|
|
The Standard Model of Human-machine Cooperative Operation Function in Intelligent Manufacturing |
Liu Zeshuang1,Han Jin 1,Wang Yifan2 |
(1.School of Economics and Management, Xi'an University of Technology, Xi'an 710054, China;2.School of Economics and Management, Shihezi University, Shihezi 832003, China) |
|
|
Abstract As the Industry 4.0 strategy advances, its initiatives are gradually changing production and operations management systems. The way people interact with technology needs to be improved in order to achieve the transformation to a smart factory. Artificial intelligence technology will be a key factor in smart manufacturing, not only because it expands the scope of manufacturing subjects and optimizes smart production processes, but also changes the human-computer collaboration model. However, there is a lack of theoretical analysis on the systematization of human-computer collaboration under the influence of intelligent manufacturing and related processing ideas of intelligent human-computer collaboration, which requires further consideration to supplement the theories related to human-machine relationship, as well as improve the standard and runtime functional framework of human-computer collaboration under intelligent manufacturing to maintain the smooth operation of intelligent human-machine collaboration.#br#Although some results have been achieved in the technical research on human-machine collaborative task planning, most scholars at home and abroad are mainly concerned with the impact of the overall development of AI technology as an antecedent variable on society, enterprises and individuals, and seldom explore the collaborative innovation synergy formed by both parties from the perspective of intelligent machines or human-machine interaction.There is a lack of a theoretical system on the criteria for the application of AI to human-computer collaboration. Only a qualitative and descriptive outlook is available, and a modeling of the human-machine task system as an object, process and as a whole is missing, because the complexity of task activities increases with the flexibility of human participation in the system and machine performance, and the intricate relationships between the standard dimensions of human-machine collaborative operational functions embedded in it require a modeling approach that can deal with the complexity of the system, for these reasons this study proposes the use of OPM to build the model.#br#Given the requirements of human-machine relationship and the definition of the content involved in the intelligent manufacturing system in the national intelligent manufacturing standard system construction guidelines, this study designs an interview outline and selects 14 middle and senior managers who have been working for many years in large and medium-sized manufacturing enterprises that are undergoing digital intelligent transformation. Combined with the specifications of assisted robots issued by the International Organization for Standardization, this study obtains 130 000 words of primary data and collects secondary data 200 000 words as triangular test through the authoritative way. The specific content includes initial, focus, axis, theoretical coding, saturation test five links, and the supplementary interviews and literature are takenas a saturation test and expert discussion is held to develop the scale items, the grassroots, middle and senior managers of intelligent manufacturing. Intelligent manufacturing link enterprises were selected as the respondents, and a large-sample questionnaire was issued. Then the test is conducted based on the large-sample data to obtain a reliable human-computer collaboration operation function standard measurement scale with 21 items, and the content structure of the human-computer collaboration operation function standard is formed, namely the six core dimensions of flexibility, predictability, repeatability, extensibility, elasticity, and multi-role, respectively. They are the core dimensions of the human-computer collaborative operation function criteria measurement scale. Only when such criteria are met can the advantages of human-computer collaboration be maximized and the companies achieve maximum performance improvement.#br#This paper uses the object process methodology for modeling human-machine collaboration criteria, unifies static and dynamic models based on the aforementioned conceptual model of human-machine collaboration operational functional criteria to propose an overall conceptual model that can be dynamically extrapolated based on the logical relationships between subcategories. Then it performs dynamic feasibility analysis of the conceptual model functional operation in OPCAT software. The model is used to measure and correlate the level of human capabilities and machine assistance and cooperation, and determine the degree of human-machine complementarity in performing a given task. It provides a possible way to view the whole process of "design-improvement-optimization" to achieve the human-machine collaboration standard. According to the OPD diagram, the functional characteristics can be dynamically adjusted according to the actual behavior of a pair of workers and robots to achieve the optimal allocation of human resources in smart manufacturing enterprises. This study not only provides a reliable measurement tool for subsequent research, but also expands a new perspective of human-computer collaboration theory whichapplicable in actual manufacturing enterprise management cases.#br#
|
Received: 17 January 2022
|
|
|
|
|
[1] SPRINGER GABLER PREIS.Einführung und umsetzung von Industrie 4.0: grundlagen, vorgehensmodell und use cases aus der praxis[M]. Berlin:Springer-Verlag, 2016.[2] EVANS P C, ANNUNZIATA M. Industrial internet: pushing the boundaries of minds and machines[R]. Boston:General Electric, 2012.[3] 王亮.人工代理的道德责任何以可能——基于“道德问责”和“虚拟责任”的反思[J].大连理工大学学报(社会科学版),2022,43(1):113-120.[4] 何勤,董晓雨,朱晓妹.人工智能引发劳动关系变革:系统重构与治理框架[J].中国人力资源开发,2022,39(1):134-148.[5] 李茹,赵曙明.数字经济背景下人与环境匹配的新变化及应对策略[J].南京社会科学,2021,32(9):37-44.[6] 宋旭光,左马华青.智能制造时代需要怎样的技能人才[J].东北大学学报(社会科学版),2022,24(1):16-24.[7] 黄思翰,王柏村,张美迪,等.面向人本智造的新一代操作工:参考架构、使能技术与典型场景[J/OL].机械工程学报,[2022-03-11].https://kns.cnki.net/kns8/defaultresult/index.[8] 刘大卫.人工智能背景下人力资源雇佣关系重构及社会影响分析[J].云南社会科学,2020,40(1):47-52.[9] 王柏村,薛塬,延建林,等.以人为本的智能制造:理念、技术与应用[J].中国工程科学,2020,22(4):139-146.[10] 许为,葛列众,高在峰.人~AI交互:实现“以人为中心AI”理念的跨学科新领域[J].智能系统学报,2021,16(4):605-621.[11] 周世军,赵丹丹.人工智能重塑就业的未来趋势、特征及对策[J].经济体制改革,2022,40(1):188-194.[12] 胡晟明,王林辉,赵贺.人工智能应用、人机协作与劳动生产率[J].中国人口科学,2021,35(5):48-62,127.[13] 朱晓妹,王森,何勤.人工智能嵌入视域下岗位技能要求对员工工作旺盛感的影响研究[J].外国经济与管理,2021,43(11):15-25.[14] 张劲松,武红阵.人工智能嵌入人类生活的风险及其防控[J].苏州大学学报(哲学社会科学版),2021,42(5):26-33.[15] 程承坪.人工智能:工具或主体——兼论人工智能奇点[J].上海师范大学学报(哲学社会科学版),2021,50(6):5-12.[16] PREZ L, RODRGUEZ-JIMNEZ S, RODRGUEZ N, et al. Symbiotic human-robot collaborative approach for increased productivity and enhanced safety in the aerospace manufacturing industry[J]. The International Journal of Advanced Manufacturing Technology, 2020, 106(3): 851-863.[17] ROMERO D, STAHRE J, WUEST T, et al. Towards an operator 4.0 typology: a human-centric perspective on the fourth industrial revolution technologies[C]//Proceedings of the International Conference on Computers and Industrial Engineering (CIE46).Tianjin, China,2016: 29-31.[18] ROMERO D,BERNUS P,NORAN O,et al. The operator 4.0:human cyber-physical systems & adaptive automation towards human-automationsymbiosis work systems[C]// IFIP International Conference on Advances in Production Management Systems. Cham:Springer,2016:677-686.[19] JIN M. Data-efficient analytics for optimal human-cyber-physical systems[D].Berkeley:University of California,2017.[20] LV Q, ZHANG R, SUN X, et al. A digital twin-driven human-robot collaborative assembly approach in the wake of COVID-19[J]. Journal of Manufacturing Systems, 2021, 60: 837-851.[21] MCCAFFREY T,SPECTOR L.An approach to human-machine collaboration in innovation[J]. Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 2018, 32(1):1-15.[22] 李慧,李贵卿.人工智能时代人机协作工作模型构建研究[J].现代管理,2020,10(3):360-367.[23] YILMA B A,PANETTO H, NAUDET Y.A meta-model of cyber-physical-social system: the cpss paradigm to support human-machine collaboration in industry 4.0[C]//Working Conference on Virtual Enterprises.Cham:Springer, 2019: 11-20.[24] HAESEVOETS TESSA, DE CREMER DAVID,DIERCKX KIM,et al.Human-machine collaboration in managerial decision making[J].Computers in Human Behavior,2021,119:106730.[25] ZANCHETTIN A M,CASALINO A,PIRODDI L,et al. Prediction of human activity patterns for human-robot collaborative assembly tasks[J]. IEEE Transactions on Industrial Informatics, 2018, 15(7): 3934-3942. [26] MICHALOS G, MAKRIS S,SPILIOTOPOULOS J, et al. ROBO-PARTNER: seamless human-robot cooperation for intelligent, flexible and safe operations in the assembly factories of the future[J]. Procedia CIRP, 2014, 23:71-76.[27] TAKATA S,HIRANO T.Human and robot allocation method for hybrid assembly systems[J].CIRP Annals, 2011,60(1):9-12.[28] TSAROUCHI P, MICHALOS G, MAKRIS S, et al. On a human-robot workplace design and task allocation system[J]. International Journal of Computer Integrated Manufacturing, 2017, 30(12): 1272-1279.[29] REIMANN J, SZIEBIG G.The intelligent factory space:a concept for observing, learning and communicating in the digitalized factory[J]. IEEE Access, 2019, 7:70891-70900.[30] 董豪,杨静,李少波,等.基于深度强化学习的机器人运动控制研究进展[J].控制与决策,2022,37(2):278-292.[31] WANG J, CAO J, STOJMENOVIC M, et al. Pattern-rl: multi-robot cooperative pattern formation via deep reinforcement learning[C]//2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). IEEE, 2019: 210-215.[32] CHUNG J. Playing atari with deep reinforcement learning[J]. Comput. Ence, 2013, 21: 351-362.[33] MOUSSA M A. Combining expert neural networks using reinforcement feedback for learning primitive grasping behavior[J]. IEEE Transactions on Neural Networks,2004, 15(3): 629-638.[34] LENAT D B, BROWN J S. Why AM and EURISKO appear to work[J]. Artificial Intelligence, 1984, 23(3): 269-294.[35] RITCHIE G D, HANNA F K. AM: a case study in AI methodology[J]. Artificial Intelligence, 1984, 23(3): 249-268.[36] MCCAFFREY T. Innovation relies on the obscure: a key to overcoming the classic problem of functional fixedness[J]. Psychological Science, 2012, 23(3): 215-218.[37] DING N, FANG Z, DUAN L, et al. Incentive mechanism design for distributed coded machine learning[C]//2021-IEEE Conference on Computer Communications. IEEE,2021: 1-10.[38] TEIXEIRA J V S, REIS A M, MENDES F B, et al. Collaborative robots[M]//Occupational and Environmental Safety and Health. Cham:Springer, 2019: 791-796.[39] JULIET CORBIN,ANSELM STRAUSS. Basics of qualitative research: techniques and procedures for developing grounded theory[M]. Sage Publications, Inc, 2007.[40] MORDECAI Y, DORI D. Model-based operational-functional unified specification for mission systems[C]//2016 Annual IEEE Systems Conference (SysCon). IEEE, 2016: 1-8. |
|
|
|