Control-oriented dynamic model of an inductively coupled plasma torch by artificial intelligence methodology

Kh, Kim

doi:10.1088/1361-6587/aaffb4

Cited by 3 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was mentioned that such approach can better capture the dynamic characteristics, comparing with the normal neural network. Kim examined a linear autoregressive with exogenous (ARX) model and ARX-type neural network models to develop a control-oriented dynamic model of an inductively coupled plasma torch, similar to the work of Liu et al (Ref 39 ). The present work uses RF to prepare three models: the baseline, the simple embedded and the differenced embedded.…”

Section: Discussionmentioning

confidence: 99%

Ensemble Methods for APS In-Flight Particle Temperature and Velocity Prediction Considering Torch Electrodes Ageing

Cojocaru

Ilinca

et al. 2023

J Therm Spray Tech

View full text Add to dashboard Cite

The nonlinear relationship between the input process parameters and in-flight particle characteristics of the atmospheric plasma spray (APS) is of paramount importance for coating properties design and quality. It is also known that the ageing of torch electrodes affects this relationship. In recent years, machine learning algorithms have proven to be able to take into account such complex nonlinear interactions. This work illustrates the application of ensemble methods to predict the in-flight particle temperature and velocity during an APS process considering torch electrodes ageing. Experiments were performed to record simultaneously the input process parameters, the in-flight powder particle characteristics and the electrodes usage time. Random Forest (RF) and Gradient Boosting (GB) were used to rank and select the features for the APS process data recorded as the electrodes aged and the corresponding predictive models were compared. The time series aspect of the multivariate APS in-flight particle characteristics data is explored. Two strategies of time series embedding are considered. The first one simply embeds the attributes and the targets from the previous $$n$$ n time segments considered without any modification; whereas the second strategy first performs differencing to make the time series stationary before embedding. For the present application, RF is found to be more suitable than GB since RF can predict both the in-flight particle velocity and temperature simultaneously, properly considering the interactions between the two targets. On the other hand, GB can only predict these two targets one at a time. The superior performance of both embedded predictive models and the feature rankings of them suggest that it is better to consider the APS data as time series for the in-flight particle characteristic prediction. In particular, it is demonstrated that it is advantageous to first make the time series stationary using the traditional differencing technique, even when modeling using RF.

show abstract

Section: Discussionmentioning

confidence: 99%

Ensemble Methods for APS In-Flight Particle Temperature and Velocity Prediction Considering Torch Electrodes Ageing

Cojocaru

Ilinca

et al. 2023

J Therm Spray Tech

View full text Add to dashboard Cite

show abstract

Control of Plasma Systems

2022

Voltage‐Enhanced Processing of Biomass and Biochar

View full text Add to dashboard Cite

Robust model reference adaptive controller for atmospheric plasma spray process

Guduri

Batra

2022

SN Appl. Sci.

View full text Add to dashboard Cite

We add the σ-modification and the low-frequency learning to the model reference adaptive controller (MRAC) (Guduri et al. in SN Appl Sci 3:1–21, 2021) to make it robust in the presence of two simultaneous bounded disturbances and maintain consistent mean particles’ temperature and velocity collectively called mean particles’ states (MPSs) when they impact the substrate to be coated. The MPSs affect the coating quality. Even though results are applicable to several coating processes, we consider an atmospheric plasma spray process (APSP). It is shown that the proposed controller can quickly adopt to disturbances in the average injection velocity of powder particles and in the arc voltage to change the input current, and the argon and the hydrogen flow rates to maintain constant values of the MPSs. The effects of the parameter values in the MRAC, the MRAC with $$\sigma$$ σ -modification (R-MRAC), and the R-MRAC with low-frequency learning (MR-MRAC) schemes on tracking error convergence, steady-state tracking error, disturbance rejection and the presence of overshoot have been studied. The numerical experiments suggest that $$2 \le \gamma \le 20,$$ 2 ≤ γ ≤ 20 , $$10 \le \sigma \le 100,$$ 10 ≤ σ ≤ 100 , and $$20 \le \lambda \le 80$$ 20 ≤ λ ≤ 80 for the MR-MRAC provide fast adaptation, no overshoot, and low tracking error in the controlled response. The parameter $$\lambda > 0$$ λ > 0 suppresses high-frequency oscillations in the closed-loop control system, and $$\gamma$$ γ serves to tune the controller gains. The control scheme has been tested using the software, LAVA-P, that simulates well an APSP.

show abstract

Control-oriented dynamic model of an inductively coupled plasma torch by artificial intelligence methodology

Cited by 3 publications

References 27 publications

Ensemble Methods for APS In-Flight Particle Temperature and Velocity Prediction Considering Torch Electrodes Ageing

Ensemble Methods for APS In-Flight Particle Temperature and Velocity Prediction Considering Torch Electrodes Ageing

Control of Plasma Systems

Robust model reference adaptive controller for atmospheric plasma spray process

Contact Info

Product

Resources

About