Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

The Artificial Neural Twin -- Process Optimization and Continual Learning in Distributed Process Chains (2403.18343v1)

Published 27 Mar 2024 in cs.LG

Abstract: Industrial process optimization and control is crucial to increase economic and ecologic efficiency. However, data sovereignty, differing goals, or the required expert knowledge for implementation impede holistic implementation. Further, the increasing use of data-driven AI-methods in process models and industrial sensory often requires regular fine-tuning to accommodate distribution drifts. We propose the Artificial Neural Twin, which combines concepts from model predictive control, deep learning, and sensor networks to address these issues. Our approach introduces differentiable data fusion to estimate the state of distributed process steps and their dependence on input data. By treating the interconnected process steps as a quasi neural-network, we can backpropagate loss gradients for process optimization or model fine-tuning to process parameters or AI models respectively. The concept is demonstrated on a virtual machine park simulated in Unity, consisting of bulk material processes in plastic recycling.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Fusion of multiple estimates by covariance intersection: Why and howit is suboptimal. International Journal of Applied Mathematics and Computer Science, 28(3):521–530.
  2. Benaskeur, A. (2002). Consistent fusion of correlated data sources. In IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02. IEEE.
  3. The tradeoffs of large scale learning. In Platt, J., Koller, D., Singer, Y., and Roweis, S., editors, Advances in Neural Information Processing Systems 20 (NIPS 2007), pages 161–168. NIPS Foundation (http://books.nips.cc).
  4. Distributed model predictive control: A tutorial review and future research directions. Computers and Chemical Engineering, 51:21–41.
  5. Progressive bayes: a new framework for nonlinear state estimation. In Dasarathy, B. V., editor, Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2003. SPIE.
  6. Optimization Algorithms as Robust Feedback Controllers. arXiv e-prints, page arXiv:2103.11329.
  7. Towards arbitrary noise augmentation - deep learning for sampling from arbitrary probability distributions.
  8. Hurley, M. (2002). An information theoretic justification for covariance intersection and its generalization. In Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997). Int. Soc. Inf. Fusion.
  9. Improving the rprop learning algorithm. In Proceedings of the Second International Symposium on Neural Computation, NC’2000.
  10. Jackson, D. D. (1979). The use of a priori data to resolve non-uniqueness in linear inversion. Geophysical Journal International, 57(1):137–157.
  11. Smart environment monitoring system by employing wireless sensor networks on vehicles for pollution free smart cities. Procedia Engineering, 107:480–484.
  12. Unity: A general platform for intelligent agents.
  13. A non-divergent estimation algorithm in the presence of unknown correlations. In Proceedings of the 1997 American Control Conference (Cat. No.97CH36041). IEEE.
  14. Statistical and Computational Inverse Problems (Applied Mathematical Sciences). Springer.
  15. Advances and open problems in federated learning. Foundations and Trends® in Machine Learning, 14(1–2):1–210.
  16. An improved analysis of gradient tracking for decentralized machine learning. In Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., and Vaughan, J. W., editors, Advances in Neural Information Processing Systems, volume 34, pages 11422–11435. Curran Associates, Inc.
  17. Federated optimization: Distributed machine learning for on-device intelligence.
  18. Model Predictive Control Classical, Robust and Stochastic. Springer International Publishing AG.
  19. Selection and Application of Machine Learning- Algorithms in Production Quality, pages 46–57. Springer Berlin Heidelberg.
  20. Efficient in-network moving object tracking in wireless sensor networks. IEEE Transactions on Mobile Computing, 5(8):1044–1056.
  21. Hydrodynamic mathematical modelling of aerobic plug flow and nonideal flow reactors: A critical and historical review. Critical Reviews in Environmental Science and Technology, 44(23):2642–2673.
  22. Decoupled Weight Decay Regularization.
  23. Known operator learning and hybrid machine learning in medical imaging—a review of the past, the present, and the future. Progress in Biomedical Engineering, 4(2):022002.
  24. A gentle introduction to deep learning in medical image processing. Zeitschrift für Medizinische Physik, 29(2):86–101.
  25. Learning with known operators reduces maximum error bounds. Nature machine intelligence, 1(8):373–380.
  26. Handbook of Multisensor Data Fusion Theory and Practice, Second Edition. Taylor & Francis Group.
  27. Communication-efficient learning of deep networks from decentralized data.
  28. Mitchell, T. M. (1997). Machine Learning. McGraw-Hill Science/Engineering/Math.
  29. Niehsen, W. (2002). Information fusion based on fast covariance intersection filtering. In Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997). Int. Soc. Inf. Fusion.
  30. Inverse covariance intersection: New insights and properties. In 2017 20th International Conference on Information Fusion (Fusion). IEEE.
  31. Decentralized data fusion with inverse covariance intersection. Automatica, 79:35–41.
  32. Olfati-Saber, R. (2007). Distributed kalman filtering for sensor networks. In 2007 46th IEEE Conference on Decision and Control. IEEE.
  33. Continual lifelong learning with neural networks: A review. Neural Networks, 113:54–71.
  34. Distributed detection via bayesian updates and consensus. In 2015 34th Chinese Control Conference (CCC). IEEE.
  35. Rawlings, J. (2000). Tutorial overview of model predictive control. IEEE Control Systems, 20(3):38–52.
  36. Minimum covariance bounds for the fusion under unknown correlations. IEEE Signal Processing Letters, 22(9):1210–1214.
  37. Rprop - a fast adaptive learning algorithm. In Proceedings of the 7th International Symposium of Computer and Information Science (ISCIS).
  38. Centralized and decentralized process and sensor fault monitoring using data fusion based on adaptive extended kalman filter algorithm. Measurement, 41(10):1059–1076.
  39. Sensitivity-based coordination in distributed model predictive control. Journal of Process Control, 21(5):715–728.
  40. Modellbildung in der messtechnik und ihre künftige entwicklung. VDI-Berichte, (2390):179–188.
  41. Architektur einer vernetzten, adaptiven produktion. In Aachener Werkzeugmaschinen-Kolloquium: Internet of Production–Turning Data into Value, pages 4–19.
  42. State fusion with unknown correlation: Ellipsoidal intersection. Automatica, 48(8):1874–1878.
  43. A bayesian approach to information fusion for evaluating the measurement uncertainty. Robotics and Autonomous Systems, 57(3):339–344.
  44. Generalized nonlinear inverse problems solved using the least squares criterion. Reviews of Geophysics, 20(2):219.
  45. Homogeneous functionals and bayesian data fusion with unknown correlation. Information Fusion, 45:179–189.
  46. Distributed optimization of multiuser MIMO relay network using backpropagation algorithm. In 2021 55th Asilomar Conference on Signals, Systems, and Computers. IEEE.
  47. A distributed MIMO relay scheme inspired by backpropagation algorithm. In 2021 IEEE Global Communications Conference (GLOBECOM). IEEE.
  48. A general framework for decentralized optimization with first-order methods.
  49. An exact maximum likelihood registration algorithm for data fusion. IEEE Transactions on Signal Processing, 45(6):1560–1573.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets