univ, State Key Lab Adv Design & Mfg Vehicle Body, Changsha 410082, Peoples R China.
通讯机构:
[Yuan, ZP ] C;Cent South Univ Forestry & Technol, Coll Mech & Elect Engn, Changsha 410004, Peoples R China.
关键词:
Centrifugal air compressor;Fuel cell;Performance prediction;Backpropagation neural network;Support vector machine;Hybrid model
摘要:
The centrifugal air compressor plays a critical role as a core component in fuel cells, and building an accurate prediction model is essential for evaluating its performance. In this study, three algorithms were used to establish the air compressor performance prediction model based on multiple samples. Through comparing the prediction results, it was found that the backpropagation neural network optimized by genetic algorithm (GA-BP) model fit the real sample data more closely than support vector machine (SVM) and backpropagation neural network (BPNN) models, and could better approximate the performance map of the air compressor. Moreover, a GA-BP-SVM hybrid model was established by combining GA-BP and SVM through the model weighting method, which performed optimally in all performance indexes. This method effectively improves the accuracy of the prediction model and provides a feasible solution for air compressor performance prediction in fuel cell applications.
通讯机构:
[Huang, Dan] D;Department of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China. Electronic address:
关键词:
Far infrared drying;Ultrasonic pretreatment;Ginger slices;Energy consumption;Color change
摘要:
Three drying methods, including far infrared drying, infrared convection drying, and ultrasonic pretreatment assisted far infrared drying, were adopted in the drying of ginger slices. The effects of main parameters (ultrasonic pretreatment power and time, far infrared temperature and power, sample thickness, infrared convection temperature) on the drying kinetics, energy consumption, and color change were investigated and discussed in detail. The results showed that the drying process of ginger slices was controlled by falling rate period. For far infrared drying, the drying rate increased with the increase of infrared temperature and decrease of sample thickness, while the infrared power had no obvious effect on the drying process. The infrared convection drying showed the fastest drying rate and the smallest color change, however, the energy consumption was the highest. For ultrasonic pretreatment assisted far infrared drying, an appropriate ultrasonic pretreatment time and power would promote the far infrared drying process and the energy consumption was only slightly increased. However, the color change was relatively large. The ultrasound technology showed its greatest potential to enhance the drying rate at the early stage of drying and increasing ultrasonic power was more effective than prolonging the pretreatment time in promoting far infrared drying.
摘要:
The classical flexible job shop scheduling problem (FJSP) normally assumes that operations of each job have strict sequence constraints, i.e., each operation can be processed only after its previous operation is completed. However, in the actual production, the phenomenon that some operations of a job don't have any sequence constraints is very common. With regard to this, we firstly propose a FJSP with discrete operation sequence flexibility (FJSPDS) aiming at minimizing the makespan and total energy consumption, simultaneously. An effective mathematical model is established for the FJSPDS and its validity is proved by the CPLEX; and then an improved memetic algorithm (IMA) is designed to solve the FJSPDS. In the IMA, a new flexible sequencing method for determining process plan of each job and a right-leaning decoding method are proposed. And some effective crossover and mutation operators and an effective local search operator are designed to accelerate the convergence speed and expand the solution space of the algorithm. A total of 110 FJSPDS benchmark instances are constructed to conduct numerical simulation experiments. Experimental results show that our proposed IMA has superior performance in almost all of the instances compared with three well-known evolutionary algorithms. Our proposed model and algorithm can help the production managers who work with flexible manufacturing systems to obtain optimal scheduling schemes considering operations which have or don't have sequence constraints.
期刊:
Chemical Engineering Journal,2023年474:145565 ISSN:1385-8947
通讯作者:
Ma, XC;Li, LQ;Su, RK
作者机构:
[Wen, Tao; Huo, Haoling; Ma, Xiancheng; Xu, Wenjun; Yuan, Zhipeng] Cent South Univ Forestry & Technol, Coll Mech & Elect Engn, Changsha 410004, Hunan, Peoples R China.;[Li, LQ; Zeng, Zheng; Li, Liqing] Cent South Univ, Sch Energy Sci & Engn, Changsha 410083, Hunan, Peoples R China.;[Su, Rongkui; Wang, Hanqing] Cent South Univ Forestry & Technol, Coll Environm Sci & Engn, Changsha 410083, Hunan, Peoples R China.;[Huo, Haoling] Jinan Univ, Inst Adv Wear & Corros Resistant & Funct Mat, Guangzhou 510632, Peoples R China.;[Liang, Xin] China Construct Fifth Engn Div Corp Ltd, Changsha 410004, Hunan, Peoples R China.
通讯机构:
[Li, LQ ; Su, RK ; Ma, XC ] C;Cent South Univ Forestry & Technol, Coll Mech & Elect Engn, Changsha 410004, Hunan, Peoples R China.;Cent South Univ, Sch Energy Sci & Engn, Changsha 410083, Hunan, Peoples R China.;Cent South Univ Forestry & Technol, Coll Environm Sci & Engn, Changsha 410083, Hunan, Peoples R China.
关键词:
Porous carbon;Acetone and methanol adsorption;Acetone/methanol selectivity;Pore structure;Oxygen groups
摘要:
Currently, the focus of research on carbon-based materials primarily revolves around studying the adsorption properties of methanol and acetone. However, there is limited research on the adsorption and separation of methanol and acetone azeotropes, and the mechanism is still unclear. Here, the impact of oxygen groups and pore size on the adsorption and separation of acetone and methanol in porous carbon materials was investigated using molecular simulations. The results demonstrated that the adsorption capacity of acetone and methanol is influenced by the micropore structure and oxygen content at relatively low pressures, while at relatively high pressures, the adsorption capacity primarily depends on pore structure. Notably, the micropore structure emerged as a key determinant of acetone/methanol selectivity, while the doping of oxygen groups in porous carbon has a negative impact on selectivity. To validate our theoretical findings, three types of porous carbons with varying oxygen contents and gradient pore size distributions were synthesized. The acetone and methanol adsorption isotherms were measured, and the acetone/methanol selectivity was calculated. Comparative analysis of the impact of pore size and oxygen content on the adsorption and separation performance of acetone and methanol yielded consistent results between experimental and theoretical calculations. These findings elucidate the effects of oxygen content and pore size on the adsorption performance of acetone and methanol adsorption and separation performance from both experimental and theoretical perspectives, providing a basis for further design and development of adsorbents of high-performance volatile organic compounds (VOCs) adsorbents.
作者机构:
[文韬; 李大鹏; 龚中良; 何伟韬; 聂齐毅; 龙江] School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Hu’nan, Changsha, 410004, China
通讯机构:
[Wen, T.] S;School of Mechanical and Electrical Engineering, Hu’nan, China
摘要:
Inverse heat conduction problems (IHCPs) are problems of estimating unknown quantities of interest (QoIs) of the heat conduction with given temperature observations. The challenge of IHCPs is that it is usually ill-posed since the observations are noisy, and the estimations of QoIs are generally not unique or unstable, especially when there are unknown spatially varying QoIs. In this study, an ensemble physics-informed neural network (E-PINN) is proposed to handle function estimation and uncertainty quantification of space-dependent IHCPs. The distinctive characteristics of E-PINN are ensemble learning and adversarial training (AT). Compared with other data-driven UQ approaches, the suggested method is more than straightforward to implement and also achieves high-quality uncertainty estimates of the QoI. Furthermore, an adaptive active sampling (AS) strategy based on the uncertainty estimates from E-PINNs is also proposed to improve the accuracy of material field inversion problems. Finally, the proposed method is validated through several numerical experiments of IHCPs.
期刊:
Expert Systems with Applications,2023年224:119840 ISSN:0957-4174
通讯作者:
Guiliang Gong
作者机构:
[Gong, Guiliang; Li, Xiaoqiang; Zhang, Liqiang; Zhu, Kaikai; Huang, Dan] Cent South Univ Forestry & Technol, Dept Mech & Elect Engn, Changsha 410004, Peoples R China.;[Gong, Guiliang; Luo, Qiang] Hunan Univ, State Key Lab Adv Design & Mfg Vehicle Body, Changsha 410082, Peoples R China.;[Peng, Ningtao] Cent South Univ, Dept Mech & Elect Engn, Changsha 410083, Peoples R China.
通讯机构:
[Guiliang Gong] D;Department of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China<&wdkj&>State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha 410082, China