Handling Constraints and Raw Material Variability in Rotomolding through Data-Driven Model Predictive Control

Garg, Abhinav; Abdulhussain, Hassan A.; Mhaskar, Prashant; Thompson, Michael R.

doi:10.3390/pr7090610

Cited by 6 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the subsequent sections we will introduce a method of SSID for multiphase process, MPSSID. The accuracy of MPSSID in comparison to traditional, one-phase SSID will then be tested using data sets obtained from historical batch runs, some of which were analyzed in refs and . The mathematical background required for an understanding MPSSID is presented in the next subsection.…”

Section: Preliminariesmentioning

confidence: 99%

“…SSID was tested on a laboratory-scale, uniaxial rotomolding process in refs and , but the underlying models utilized in these works are not designed to capture the multiphase nature of the process. This is especially problematic early in the process, when the prediction horizon of the model is large and spans multiple phases.…”

Section: Preliminariesmentioning

confidence: 99%

“…We tested this question using data obtained from historical batch runs of the laboratory-scale, uniaxial rotomolding process that was mentioned in section , which is characterized by multiple, distinct phases. Previous one-phase SSID model-based predictive control formulations were able to meet the specified quality standards; , however, the emphasis here is to seek improvements to the predictive capability of the data-driven model to yield improved control performance. Increased confidence in the model and controller is likely to make it easier to transition from lab to industrial scale and experiment with new MPC formulations such as economic control.…”

Section: Application To the Motivating Examplementioning

confidence: 99%

See 2 more Smart Citations

Data-Driven Modeling for Multiphase Processes: Application to a Rotomolding Process

Ubene

Mhaskar

2023

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

This paper addresses the problem of capturing the multiphase nature of a rotational molding process using subspace identification (SSID) to enable improved control. Existing SSID techniques are not designed to utilize any known, multiphase nature of a process in the model identification stage. This work adapts existing SSID methods to account for multiple phases by splitting the data into phases during the identification step and building a distinct SSID model for each phase while carefully connecting the individual models through the means of subspace states. This is achieved via a partial least-squares (PLS) model that relates the final states of the preceding phase to the initial states of the proceeding phase. This multiphase subspace identification (MPSSID) approach exploits the ability of SSID techniques for dynamic modeling of batch processes, which allows for model construction using batches of nonuniform length. In this work, the proposed approach is applied to the rotational molding process. For rotational molding, the final product quality is dependent on the temperature trajectory of the polymer inside the mold, and the process goes through visibly distinct phases that can be recognized when a specific temperature (not time) is reached. Data from past experiments are used to build the model and validate it, comparing the predictive ability of multiphase models to conventional one-phase models. Results demonstrate the ability of the multiphase models to better predict both the temperature trajectories and final product quality of validation batches.

show abstract

Section: Preliminariesmentioning

confidence: 99%

Section: Preliminariesmentioning

confidence: 99%

Section: Application To the Motivating Examplementioning

confidence: 99%

See 1 more Smart Citation

Data-Driven Modeling for Multiphase Processes: Application to a Rotomolding Process

Ubene

Mhaskar

2023

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Model predictive control (MPC) has been widely used in industrial communities due to its robustness, ability to tackle safety constraints, and inaccurate model [1,2]. As we all know, PID control is normally applied at the system's base layer, while the MPC controllers are usually employed at the supervisory layer [3].…”

Section: Introductionmentioning

confidence: 99%

An Improved Approach for Robust MPC Tuning Based on Machine Learning

Zhang

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A robust tuning method based on an artificial neural network for model predictive control (MPC) of industrial systems with parametric uncertainties is put forward in this work. Firstly, an efficient approach to characterize the mapping relationship between the controller parameters and the robust performance indices is established. As there are normally multiple conflicted robust performance indices to be considered in MPC tuning, the neural network is further used to fuse the indices to produce a simple label representing the acceptable level of the robust performance. Finally, an automated algorithm is proposed to tune the MPC parameters for the considered uncertain system to achieve the desired robust performance. In addition, the regulation of the pH value of the sewage treatment system is used to verify the effectiveness of the robust tuning algorithm which is described in this paper.

show abstract

“…Garg et al [12] present a method of uniquely specifying and robustly achieving user-specified product quality in a complex industrial batch process. They demonstrate this method using a lab-scale uni-axial rotational molding process.…”

mentioning

confidence: 99%