Model Selection ensuring Practical Identifiability for Models of Electric Drives with Coupled Mechanics

Tantau, Mathias; Popp, Eduard; Perner, Lars; Wielitzka, Mark; Ortmaier, Tobias

doi:10.1016/j.ifacol.2020.12.1400

“…Chen et al (2002); Villwock (2007), works on model selection are mainly limited to data-driven, static models (Hoeting et al (1999)) of other disciplines such as biology (Volinsky et al (1996)) and finance (Draper (1995)). Here, transfer function models of servo systems are identified in frequency domain allowing an intuitive comparison with the measurements and avoiding the difficulty to automatize time domain simulations, see Tantau et al (2019Tantau et al ( , 2020. The challenge with these models is that linearity in the physical parameters is generally not maintained.…”

Section: Introductionmentioning

confidence: 99%

Model selection for servo control systems

Tantau¹,

Perner²,

Wielitzka³

2021

IJMA

0

View full text Add to dashboard Cite

Physically motivated models of electromechanical motion systems are required in several applications related to control design, model-based fault detection and simply interpretation. Often, however, the high effort of modelling prohibits these model-based methods in industrial applications. Therefore, all approaches of automatic modelling / model selection are naturally appealing. An intuitive approach is to identify the parameters of several model candidates and to select the one with the best fit on unseen data. A shortcoming of this approach is that the chosen model may be one with high complexity in which some of the physically interpretable parameters are not practically identifiable and uncertain. Also, ambiguities in selecting the model structure would not be disguised resulting in false confidence in a chosen model. Designing a reasonable set of candidate models requires that distinguishability of models can be checked prior to the identification procedure.This paper proposes a strategy for frequency domain model selection. The resulting model is tailored to ensure practical identifiability of all parameters for the given excitation. The analysis is based on local sensitivity calculated for the frequency domain cost function. Also, the paper describes distinguishability analysis of candidate models utilizing transfer function coefficients and Markov parameters. Model selection and distinguishability analysis are applied to a class of models as they are commonly used to describe servo control systems. It is shown in experiments on an industrial stacker crane that model selection works with little user interaction, except from defining normalized hyperparameters and ensuring that the resulting model is sound. Distinguishability is analysed systematically for all models that result from rearranging actuator, sensor and spring-damper elements along a chain of discrete masses. It can be proved or disproved for almost all combinations of potential models.

show abstract

Control-Relevant Model Selection for Servo Control Systems

Tantau

¹

,

Jonsky²,

Ziaukas

³

et al. 2022

2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)

0

View full text Add to dashboard Cite

Model selection for servo control systems

Tantau¹,

Perner²,

Wielitzka³

2021

IJMA

0

View full text Add to dashboard Cite

Physically motivated models of electromechanical motion systems are required in several applications related to control design, model-based fault detection and simply interpretation. Often, however, the high effort of modelling prohibits these model-based methods in industrial applications. Therefore, all approaches of automatic modelling / model selection are naturally appealing. An intuitive approach is to identify the parameters of several model candidates and to select the one with the best fit on unseen data. A shortcoming of this approach is that the chosen model may be one with high complexity in which some of the physically interpretable parameters are not practically identifiable and uncertain. Also, ambiguities in selecting the model structure would not be disguised resulting in false confidence in a chosen model. Designing a reasonable set of candidate models requires that distinguishability of models can be checked prior to the identification procedure.This paper proposes a strategy for frequency domain model selection. The resulting model is tailored to ensure practical identifiability of all parameters for the given excitation. The analysis is based on local sensitivity calculated for the frequency domain cost function. Also, the paper describes distinguishability analysis of candidate models utilizing transfer function coefficients and Markov parameters. Model selection and distinguishability analysis are applied to a class of models as they are commonly used to describe servo control systems. It is shown in experiments on an industrial stacker crane that model selection works with little user interaction, except from defining normalized hyperparameters and ensuring that the resulting model is sound. Distinguishability is analysed systematically for all models that result from rearranging actuator, sensor and spring-damper elements along a chain of discrete masses. It can be proved or disproved for almost all combinations of potential models.

show abstract

Model Selection ensuring Practical Identifiability for Models of Electric Drives with Coupled Mechanics

Cited by 4 publications

References 17 publications

Model selection for servo control systems

Model selection for servo control systems

Control-Relevant Model Selection for Servo Control Systems

Model selection for servo control systems

Contact Info

Product

Resources

About