Constrained iterative learning control of batch transesterification process under uncertainty

De, Riju; Bhartiya, Sharad; Shastri, Yogendra

doi:10.1016/j.conengprac.2020.104580

Cited by 9 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The kinetic model involving the mass balances on the reactants is adopted from [43,44] and is given as:…”

Section: System Descriptionmentioning

confidence: 99%

TASAC: a twin-actor reinforcement learning framework with stochastic policy for batch process control

Joshi¹,

Kodamanaa²,

Kandath³

et al. 2022

Preprint

View full text Add to dashboard Cite

Due to their complex nonlinear dynamics and batch-to-batch variability, batch processes pose a challenge for process control. Due to the absence of accurate models and resulting plant-model mismatch, these problems become harder to address for advanced model-based control strategies. Reinforcement Learning (RL), wherein an agent learns the policy by directly interacting with the environment, offers a potential alternative in this context. RL frameworks with actor-critic architecture have recently become popular for controlling systems where state and action spaces are continuous. It has been shown that an ensemble of actor and critic networks further helps the agent learn better policies due to the enhanced exploration due to simultaneous policy learning. To this end, the current study proposes a stochastic actor-critic RL algorithm, termed Twin Actor Soft Actor-Critic (TASAC), by incorporating an ensemble of actors for learning, in a maximum entropy framework, for batch process control.

show abstract

“…The kinetic model involving the mass balances on the reactants is adopted from [43,44] and is given as:…”

Section: System Descriptionmentioning

confidence: 99%

TASAC: a twin-actor reinforcement learning framework with stochastic policy for batch process control

Joshi¹,

Kodamanaa²,

Kandath³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“… 30 , 31 Along similar lines, a constrained batch-to-batch ILC that utilizes the previous knowledge of the process to obtain the updated control policy was proposed. 32 , 33 It is also shown that latent variable point-to-point iterative learning MPC (LV-PTP-ILMPC) shows faster convergence and better efficiency as compared to the PTP-ILC. 34 Tube-based ILMPC proved to show superior performance for nonlinear batch processes as compared to the ILMPC.…”

Section: Introductionmentioning

confidence: 99%

“…In related work, to capture inherently time-varying parameters and non-linearities, the linear parameter varying model has been used in a model learning MPC framework for the batch process . Further, it has been shown that a combination of ILC with appropriate process knowledge and system identification techniques helps in multi-variable nonlinear tracking problem. , Along similar lines, a constrained batch-to-batch ILC that utilizes the previous knowledge of the process to obtain the updated control policy was proposed. , It is also shown that latent variable point-to-point iterative learning MPC (LV-PTP-ILMPC) shows faster convergence and better efficiency as compared to the PTP-ILC . Tube-based ILMPC proved to show superior performance for nonlinear batch processes as compared to the ILMPC .…”

Section: Introductionmentioning

confidence: 99%

“…The batch-MPC scheme has shown success in rejection of both non-repetitive and repetitive disturbances in selective laser melting applications . Even though various accounts that independently validate MPC and ILC for the control of various batch processes have been reported in literature, ,,− there have been only limited attempts to integrate them and study their performance. Therefore, these individual experimental reports ,,− provide the motivation to explore potential of joint MPC and ILC frameworks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Batch-to-Batch Adaptive Iterative Learning Control─Explicit Model Predictive Control Two-Tier Framework for the Control of Batch Transesterification Process

Gupta

Kodamana

et al. 2022

ACS Omega

Self Cite

View full text Add to dashboard Cite

To harness energy security and reduce carbon emissions, humankind is trying to switch toward renewable energy resources. To this extent, fatty acid methyl esters, also known as biodiesel, are popularly used as a green fuel. Fatty acid methyl esters can be produced by a batch transesterification reaction between vegetable oil and alcohol. Being a batch process, fatty acid methyl esters production is beset with issues such as uncertainties and unsteady state behavior, and therefore, adequate process control measures are necessitated. In this study, we have proposed a novel two-tier framework for the control of the fatty acid methyl esters production process. The proposed approach combines the constrained batch-to-batch iterative learning control technique and explicit model predictive control to obtain the desired concentration of the fatty acid methyl esters. In particular, the batch-to-batch iterative learning control technique is used to generate reactor temperature set-points, which is further utilized to obtain an optimal coolant flow rate by solving a quadratic objective cost function, with the help of explicit model predictive control. Our simulation results indicate that the fatty acid methyl esters concentration trajectory converges to the desired batch trajectory within four batches for uncertainty in activation energy and six batches for uncertainty in both inlet concentration of triglyceride and in activation energy even in the presence of process disturbances. The proposed approach was compared to the heuristic-based approach and constraint iterative learning control approach to showcase its efficacy.

show abstract

“…With less modelling investigation about the temperature control of a semi-batch chemical reactor, a feedback-feedforward ILC is proposed for temperature trajectory tracking (Mezghani et al, 2002). In the case of model uncertainties and unmeasured disturbances, a constrained quadratic programming problem based batch-to-batch ILC framework is demonstrated for optimizing the endpoint fatty acid methyl esters concentration by controlling the hot water flow profile passing through the reactor jacket (De et al, 2020). By using batch-wise linearized models identified from operation data, a batch-to-batch ILC is designed for a fed-batch fermentation process (Jewaratnam et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

ILC-based initial disturbance compensation feedforward controller for tricalcium neutralization process

Pei

Zhao

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

Tricalcium neutralization process (TNP) is one of the key recover process in citric acid production process. In this process, the amount of calcium carbonate added needs to be controlled to ensure the pH of the reactants within the target range at the end-point of every batch. But the random initial pH of the fermentation broth impacts a lot on the stability of the end point pH. In this work, an ILC-based control strategy is proposed to optimize the addition of calcium carbonate. First, the ILC is performed and the optimal input of the process can be obtained after several batches. Second, an initial disturbance compensation controller optimized by ILC is proposed. An experimental platform for TNP is designed, and the results demonstrate the proposed control strategy can achieve the end point pH control and suppress the disturbance by the indeterminate initial pH value.

show abstract

Constrained iterative learning control of batch transesterification process under uncertainty

Cited by 9 publications

References 37 publications

TASAC: a twin-actor reinforcement learning framework with stochastic policy for batch process control

TASAC: a twin-actor reinforcement learning framework with stochastic policy for batch process control

Batch-to-Batch Adaptive Iterative Learning Control─Explicit Model Predictive Control Two-Tier Framework for the Control of Batch Transesterification Process

ILC-based initial disturbance compensation feedforward controller for tricalcium neutralization process

Contact Info

Product

Resources

About