Table of Content

28 October 2023, Volume 57 Issue 10 Previous Issue    Next Issue

Chemistry and Chemical Engineering

Select

Application of Machine Learning in Chemical Synthesis and Characterization SUN Jie, LI Zihao, ZHANG Shuyu 2023, 57 (10):  1231-1244.  doi: 10.16183/j.cnki.jsjtu.2023.078 Abstract ( 648 )   HTML ( 55 )   PDF (4421KB) ( 539 )   Save Automated chemical synthesis is one of the long-term goals pursued in the field of chemistry. In recent years, the advent of machine learning (ML) has made it possible to achieve this goal. Data-driven ML uses computers to learn relative information in massive chemical data, find objective connections between information, train models by using objective connections, and analyze the actual problems which can be solved according to these models. With its excellent computational prediction capabilities, ML helps chemists solve chemical synthesis problems quickly and efficiently and accelerate the research process. The emergence and development of ML has shown a strong research assistance in the field of chemical synthesis and characterization. However, there is no highly versatile ML model at present, and chemists still need to choose different models for training and learning according to actual situations. This paper aims to show chemists the best cases of common learning methods in chemical synthesis and characterization from the perspective of ML, such as supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, etc., and help them use ML knowledge to further broaden their research ideas. Figures and Tables | References | Related Articles | Metrics

Select

Nickel-Catalyzed Cyanation of Aryl Triflates Using Acetonitrile as a Cyano Source ZHOU Kun, SHEN Zengming 2023, 57 (10):  1245-1249.  doi: 10.16183/j.cnki.jsjtu.2022.108 Abstract ( 270 )   HTML ( 24 )   PDF (954KB) ( 192 )   Save In classic cyanation reactions, toxic metal cyanide sources or complex organic cyanide sources are often used. Therefore, it is particularly important to develop a green and economical cyano source. Initially, 4-biphenylyl trifluoromethanesulfonate is chosen as the model substrate. Through extensive screening of catalysts, ligands, additives, reductant, temperature and other conditions, the optimal conditions are obtained (Ni(OTf)2, 1, 3-bis (diphenyphosphino)propane, Zn(OTf)2, Zn with a mole fraction of 0.1, 0.1, 0.2, 2, respectively, 0.7 mL CH3CN, N2, 60 h, 100 ℃). Subsequently, the generation and limitations of the substrates are studied under optimal conditions. It is found that substrates bearing electron-donating substituents exhibit an excellent efficiency for the cyanation of aryl trifluoromethanesulfonates. The cyanation of aryl trifluoromethanesulfonates is first realized under the catalysis of nickel with acetonitrile as a green and economical cyano source. Figures and Tables | References | Related Articles | Metrics

Transportation Engineering

Select

An Evaluation Method for Link Importance Based on Seismic Resilience of Road Network CHEN Yiqin, HUANG Shuping 2023, 57 (10):  1250-1260.  doi: 10.16183/j.cnki.jsjtu.2022.359 Abstract ( 226 )   HTML ( 11 )   PDF (1958KB) ( 149 )   Save The evalution of link resilience importance is essential for improving the seismic resilience level of the road network. Using resilience achievement worth (RAW) as evaluation index, an evaluation method of link importance based on seismic resilience of road networks was proposed. With the help of the bidirectional inference ability of dynamic Bayesian network (DBN), taking the initial DBN as the benchmark and the link connectivity at different times as the evidence, the resilience curve of the road network was updated, the RAW was calculated, and the link resilience importance at different times was evaluated. Taking the local road network in Shinan District of Qingdao as an example, the evaluation method of link importance was verified. The results show that the seismic resilience importance varies with each link at the same time. The resilience importance of the same link is positively correlated with maintenance rate. The resilience importance of different links varies in sensitivity to time. The proposed importance evaluation method redefines and quantifies the seismic resilience importance of links at different times, and identifies the links with high resilience importance and sensitivity to time. The post-earthquake recovery strategy that inclines the limited maintenance resources to these links and the pre-earthquake prevention strategy that reinforces the links with higher resilience importance can more efficiently improve the seismic resilience of the road network. Figures and Tables | References | Related Articles | Metrics

Select

Container Allocation in Multi-Blocks and Optimization of Yard Crane Dispatching in Non-Engagement of Container Delivery Truck FAN Houming, MA Xiaobin, PENG Wenhao, YUE Lijun, MA Mengzhi 2023, 57 (10):  1261-1272.  doi: 10.16183/j.cnki.jsjtu.2022.501 Abstract ( 231 )   HTML ( 9 )   PDF (2356KB) ( 212 )   Save Container collection should be completed within the specified time limit to prevent the arriving ships from being unable to leave the port on schedule. The storage yard should formulate a container allocation plan and yard crane scheduling plan based on the scheduled arrival time of container delivery and loading. Otherwise, the plan will become invalid, which will lead to the problem of container turnover and loading inefficiency. Aimed at the impact of the non-engagement of container delivery and truck collection on the container location allocation plan, yard crane scheduling plan, and the waiting time of the truck, an optimization problem of container location allocation and yard crane scheduling in multi-container areas under non-engagement of container delivery and truck collection is proposed. Considering the constraints such as the booking period of the truck and the safe distance between the two yard cranes, a mixed integer programming model is established with the goal of minimizing the time of port concentration. The hybrid genetic variable neighborhood algorithm is used to solve the model. A comparison of the experimental results of different algorithms indicates that the algorithm in this paper has a fast convergence speed and excellent solution results. Based on the actual arrival time of the container truck, a disturbance recovery strategy is proposed to measure the impact of non-engagement on the completion time and container truck waiting time in different scenarios, an interference recovery strategy is proposed. Experiments show that the interference recovery strategy proposed in this paper not only shortens the job completion time and the number of containers overturned due to box delivery breach, but also reduces the waiting time of container delivery trucks. Figures and Tables | References | Related Articles | Metrics

Select

Vertical Force Estimation of Heavy-Loaded Radial Tire Based on Circumferential Strain Analysis LIU Yixun, LIU Zhihao, GAO Qinhe, HUANG Tong, MA Dong 2023, 57 (10):  1273-1281.  doi: 10.16183/j.cnki.jsjtu.2022.249 Abstract ( 229 )   HTML ( 10 )   PDF (14550KB) ( 155 )   Save In order to realize the quantitative estimation of tire vertical force, the algorithm of heavy-loaded tire vertical force estimation based on circumferential strain analysis is studied. A finite element analysis model of 16.00R20 tire is established. A comparison of tire loading test and modal vibration test indicates that the vertical stiffness error and vibration frequency error of the model are less than 7.79% and 5.49% respectively, which verifies the validity of the model. Using the finite element method, the influence of vertical force on tire grounding characteristics and circumferential strain of inner liner is studied. The characterization index of tire contact angle is proposed and verified by circumferential strain analysis, and the errors of the three indexes are all less than 8%. Taking the grounding angle and grounding length as identification features, the vertical force estimation model is established by combining grey wolf optimization (GWO) and the support vector regression (SVR), and the estimation accuracy is verified by finite element simulation. The results indicate that the characterization index in combination with the of characteristic point spacing angle of zero-order, first-order and second-order derivative of strain curve can accurately estimate tire contact angle. The error between the estimated value of the vertical force estimation algorithm based on GWO-SVR and the finite element simulation value is less than 1.8%. Figures and Tables | References | Related Articles | Metrics

Select

3D Path Planning of UAV Based on Adaptive Slime Mould Algorithm Optimization HUANG He, GAO Yongbo, RU Feng, YANG Lan, WANG Huifeng 2023, 57 (10):  1282-1291.  doi: 10.16183/j.cnki.jsjtu.2022.191 Abstract ( 255 )   HTML ( 10 )   PDF (4295KB) ( 203 )   Save Aimed at the problems of insufficient search range and optimization performance in 3D path planning of unmanned aerial vehicles (UAVs), and the lack of optimization accuracy of the existing slime mould algorithm (SMA), which is easy to fall into local optimization, a 3D path planning method for UAV based on adaptive slime mould algorithm optimization is proposed. First, according to the actual environment that the UAV passes through, the 3D terrain, the threat source and the constraints of the AUV were established. Next, for the problem of insufficient search range, an improved Logistic chaotic map is designed to increase the diversity of the population and expand the search range, which improves the global search ability of SMA. Then, a nonlinear adaptive inertia weight factor is designed to change the linear convergence method into nonlinear convergence, and the weight value is used to update the position of the slime mould, which improves the convergence speed. Finally, in the later stage of the algorithm, the adaptive cauchy mutation is designed, which increases the search space of the slime mould and improves the optimization accuracy. The experimental results show that GSMA has a shorter and smoother path, a faster convergence, a higher optimization accuracy, and a lower energy consumption compared with the gray wolf optimizer (GWO) algorithm, the SMA, and the seagull algorithm (SOA), which further improves the path planning capability of the UAV. Figures and Tables | References | Related Articles | Metrics

Select

Airport Pavement Snow and Ice State Perception Based on Improved YOLOX-s XING Zhiwei, KAN Ben, LIU Zishuo, LI Biao, LUO Qian 2023, 57 (10):  1292-1304.  doi: 10.16183/j.cnki.jsjtu.2022.303 Abstract ( 197 )   HTML ( 10 )   PDF (30812KB) ( 212 )   Save Aimed at the lack of awarness of safety and airworthiness state perception ability of airport ice runway and the new demand of interaction of runway surface condition report, a multi-scale feature fusion based ice and snow state perception model of airport runway is proposed. Based on the YOLOX-s model, first, the global context block (GC block) is introduced into the backbone feature extraction network to obtain more abundant shallow and deep features. Then, the PANet networks in neck are replaced with the bi-directional feature pyramid network (BiFPN) to improve the feature fusion ability. Afterwards, an adaptive spatial feature fusion (ASFF) structure is added to the tail of the enhanced feature extraction network to further enhance the feature fusion effect. Finally, α-EIoU is used to optimize the loss function to improve the convergence speed and accuracy of the model. The experimental results show that the improved YOLOX-s model has an average accuracy of 91.53% in the snow and ice pollutant data set obtained from the runway snow and ice experimental system, which is 4.68% higher than the original YOLOX-s model, and can provide decision-making support for airport runway snow removal operations. Figures and Tables | References | Related Articles | Metrics

Mechanical Engineering

Select

A Forward Development Method for Functional Design of Civil Aircraft Flight Control System CHENG Shuai, LI Chen, ZHANG Yilun, TANG Chao, MENG Xianghui, XIE Youbai 2023, 57 (10):  1305-1315.  doi: 10.16183/j.cnki.jsjtu.2022.100 Abstract ( 286 )   HTML ( 11 )   PDF (2570KB) ( 219 )   Save Functional design is an extremely important part in the design and development of complex systems. It is necessary to establish a forward development method to ensure the correctness and completeness of functional design. Therefore, taking the flight control system of civil aircraft as an example, a forward development method for functional design is proposed. First, system modeling language is used to establish the functional requirements relationship model from aircraft level to system level and then to item level. Then, the functional requirements are combined with the safety requirements in SAE ARP4754A aircraft development guide to construct the functional knowledge set of the flight control system. Finally, the functional model of the flight control system is established based on functional unit block diagram and functional integration block diagram. This method can be used as a reference for the functional design of complex systems. Figures and Tables | References | Related Articles | Metrics

Select

Defect Classification of Weld Metallographic Structure Based on Data Augmentation of Poisson Fusion BAI Xiongfei, GONG Shuicheng, LI Xuesong, XU Bo, YANG Xiaoli, WANG Mingyan 2023, 57 (10):  1316-1328.  doi: 10.16183/j.cnki.jsjtu.2022.202 Abstract ( 354 )   HTML ( 12 )   PDF (10332KB) ( 325 )   Save The classification of the defects in welding applications based on the metallographic structure images plays an important part in industrial welding quality inspections. In order to improve the classification performance of defects in the weld metallographic structure images with a small sample dataset available (the amount of samples being less than 30), a Poisson fusion method is used for data augmentation of the defect images and the ResNet18_PRO network is proposed. Both of the methods notably improve the defects classification performance. During data augmentation, the defect area is extracted from original defect samples via digital image processing, and the defect area is fused with normal samples by the Poisson fusion method to generate new defect samples, thus increasing the number of defect samples. The model in this paper is improved based on the ResNet18 network. The downsampling structure is improved to reduce the information loss in the original downsampling structure, and an improved space pyramid pooling structure is added at the end of the network to integrate multi-scale feature information. The classification performance before and after data augmentation is compared by different classification models, which verifies the significant effect of the data augmentation on the classification performance. Meanwhile, the ablation experiment of the ResNet18_PRO is conducted to verify the effectiveness of the improved network structure and the training strategy. It is found that the average classification accuracy of ResNet18_PRO reaches 98.83% and the average F1-score reaches 98.76%, which greatly improves the classification accuracy of metallographic structure defects. Finally, the network is trained and tested with another industrial defect dataset and obtains good classification results. These results show that the proposed network has a good robustness and practical application value. Figures and Tables | References | Related Articles | Metrics

Select

Numerical Simulation of Stamping-Spinning Hybrid Process for Aluminum Alloy Hemispherical Shells YU Xiaopeng, WANG Zimin, YU Zhongqi, LUO Yimin, YU Li 2023, 57 (10):  1329-1336.  doi: 10.16183/j.cnki.jsjtu.2022.165 Abstract ( 206 )   HTML ( 7 )   PDF (4480KB) ( 359 )   Save Aimed at the poor accuracy in traditional deep drawing of aerospace aluminum alloy hemispherical shells, and by introducing metal spinning, a stamping-spinning hybrid process strategy for aluminum alloy hemispherical shells is proposed, which can achieve the forming processing of the formed component with a high thickness uniformity and high shape accuracy. The finite element simulation model of the hybrid process of the aluminum alloy hemispherical shell is developed, which realizes the simulation. In addition, the variation law of the wall thickness and shape fitting of the hemispherical shells formed by the hybrid process are analyzed. The simulation results show that the uniformity of wall thickness of the hemispherical shells formed by 50% stamping + 50% spinning is significantly improved. The shape accuracy of the component can be obviously improved by changing the stress state of the forming component by power spinning. Meanwhile, the hybrid process is verified by using an aluminum alloy hemispherical shell with a diameter of 1 m in processing test, which improves the thickness uniformity and the shape accuracy of the hemispherical shell. Figures and Tables | References | Related Articles | Metrics

Select

Experiment of Laser Assisted Shear Spinning for Aluminum Alloy Spherical Thin-Walled Parts RAN Jinyu, WANG Fengqi, YU Zhongqi, DU Chenyang, EVSYUKOV S A 2023, 57 (10):  1337-1345.  doi: 10.16183/j.cnki.jsjtu.2022.166 Abstract ( 205 )   HTML ( 4 )   PDF (15100KB) ( 203 )   Save Thermal energy field is the main way to improve the formability and dimensional precision of components in sheet forming. In order to solve the temperature fluctuation of traditional heat sources, a well-controlled laser heat source was introduced into sheet metal shear spinning to improve the spinnability and forming accuracy by matching local deformation with local heating reasonably. Laser-assisted shear spinning facility was built based on the existing spinning machine, and a model of laser irradiation point drift of ellipsoidal components under the rigid connection of laser heat source was established to analyse the optimal region of laser thermal field loading. The theoretical analysis shows that, during laser-assisted spinning, the rigid connection can be deemed as precise heating under the condition of mandrel with small variation of section circle radius. Subsequently, laser-assisted shear spinning tests on the thin-walled aluminum alloy ellipsoidal components were conducted. The results show that, compared with cold spinning, the laser assisted method extends the spinnability of difficult-to-deformation material in shear spinning and significantly improves the precision and thickness of the spun thin-walled components, which verifies the feasibility of the developed test setup and process design method. Figures and Tables | References | Related Articles | Metrics

Select

Abnormal Detection Method of Tool Machining Monitoring Data Based on Self-Paced Learning ZHANG Jian, HU Xiaofeng, ZHANG Yahui 2023, 57 (10):  1346-1354.  doi: 10.16183/j.cnki.jsjtu.2022.234 Abstract ( 308 )   HTML ( 5 )   PDF (2945KB) ( 201 )   Save Aimed at the problem that the accuracy of tool remaining life prediction was reduced due to the abnormal monitoring data in machining process, a data anomaly detection method based on self-paced learning was proposed. First, a multi-layer perceptron model was established to correlate the tool processing monitoring data with the tool remaining life. Next, in the process of updating model weight, the model weight parameters were fixed first, and the loss threshold of abnormal samples was obtained by predicting loss fitting Gaussian distribution. Then, the loss function based on the self-paced learning method was constructed to update model parameters iteratively. At the end of the model training, abnormal samples were divided according to the loss threshold. Finally, the actual processing monitoring data of turbine rotor groove were used to verify the proposed method, and compare with the local anomaly factor algorithm, the density-based clustering algorithm, the K-means algorithm, the isolated forest algorithm, and the one-class support vector machines. Figures and Tables | References | Related Articles | Metrics

Select

Flow Distribution Characteristics in Microchannel Heat Sinks in Pumping Liquid Cooling System XIN Pengfei, MIAO Jianyin, KUANG Yiwu, ZHANG Hongxing, WANG Wen 2023, 57 (10):  1355-1366.  doi: 10.16183/j.cnki.jsjtu.2022.248 Abstract ( 255 )   HTML ( 5 )   PDF (3680KB) ( 276 )   Save With the continuous improvement of pump-driven liquid cooling requirements for electronic devices, the cooling requirements for multiple dispersed units are inevitable, resulting in higher requirements of equal cooling capacity for parallel microchannel evaporators. Because of the existence of negative slope region in the characteristic curve of two phase flow in microchannel sink, the flow excursion will occur. The flow distribution in the parallel microchannel evaporator is simulated with ammonia as the working medium, and the effects of inlet subcooling degree, heat flux and length of connecting pipe on flow characteristic curve in a microchannel evaporator are studied. Besides, the influence of flow excursion on the overall temperature distribution of evaporator, and the influence of heat flux, inlet subcooling degree, and length of connecting pipe on the flow distribution of two parallel evaporators are investigated. The results show that the flow excursion between evaporators does not necessarily deteriorate the heat transfer capacity of the system, and the arrangement of heating flux, inlet and outlet connecting pipes has a great influence on the stability of the parallel evaporator system. Figures and Tables | References | Related Articles | Metrics

Select

Matching Characteristics of Expansion Valve Opening and Flow Rate of High Temperature Heat Pump with Green Refrigerant HP-1 WANG Yuehan, NAN Xiaohong, OUYANG Hongsheng, GUO Zhikai, HU Bin, WANG Ruzhu 2023, 57 (10):  1367-1377.  doi: 10.16183/j.cnki.jsjtu.2022.155 Abstract ( 312 )   HTML ( 11 )   PDF (1421KB) ( 449 )   Save The throttling process, as an important part of the heat pump system, plays a crucial role in the efficient and reliable operation of the whole system. This paper, taking the quasi two-stage compression high-temperature heat pump with green refrigerant HP-1 as the research subject, established the mathematical models of the circulatory system and electronic expansion valve by using MATLAB and considering the influence of the opening of electronic expansion valve and thermodynamic properties of the new green refrigerant. It simulated the matching characteristics of electronic expansion valve opening and flow rate under variable operating conditions, and fitted the HP-1 dimensionless flow coefficient correlation by power-law distribution using experimental data. The research results show that the electronic expansion valve with an elliptical conical body structure adapts to the throttling characteristics of the HP-1 high-temperature heat pump system under variable operating conditions. When the evaporating temperature varies from 50 ℃ to 90 ℃ and the condensing temperature varies from 60 ℃ to 120 ℃, the opening adjustment range of this type of valve body is from 49.8% to 69.8% for the main throttle valve, and from 41.5% to 56.0% for the injection throttle valve. The relative deviation of the fitted correlation results and the actual test data is between -7.8% and +7.5%, and the flow coefficient correlation can accurately predict the flow characteristics of the electronic expansion valve with a similar body structure. The selection of favorable electronic expansion valve matching refrigerant properties and the optimization of the electronic expansion valve control system are essential for the actual operating performance. This study provides a good research foundation for the selection of electronic expansion valves and the optimization of the control system for the HP-1 high temperature heat pump. Figures and Tables | References | Related Articles | Metrics

Select

An Improved Multi-Swarm Migrating Birds Optimization Algorithm for Hybrid Flow Shop Scheduling ZHANG Sujun, YANG Wenqiang, GU Xingsheng 2023, 57 (10):  1378-1388.  doi: 10.16183/j.cnki.jsjtu.2022.242 Abstract ( 223 )   HTML ( 9 )   PDF (1445KB) ( 249 )   Save An improved multi-swarm migrating birds optimization (IMMBO) algorithm is proposed for hybrid flow shop scheduling with sequence-dependent setup times (HFS-SDST), to minimize the total maximum completion time (i.e., makespan). Permutation-based encoding is adopted to substitute the individual. The modified Nawaz-Enscore-Ham (MNEH) algorithm is employed to generate initial population which are assigned to each sub-swarm according to the makespan. For each sub-swarm, the neighborhood individuals of the leader and followers are generated respectively by performing serial and parallel neighborhood strategies. If the follower is better than the leader according to their makespan, they are exchanged to ensure the information interaction of individuals within the sub-swarm. Moreover, the discrete whale optimization strategy is embedded in IMMBO to optimize the leaders of all sub-swarms to enhance the interaction among them. Furthermore, the local search is designed for the optimal individual to further improve the local search ability of the algorithm. Meanwhile, to avoid algorithm premature convergence, the control strategy for population diversification is designed to the leader of each sub-swarm. Finally, based on adjusting the algorithm parameters experimentally, simulation experiments are conducted on four variants of IMMBO to verify the function of each part by testing an adaptation dataset of Ta. Moreover, the IMMBO is compared with three existing algorithms by testing an adaptation dataset of Ta, and the experimental results demonstrate the effectiveness of the IMMBO algorithm to solve the hybrid flow shop scheduling problem. Figures and Tables | References | Related Articles | Metrics