Least Square Fast Learning Network for modeling the combustion efficiency of a 300WM coal-fired boiler

Li, Guoqiang; Niu, Peifeng; Wang, Huaibao; Liu, Yongchao

doi:10.1016/j.neunet.2013.12.006

Cited by 29 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Equation (10) is a penalized logistic log-likelihood function and it can be iterated to maximize. The iterative reweighted least squares (IRLS) algorithm [22] is used to find the W to maximize Equation (10). The first and second derivatives of equation (10) with respect to W can be written as…”

Section: Sparse Bayesian Learning For Flnmentioning

confidence: 99%

“…Similarly with original ELM, FLN transforms network training into solving linear least-squares problems, and then computes the output weights through the Moore-Penrose generalized inverse [9], so the training speed is very fast. Due to these advantages, FLN has been successfully applied in the real world problem [10][11][12]. In recent years, various improved training algorithms have been proposed for ELM to improve the pseudoinverse operation in ELM training [13,14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sparse Bayesian approach to fast learning network for multiclassification

Zhao¹,

Liu²,

Wu³

et al. 2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This paper proposes a novel artificial neural network called sparse-Bayesian-based fast learning network (SBFLN). In SBFLN, sparse Bayesian regression is used to train the fast learning network (FLN), which is an improved extreme learning machine (ELM). The training process of SBFLN is to randomly generate the input weights and the hidden layer biases, and then find the probability distribution of other weights by the sparse Bayesian approach. SBFLN calculates the predicted output through Bayes estimator, so it can provide a natural marginal possibility for classification problems and can solve the overfitting problem caused by the least-squares estimation in FLN. In addition, the sparse Bayesian approach can automatically trim most redundant neurons in hidden layer, which makes the network more compact and accurate. To verify the effectiveness of the improvements in this paper, the results of SBFLN are evaluated in 15 benchmark classification problems. The experimental results show that SBFLN is not sensitive to the number of neurons in the hidden layer, and the performance of SBFLN is competitive or superior to some other state-of-the-art algorithms.

show abstract

Section: Sparse Bayesian Learning For Flnmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Sparse Bayesian approach to fast learning network for multiclassification

Zhao¹,

Liu²,

Wu³

et al. 2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…Boilers are the key equipment for energy conversion. The energy consumption management of a power plant mainly focuses on the modeling of a boiler combustion system based on big data, (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12)(13) the optimization of a combustion coal mixture strategy, (14)(15)(16) and boiler unit equipment improvement. (17) References 1-5 indicate the use of the neural network method to model the key parameters of boiler combustion optimization and the selection of input parameters that is only based on manual operation experience.…”

Section: Introductionmentioning

confidence: 99%

Research on Energy Management Strategy of Captive Power Plant Based on Hybrid Method

Liu¹,

Huang²,

Liu³

et al. 2019

Sensors and Materials

View full text Add to dashboard Cite

Compared with a regular power plant, the load and fuel composition of a captive power plant vary greatly, resulting in complex and variable working conditions, and for specific operating conditions, there is a lack of data. Considering the irregularity and incompleteness of the data, a data-mining-based boiler energy management analysis method was proposed in this paper. This study adopted the random forest and recursive feature elimination (RF-RFE) method to select the features of distributed control system (DCS) monitoring data. According to different load intervals, some data with better running conditions were selected for clustering. According to the clustering center, adjustable parameters were optimized, and the obtained optimization results were input to the support vector machine model for energy consumption comparison. The results show that the method used in this study can reduce the unit energy consumption by 3-5% by adjusting the controllable parameters.

show abstract

“…Kusiak and Song (2006) and Song and Kusiak (2007) adopted data-mining approach to optimize combustion efficiency of a coal-fired boiler and validate the experimental results by a virtual testing procedure. Li et al (2014) employed a least square fast learning network to build the combustion characteristics of a 300 MW coal-fired boiler which achieved very good generalization performance and stability under various operational conditions. Chu et al (2003) also employed artificial neural network to model the combustion process of a coal-fired boiler, and made the maximization of thermal efficiency within NOx and CO emission limits.…”

Section: Introductionmentioning

confidence: 99%

“…In order to deal with the above problems, the present paper proposes an Online Least Squared Fast Learning Network (OLSFLN), which is based on Least Squared Fast Learning Network published in the literature (Li et al, 2014). In OLSFLN, all of the initial weights and biases are analytically calculated by the twice least square method, and then, continually updated according to sequentially samples.…”

Section: Introductionmentioning

confidence: 99%

Modeling Thermal Efficiency of a 300 MW Coal-Fired Boiler by Online Least Square Fast Learning Network

Chen

Chan

et al. 2018

J. Chem. Eng. Japan / JCEJ

View full text Add to dashboard Cite

Improving boiler thermal e ciency plays a very important role in the economic development of power plants. In order to implement a real-time improvement in the boiler thermal e ciency, a precise and rapid online model of the thermal e ciency is required. The present paper presents an e ective machine learning method called the Online Least Square Fast Learning Network (OLSFLN) to build a prediction model for 300 MW coal-red boiler thermal e ciency. Experimental results demonstrate that the proposed OLSFLN could predict the boiler thermal e ciency with high accuracy and outperform in learning ability, generalization ability and repeatability under various boiler operating conditions than other state-of-the-art algorithms.

show abstract

Least Square Fast Learning Network for modeling the combustion efficiency of a 300WM coal-fired boiler

Cited by 29 publications

References 17 publications

Sparse Bayesian approach to fast learning network for multiclassification

Sparse Bayesian approach to fast learning network for multiclassification

Research on Energy Management Strategy of Captive Power Plant Based on Hybrid Method

Modeling Thermal Efficiency of a 300 MW Coal-Fired Boiler by Online Least Square Fast Learning Network

Contact Info

Product

Resources

About