Generalized expectation–maximization approach to LPV process identification with randomly missing output data

Yang, Xianqiang; Huang, Biao; Zhao, Yujia; Lu, Yaojie; Xiong, Weili; Gao, Huijun

doi:10.1016/j.chemolab.2015.08.013

Cited by 14 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A substantial number of algorithms have been used in studies conducted for the purpose of imputation. K-nearest neighbour technique [57] and expectation maximisation algorithm [44,58] are among the most popular. They have been proven to result in a low imputation error in many cases, although their complexity and iterative manner make it computationally inefficient to utilise them for large datasets.…”

Section: Treatment Of Missing Valuesmentioning

confidence: 99%

Power production prediction of wind turbines using a fusion of MLP and ANFIS networks

Morshedizadeh

Kordestani

Carriveau

et al. 2018

IET Renewable Power Generation

View full text Add to dashboard Cite

Access to accurate power production prediction of a wind turbine in future hours enables operators to detect possible underperformance and anomalies in advance. This may enable more proactive and strategic operations optimisation. This study examines common Supervisory Control And Data Acquisition (SCADA) data over a period of 20 months for 21 pitch regulated 2.3 MW turbines. In this study, an algorithm is proposed to impute values of data that are missing, out-of-range, or outliers. It is shown that an appropriate combination of a decision tree and mean value for imputation can improve the data analysis and prediction performance by the creation of a smoother dataset. In addition, principal component analysis is employed to extract parameters with power production influence based on all available signals in the SCADA data. Then, a new data fusion technique is applied, combining dynamic multilayer perceptron (MLP) and adaptive neuro-fuzzy inference system (ANFIS) networks to predict future performance of wind turbines. This prediction is made on a scale of one-hour intervals. This novel combination of feature extraction, imputation, and MLP/ANFIS fusion performs well with favourably low prediction error levels. Thus, such an approach may be a valuable tool for turbine power production prediction.

show abstract

Section: Treatment Of Missing Valuesmentioning

confidence: 99%

Power production prediction of wind turbines using a fusion of MLP and ANFIS networks

Morshedizadeh

Kordestani

Carriveau

et al. 2018

IET Renewable Power Generation

View full text Add to dashboard Cite

show abstract

“…The identification of LPV time-delay system with parameter-varying time-delay and constant input timedelay was respectively considered in [7] and the unknown model parameters and time-delays were estimated. In [8], the identification of LPV system based on incomplete data set was handled and two algorithms to estimate the multiplemodel LPV finite impulse response (FIR) and the multiplemodel LPV output error (OE) model were developed. In [9], The associate editor coordinating the review of this manuscript and approving it for publication was Zhaojun Li .…”

Section: Introductionmentioning

confidence: 99%

Robust Parameter Estimation for a Class of Nonlinear System With EM Algorithm

Zhang

Liu

2020

IEEE Access

View full text Add to dashboard Cite

This paper is concerned with the robust parameter estimation for linear parameter varying (LPV) finite impulse response (FIR) model. The practical process data are typically polluted by outliers and conventional parameter estimation methods may fail to derive an unbiased estimate. In order to deal with outliers, the Laplace noise model is adopted and the robust system model for the described parameter estimation problem is established. The robust parameter estimation for LPV FIR model is formulated and solved in the EM algorithm scheme and the equations to estimate all the unknown parameters are derived. The efficacy of the proposed method is verified through a numerical simulation and a chemical unit.

show abstract

“…Another kind of methods are to compensate the missing data and identify the fast rate model directly. These methods include last reservation carried forward, regression substitution [21], expectation-maximization algorithm [22]- [25], and so on.…”

Section: Introductionmentioning

confidence: 99%

Variational Bayesian Inference for FIR Models With Randomly Missing Measurements

Yang

Yin

2017

IEEE Trans. Ind. Electron.

Self Cite

View full text Add to dashboard Cite

This paper is concerned with parameter and output estimation for industrial processes described by finite impulse response (FIR) model in presence of randomly missing output measurements. The statistical models for describing the estimation problems are given and the prior distributions over unknown parameters and variables are constructed. The estimation problems with incomplete data set are formulated in the variational Bayesian framework and the problems of randomly missing measurements, overfitting, and high sensitivity of parameter estimate to noise are handled simultaneously. The iterative formulas to estimate the posterior distributions of missing output data and unknown parameters based on available process data are derived. The simulation example and the hybrid tank system experiment are performed to demonstrate the effectiveness of the proposed method.

show abstract

Generalized expectation–maximization approach to LPV process identification with randomly missing output data

Cited by 14 publications

References 20 publications

Power production prediction of wind turbines using a fusion of MLP and ANFIS networks

Power production prediction of wind turbines using a fusion of MLP and ANFIS networks

Robust Parameter Estimation for a Class of Nonlinear System With EM Algorithm

Variational Bayesian Inference for FIR Models With Randomly Missing Measurements

Contact Info

Product

Resources

About