# Investigating Data-Driven Systems as Digital Twins: Numerical Behavior of Ho–Kalman Method for Order Estimation

## Abstract

**:**

## 1. Introduction

## 2. Framework

- Data are aggregated for various cases (i.e., different materials)
- Ho–Kalman algorithm is applied to estimate the order of the system
- Plain estimation techniques are applied (i.e., mean least squares) to retrieve the transfer function(s)

- Sensors are used to detect the model that should be applied
- The controller is designed (i.e., Proportional–Integral–Derivative)

- Sensors are used to measure input and output of the system
- (optional) An observer is used to estimate the state (inner variables) of the system
- The control signal is generated and control is applied (these may be two different steps depending on the implementation)

## 3. Method

#### Comparison to Other Methods and Correlation to Information

## 4. Numerical Behaviour and Applicability

#### 4.1. Simple Numerical Examples

#### 4.2. Performance on Systems of Higher Order

#### 4.3. Non-Homogeneous Systems

## 5. Summary and Future Outlook

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Seborg, D.; Edgar, T.; Shah, S. Adaptive control strategies for process control: A survey. AIChE J.
**1986**, 32, 881–913. [Google Scholar] [CrossRef] - Dumont, G.A.; Huzmezan, M. Concepts, methods and techniques in adaptive control. In Proceedings of the American Control Conference, Anchorage, AK, USA, 10 May 2002; Volume 2, pp. 1137–1150. [Google Scholar]
- Yechiel, O.; Guterman, H. A Survey of Adaptive Control. Int. Rob. Auto J.
**2017**, 3, 00053. [Google Scholar] [CrossRef] [Green Version] - Aseltine, J.; Mancini, A.; Sarture, C. A survey of adaptive control systems. IRE Trans. Autom. Control.
**1958**, 6, 102–108. [Google Scholar] [CrossRef] - Trotta, D.; Garengo, P. Industry 4.0 key research topics: A bibliometric review. In Proceedings of the 2018 7th International Conference on Industrial Technology and Management (ICITM), Oxford, UK, 9 March 2018; pp. 113–117. [Google Scholar]
- Mourtzis, D.; Vlachou, E.; Milas, N. Industrial Big Data as a result of IoT adoption in manufacturing. Procedia CIRP
**2016**, 55, 290–295. [Google Scholar] [CrossRef] [Green Version] - Brandtstaedter, H.; Ludwig, C.; Hübner, L.; Tsouchnika, E.; Jungiewicz, A.; Wever, U. Digital twins for large electric drive trains. In Proceedings of the 2018 Petroleum and Chemical Industry Conference Europe (PCIC Europe), Antwerp, Belgium, 7 June 2018; pp. 1–5. [Google Scholar]
- Han, D.M.; Lim, J.H. Design and implementation of smart home energy management systems based on zigbee. IEEE Trans. Consum. Electron.
**2010**, 56, 1417–1425. [Google Scholar] [CrossRef] - Nivison, S.A.; Khargonekar, P. A Sparse Neural Network Approach to Model Reference Adaptive Control with Hypersonic Flight Applications. In Proceedings of the 2018 AIAA Guidance, Navigation, and Control Conference, Kissimmee, FL, USA, 12 January 2018; p. 0842. [Google Scholar]
- Chryssolouris, G. Manufacturing Systems: Theory and Practice; Springer: New York, NY, USA, 2006. [Google Scholar]
- Papacharalampopoulos, A.; Stavridis, J.; Stavropoulos, P.; Chryssolouris, G. Cloud-based control of thermal based manufacturing processes. Procedia CIRP
**2016**, 55, 254–259. [Google Scholar] [CrossRef] [Green Version] - Matlab Model Structure. Available online: https://www.mathworks.com/help/ident/ug/model-structure-selection-determining-model-order-and-input-delay.html (accessed on 1 February 2019).
- Brincker, R.; Zhang, L.; Andersen, P. Modal identification from ambient responses using frequency domain decomposition. In Proceedings of the 18th International Modal Analysis Conference (IMAC), San Antonio, TX, USA, 7–10 February 2000. [Google Scholar]
- Karimian-Azari, S.; Jensen, J.R.; Christensen, M.G. Fundamental frequency and model order estimation using spatial filtering. In Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, 9 May 2014; pp. 5964–5968. [Google Scholar]
- Stoica, P.; Selen, Y. Model-order selection: A review of information criterion rules. IEEE Signal Process. Mag.
**2004**, 21, 36–47. [Google Scholar] [CrossRef] - Choi, B. ARMA Model Identification; Springer Science & Business Media: New York, NY, USA, 2012. [Google Scholar]
- McQuarrie, A.D.; Tsai, C.L. Regression and Time Series Model Selection; World Scientific: Singapore, 1998. [Google Scholar]
- Burnham, K.P.; Anderson, D.R. Multimodel inference: Understanding AIC and BIC in model selection. Sociol. Methods Res.
**2004**, 33, 261–304. [Google Scholar] [CrossRef] - Fabozzi, F.J.; Focardi, S.M.; Rachev, S.T.; Arshanapalli, B.G. The Basics of Financial Econometrics: Tools, Concepts, and Asset Management Applications; John Wiley & Sons: Hoboken, NJ, USA, 2014. [Google Scholar]
- Kapsalas, C.; Sakellariou, J.; Koustoumpardis, P.; Aspragathos, N. An ARX-based method for the vibration control of flexible beams manipulated by industrial robots. Robot. Comput. Integr. Manuf.
**2018**, 52, 76–91. [Google Scholar] [CrossRef] - Ho, B.; Kalman, R.E. Effective construction of linear state-variable models from input/output functions. Automatisierungstechnik
**1966**, 14, 545–548. [Google Scholar] [CrossRef] - Papacharalampopoulos, A.; Stavropoulos, P. Towards a Digital Twin for Thermal Processes: Control-centric approach. Procedia CIRP
**2019**, 86, 110–115. [Google Scholar] [CrossRef] - Chaitin, G.J. Meta math! The quest for omega. arXiv
**2004**, arXiv:math/0404335. [Google Scholar] - Stavropoulos, A.; Papacharalampopoulos, A.; Souflas, T. Indirect online tool wear monitoring and model-based identification of process-related signal. AIME
**2020**. submitted. [Google Scholar] - Stavropoulos, P.; Papacharalampopoulos, A.; Vasiliadis, E.; Chryssolouris, G. Tool wear predictability estimation in milling based on multi-sensorial data. Int. J. Adv. Manuf. Technol.
**2016**, 82, 509–521. [Google Scholar] [CrossRef] [Green Version] - Spanos, N.; Sakellariou, J.; Fassois, S. Vibration–response–only Statistical Time Series SHM methods: A critical assessment via a lab–scale wind turbine jacket foundation structure and two sensor types. In Proceedings of the ISMA 2016–International Conference on Noise and Vibration Engineering, Leuven, Belgium, 21 September 2016; pp. 4081–4095. [Google Scholar]
- Havlicek, H.; Svozil, K. Dimensional lifting through the generalized Gram–Schmidt process. Entropy
**2018**, 20, 284. [Google Scholar] [CrossRef] [Green Version]

**Figure 2.**Akaike information criterion (AIC) values as a function of the system order (for system of Equation (3)).

**Figure 4.**The rank of the responses matrices as a function of the responses matrix dimensions for the case of a first order system.

**Figure 5.**The rank of the responses matrices as a function of the responses matrix dimensions and the proximity of the poles in the case of a second order system. Noise is present.

**Figure 6.**The rank of the responses matrices as a function of the responses matrix dimensions, for the case of Equation 6, where ${f}_{0}\left[n\right]=sin\left[n\right]$ and the upper limit of the sum ${N}_{0}$ varies. The values of ${N}_{0}$ are shown within the plots.

**Figure 7.**The rank of the responses matrices as a function of the responses matrix dimensions, for the case of Equation 6, where ${f}_{0}\left[n\right]={e}^{-n}$ and the upper limit of the sum ${N}_{0}$ varies. The values of ${N}_{0}$ are shown above the plots.

Order of System | Determinant of Co-variance Matrix |
---|---|

2 | $0.00106278$ |

3 | $1.96022\times {10}^{-12}$ |

4 | $-5.85109\times {10}^{-26}$ |

5 | $-4.11625\times {10}^{-40}$ |

6 | $6.85315\times {10}^{-55}$ |

7 | $1.71849\times {10}^{-68}$ |

8 | $1.78185\times {10}^{-82}$ |

© 2020 by the author. 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 (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Papacharalampopoulos, A.
Investigating Data-Driven Systems as Digital Twins: Numerical Behavior of Ho–Kalman Method for Order Estimation. *Processes* **2020**, *8*, 431.
https://doi.org/10.3390/pr8040431

**AMA Style**

Papacharalampopoulos A.
Investigating Data-Driven Systems as Digital Twins: Numerical Behavior of Ho–Kalman Method for Order Estimation. *Processes*. 2020; 8(4):431.
https://doi.org/10.3390/pr8040431

**Chicago/Turabian Style**

Papacharalampopoulos, Alexios.
2020. "Investigating Data-Driven Systems as Digital Twins: Numerical Behavior of Ho–Kalman Method for Order Estimation" *Processes* 8, no. 4: 431.
https://doi.org/10.3390/pr8040431