Table of Content

10 April 2020, Volume 31 Issue 07

Previous Issue    Next Issue

Technology and Application of Data-driven Intelligent Services for Complex Products

LI Hao, WANG Haoqi, CHENG Ying, TAO Fei, HAO Bing, WANG Xinchang, JI Yangjian, SONG Wenyan, DU Wenliao, WEN Xiaoyu, GONG Xiaoyun, LI Ke, ZHANG Yingfeng, LUO Guofu, LI Qifeng

2020, 31(07):  757-772. 

Asbtract ( )   HTML   PDF (31391KB) ( )  

References | Related Articles | Metrics

With the applications of sensors, data acquisition devices and other modules with sensing ability in the service operation stages of complex products, the operation and maintenance system of complex products was becoming more and more digital and intelligent. Data with real-time, multi-source, heterogeneous, and massive characteristics were become the basis of decision making to improve the reliability and low cost operation for complex product systems, especially the DT technology provided an effective way. Thus, the research progress of data-driven intelligent service for complex products was introduced. The characteristics and framework mode of data-driven intelligent services were analyzed herein, and data-driven intelligent service approaches for complex products were proposed, which included service-oriented complex product modeling and simulation methods, accurate analysis and prediction method for data-driven service demand acquisition, equipment fault identification and dynamic performance prediction based on DT, data-driven multi-objective decision-making optimization method for equipment condition-based maintenance and spare parts inventory, assisted maintenance technology for complex products based on DT, precise analysis and prediction method for energy efficiency of complex equipment based on multi-element cooperation, and optimal control method for complex product operation based on data mining. The application case of intelligent service system was given. The proposed framework and approach may provide reference for the intelligent transformation and upgrading of modern manufacturing services.

Implementation of Intelligent Decision Cloud Service for Camshaft Grinding Processes

LIU Tao, DENG Zhaohui, GE Zhiguang, LYU Lishu, LIU Wei, PENG Keli

2020, 31(07):  773-780. 

Asbtract ( )   HTML   PDF (8900KB) ( )  

References | Related Articles | Metrics

Cloud service mode of intelligent decision in the camshaft grinding processes was established on the basis of analyses of characteristics in camshaft grinding processes and needs of intelligent decision-making under the cloud manufacturing mode. The overall framework of software for intelligent decision of the camshaft grinding processes was designed. Then the process intelligent decision-making software was developed, which included modules such as foundation integrated database, process knowledge base, process definition and decision-making optimization. Finally, the cloud service platform of intelligent decision for camshaft grinding processes was built and example verification was carried out，which realizes the cooperative development with intelligent decision and process data, a new way and the implementation approach are offered for efficient grinding processes of camshafts.

Multi-parameter Fusion Similarity-based Method for Remaining Useful Life Predicition of Civil Aviation Engines

CAO Huiling, CUI Kelu, LIANG Jiawang

2020, 31(07):  781-787. 

Asbtract ( )   HTML   PDF (2398KB) ( )  

References | Related Articles | Metrics

Aiming at the problems that single parameter monitoring was not comprehensive and multi-monitoring parameter utilization rate was low in the research of civil aviation engine life prediction, a life prediction method was proposed based on multi-parameter fusion. In order to correct the parameter sensitivity, the ReliefF-PCA algorithm was used to screen the attributes of various monitoring parameters of the engine and to fuse them into the parameter-health index representing the engine health states. According to the different recession stages of the engine, the trend sensitivity of the similarity measurement algorithm was modified to increase the influence of the change trend on the prediction results. The effects of time domain on the algorithm were reduced by the translation of sample trajectory. Finally, the validity of the proposed method was verified by comparing the actual data. The results show that the improved method has better prediction accuracy.

Interactive Cloud Manufacturing Mode for Mass Personalization

LI Qiang, RU Ke, LIU Jiliang, ZHANG Ke

2020, 31(07):  788-796. 

Asbtract ( )   HTML   PDF (1180KB) ( )  

References | Related Articles | Metrics

Combined with the characteristics of cloud manufacturing and mass personalization, mass personalized application development and analysis of the current status of user needs were analyzed, an interactive cloud mode for mass personalization was proposed. The mass personalized intelligent interaction process and the demand interaction transformation process model were designed in the cloud environment; mass personalized interactive cloud architecture and workflow were established. Intelligent interactive cloud platform was built to realize the personalized, large-scale, low-cost rapid provision and production of customized requirements. Finally, car customization was used as an example, demand analysis and transformation processes were discussed, the feasibility and effectiveness of this platform were verified.

Digital Twin: Recent Development and Future Trend from Bibliometrics Perspective

CHEN Yong, CHEN Yi, PEI Zhi, WANG Cheng

2020, 31(07):  797-807. 

Asbtract ( )   HTML   PDF (6756KB) ( )  

References | Related Articles | Metrics

With the rapid development of internet of things, cloud computing and machine learning, digital twin technology gradually became one of the most important technologies in the 21st century. By means of bibliometrics, the research fields, countries/regions, journals, keywords, research authors, and highly cited papers of 486 digitally twin related papers retrieved were analyzed in detail.The results show that as a new research topic, digital twin has strong excavation ability and has been widely used in many fields such as manufacturing engineering, computer science and electronic engineering. Driven by the rigid demands of intelligent manufacturing, digital twin technology possesses a very good theoretical research and technological application prospects in the future.

Production Management and Control Method of Aerospace Manufacturing Workshops Based on Digital Twin

GUO Jutao, HONG Haibo, ZHONG Keke, LIU Xiaojia, GUO Yu

2020, 31(07):  808-814. 

Asbtract ( )   HTML   PDF (14323KB) ( )  

References | Related Articles | Metrics

To solve the problems of low efficiency, poor precision and insufficient dynamic response ability in the production management of aerospace manufacturing workshops, a production and control management and control method of manufacturing workshops was carried out based on digital twin theory herein. An aerospace digital twin workshop architecture was designed based on asynchronous interaction of cross-network information. Besides, the basic composition of aerospace digital twin workshops was proposed as well as the hierarchical management mode of virtual-real fusion manufacturing workshops. Moreover, the applications of manufacturing intelligence(MI) and business intelligence(BI) were discussed, which were suitable for different objects. The restuls provide a feasible technical way for workshop production management and control in military enterprises.

Health Prediction of Shearers Driven by Digital Twin and Deep Learning

DING Hua, YANG Liangliang, YANG Zhaojian, WANG Yiliang,

2020, 31(07):  815-823. 

Asbtract ( )   HTML   PDF (15334KB) ( )  

References | Related Articles | Metrics

In view of the difficult problems of condition monitoring and maintenance of shearers in poor working environment, combined with the high-fidelity behavior simulation characteristics of digital twin and the powerful data mining ability of deep learning,a prediction method of shearer health status driven by the fusion of digital twin and deep learning was proposed. The digital twin of shearers was constructed based on multi-physical parameters of physical space, and the health state early prognosis of shearers was realized by visual display and analysis in virtual space. A prediction model of RUL of shearer key parts was established based on deep learning, and the online RUL prediction of parts driven by real-time monitoring data was realized. The prediction of shearer health was obtained based on the status of digital twin and the value of RUL. Finally, the effectiveness of the method was verified by experiments, which provides a new idea for the monitoring and management of the health status of the shearers.

Evolution and Operation Mechanism of Digital Twin Shopfloors

JIANG Haifan, DING Guofu, ZHANG Jian

2020, 31(07):  824-832,841. 

Asbtract ( )   HTML   PDF (6330KB) ( )  

References | Related Articles | Metrics

The evolution mechanism of the DTSs was not clear, resulting in a lack of technology roadmap for DTS in the manufacturing fields. To fill this gap, firstly the existing problems and challenges in production shopfloors were analyzed in the view of the role and relationship of information flow, material flow and control flow. Then, after summarizing the research status of digital twin, the method how to construct an interactive, controllable and computable virtual workshop was proposed from three dimensions namely visualization, logic and data. Further,evolution mechanism from virtual shopfloors to digital model shopfloors, digital shadow shopfloors and DTSs was explored. Finally, the DTS was realized from digital, intelligent and smart stages, and the operation mechanism and enabling technologies of each stage were expounded, which provides reference for the promotion and applications of DTS in the manufacturing fields.

Digital Twin-driven Aero-engine Assembly Technology

SUN Huibin, YAN Jianxing, WEI Xiaohong, CHANG Zhiyong,

2020, 31(07):  833-841. 

Asbtract ( )   HTML   PDF (10186KB) ( )  

References | Related Articles | Metrics

In order to implement the interaction and fusion between virtual models and physical states, a digital twin-driven aero-engine assembly technology was investigated herein. The composition, structure, function and procedure were addressed. Key enabling technologies, including assembly procedure control, part selection and matching, assembly operation guide, assembly clearance control, configuration control, and correlation analysis of assembly data and test driving data were studied in detail. The work was believed to improve intelligence, activeness, predictability of assembly procedure control and configuration control and also to support decision-making and optimization based on physical states. The assembly efficiency, normalization, successful assembly ratio, and quality consistency may be improved. The work provides a theoretical and technical reference for research and development of digital twin-driven aero-engine assembly technology.

Patent Data-driven Product Innovative Design Based on Complex Network

LIN Wenguang, LAI Rongshen, XIAO Renbin

2020, 31(07):  842-852. 

Asbtract ( )   HTML   PDF (6018KB) ( )  

References | Related Articles | Metrics

For solving the problems of patent aided product design, a method of patent data-driven product innovative design was proposed based on complex network. Complex network was constructed by patent classification number of patents, and nodes of network were ranked by degree centrality, then key functions of the nodes were founded. Behavior knowledge was discovered from text and figures of key node patents, and mapped with function knowledge by morphological matrix. By using apriori algorithm of frequent subgraph, behavior portfolio with minimum support value computed was choose as priority development alternative, and the patents' structured knowledge was extracted, and utilized to generate shower components network for analysis of patent technology. Key components were found by structure hole from network and used to make innovative design. Lastly, a novel mixture shower with adjustment function was designed to verify the effectiveness and feasibility of the method.

Conceptual Scheme Construction of Smart PSS Based on Functional Model and AHP

WU Chunlong, ZHU Tianming, ZHANG Peng, SUN Jianguang, TAN Runhua,

2020, 31(07):  853-864,870. 

Asbtract ( )   HTML   PDF (5844KB) ( )  

References | Related Articles | Metrics

To study the conceptual scheme construction of smart PSS and solve the complex characteristics and functional coupling characteristics of the system,the two instruments TRIZ function model and AHP were applied.In the conceptual design phase, TRIZ function model was used to qualitative analysis on the model.With the aid of AHP, different service function modules provided by the service providers for decision analysis were analyzed quantitatively by preferential integration related function module, and the construction of smart PSS conceptual scheme was formed. Finally, the validity of the method was verified by taking the service function module construction of three service providers as an example.

Data-driven Multi-attribute Optimization Decision-making for Complex Product Design Schemes

WU Yangdong, ZHANG Taihua, LIU Dan, WANG Yiquan

2020, 31(07):  865-870. 

Asbtract ( )   HTML   PDF (642KB) ( )  

References | Related Articles | Metrics

At present, the quality of product design scheme mainly depended on the experiences and levels of designers, to solve this problem, a data-driven multi-attribute decision-making method for product design schemes was proposed, which might be applied to the evaluation of the best program at all stages of product design. Each group of reviewers used the TOPSIS method to evaluate the scheme, for the weight of decision criteria, the entropy weight method was used to determine the weights, the Borda function method was applied to assemble the decisions of each group, the final decision results were obtained, and the comprehensive evaluations of the design scheme were completed. This method was more fully used for data, avoiding subjectivity to the greatest extent, and the evaluation results were more reasonable. Finally, the method was applied to the design of oilfield polymer injection devices, and the opinions of designers, processors and managers are gathered to provide more comprehensive optimization decision results.

Product Design Requirement Information Visualization Approach for Intelligent Manufacturing Services

LI Xiaoying, ZHOU Datao

2020, 31(07):  871-881. 

Asbtract ( )   HTML   PDF (1046KB) ( )  

References | Related Articles | Metrics

From the perspective of intelligent manufacturing services, a design requirement visualization method was constructed to achieve a comprehensive, accurate, efficient and clear expression of design requirement informations. Firstly, the relevant platforms of the status of the competition informations, user feedback informations and other research object data text were captured by the web crawler tools. Secondly, the design requirement data were reprocessed and features were extracted by natural language processing technology to obtain the encoded text data. Thirdly, the text data were coded and analyzed by means of co-occurrence matrix, cluster graph and strategic coordinate graph to realize the visual expression of product design requirement informations, and to calculate the requirement weights with qualitative adjustment function. In order to verify the feasibility and validity of the method, the analysis of competitive status informations, a type of grain combine harvester was taken as an example.