Cyber-enabled Product Lifecycle Management: A Multi-agent Framework

Abstract Trouble free use of a product and its associated services for a specified minimum period of time is a major factor to win the customer’s trust in the product. Rapid and easy serviceability to maintain its functionalities plays a key role in achieving this goal. However, the sustainability of such a model cannot be promised unless the current health status of the product is monitored and condition-based maintenance is exercised. Internet of Things (IoT), an important connectivity paradigm of recent times, which connects physical objects to the internet for real-time information exchange and execution of physical actions via wired/wireless protocols. While the literature is full of various feasibility and viability studies focusing on architecture, design, and model development aspects, there is limited work addressing an IoT-based health monitoring of systems having high collateral damage. This motivated the research to develop a multi-agent framework for monitoring the performance and predicting impending failure to prevent unscheduled maintenance and downtime over internet, referred to as for cyber-enabled product lifecycle management (C-PLM). The framework incorporates a number of autonomous agents, such as hard agent, soft agent, and wave agent, to establish network connectivity to collect and exchange real-time health information for prognostics and health management (PHM). The proposed framework will help manufacturers not only to resolve the warranty failure issues more efficiently and economically but also improve their corporate image. The framework further leads to efficient handling of warranty failure issues and reduces the chances of future failure, i.e., offering durable products. From the sustainability point of view, this framework also addresses the reusability of the parts that still have a significant value using the prognostics and health data. Finally, multi-agent implementation of the proposed approach using a power substations for IoT-based C-PLM is included to show is efficacy.

[1]  Rong Li,et al.  Residual-life distributions from component degradation signals: A Bayesian approach , 2005 .

[2]  Luigi Alfredo Grieco,et al.  Security, privacy and trust in Internet of Things: The road ahead , 2015, Comput. Networks.

[3]  Manoj Kumar Tiwari,et al.  Physical programming and conjoint analysis-based redundancy allocation in multistate systems: A Taguchi embedded algorithm selection and control (TAS&C) approach , 2009 .

[4]  Vikas Kumar,et al.  Economical impact of RFID implementation in remanufacturing: a Chaos-based Interactive Artificial Bee Colony approach , 2015, J. Intell. Manuf..

[5]  Lin Ma,et al.  Prognostic modelling options for remaining useful life estimation by industry , 2011 .

[6]  Namhun Kim,et al.  PHM-based wiring system damage estimation for near zero downtime in manufacturing facilities , 2018, Reliab. Eng. Syst. Saf..

[7]  Ming Jian Zuo,et al.  Health Condition Prediction of Gears Using a Recurrent Neural Network Approach , 2010, IEEE Transactions on Reliability.

[8]  Felix T.S. Chan,et al.  A superiority search and optimisation algorithm to solve RFID and an environmental factor embedded closed loop logistics model , 2011 .

[9]  Aleksandr Ometov,et al.  Facilitating the Delegation of Use for Private Devices in the Era of the Internet of Wearable Things , 2017, IEEE Internet of Things Journal.

[10]  Marimuthu Palaniswami,et al.  Internet of Things (IoT): A vision, architectural elements, and future directions , 2012, Future Gener. Comput. Syst..

[11]  Jaime Campos,et al.  Development in the application of ICT in condition monitoring and maintenance , 2009, Comput. Ind..

[12]  Luca Maria Gambardella,et al.  Ant colony system: a cooperative learning approach to the traveling salesman problem , 1997, IEEE Trans. Evol. Comput..

[13]  Wai Lam,et al.  LEARNING BAYESIAN BELIEF NETWORKS: AN APPROACH BASED ON THE MDL PRINCIPLE , 1994, Comput. Intell..

[14]  Michael G. Pecht,et al.  IoT-Based Prognostics and Systems Health Management for Industrial Applications , 2016, IEEE Access.

[15]  Gregory F. Cooper,et al.  A Bayesian method for the induction of probabilistic networks from data , 1992, Machine Learning.

[16]  Nader Mohamed,et al.  Middleware: middleware challenges and approaches for wireless sensor networks , 2006, IEEE Distributed Systems Online.

[17]  David Ben-Arieh,et al.  Simultaneous optimization of parts and operations sequences in SSMS: a chaos embedded Taguchi particle swarm optimization approach , 2010, J. Intell. Manuf..

[18]  David He,et al.  Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis , 2007, Eur. J. Oper. Res..

[19]  Maria Rita Palattella,et al.  Internet of Things in the 5G Era: Enablers, Architecture, and Business Models , 2016, IEEE Journal on Selected Areas in Communications.

[20]  Krishna R. Pattipati,et al.  Model-Based Prognostic Techniques Applied to a Suspension System , 2008, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[21]  H. Kaebernick,et al.  A concept of reliability evaluation for reuse and remanufacturing , 2008 .

[22]  Ratna Babu Chinnam,et al.  Health-State Estimation and Prognostics in Machining Processes , 2010, IEEE Transactions on Automation Science and Engineering.

[23]  Donghua Zhou,et al.  Remaining useful life estimation - A review on the statistical data driven approaches , 2011, Eur. J. Oper. Res..

[24]  Marko Hölbl,et al.  A novel user authentication and key agreement scheme for heterogeneous ad hoc wireless sensor networks, based on the Internet of Things notion , 2014, Ad Hoc Networks.

[25]  Feng Wu,et al.  Researches on Wireless Embedded Middleware for Service Sharing , 2013, CWSN.

[26]  Leilani Battle,et al.  Building the Internet of Things Using RFID: The RFID Ecosystem Experience , 2009, IEEE Internet Computing.