2020
DOI: 10.1109/access.2020.3017532
|View full text |Cite
|
Sign up to set email alerts
|

Parameter Self-Tuning of SISO Compact-Form Model-Free Adaptive Controller Based on Long Short-Term Memory Neural Network

Abstract: Model-free adaptive controller (MFAC) is a novel data-driven control methodology that relies only on input/output (I/O) measurement data instead of classic mathematical models of actual controlled plants. The single-input single-output (SISO) compact-form MFAC (SISO-CFMFAC) is a promising method for controlling SISO nonlinear time-varying systems. The parameters in SISO-CFMFAC must be carefully tuned before use, as inappropriate parameters may lead to poor control performance. However, up to now, parameter tun… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
16
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
5
1

Relationship

2
4

Authors

Journals

citations
Cited by 9 publications
(17 citation statements)
references
References 40 publications
1
16
0
Order By: Relevance
“…In practical application scenarios, as the amount of data grows and the controlled systems become more complex, ordinary neural networks such as BP neural networks can no longer tune parameters accurately, which are easy to fail into local optimum [29]. In previous research work [30], it has been found that the LSTM neural network can estimate the parameters to be tuned in the MFAC in real time, and its optimization effect on the MFAC is more obvious than that of the BP neural network, which proves the superiority of LSTM neural network and the necessity of introducing it to tune essential parameters online of partial-form MFAC. Moreover, for partial-form MFAC, PG's change will also become complicated when the controlled system is strongly nonlinear.…”
Section: Introductionmentioning
confidence: 99%
“…In practical application scenarios, as the amount of data grows and the controlled systems become more complex, ordinary neural networks such as BP neural networks can no longer tune parameters accurately, which are easy to fail into local optimum [29]. In previous research work [30], it has been found that the LSTM neural network can estimate the parameters to be tuned in the MFAC in real time, and its optimization effect on the MFAC is more obvious than that of the BP neural network, which proves the superiority of LSTM neural network and the necessity of introducing it to tune essential parameters online of partial-form MFAC. Moreover, for partial-form MFAC, PG's change will also become complicated when the controlled system is strongly nonlinear.…”
Section: Introductionmentioning
confidence: 99%
“…If only the projection method of MFAC is utilized to calculate PG values alone, the estimated values may significantly deviate from the ideal values, impairing the control performance. As previous research has found, the PG values of MFAC remain the initial constant values during part of the time interval in the three-tank system simulation [ 27 ]. This demonstrates that when dealing with control problems with significant time delays, the default PG estimation projection algorithm in MFAC has a certain probability of triggering the reset mechanism, resulting in the method failing to capture the nonlinear properties of the controlled system.…”
Section: Introductionmentioning
confidence: 66%
“…Parameters and have been shown to be significantly important in the design of FFMFAC by several studies [ 24 , 25 , 27 ].These studies emphasize the significance of fine-adjusting these parameters in response to changes in the controlled system, with theoretical analysis and simulation findings indicating how improper parameter selection can impact the stability of the controller, resulting in reduced control performance. Furthermore, it should be stressed that PG values should be precisely estimated in order to realize the FFMFAC.…”
Section: Problem Definitionmentioning
confidence: 99%
See 1 more Smart Citation
“…In [18], CFMFAC which has characteristics of straightforward operation is combined with a parameter self-tuning mechanism using backpropagation neural networks (BPNN). However, by combining a CFMFAC with a neural network with long-term short-term memory architecture, authors in [19] has shown better tracking performances compared to [18]. Unfortunately, many adaptive weights were used which increases the computational load.…”
Section: Introductionmentioning
confidence: 99%