Abstract:In this paper, a new subspace identification approach based on principal component analysis (PCA) and noise estimation is developed for multivariable dynamic process modeling. In contrast to typical subspace identification methods based on standard PCA with instrumental variables, the noise term is first estimated and naturally eliminated in the proposed approach, and then a PCA procedure is used to determine system observability subspace and extract system matrices A, B, C, and D from the estimated observabil… Show more
“…The unbiased estimate of the noise term E can be derived by a least‐squares method through Equation as the sampling number tends to infinity. The noise term estimation can be obtained by minimizing the objective J , where indicates the Frobenius norm operator . In order to solve Equation , QR factorization is performed to estimate the least‐squares residual .…”
Section: Methodology Of Eepcamentioning
confidence: 99%
“…A can be calculated by the following equation: where Γ is the constant nonsingular matrix and . By taking Γ as the identity matrix, the model coefficient matrix A could be estimated from and .…”
Section: Methodology Of Eepcamentioning
confidence: 99%
“…where • k k 2 F indicates the Frobenius norm operator. 35 In order to solve Equation 7, QR factorization is per-…”
Section: Noise Term Estimationmentioning
confidence: 99%
“…By taking Γ as the identity matrix, the model coefficient matrix A could be estimated [35][36][37] from e P β and e P α .…”
Summary
In a large‐scale chemical plant, it is important to evaluate the energy efficiency (EE) of production to improve the production process and make production decisions. Essentially, finding the relationship model is the foundation of EE evaluation. Given the requirements of universality and practicability, the data‐driven model is widely used to describe the variable relationships. However, the variables stored in the data bank may be redundant, and some variables contain disturbances in the large‐scale chemical process, increasing the complexity of the model establishment. In this paper, a new EE factor extraction and EE evaluation method based on principal component analysis (PCA) (EEPCA) is proposed to enhance the accuracy of the EE values. By three stages (noise term estimation, model establishment, and model variable selection) in EEPCA, the accurate relationship models of utilized energy mediums and chemical products are established. On the basis of the built models, the EE of the chemical processes is evaluated and inferred. The effectiveness and practicality of the proposed method are demonstrated via a simulated process and a practical ethylene production.
“…The unbiased estimate of the noise term E can be derived by a least‐squares method through Equation as the sampling number tends to infinity. The noise term estimation can be obtained by minimizing the objective J , where indicates the Frobenius norm operator . In order to solve Equation , QR factorization is performed to estimate the least‐squares residual .…”
Section: Methodology Of Eepcamentioning
confidence: 99%
“…A can be calculated by the following equation: where Γ is the constant nonsingular matrix and . By taking Γ as the identity matrix, the model coefficient matrix A could be estimated from and .…”
Section: Methodology Of Eepcamentioning
confidence: 99%
“…where • k k 2 F indicates the Frobenius norm operator. 35 In order to solve Equation 7, QR factorization is per-…”
Section: Noise Term Estimationmentioning
confidence: 99%
“…By taking Γ as the identity matrix, the model coefficient matrix A could be estimated [35][36][37] from e P β and e P α .…”
Summary
In a large‐scale chemical plant, it is important to evaluate the energy efficiency (EE) of production to improve the production process and make production decisions. Essentially, finding the relationship model is the foundation of EE evaluation. Given the requirements of universality and practicability, the data‐driven model is widely used to describe the variable relationships. However, the variables stored in the data bank may be redundant, and some variables contain disturbances in the large‐scale chemical process, increasing the complexity of the model establishment. In this paper, a new EE factor extraction and EE evaluation method based on principal component analysis (PCA) (EEPCA) is proposed to enhance the accuracy of the EE values. By three stages (noise term estimation, model establishment, and model variable selection) in EEPCA, the accurate relationship models of utilized energy mediums and chemical products are established. On the basis of the built models, the EE of the chemical processes is evaluated and inferred. The effectiveness and practicality of the proposed method are demonstrated via a simulated process and a practical ethylene production.
“…For example, the ARX and ARARX processes have been extended for the case of additive white noise on the input and output observation 23 . Similarly, subspace identification based on principal component analysis has been proposed by estimating the noise term 24 . Under different noise models using closed‐loop operation data, several subspace identification methods (i.e., canonical variate analysis, CVA, N4SID, PLS, ARX) were able to identify correctly the process models 25 .…”
This work focuses on machine learning modeling and predictive control of nonlinear processes using noisy data. We use long short‐term memory (LSTM) networks with training data from sensor measurements corrupted by two types of noise: Gaussian and non‐Gaussian noise, to train the process model that will be used in a model predictive controller (MPC). We first discuss the LSTM training with noisy data following a Gaussian distribution, and demonstrate that the standard LSTM network is capable of capturing the underlying process dynamic behavior by reducing the impact of noise. Subsequently, given that the standard LSTM performs poorly on a noisy data set from industrial operation (i.e., non‐Gaussian noisy data), we propose an LSTM network using Monte Carlo dropout method to reduce the overfitting to noisy data. Furthermore, an LSTM network using co‐teaching training method is proposed to further improve its approximation performance when noise‐free data from a process model capturing the nominal process state evolution is available. A chemical process example is used throughout the manuscript to illustrate the application of the proposed modeling approaches and demonstrate their open‐ and closed‐loop performance under a Lyapunov‐based model predictive controller with state measurements corrupted by industrial noise.
In this paper, an alternative consistent subspace identification method using parity space is proposed. The future/past input data and the past output data are used to construct the instrument variable to eliminate the noise effect on consistent estimation. The extended observability matrix and the triangular block-Toeplitz matrix are then retrieved from a parity space of the noise-free matrix using a singular value decomposition based method. The system matrices are finally estimated from the above estimated matrices. The consistency of the proposed method for estimation of the extended observability matrix and the triangular block-Toeplitz matrix is established. Compared with the classical SIMs using parity space like SIMPCA and SIMPCA-Wc, the proposed method generally enhances the estimated model efficiency/accuracy thanks to the use of future input data. Two examples are presented to illustrate the effectiveness and merit of the proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.