Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Artificial Intelligence in Industry 4.0: A Review of Integration Challenges for Industrial Systems (2405.18580v3)

Published 28 May 2024 in cs.AI and cs.LG

Abstract: In Industry 4.0, Cyber-Physical Systems (CPS) generate vast data sets that can be leveraged by AI for applications including predictive maintenance and production planning. However, despite the demonstrated potential of AI, its widespread adoption in sectors like manufacturing remains limited. Our comprehensive review of recent literature, including standards and reports, pinpoints key challenges: system integration, data-related issues, managing workforce-related concerns and ensuring trustworthy AI. A quantitative analysis highlights particular challenges and topics that are important for practitioners but still need to be sufficiently investigated by academics. The paper briefly discusses existing solutions to these challenges and proposes avenues for future research. We hope that this survey serves as a resource for practitioners evaluating the cost-benefit implications of AI in CPS and for researchers aiming to address these urgent challenges.

View on arXiv
Definition Search Book Streamline Icon: https://streamlinehq.com
References (70)
  1. Attention is All you Need. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017. URL https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf.
  2. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations, 2021.
  3. Highly accurate protein structure prediction with AlphaFold. Nature, 596(7873):583–589, 2021. doi:10.1038/s41586-021-03819-2.
  4. Systematische Literaturanalyse zum KI-Einsatz und KI-basierten Geschäftsmodellen in produzierenden kleinen und mittleren Unternehmen. Zeitschrift für Arbeitswissenschaft, 77(3):453–468, 2023. doi:10.1007/s41449-022-00323-9.
  5. Insights and Example Use Cases on Industrial Transfer Learning. Procedia CIRP, 107:511–516, 2022. doi:10.1016/j.procir.2022.05.017.
  6. World Economic Forum and Boston Consulting Group. Using AI in Industrial Operations Guidebook. Technical report, 2023. URL https://www3.weforum.org/docs/WEF_Harnessing_the_AI_Revolution_in_Industrial_Operations_2023.pdf.
  7. Challenges in Deploying Machine Learning: A Survey of Case Studies. ACM Computing Surveys, 55(6):1–29, 2022. doi:10.1145/3533378.
  8. Artificial Intelligence for Safety-Critical Systems in Industrial and Transportation Domains: A Survey. ACM Computing Surveys, page 3626314, 2024. doi:10.1145/3626314.
  9. Hidden Technical Debt in Machine Learning Systems. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc., 2015. URL https://proceedings.neurips.cc/paper_files/paper/2015/file/86df7dcfd896fcaf2674f757a2463eba-Paper.pdf.
  10. A Taxonomy of Software Engineering Challenges for Machine Learning Systems: An Empirical Investigation. In Philippe Kruchten, Steven Fraser, and François Coallier, editors, Agile Processes in Software Engineering and Extreme Programming, volume 355, pages 227–243. Springer International Publishing, 2019. doi:10.1007/978-3-030-19034-7_14.
  11. Edward A. Lee. Cyber Physical Systems: Design Challenges. In 2008 11th IEEE International Symposium on Object and Component-Oriented Real-Time Distributed Computing (ISORC), pages 363–369, 2008. doi:10.1109/ISORC.2008.25.
  12. A Survey on Concepts, Applications, and Challenges in Cyber-Physical Systems. KSII Transactions on Internet and Information Systems, 8(12):4242–4268, 2014. doi:10.3837/tiis.2014.12.001.
  13. Challenges in Engineering Cyber-Physical Systems. Computer, 47(2):70–72, 2014. doi:10.1109/MC.2014.30.
  14. Challenges for Software Engineering in Automation. Journal of Software Engineering and Applications, 7(5):440–451, 2014. doi:10.4236/jsea.2014.75041.
  15. Industrial Internet of Things: Challenges, Opportunities, and Directions. IEEE Transactions on Industrial Informatics, 14(11):4724–4734, 2018. doi:10.1109/TII.2018.2852491.
  16. Industry 4.0 readiness in manufacturing companies: Challenges and enablers towards increased digitalization. Procedia CIRP, 81:1113–1118, 2019. doi:10.1016/j.procir.2019.03.262.
  17. How Do Engineers Perceive Difficulties in Engineering of Machine-Learning Systems? - Questionnaire Survey. In 2019 IEEE/ACM Joint 7th International Workshop on Conducting Empirical Studies in Industry (CESI) and 6th International Workshop on Software Engineering Research and Industrial Practice (SER&IP), pages 2–9, 2019. doi:10.1109/CESSER-IP.2019.00009.
  18. AutoML: A Survey of the State-of-the-Art. Knowledge-Based Systems, 212:106622, 2021. doi:10.1016/j.knosys.2020.106622.
  19. Technology readiness levels for machine learning systems. Nature Communications, 13(1):6039, 2022. doi:10.1038/s41467-022-33128-9.
  20. Challenges of Machine Learning Applied to Safety-Critical Cyber-Physical Systems. Machine Learning and Knowledge Extraction, 2(4):579–602, 2020. doi:10.3390/make2040031.
  21. The Duo of Artificial Intelligence and Big Data for Industry 4.0: Applications, Techniques, Challenges, and Future Research Directions. IEEE Internet of Things Journal, 9(15):12861–12885, 2022. doi:10.1109/JIOT.2021.3139827.
  22. Artificial intelligence, cyber-threats and Industry 4.0: Challenges and opportunities. Artificial Intelligence Review, 54(5):3849–3886, 2021. doi:10.1007/s10462-020-09942-2.
  23. MLOps Challenges in Industry 4.0. SN Computer Science, 4(6):828, 2023. doi:10.1007/s42979-023-02282-2.
  24. Abd El Hedi Gabsi. Integrating artificial intelligence in industry 4.0: Insights, challenges, and future prospects–a literature review. Annals of Operations Research, 2024. doi:10.1007/s10479-024-06012-6.
  25. A Review on AI for Smart Manufacturing: Deep Learning Challenges and Solutions. Applied Sciences, 12(16):8239, 2022. doi:10.3390/app12168239.
  26. Artificial intelligence for industry 4.0: Systematic review of applications, challenges, and opportunities. Expert Systems with Applications, 216:119456, 2023. doi:10.1016/j.eswa.2022.119456.
  27. Machine Learning in Manufacturing towards Industry 4.0: From ‘For Now’ to ‘Four-Know’. Applied Sciences, 13(3):1903, 2023. doi:10.3390/app13031903.
  28. Safely Entering the Deep: A Review of Verification and Validation for Machine Learning and a Challenge Elicitation in the Automotive Industry. Journal of Automotive Software Engineering, 1(1):1–19, 2020. doi:10.2991/jase.d.190131.001.
  29. The artificial intelligence technologies in Industry 4.0: A taxonomy, approaches, and future directions. Computers & Industrial Engineering, 185:109662, 2023. doi:10.1016/j.cie.2023.109662.
  30. Industry 4.0: Towards future industrial opportunities and challenges. In 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), pages 2147–2152, 2015. doi:10.1109/FSKD.2015.7382284.
  31. Industrial Artificial Intelligence in Industry 4.0 - Systematic Review, Challenges and Outlook. IEEE Access, 8:220121–220139, 2020. doi:10.1109/ACCESS.2020.3042874.
  32. Machine Learning Techniques for Smart Manufacturing: Applications and Challenges in Industry 4.0. In 9th International Scientific and Expert Conference TEAM 2018, oct 2018.
  33. Machine learning in manufacturing: Advantages, challenges, and applications. Production & Manufacturing Research, 4(1):23–45, 2016. doi:10.1080/21693277.2016.1192517.
  34. Industry 4.0: Adoption challenges and benefits for SMEs. Computers in Industry, 121:103261, 2020. doi:10.1016/j.compind.2020.103261.
  35. KI im Mittelstand – Potenziale erkennen, Voraussetzungen schaffen, Transformation meistern. Technical report, Acatech, 2021. URL https://www.acatech.de/publikation/ki-im-mittelstand-potenziale-erkennen-voraussetzungen-schaffen-transformation-meistern/.
  36. Artificial Intelligence High-Level Expert Group. Ethics Guidelines for truthworthy AI, 2019. URL https://digital-strategy.ec.europa.eu/en/library/ethics-guidelines-trustworthy-ai.
  37. EASA. EASA Concept Paper: First usable guidance for level 1 & 2 machine learning applications. Technical report, European Union Aviation Safety Agency, 2023.
  38. Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology. Machine Learning and Knowledge Extraction, 3(2):392–413, 2021. doi:10.3390/make3020020.
  39. Engineering problems in machine learning systems. Machine Learning, 109(5):1103–1126, 2020. doi:10.1007/s10994-020-05872-w.
  40. Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges. ACM Computing Surveys, 54(5):1–39, 2021. doi:10.1145/3453444.
  41. DIN, DKE. Deutsche Normungsroadmap Künstliche Intelligenz (Ausgabe 2). Technical report, Deutsches Institut für Normung, 2022. URL https://www.din.de/go/normungsroadmapki.
  42. Technology Scenario ‘Artificial Intelligence in Industrie 4.0’. Technical report, Bundesministerium für Wirtschaft und Energie (BMWi), 2019.
  43. FliPSi: Generating Data for the Training of Machine Learning Algorithms for CPPS. Annual Conference of the PHM Society, 14(1), 2022. doi:10.36001/phmconf.2022.v14i1.3229.
  44. Opportunities of Federated Learning in Connected, Cooperative, and Automated Industrial Systems. IEEE Communications Magazine, 59(2):16–21, 2021. doi:10.1109/MCOM.001.2000200.
  45. European Parliament. Regulation (eu) 2024/… of the european parliament and of the council of … laying down harmonised rules on artificial intelligence and amending regulations (ec) no 300/2008, (eu) no 167/2013, (eu) no 168/2013, (eu) 2018/858, (eu) 2018/1139 and (eu) 2019/2144 and directives 2014/90/eu, (eu) 2016/797 and (eu) 2020/1828 (artificial intelligence act), 2024. URL https://artificialintelligenceact.eu/the-act/.
  46. The White House. Blueprint for an AI Bill of Rights: Making Automated Systems Work for the American People, 2022. URL https://www.whitehouse.gov/ostp/ai-bill-of-rights/.
  47. Department for Science, Innovation & Technology. A pro-innovation approach to AI regulation, 2023. URL https://www.gov.uk/government/publications/ai-regulation-a-pro-innovation-approach.
  48. Measuring the Robustness of ML Models Against Data Quality Issues in Industrial Time Series Data. In 2023 IEEE 21st International Conference on Industrial Informatics (INDIN), pages 1–8, Lemgo, Germany, 2023. IEEE. doi:10.1109/INDIN51400.2023.10218129.
  49. From Artificial Intelligence to Explainable Artificial Intelligence in Industry 4.0: A Survey on What, How, and Where. IEEE Transactions on Industrial Informatics, 18(8):5031–5042, 2022. doi:10.1109/TII.2022.3146552.
  50. Model cards for model reporting. In Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* ’19, page 220–229. Association for Computing Machinery, 2019. doi:10.1145/3287560.3287596.
  51. Software Engineering for Machine Learning: A Case Study. In 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), pages 291–300, 2019. doi:10.1109/ICSE-SEIP.2019.00042.
  52. Artificial Intelligence in Advanced Manufacturing: Current Status and Future Outlook. Journal of Manufacturing Science and Engineering, 142(110804), 2020. doi:10.1115/1.4047855.
  53. FactSheets: Increasing trust in AI services through supplier’s declarations of conformity. IBM Journal of Research and Development, 63(4/5):6:1–6:13, 2019. doi:10.1147/JRD.2019.2942288.
  54. Requirements Engineering Challenges in Building AI-Based Complex Systems. In 2019 IEEE 27th International Requirements Engineering Conference Workshops (REW), pages 252–255. IEEE, 2019. doi:10.1109/REW.2019.00051.
  55. Machine learning for industrial applications: A comprehensive literature review. Expert Systems with Applications, 175:114820, 2021. doi:10.1016/j.eswa.2021.114820.
  56. Engineering AI Systems: A Research Agenda, 2020.
  57. Martin Ebers. Standardizing AI: The Case of the European Commission’s Proposal for an ‘Artificial Intelligence Act’. In Larry A. DiMatteo, Cristina Poncibò, and MichelEditors Cannarsa, editors, The Cambridge Handbook of Artificial Intelligence: Global Perspectives on Law and Ethics, Cambridge Law Handbooks, page 321–344. Cambridge University Press, 2022.
  58. Datasheets for datasets. Communications of the ACM, 64(12):86–92, 2021. doi:10.1145/3458723.
  59. ISO IEC. TR 24030 - Artificial Intelligence - Use Cases. Technical report, International Organization for Standardization, 2021.
  60. ISO IEC. 22989 - Artificial Intelligence Concepts and Terminology, 2022.
  61. International Electrotechnical Commission. Artificial intelligence across industries, 2018.
  62. Industrial artificial intelligence for industry 4.0-based manufacturing systems. Manufacturing Letters, 18:20–23, 2018. doi:10.1016/j.mfglet.2018.09.002.
  63. Künstliche Intelligenz zur Umsetzung von Industrie 4.0 im Mittelstand. Technical report, Forschungsbeirat der Plattform Industrie 4.0 / acatech – Deutsche Akademie der Technikwissenschaften, 2021. URL https://www.acatech.de/publikation/fb4-0-ki-in-kmu/.
  64. Machine Learning for Cyber-Physical Systems. In Birgit Vogel-Heuser and Manuel Wimmer, editors, Digital Transformation, pages 415–446. Springer Berlin Heidelberg, 2023. doi:10.1007/978-3-662-65004-2_17.
  65. Predictive Manufacturing Systems in Industry 4.0: Trends, Benefits and Challenges. In Branko Katalinic, editor, DAAAM Proceedings, volume 1, pages 796–802. DAAAM International Vienna, 1 edition, 2017. doi:10.2507/28th.daaam.proceedings.112.
  66. Applications of Artificial Intelligence in Engineering and Manufacturing: A Systematic Review. Journal of Intelligent Manufacturing, 33(6):1581–1601, 2022. doi:10.1007/s10845-021-01771-6.
  67. OECD. Artificial Intelligence in Society, 2019. URL https://www.oecd-ilibrary.org/science-and-technology/artificial-intelligence-in-society_eedfee77-en.
  68. Demystifying MLOps and Presenting a Recipe for the Selection of Open-Source Tools. Applied Sciences, 11(19):8861, 2021. doi:10.3390/app11198861.
  69. Introducing MLOps. O’Reilly Media, 2020.
  70. Benchmark and Survey of Automated Machine Learning Frameworks. Journal of Artificial Intelligence Research, 70:409–472, 2021. doi:10.1613/jair.1.11854.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Alexander Windmann (8 papers)
  2. Philipp Wittenberg (8 papers)
  3. Marvin Schieseck (5 papers)
  4. Oliver Niggemann (34 papers)
Citations (2)
View on Semantic Scholar

Summary

A Comprehensive Overview of AI Integration Challenges in Industry 4.0

The paper "Artificial Intelligence in Industry 4.0: A Review of Integration Challenges for Industrial Systems" provides an in-depth review of the various challenges posed by the integration of AI into Cyber-Physical Systems (CPS) within the context of Industry 4.0. The authors dissect the impediments into distinct categories and offer a meticulous examination of each, which serves as a critical resource for both practitioners in the field and researchers aiming to address these challenges.

Key Challenges in AI Integration

The authors categorize the challenges into four primary themes: system integration, data, workforce, and trustworthy AI. Each category presents unique barriers to the integration of AI into industrial systems:

  1. System Integration: This encompasses issues related to the convergence of Information Technology (IT) and Operational Technology (OT), the demanding infrastructure requirements of AI systems, cybersecurity threats, the selection of suitable AI models, and the complex cost-benefit analysis that AI investments entail. A notable statistic from a 2023 Boston Consulting Group survey reveals that although 89% of manufacturers view AI as essential, just 68% have implemented AI use cases, and only 16% have achieved their AI-related targets.
  2. Data Challenges: The quality and availability of data emerge as critical concerns in AI-driven industrial applications. The scarcity of relevant data and the presence of noise and inaccuracies necessitate enhanced data preprocessing techniques and the development of data synthetization methods. Furthermore, legal and privacy issues add layers of complexity, with strict regulatory frameworks like GDPR influencing data handling practices.
  3. Workforce Challenges: A shortage of skilled AI professionals and the need for interdisciplinary collaboration are pressing issues. The reluctance among workers regarding AI adoption, due to job security concerns and prior unsuccessful AI initiatives, further compounds these challenges.
  4. Trustworthy AI: Key issues include ensuring the interpretability, robustness, and quality assurance of AI models. The unpredictability of AI, often termed as the "black-box" problem, poses significant challenges in sectors where safety and reliability are paramount. The emerging regulatory landscape underscores these concerns, as new laws seek to govern AI technologies' ethical and safe deployment.

Quantitative Analysis and Research Gaps

The paper’s quantitative analysis reveals that data-related challenges and the trustworthiness of AI are the most frequently discussed issues in the literature. However, significant research gaps remain in workforce and system integration challenges. The lack of comprehensive studies addressing the practical barriers faced by industry practitioners, particularly SMEs, highlights a disconnect between academic research and real-world application.

Implications and Future Directions

The authors encourage more research on developing advanced testing frameworks, explainable AI (XAI), and robust process models to bolster the trustworthiness and effectiveness of AI systems. The establishment of standardized protocols and guidelines is also essential to navigating the evolving regulatory landscape.

Further, addressing system integration challenges through automated machine learning (AutoML) and transfer learning could enhance the accessibility of AI technologies, thereby mitigating the shortage of skilled labor. Bridging these gaps will require collaborative efforts from researchers, industry experts, and policymakers to create environments conducive for seamless AI integration in Industry 4.0 settings.

Conclusion

This paper offers a critical synthesis of the existing literature on AI integration in Industry 4.0, outlining the key challenges and identifying gaps that warrant further investigation. By providing a structured roadmap and prioritizing areas for future research, the authors contribute significantly to the ongoing discourse on AI in industrial applications. Robust solutions to these challenges are pivotal in realizing the full potential of AI-enhanced CPS in advancing Industry 4.0.

File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets