A Kalman smoother based estimation approach for dynamic adjustment systems with irregularly missing output data
- Resource Type
- Conference
- Authors
- Ding, Shaohua; Liu, Yanjun; Chen, Jing; Ma, Junxia
- Source
- 2021 4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS) Industrial Cyber-Physical Systems (ICPS), 2021 4th IEEE International Conference on. :749-754 May, 2021
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Analytical models
Parameter estimation
Heuristic algorithms
Conferences
Estimation
Stochastic processes
Cyber-physical systems
irregularly missing output
model equivalent transformation
auxiliary model
Kalman smoother
- Language
This paper focuses on the identification of dynamical adjustment systems with irregularly missing outputs. A problem of the existing auxiliary model-based generalized stochastic gradient (AM-GSG) algorithm is that the parameter estimation accuracy is unsatisfactory since it relies on the estimations of the missing outputs and the noise terms involved in the information vector. In order to overcome this problem, this paper presents two identification approaches. A model equivalent transformation and auxiliary model-based modified stochastic gradient (MET-AM-M-SG) algorithm is presented to avoid estimating the unknown noise terms. And a model equivalent transformation and Kalman smoother-based modified stochastic gradient (MET-KS-M-SG) algorithm is further proposed by improving the missing output estimator. A simulation example is given to show the effectiveness of the proposed algorithms.