• Issue 3,2020 Table of Contents
    Select All
    Display Type: |
    • >Special Column: National Young Scholar/Local Science Foundation
    • Study on single machine scheduling with time-based maintenance and step-deteriorating jobs

      2020, 41(3):201-209. DOI: 10.7535/hbkd.2020yx03001

      Abstract (905) HTML (0) PDF 1.24 M (872) Comment (0) Favorites

      Abstract:Nowadays, the demand of “personalization” and “multiple varieties and small batch production” in machining is increasing dramatically. The great challenges of scheduling are brought about by the high flexibility of production and the necessity of equipment maintenance, and the scheduling problems are more complex due to the deteriorating effect of the production process. In order to solve the single machine scheduling problem with step-deteriorating jobs and fixed periodic maintenance strategy, the processing time was described by the piecewise linear function. Based on the properties of the periodic maintenance and the flexible periodic maintenance, two scheduling models were established respectively to minimize the tardiness penalties and maintenance cost. According to the numerical experiments and parameter analysis, the key factors and non-key factors of maintenance decision were determined. The result shows that flexible periodic maintenance has no idle time between adjacent batches. The objective function value increases step by step with the increase of ratio, which can realize “adaptive” adjustment of cost and has significant advantages over fixed cycle maintenance. The construction of a joint scheduling model of production and maintenance can realize the comparison of the advantages and disadvantages of maintenance strategies and the joint decision of production and maintenance, and reduce the operating cost of enterprise production and maintenance.

    • Research progress of water strider in bionic characteristic and engineering application

      2020, 41(3):210-217. DOI: 10.7535/hbkd.2020yx03002

      Abstract (1012) HTML (0) PDF 1.63 M (987) Comment (0) Favorites

      Abstract:The water strider is a small insect in lakes, ponds, and wetlands, which can stand stably on water because of the excellent superhydrophobic property of legs that comes from the composite micro-nano structure. This feature has attracted numerous studies and become a research hopspot gradually. Scholars have conducted the investigation on the locomotion characteristic of water strider in order to acquire design inspirations to develop superhydrophobic surface and bionic water strider robots. Starting from the locomotion characteristic of water strider, this paper summarized the testing methods of water strider′s locomotion force, and focused on the development of superhydrophobic surface preparation and water walking or jumping robots in the engineering bionic field. The preparation of superhydrophobic surface should be lucubrated in the aspects of micro-morphological characteristic, preparation process and production cost, and the development of bionic strider robots needs to be considered in terms of the motion, driving mode and supporting characteristic. It will be the main trend in the future to develop superhydrophobic surface with remarkable and lasting efficacy and bionic water strider robots with excellent performance, complete function and highly similar motion characteristic, based on the micro-morphological structure characteristic of water strider leg.

    • >Mechanical, Electronics and Information Science
    • Multi-feature weighted nearest neighbor data association and tracking algorithm based on Kalman filter

      2020, 41(3):218-224. DOI: 10.7535/hbkd.2020yx03003

      Abstract (1076) HTML (0) PDF 1.10 M (592) Comment (0) Favorites

      Abstract:Aiming at the problems of low accuracy and missing association in traditional nearest neighbor data association algorithm , a multi-feature weighted nearest neighbor association algorithm was proposed. A similarity function was defined according to the obstacle data obtained by the intelligent vehicle environment perception system, and a method was proposed to calculate the effective correlation degree based on the life cycle, so as to determine whether the objects are related. Based on Kalman filter, the associated target was updated iteratively to realize the tracking of the target. The tracking trajectory of stationary target, low-speed moving target without interaction and low-speed moving target with interaction were compared through experiments. Experimental results show that compared with the conventional nearest neighbor data association algorithm, the improved algorithm proposed in this paper can realize the accurate and continuous associated tracking of low-speed moving targets, and there will be no the phenomenon of target loss or position mutation. With high effectiveness and practicability, the interaction and occlusion of tracking targets have less effect on the tracking performance. The research results may provide reference for the target tracking design of intelligent vehicles.

    • An online health community user intention identification method based on BERT-BiGRU-Attention

      2020, 41(3):225-232. DOI: 10.7535/hbkd.2020yx03004

      Abstract (1464) HTML (0) PDF 1.13 M (762) Comment (0) Favorites

      Abstract:Aiming at the problem of high cost and low expansibility of traditional user intention recognition, which mainly uses template matching or artificial feature set, a hybrid neural network intention recognition model based on BERT word embedding and BiGRU-Attention was proposed. First, the word embedding pre-trained by BERT was used as the input, and the features of the interrogative sentences were extracted by BiGRU. Then, the attention mechanism was introduced to extract the information of words that have important influence on the meaning of sentences and allocate the corresponding weights, so as to obtain the sentence embedding that integrates the word-level weights and input it into the softmax classifier to realize intention classification. According to the experiment on the crawling corpus, it shows that the performance of BERT-BiGRU-Attention method is better than that of traditional template matching, SVM and lately popular CNN-LSTM deep learning combined model. The proposed method can effectively improve the performance of intention recognition model and the quality of online health information service, which provide technical support for the online health community question answering system.

    • Disambiguation method of name entities embedded in meta-path heterogeneous networks

      2020, 41(3):233-241. DOI: 10.7535/hbkd.2020yx03005

      Abstract (954) HTML (0) PDF 1.46 M (499) Comment (0) Favorites

      Abstract:In order to solve the problem of disambiguation of duplicate authors in large academic databases, a name entity disambiguation model based on meta-path heterogeneous network was proposed. Based on the public data of the large online academic search system DBLP, the author information, title, name of conference journal and other characteristic attributes of academic publications were extracted first. Then the characteristic attribute words generated by the word2vec model tool were embedded into the GRU network for training, so that a PHNet matrix network for random walk operation was constructed to capture the relationship between different types of nodes and finally similar nodes were divided to complete the name disambiguation. The experimental results show that the accuracy of the method is 0.865, the recall rate is 0.792, and the F1 value is 0.815.The meta-path-based heterogeneous network embedding model is superior to the comparison model in terms of accuracy and recall rate. Therefore, the proposed model has a good application prospect in improving the accuracy of disambiguation of large academic databases.

    • Diagnosis of thyroid SPECT image based on ResNet model

      2020, 41(3):242-248. DOI: 10.7535/hbkd.2020yx03006

      Abstract (857) HTML (0) PDF 1.17 M (428) Comment (0) Favorites

      Abstract:In order to reduce the clinical misdiagnosis rate of of thyroid disease by using SPECT images, and improve the accuracy of deep learning algorithm in recognizing the features of cross images in nuclear medical image-assisted diagnosis, a thyroid SPECT image diagnosis method based on ResNet model was proposed. Deep Convolution Generative Adversarial Network (DCGAN) and Super-Resolution Generative Adversarial Network (SRGAN) were used to generate images and improve the resolution to make up for the deficiency of training data. At the same time, xi with the cross-feature image information was added to the residual block output information, and the learning of the cross-feature on the basis of retaining the learned image features, so as to improve the model. As for cross-image features, a cross-training set was proposed to retrain the improved ResNet neural network model that had been trained with a single feature image. The experimental results show that after 100 rounds of iteration, the verification accuracy of the improved residual neural network model trained by the cross-training set is as high as 0963 3, and the verification loss is reduced to 0.118 7, which tends to be stable. The recall rate, precision rate, specificity and F1 score are all above 93.8% in the recognition results. The improved neural network model and the new training method show higher typical symptom recognition rate for thyroid SPECT images than other methods based on convolutional neural network (CNN), and have reference value for clinical image diagnosis.

    • >Chemistry and Chemical Industry
    • Computational study on the control of electron excitation properties of triphenylamine sensitized dye

      2020, 41(3):249-256. DOI: 10.7535/hbkd.2020yx03007

      Abstract (821) HTML (0) PDF 1.16 M (638) Comment (0) Favorites

      Abstract:In order to enforce the electron withdrawn ability of traditional ethylene bond π bridge, focusing on the intramolecular reflux phenomenon in the electron transfer process of the classical D-A-π-A triphenylamine sensitized dye RL1, four different conjugated units, including benzene, thiophene, oxole, and pyridine, were added separately between the additional receptor Benzothiadiazole and π-bridge. Then the control regulation of the excitation property of dye RL1 was investigated based on First Principle Calculation. The results show that Benzothiadiazole could push and pull on the electron as the extra receptor. However, due to the strong electron-withdrawing ability of benzothiadiazole, the electron reflux will happen in the electron transfer process. Compared with dye RL1, the four conjugated units not only weaken the electron-withdrawing ability of benzothiadiazole, but also play a role as an electron donor, so the electron-withdrawing ability of cyanoacetic acid group can be significantly enhanced. So the research result can provide theoretical basis for further improving the photoelectric transformation efficiency of dyes in the design and preparation of dye molecules.

    • >Food Science and Biological Science
    • Advances in microalgae cell wall disruption

      2020, 41(3):257-267. DOI: 10.7535/hbkd.2020yx03008

      Abstract (901) HTML (0) PDF 2.08 M (680) Comment (0) Favorites

      Abstract:Microalgae cultivation shows the advantages of high photosynthesis efficiency, good environmental adaptability, fast growth, high bioproducts productivity and good environmental value, and many valuable products including astaxanthin, lutein, high-unsaturated fatty acids, lipids, etc. can accumulate in microalgae cells, so microalgae has become the focus in scientific research in recent years. Cell disruption is the key and difficult step to extract those products. Starting from discussing the cell wall structural characteristics of three species of microalgae, the current situation, trends in scientific research and technical development of cell disruption strategies including mechanical, wave-based, pyrolysis, chemical and biological methods were discussed and summarized. It is pointed out that practically the combination of chemical and mechanical methods, with chemical procedures as pretreatment and mechanical step as final disruption, can solve cell disruption problems for most microalga, and is a more feasible cell disruption industrialization technology. Prospectively, biological method is feasible economically and theoretically for most microalga because of its low energy cost and mild process conditions, and tends to be a deservable method.

    • >Transportation & Logistics
    • Visual comparative analysis of green logistics research at home and abroad based on knowledge map

      2020, 41(3):268-280. DOI: 10.7535/hbkd.2020yx03009

      Abstract (916) HTML (0) PDF 2.04 M (414) Comment (0) Favorites

      Abstract:In order to explore the focus and direction of green logistics research and providing reference for China′s green logistics research, a comparative analysis of relevant domestic and foreign documents was conducted. Based on 936 domestic and foreign data retrieved from CNKI and Web of Science, the hotspots, evolution paths and cutting-edge technologies of green logistics at home and abroad were analyzed by using the knowledge maps of document co-citation, keyword co-occurrence, clustering, time zone map and mutation words generated by visual software citespaceⅤ. The result shows that the recent and future sustainable hotspots and frontiers in China are in the area of regional green logistics, such as cold chain logistics, tourism logistics, and agricultural product logistics, etc., while foreign countries are specific to supply chains, optimization models, vehicle routes, and fuel consumption. Regarding the research on green logistics, foreign countries focus on innovation and micro level, but domestic studies lay particular emphasis on macro aspects. The research on micro aspects should be strengthened and the process of green logistics should be accelerated by technological innovation in China. The research results are of great significance for analyzing the evolution path of green logistics and the prediction of research frontier, and provide theoretical basis for the follow-up research.

    • >Material Science
    • Effect of pouring method on wear resistance of WCp/Fe composites

      2020, 41(3):281-288. DOI: 10.7535/hbkd.2020yx03010

      Abstract (869) HTML (0) PDF 1.47 M (641) Comment (0) Favorites

      Abstract:In order to find a more suitable wear-resistant material forming method for current industrial applications, WCp/Fe composites were prepared by the lost foam casting process, and the effects of the pouring method on the hardness and wear resistance of composites were studied. The results show that the hardness and wear resistance of the composite samples prepared by top pouring, gap pouring and bottom pouring are improved significantly after adding WC particles of different sizes. Compared with the filling process of top pouring and bottom pouring, the filling process of gap pouring is more stable, the hardness and wear resistance of the samples are higher, and the hardness and wear resistance of the samples increase with the decrease of WC particle size. When the WC particle size is 5.5 μm(2 500 mesh), the hardness reaches HRC 50, and the wear resistance increases by 2.21 times. The changes of hardness and wear resistance of the composite samples prepared by different pouring methods can provide a reference for the industrial production and application of WCp/Fe composites in lost foam casting.

Editor in chief:朱立光


International standard number:ISSN 1008-1542

Unified domestic issue:CN 13-1225/TS

Domestic postal code:

  • Most Read
  • Most Cited
  • Most Downloaded
Press search
Search term
From To