Model turbine heat rate by fast learning network with tuning based on ameliorated krill herd algorithm
Introduction
With the rapid growth of energy consumption and the aggravation of environmental pollution, the steam turbine heat rate forecast problem of power plants attracts the attention of technology staffs and researchers. Heat rate refers to the calories required to produce a kilowatt-hour of energy. The steam turbine heat rate is an important economic indicator that reflects the process of energy conversion. During steam turbine operation, the operators aim to ascertain the real-time heat rate value to ensure the economical and safe operation of the steam turbine. So establishing a high-precision prediction model is very important for optimizing and monitoring the operations of power plants, many research works on how to model and forecast the heat rate of stream turbine have been published [1], [2], [3], [4], [5] in past ten years. The field calculation of heat rate is typically depended on precise mass and energy balance equations, or thermal performance experiments, which require numerous operation parameters. However, the operating characteristics of steam turbine are unstable, and the related operation parameters often deviate from design conditions, thus affecting the computational accuracy of heat rate.
The krill herd algorithm (KH) [6] is a new and efficient meta-heuristic optimization algorithm based on the herding behavior of krill, which is proposed by Gandomi et al. Like other population-based optimization methods such as biogeography-based optimization (BBO) [7], particle swarm optimization (PSO) [8], [9], artificial bee colony (ABC) [10], [11], gravitational search algorithm (GSA) [12], and evolutionary optimization (DE) [13], [14], the KH algorithm is also a population-based optimization method and used to find the global optimum. In some searches [15], [16], the performance of KH has already been compared with the other optimizition methods, such as bat algorithm (BA) [17], genetic algorithm (GA) [18] and harmony search (HS) [19]. The crucial advantage of KH algorithm is its strong diversity, simple operation and less adjustment parameters. In addition, the KH algorithm has been applied to some complex computational problems, such as design of planar steel frames, data clustering and mechanical design et al.
The fast learning network (FLN) [20] is a novel artificial neural network based on the thought of extreme learning machine (ELM), which is a double paralleled forward neural network and owns strong non-linear fitting capability, generalization and fault tolerance ability. In FLN, input weights and hidden layer biases are randomly generated, and the weight values of the connection between the output layer and the input layer and the weight values connecting the output node and the input nodes are analytically determined based on least squares methods.
Regression models and monitoring methods have been proposed to determine the mathematical relationship of the turbine heat rate. Liu et al. [21] proposed a soft computing method based on least squares support vector machine (LSSVM) and gravitational search algorithm to forecast turbine heat rate. Zhang et al. [22] provided a new approach for model-based monitoring of turbine heat rate. Chaibakhsh et al. [23] presented a non-linear dynamical model for heat recovery steam generator units. Li Hui [24] proposed a heat rate forecasting method based on the accurate online support vector regression algorithm (AOSVR). The neural network models [25], [26] are usually applied in forecasting works. However, the linear processing of related operation parameters will affect heat rate calculation inevitably. In order to overcome above shortcomings, this paper proposes an integrated modeling method based on ameliorated krill herd algorithm (A-KH) and fast learning network (FLN).
In this paper, in order to improve the solution quality and to quicken the global convergence speed of KH, an ameliorated krill herd algorithm called A-KH is proposed. In A-KH, there are four major highlights: First, the opposition-based learning is adopted to initialize the population. Second, the linear decreasing Ct is used to maintain the balance between exploration and exploitation ability. Third, sine map is used to tune the inertia weights (ωn,ωf) during the process of the search. Finally, we propose to make three major changes by introducing the best-so-far solution, inertia weight and acceleration coefficients to modify the search process. In order to verify the validity of the proposed meta-heuristic A-KH algorithm, ten famous numerical optimization problems are adopted to test A-KH search performance and compared with other four algorithms (biogeography-based optimization, particle swarm optimization, artificial bee colony and krill herd algorithm). Experiment results show that the A-KH could find the global optimal solutions or the solutions close to the optimal solutions effectively, simultaneously have much faster convergence speed than other four methods on most numerical functions. In addition, the A-KH and other four state-of-art optimization algorithms are also used to adjust the input weights and hidden layer biases of FLN so as to obtain a high-precision prediction model of heat rate for a 600MW supercritical stream turbine. The results show that the A-KH-FLN model has better generalization ability and regression precision. Compared with related studies, the specialty place of this article is that an ameliorated krill herd algorithm is proposed and the results show that the A-KH method has better search performance proved by experiments. Then, the A-KH is adopted to adjust the parameters of the fast learning network (FLN) in order to obtain a high-precision prediction model of heat rate for a 600MW supercritical stream turbine, simulation results show that the A-KH-FLN model can predict turbine heat rate accurately and efficiently. So the A-KH method is suitable for application to optimize problems of various fields.
Specified parts of this paper are organized as follows: Section 2, introduce the summarization of the research work. Ameliorated krill herd algorithm is proposed in Section 3. Section 4, the A-KH is applied to optimize some classical benchmark functions and compared with BBO, PSO, ABC and KH. Section 5, describes the parameter optimization of FLN based A-KH. Finally, concludes the paper.
Section snippets
Krill herd algorithm
The krill herd (KH) algorithm is a new type of meta-heuristic swarm intelligence method for solving optimization tasks. This method is inspired by the herding of krill swarms when searching for the food and communicating each other [27]. The krill individuals include two main goals: (1) increasing krill density, and (2) reaching food. For each krill, the time-dependent position of an individual krill in two-dimensional surface is determined by three components described below [28]:
- i
Movement
Ameliorated krill herd algorithm
The crucial advantage of KH algorithm is its simplicity, then making KH implement easily and lending itself to parallel computation [32]. However the search relies completely on randomness, the KH cannot always find the optimal solutions [33], [34]. Therefore, an ameliorated KH algorithm called A-KH is proposed to improve the solution quality and to quicken global convergence speed of the original KH. In A-KH, there are four major highlights, which are detailed expressed as follows:
First, the
Experimental setup
In this subsection, ten famous benchmark optimization problems are adopted to verify the performance of the A-KH algorithm, which are described in Table 1. In Table 1, S denotes a subset of Rn, n denotes dimension, and synchronously the locations of benchmark problems and global optimum solutions are also given in Table 1. Moreover, the performance of A-KH is compared with other four population-based optimization algorithms: BBO, PSO, ABC and the original KH. The parameter settings of each
Tuning FLN based on A-KH to model turbine heat rate
In this section, we adopt the FLN tuned by A-KH to model turbine heat rate from a 600MW supercritical stream turbine unit. In order to verify the validity of A-KH, another four state-of-art optimization algorithms: BBO, PSO, ABC and KH are employed to adjust the parameters of FLN. Firstly, experimental data of heat rate model were obtained from a 600MW supercritical stream turbine unit found in distributed control system (DCS) of power plants. The data were sampled once every two hours, with 12
Conclusions
In this paper, an ameliorated krill herd algorithm called A-KH is proposed to improve search accuracy and convergence speed and enhance the capacity to escape from local optimum of KH simultaneously. In order to verify the validity of the algorithm, it is adopted to some classical benchmark function optimizations, and compared with other four outstanding optimization algorithms (biogeography-based optimization, particle swarm optimization, artificial bee colony and conventional krill herd
Acknowledgments
Project supported by the National Natural Foundation of China (Grant No. 61573306 and 61403331), Natural Science Foundation of Hebei Province (Grant No. F2016203427), China Postdoctoral Science Foundation (Grant No. 2015M571280), the Doctorial Foundation of Yanshan University (Grant No.B847).
References (39)
- et al.
Forecasting of turbine heat rate with online least squares support vector machine based on gravitational search algorithm
Knowl. Based Syst.
(2013) - et al.
Krill herd: a new bio-inspired optimization algorithm
Commun. Nonlinear Sci. Numer. Simul.
(2012) - et al.
A comparative study of artificial bee colony algorithm
Appl. Math. Comput.
(2009) - et al.
On the performance of artificial bee colony (ABC) algorithm
Appl. Soft Comput.
(2008) - et al.
GSA: a gravitational search algorithm
Inf. Sci.
(2009) - et al.
Learning Bayesian networks from incomplete databases using a novel evolutionary algorithm
Decision Support Syst.
(2008) A user-friendly marketing decision support system for the product line design using evolutionary algorithms
Decision Support Syst.
(2005)- et al.
An effective krill herd algorithm with migration operator in biogeography-based optimization
Appl. Math. Modell.
(2014) - et al.
The Bees Algorithm — A novel tool for complex optimisation problems
Intell. Prod. Mach. Syst.
(2006) - et al.
Optimal parameters selection for BP neural network based on particle swarm optimization: a case study of wind speed forecasting
Knowl. Based Syst.
(2014)
A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm
Knowledge-Based Systems
Chaotic Krill Herd algorithm
Inf. Sci.
Least Square Fast Learning Network for modeling the combustion efficiency of a 300WM coal-fired boiler
Neural Netw. Official J. Int. Neural Netw. Soc.
Stud krill herd algorithm
Neurocomputing
An effective krill herd algorithm with migration operator in biogeography-based optimization
Appl. Math. Modell.
An improved krill herd algorithm: Krill herd with linear decreasing step
Appl. Math. Comput.
Chaotic Krill Herd algorithm
Inf. Sci.
Online calculation of stream turbine thermal performance based on BP neural network
Thermal Power Gen.
Investigation on multi-modeling method of steam turbine heat rate [J]
Acta Metrological Sinica
Cited by (33)
Strategic-level performance enhancement of a 660 MW<inf>e</inf> supercritical power plant and emissions reduction by AI approach
2021, Energy Conversion and ManagementCitation Excerpt :Therefore, these AI algorithms are incorporated to improve the power plant heat rate and reduce the environmental footprints. Researchers have reported various studies investigating the power plant heat rate by improved system design, retrofitting measures, and thermal analysis for the power plants [40–45]. For example, Oyedepo et al. [46] studied the effect of regeneration on the power plant performance indices.
A novel unified maximum power extraction framework for PMSG based WECS using chaotic particle swarm optimization derivatives
2021, Engineering Science and Technology, an International JournalCitation Excerpt :On numerical function optimization, CDW-PSO surpassed twenty optimization algorithms including basic methods, chaotic approaches, PSO based derivatives and state-of-the-art studies. In [28], Sine map was evaluated to update the inertia weight of PSO according to its usage in krill herd (KH) and chaotic krill herd (CKH) algorithms [29,30]. However, PSO involves different dynamics (formulations and phenomena) inside, and the necessary map can vary from one method to another.
Annealing-behaved 100-Digit challenge problem optimization
2021, Procedia Computer ScienceCombined weighted multi-objective optimizer for instance reduction in two-class imbalanced data problem
2020, Engineering Applications of Artificial IntelligenceBenchmark value determination of energy efficiency indexes for coal-fired power units based on data mining methods
2020, Advanced Engineering InformaticsCitation Excerpt :The controllable variables that can be adjusted in the operation (e.g. main steam temperature and reheat steam temperature): The KPIs are selected from these variables. Feature selection is very important for thermal system modeling and analysis in power plants [16,17]. Some variables have a large and some have only a slight influence on the NCCR.