Experimental gradient estimation of multivariable systems with correlation by various regression methods and its application to modifier adaptation

Jeong, Dong Hwi; Lee, Chang Jun; Lee, Jong Min

doi:10.1016/j.jprocont.2018.08.008

Cited by 10 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[3] Actually, market competition is placing greater demands on the process industry to optimize operations. [14] What is more, optimization efficiency is extraordinarily critical for the industrial processes whose experiment cost is high, such as the cobalt oxalate synthesis process. [25] Further, due to the complicated mechanism of modern batch processes, the running time of a single batch may even take several days, which can be regarded as one main reasons of the high operational cost.…”

Section: Methodsmentioning

confidence: 99%

“…Necessary condition of optimality (NCO) matching is especially important since it guarantees the feasibility of the solution earned from the model when it is performed in practice, [ 13 ] and it is closely relevant to the product competitiveness. [ 14 ] To this end, an online model‐plant mismatch detection and model re‐identification framework was proposed and illustrated by Kumar et al [ 15 ] Gao et al proposed a novel real‐time optimization scheme that combines the quadratic approximation approach with the iterative gradient‐modification optimization scheme to handle the model–plant mismatch. [ 16 ] Generally, uncertainties such as complex dynamics, time‐varying nature, and variance of initial conditions are significant in industrial batch processes, which lead to severe model–plant mismatch.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient cobalt oxalate synthesis process optimization via second‐order modifier adaptation with transfer learning

Chu,

Chai,

Wang

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

This paper proposes a second‐order modifier adaptation optimization based on the transfer model, which aims to improve the optimization efficiency. Although the traditional modifier adaptation strategy adds a bias to the model to meet the necessary condition of optimality (NCO), approximating only to the first‐order may neglect some key higher‐order information. Making use of as much higher‐order information as possible is an effective way to improve the efficiency of optimization. For this issue, by introducing the second‐order information into the modifier adaptation method to compensate the mismatch of higher‐order information during the optimization, the compensation of the mismatch between model and plant can get accelerated, thus improving the optimization efficiency. To overcome the difficulty of insufficient data for new process modelling, a process transfer model is also used to fit the relationship between manipulated variables and final product quality. The simulation study of the cobalt oxalate synthesis process shows that this strategy has better optimization efficiency.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient cobalt oxalate synthesis process optimization via second‐order modifier adaptation with transfer learning

Chu,

Chai,

Wang

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

show abstract

“…The estimation of such plant gradients is a very difficult task to implement in practice, due to lack of information and measurement noise. 207,208 These problems have a significant effect on the gradient estimation, consequently, they reduce the overall performance of the MA scheme. Recent advances in MA schemes are reviewed in the survey paper by.…”

Section: Industrial Applications In Manufacturingmentioning

confidence: 99%

Industrial data science – a review of machine learning applications for chemical and process industries

et al. 2022

View full text Add to dashboard Cite

show abstract

“…A widely used strategy for extracting gradient information from noisy experimental data consists in fitting polynomial or spline curves to the data and evaluating the gradients analytically by differentiating the fitted curves. For example, in the context of MA, Jeong et al 31 proposed to estimate gradients using multivariable linear regression, partial least-squares regression, and principal component analysis. Also, Gao et al 32 proposed to use least-squares regression to obtain local quadratic approximations of the cost and constraint functions and evaluate the gradients by differentiating these quadratic approximations.…”

Section: Model Adequacy and Model Accuracy Play A Crucial Rolementioning

confidence: 99%

110th Anniversary: A Feature-Based Analysis of Static Real-Time Optimization Schemes

Srinivasan

Bonvin

2019

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

This paper addresses the steady-state optimization of continuous processes in the presence of uncertainty in the form of unknown or time-varying model parameters, structural plant-model mismatch, and disturbances. To address these issues, we assume that certain measurements are available in real time, and the question is how the plant inputs can be updated based on these measurements to drive the plant to optimality. This is the field of static real-time optimization (RTO). This paper shows that there are two distinguishing features that have a significant impact on the formulation and performance of RTO schemes. The first of these features is the type of measurements that is used, either generic or specific. The former corresponds to routinely available plant outputs, while the latter includes optimization-specific information such as the cost and constraint values with appropriate input excitation. The second of these features is the manner in which optimality is implemented, that is, via either repeated optimization or feedback control. It is argued that, if specific information is available, plant optimality can be achieved irrespective of the quality of the model. Also, the implementation method must consider the speed at which the information can be collected and the computational time required for numerical optimization. The importance of these implementation aspects is illustrated in a simulation of the optimization of the Willam− Otto reactor.

show abstract

Experimental gradient estimation of multivariable systems with correlation by various regression methods and its application to modifier adaptation

Cited by 10 publications

References 23 publications

Efficient cobalt oxalate synthesis process optimization via second‐order modifier adaptation with transfer learning

Efficient cobalt oxalate synthesis process optimization via second‐order modifier adaptation with transfer learning

Industrial data science – a review of machine learning applications for chemical and process industries

110th Anniversary: A Feature-Based Analysis of Static Real-Time Optimization Schemes

Contact Info

Product

Resources

About