The Role of AI in Warehouse Digital Twins: Literature Review †
Abstract
:1. Introduction
- What AI techniques are mostly used for warehouse management under the DT paradigm?
- How is AI employed to ensure and elevate WDT functions?
- What are the challenges and barriers to adopting WDT and AI in warehouses?
2. Research Methodology
3. Bibliometric Analysis
- “Digital Twin” AND (“warehouse” OR “warehousing” OR “material handling” OR “inventory” OR “packing” OR “store” OR “storage”),
- “cyber” AND” physical” and “system” AND (“warehouse” OR “warehousing” OR “material handling” OR “inventory” OR “packing” OR “store” OR “storage”).
4. Analysis Framework
4.1. Digital Twin
- Digital Model: There is no automatic data exchange between the physical and digital worlds. Once the model is created, a change made to the physical object has no impact on it.
- Digital Shadow: A digital shadow is a digital model with a one-way data flow from the physical to the digital objects. A change in the state of the physical object leads to a change in the digital representation.
- Digital Twin: the data flow between the two counterparts is bidirectional. A change to the physical object automatically changes its virtual replica and vice versa.
- Context-awareness (CA) is the ability to distinguish incoming stimuli meaningfully. It encompasses more than just IoT and information systems (IS), extending to representing diverse situations in a virtual copy.
- Autonomy (Auto) is the DT’s ability to function independently without human intervention. This capability empowers the system to take action and make decisions based on pre-determined rules or learned behaviors, streamlining the decision-making process without human assistance or a minimum level of human intervention.
- Continuous evolving (CE) is the ability of a DT system to grow and evolve with the real system throughout its lifecycle. DT systems should continuously update themselves based on changing data, information, and knowledge from the real system and all other interconnected software. This feature allows the DT system to adapt to new environmental conditions and changes, ensuring that it remains relevant and effective over time.
- Full lifecycle management (FLM) allows the model to cover different phases across the entire system lifecycle. FLM includes the beginning of life (BOL), such as design, building, and testing; the middle of life (MOL), such as operating, usage, and maintenance; and the end-of-life (EOL), such as disassembly, recycling, and remanufacturing. By addressing all lifecycle phases, FLM enables the DT system to be more sustainable, efficient, and effective over the long term.
4.2. Artificial Intelligence
- Supervised learning (SL): the algorithm is provided with a clearly defined set of input features X and corresponding output labels Y. Supervised learning can be used in intralogistics to predict demand for specific products, to optimize inventory levels, or to predict delivery times.
- Unsupervised learning (UL): the algorithm is provided only input features X. The goal is to find patterns or structures within the data that can be used to group similar data points or to identify outliers using techniques such as cluster analysis. UL is typically used when there is no clear understanding of the underlying structure of the data or when there is no prior knowledge about the data. UL, such as clustering, can be used in intralogistics to identify similar groups of products or to cluster similar customers based on their buying behavior.
- Reinforcement learning (RL): involves an agent that learns by interacting with an environment and receiving rewards or punishments based on its actions. The learner aims to maximize the cumulative reward value over time through trial and error. Reinforcement learning is commonly used in tasks such as game playing, robotics, and autonomous navigation. RL can be applied to train an automated guided vehicle (AGV) in a warehouse to navigate through the facility while avoiding obstacles and maximizing the number of delivered packages. By interacting with the environment, the AGV learns which actions lead to the most desirable outcomes and adjusts its behavior accordingly, gradually improving its performance over time. This allows for a more flexible and adaptive approach to learning in general, which responds to new challenges and changing environments without explicit programming.
4.3. Data
- Environmental data (ED): such as temperature, humidity, and light intensity, could be crucial in decision-making processes or to represent and supervise the physical process accurately. Depending on the type of goods stored in the warehouse, these data may provide valuable insights into the most suitable storage conditions.
- Product data (PD): which entails information on inventory levels and storage locations is another key data type. Technologies such as radio frequency identification (RFID) can monitor storage locations and quantities, linking this information to the warehouse management system (WMS) and DTs for effective replenishment and stockkeeping.
- Handler data (HD) is the third type of data collected in warehouses, providing crucial information on workers and equipment, including their real-time locations. This data may be collected from workers’ handheld devices, allowing for location tracking, and measuring other physical variables. It can also refer to equipment and automation data such as conveyors and AGVs.
4.4. Intralogistics
5. Results
5.1. What AI Technics Are Most Used for Warehouse Management under the DT Paradigm?
5.1.1. Artificial Intelligence
ML | Other AI Technics | Level of DT | DT Characteristics | Data Types | Data Source | Warehouse Activities | |||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
SL | UL | RL | FL | GA | DM | DS | DT | CA | FLM | Auto | CE | Nature | ED | PD | HD | IS | IoT | Manuel Input | Arrival | Put Away | Storage | Picking | Preparation | Shipping | |
[30] | X | X | X | (X) | (X) | R | X | X | X | X | X | ||||||||||||||
[20] | X | (X) | (X) | ||||||||||||||||||||||
[35] | X | X | X | X | S | X | X | X | X | X | X | X | X | ||||||||||||
[36] | X | X | X | R | X | X | |||||||||||||||||||
[37] | X | X | (X) | R | X | X | X | X | X | ||||||||||||||||
[38] | X | (X) | X | S | X | X | |||||||||||||||||||
[31] | X | X | X | (X) | X | R | X | X | X | X | X | X | X | ||||||||||||
[28] | X | ||||||||||||||||||||||||
[27] | X | X | X | X | |||||||||||||||||||||
[39] | X | ||||||||||||||||||||||||
[32] | X | X | R | X | X | X | X | ||||||||||||||||||
[26] | X | X | R | X | X | X | X | X | X | ||||||||||||||||
[40] | X | (X) | R | X | X | X | X | ||||||||||||||||||
[41] | X | X | X | X | X | R | X | X | X | X | X | ||||||||||||||
[42] | X | X | X | (X) | X | X | R | X | X | X | X | X | X | ||||||||||||
[34] | X | X | X | X | X | R | X | X | X | X | |||||||||||||||
[33] | X | X | X | X | R | X | X | X | X | X | X | ||||||||||||||
[25] | X | X | X | X | S | X | X | X | X | X | X | ||||||||||||||
[43] | X | X | X | X | R | X | X | X | X | (X) | X | X | |||||||||||||
[44] | X | (X) | X | (X) | R | X | X | X | X | X | X | X | X | ||||||||||||
[45] | X | X | (X) | R/S | X | X | X | X | |||||||||||||||||
[46] | X | (X) | (X) | R | X | X | X | X |
5.1.2. Data
5.2. How Is AI Employed to Ensure and Elevate WDT Characteristics?
5.2.1. Context Awareness
5.2.2. Autonomy
5.2.3. Continuous Evolving
5.2.4. Full Lifecycle Management
6. Discussion and Further Research Perspectives
- Reconstruction: AI can be an important tool for the reconstruction process, creating and revisiting the virtual representation based on the raw data from the sensors.
- Application: Once the digital twin is reconstructed, another AI algorithm can be applied to the semantically rich representation of the digital twin to support the business goals.
7. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Glatt, M.; Sinnwell, C.; Yi, L.; Donohoe, S.; Ravani, B.; Aurich, J.C. Modeling and Implementation of a Digital Twin of Material Flows Based on Physics Simulation. J. Manuf. Syst. 2021, 58, 231–245. [Google Scholar] [CrossRef]
- Andjelkovic, A.; Radosavljevic, M. Improving Order-Picking Process through Implementation Warehouse Management System. Strateg. Manag. 2018, 23, 3–10. [Google Scholar] [CrossRef]
- Dinneen, J. The Future of E-Commerce: How New Consumer Behaviors are Reshaping Retailers’ Supply Chains. Available online: https://lasership.com/wp-content/uploads/2021/12/B2C-Whitepaper-2021-v2.pdf (accessed on 26 April 2023).
- Gong, Y.; de Koster, R.B.M. A Review on Stochastic Models and Analysis of Warehouse Operations. Logist. Res. 2011, 3, 191–205. [Google Scholar] [CrossRef]
- Longo, F.; Padovano, A.; Umbrello, S. Value-Oriented and Ethical Technology Engineering in Industry 5.0: A Human-Centric Perspective for the Design of the Factory of the Future. Appl. Sci. 2020, 10, 4182. [Google Scholar] [CrossRef]
- Xu, X.; Lu, Y.; Vogel-Heuser, B.; Wang, L. Industry 4.0 and Industry 5.0—Inception, Conception and Perception. J. Manuf. Syst. 2021, 61, 530–535. [Google Scholar] [CrossRef]
- Maddikunta, P.K.R.; Pham, Q.V.; Prabadevi, B.; Deepa, N.; Dev, K.; Gadekallu, T.R.; Ruby, R.; Liyanage, M. Industry 5.0: A Survey on Enabling Technologies and Potential Applications. J. Ind. Inf. Integr. 2022, 26, 100257. [Google Scholar] [CrossRef]
- Kunath, M.; Winkler, H. Integrating the Digital Twin of the Manufacturing System into a Decision Support System for Improving the Order Management Process. Procedia CIRP 2018, 72, 225–231. [Google Scholar] [CrossRef]
- D’Orazio, L.; Messina, R.; Schiraldi, M.M. Industry 4.0 and World Class Manufacturing Integration: 100 Technologies for a WCM-I4.0 Matrix. Appl. Sci. 2020, 10, 4942. [Google Scholar] [CrossRef]
- Kamble, S.S.; Gunasekaran, A.; Parekh, H.; Mani, V.; Belhadi, A.; Sharma, R. Digital Twin for Sustainable Manufacturing Supply Chains: Current Trends, Future Perspectives, and an Implementation Framework. Technol. Forecast. Soc. Chang. 2022, 176, 121448. [Google Scholar] [CrossRef]
- Herold, D.M.; Ćwiklicki, M.; Pilch, K.; Mikl, J. The Emergence and Adoption of Digitalization in the Logistics and Supply Chain Industry: An Institutional Perspective. J. Enterp. Inf. Manag. 2021, 34, 1917–1938. [Google Scholar] [CrossRef]
- Lambrechts, W.; Klaver, J.S.; Koudijzer, L.; Semeijn, J. Human Factors Influencing the Implementation of Cobots in High Volume Distribution Centres. Logistics 2021, 5, 32. [Google Scholar] [CrossRef]
- Michel, R. Warehouse/DC Operations Survey 2022: Recalibrating Operations and Spend—Material Handling 24/7. Available online: https://www.materialhandling247.com/article/warehouse_dc_operations_survey_2022_recalibrating_operations_and_spend (accessed on 22 January 2023).
- Usuga Cadavid, J.P.; Lamouri, S.; Grabot, B.; Pellerin, R.; Fortin, A. Machine Learning Applied in Production Planning and Control: A State-of-the-Art in the Era of Industry 4.0. J. Intell. Manuf. 2020, 31, 1531–1558. [Google Scholar] [CrossRef]
- Younis, H.; Sundarakani, B.; Alsharairi, M. Applications of Artificial Intelligence and Machine Learning within Supply Chains: Systematic Review and Future Research Directions. J. Model. Manag. 2021. ahead-of-print. [Google Scholar] [CrossRef]
- Tranfield, D.; Denyer, D.; Smart, P. Towards a Methodology for Developing Evidence-Informed Management Knowledge by Means of Systematic Review. Br. J. Manag. 2003, 14, 207–222. [Google Scholar] [CrossRef]
- Hribernik, K.; Cabri, G.; Mandreoli, F.; Mentzas, G. Autonomous, Context-Aware, Adaptive Digital Twins—State of the Art and Roadmap. Comput. Ind. 2021, 133, 103508. [Google Scholar] [CrossRef]
- Fuller, A.; Fan, Z.; Day, C.; Barlow, C. Digital Twin: Enabling Technologies, Challenges and Open Research. IEEE Access 2020, 8, 108952–108971. [Google Scholar] [CrossRef]
- Zheng, X.; Lu, J.; Kiritsis, D. The Emergence of Cognitive Digital Twin: Vision, Challenges and Opportunities. Int. J. Prod. Res. 2022, 60, 7610–7632. [Google Scholar] [CrossRef]
- Pan, I.; Mason, L.R.; Matar, O.K. Data-Centric Engineering: Integrating Simulation, Machine Learning and Statistics. Challenges and Opportunities. Chem. Eng. Sci. 2022, 249, 117271. [Google Scholar] [CrossRef]
- Tao, F.; Qi, Q.; Wang, L.; Nee, A.Y.C. Digital Twins and Cyber–Physical Systems toward Smart Manufacturing and Industry 4.0: Correlation and Comparison. Engineering 2019, 5, 653–661. [Google Scholar] [CrossRef]
- Mehmood, M.U.; Chun, D.; Zeeshan; Han, H.; Jeon, G.; Chen, K. A Review of the Applications of Artificial Intelligence and Big Data to Buildings for Energy-Efficiency and a Comfortable Indoor Living Environment. Energy Build. 2019, 202, 109383. [Google Scholar] [CrossRef]
- Jordan, M.I.; Mitchell, T.M. Machine Learning: Trends, Perspectives, and Prospects. Science 2015, 349, 255–260. [Google Scholar] [CrossRef] [PubMed]
- Fernandes, J.; Silva, F.J.G.; Campilho, R.D.S.G.; Pinto, G.F.L.; Baptista, A. Intralogistics and Industry 4.0: Designing a Novel Shuttle with Picking System. Procedia Manuf. 2019, 38, 1801–1832. [Google Scholar] [CrossRef]
- Bányai, Á.; Illés, B.; Glistau, E.; Machado, N.I.C.; Tamás, P.; Manzoor, F.; Bányai, T. Smart Cyber-Physical Manufacturing: Extended and Real-Time Optimization of Logistics Resources in Matrix Production. Appl. Sci. 2019, 9, 1287. [Google Scholar] [CrossRef]
- Corneli, A.; Naticchia, B.; Carbonari, A.; Bosché, F. Augmented Reality and Deep Learning towards the Management of Secondary Building Assets. In Proceedings of the International Symposium on Automation and Robotics in Construction, Banff, AB, Canada, 21–24 May 2019; pp. 332–339. [Google Scholar]
- Minerva, R.; Awan, F.; Crespi, N. Exploiting Digital Twins as Enablers for Synthetic Sensing. IEEE Internet Comput. 2021, 26, 61–67. [Google Scholar] [CrossRef]
- Zacharaki, A.; Vafeiadis, T.; Kolokas, N.; Vaxevani, A.; Xu, Y.; Peschl, M.; Ioannidis, D.; Tzovaras, D. RECLAIM: Toward a New Era of Refurbishment and Remanufacturing of Industrial Equipment. Front. Artif. Intell. 2021, 3, 570562. [Google Scholar] [CrossRef]
- Drissi Elbouzidi, A.; Bélanger, M.-J.; Ait El Cadi, A.; Pellerin, R.; Lamouri, S.; Tobon Valencia, E. The Role of AI in Warehouse Digital Twins. In Proceedings of the 34th European Modeling & Simulation Symposium, EMSS 2022, Rome, Italy, 19–21 September 2022. [Google Scholar]
- Melesse, T.Y.; Bollo, M.; Pasquale, V.D.; Centro, F.; Riemma, S. Machine Learning-Based Digital Twin for Monitoring Fruit Quality Evolution. Procedia Comput. Sci. 2022, 200, 13–20. [Google Scholar] [CrossRef]
- Zhan, X.; Wu, W.; Shen, L.; Liao, W.; Zhao, Z.; Xia, J. Industrial Internet of Things and Unsupervised Deep Learning Enabled Real-Time Occupational Safety Monitoring in Cold Storage Warehouse. Saf. Sci. 2022, 152, 105766. [Google Scholar] [CrossRef]
- Hayward, N.; Portugal, M. Machine Learning Image Analysis for Asset Inspection. In Proceedings of the SPE Offshore Europe Conference and Exhibition, Aberdeen, UK, 5–8 September 2019. [Google Scholar]
- Zhao, Z.; Shen, L.; Yang, C.; Wu, W.; Zhang, M.; Huang, G.Q. IoT and Digital Twin Enabled Smart Tracking for Safety Management. Comput. Oper. Res. 2021, 128, 105183. [Google Scholar] [CrossRef]
- Wu, W.; Zhao, Z.; Shen, L.; Kong, X.T.R.; Guo, D.; Zhong, R.Y.; Huang, G.Q. Just Trolley: Implementation of Industrial IoT and Digital Twin-Enabled Spatial-Temporal Traceability and Visibility for Finished Goods Logistics. Adv. Eng. Inform. 2022, 52, 101571. [Google Scholar] [CrossRef]
- Leung, E.K.H.; Lee, C.K.H.; Ouyang, Z. From Traditional Warehouses to Physical Internet Hubs: A Digital Twin-Based Inbound Synchronization Framework for PI-Order Management. Int. J. Prod. Econ. 2022, 244, 108353. [Google Scholar] [CrossRef]
- Huang, H.; Yang, L.; Wang, Y.; Xu, X.; Lu, Y. Digital Twin-Driven Online Anomaly Detection for an Automation System Based on Edge Intelligence. J. Manuf. Syst. 2021, 59, 138–150. [Google Scholar] [CrossRef]
- Leng, J.; Yan, D.; Liu, Q.; Zhang, H.; Zhao, G.; Wei, L.; Zhang, D.; Yu, A.; Chen, X. Digital Twin-Driven Joint Optimisation of Packing and Storage Assignment in Large-Scale Automated High-Rise Warehouse Product-Service System. Int. J. Comput. Integr. Manuf. 2021, 34, 783–800. [Google Scholar] [CrossRef]
- Kegenbekov, Z.; Jackson, I. Adaptive Supply Chain: Demand-Supply Synchronization Using Deep Reinforcement Learning. Algorithms 2021, 14, 240. [Google Scholar] [CrossRef]
- Sacks, R.; Brilakis, I.; Pikas, E.; Xie, H.S.; Girolami, M. Construction with Digital Twin Information Systems. Data-Cent. Eng. 2020, 1, e14. [Google Scholar] [CrossRef]
- Xiuyu, C.; Tianyi, G. Research on the Predicting Model of Convenience Store Model Based on Digital Twins. In Proceedings of the 2018 International Conference on Smart Grid and Electrical Automation (ICSGEA), Changsha, China, 9–10 June 2018; pp. 224–226. [Google Scholar]
- Wang, W.; Zhang, Y.; Zhong, R.Y. A Proactive Material Handling Method for CPS Enabled Shop-Floor. Robot. Comput.-Integr. Manuf. 2020, 61, 101849. [Google Scholar] [CrossRef]
- Gao, Y.; Chang, D.; Chen, C.-H.; Xu, Z. Design of Digital Twin Applications in Automated Storage Yard Scheduling. Adv. Eng. Inform. 2022, 51, 101477. [Google Scholar] [CrossRef]
- Wu, W.; Shen, L.; Zhao, Z.; Harish, A.R.; Zhong, R.Y.; Huang, G.Q. Internet of Everything and Digital Twin Enabled Service Platform for Cold Chain Logistics. J. Ind. Inf. Integr. 2023, 33, 100443. [Google Scholar] [CrossRef]
- Ud Din, F.; Paul, D. Demystifying XAOSF/AOSR Framework in the Context of Digital Twin and Industry 4.0. In Lecture Notes in Networks and Systems; Springer: Cham, Switzerland, 2023; Volume 544, p. 610. [Google Scholar]
- Arshad, R.; de Vrieze, P.; Xu, L. Incorporating a Prediction Engine to a Digital Twin Simulation for Effective Decision Support in Context of Industry 4.0. In IFIP Advances in Information and Communication Technology; Springer: Cham, Switzerland, 2022; Volume 662, p. 76. [Google Scholar]
- Félix-Cigalat, J.; Domingo, R. Towards a Digital Twin Warehouse through the Optimization of Internal Transport. Appl. Sci. 2023, 13, 4652. [Google Scholar] [CrossRef]
- Baroroh, D.K.; Chu, C.-H. Human-Centric Production System Simulation in Mixed Reality: An Exemplary Case of Logistic Facility Design. J. Manuf. Syst. 2022, 65, 146–157. [Google Scholar] [CrossRef]
- Lago Alvarez, A.; Mohammed, W.M.; Vu, T.; Ahmadi, S.; Martinez Lastra, J.L. Enhancing Digital Twins of Semi-Automatic Production Lines by Digitizing Operator Skills. Appl. Sci. 2023, 13, 1637. [Google Scholar] [CrossRef]
- Melesse, T.Y.; Bollo, M.; Di Pasquale, V.; Riemma, S. Digital Twin for Inventory Planning of Fresh Produce. IFAC-Pap. 2022, 55, 2743–2748. [Google Scholar] [CrossRef]
- Slama, D. Digital Twin 101—Digitalplaybook.org. Available online: https://www.digitalplaybook.org/index.php?title=Digital_Twin_101#cite_note-dtdef-2 (accessed on 27 January 2023).
- Croatti, A.; Gabellini, M.; Montagna, S.; Ricci, A. On the Integration of Agents and Digital Twins in Healthcare. J. Med. Syst. 2020, 44, 161. [Google Scholar] [CrossRef] [PubMed]
- Liu, Y.; Moyaux, T.; Bouleux, G.; Cheutet, V. An Agent-Based Architecture of the Digital Twin for an Emergency Department; HAL: Lyon, France, 2022. [Google Scholar]
- Agrawal, A.; Thiel, R.; Jain, P.; Singh, V.; Fischer, M. Digital Twin: Where Do Humans Fit In? Autom. Constr. 2023, 148, 104749. [Google Scholar] [CrossRef]
- Turner, C.J.; Garn, W. Next Generation DES Simulation: A Research Agenda for Human Centric Manufacturing Systems. J. Ind. Inf. Integr. 2022, 28, 100354. [Google Scholar] [CrossRef]
- Qian, W.; Guo, Y.; Zhang, H.; Huang, S.; Zhang, L.; Zhou, H.; Fang, W.; Zha, S. Digital Twin Driven Production Progress Prediction for Discrete Manufacturing Workshop. Robot. Comput. Integr. Manuf. 2023, 80, 102456. [Google Scholar] [CrossRef]
- Tufano, A.; Accorsi, R.; Manzini, R. A Machine Learning Approach for Predictive Warehouse Design. Int. J. Adv. Manuf. Technol. 2022, 119, 2369–2392. [Google Scholar] [CrossRef]
- Badakhshan, E.; Ball, P.; Badakhshan, A. Using Digital Twins for Inventory and Cash Management in Supply Chains. IFAC-Pap. 2022, 55, 1980–1985. [Google Scholar] [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Drissi Elbouzidi, A.; Ait El Cadi, A.; Pellerin, R.; Lamouri, S.; Tobon Valencia, E.; Bélanger, M.-J. The Role of AI in Warehouse Digital Twins: Literature Review. Appl. Sci. 2023, 13, 6746. https://doi.org/10.3390/app13116746
Drissi Elbouzidi A, Ait El Cadi A, Pellerin R, Lamouri S, Tobon Valencia E, Bélanger M-J. The Role of AI in Warehouse Digital Twins: Literature Review. Applied Sciences. 2023; 13(11):6746. https://doi.org/10.3390/app13116746
Chicago/Turabian StyleDrissi Elbouzidi, Adnane, Abdessamad Ait El Cadi, Robert Pellerin, Samir Lamouri, Estefania Tobon Valencia, and Marie-Jane Bélanger. 2023. "The Role of AI in Warehouse Digital Twins: Literature Review" Applied Sciences 13, no. 11: 6746. https://doi.org/10.3390/app13116746