Boiler Combustion Optimization Research Articles

A Survey on Intelligent Optimization Approaches to Boiler Combustion Optimization

A Survey on Intelligent Optimization Approaches to Boiler Combustion Optimization

A new on-line combustion optimization approach for ultra-supercritical coal-fired boiler to improve boiler efficiency, reduce NOx emission and enhance operating safety

To take into account the economy, environment protection and operating safety of the boiler in the combustion optimization process, a new on-line combustion optimization approach for boiler is proposed. The historical combustion data collected from DCS of the coal-fired power plant is preprocessed at first. Then improved biogeography optimization-based long short-term memory neural network (IBBO-LSTM) and similarity measurement method are designed to construct the adaptive dynamic combustion model for boiler with boiler efficiency, NOx emission and the temperature of water wall as outputs respectively. After that improved non-dominated sorting genetic algorithm-Ⅱ (INSGA-Ⅱ) is designed to generate a series of boiler combustion optimization solutions under different running load offline, and improved multi-level fuzzy comprehensive evaluation (IDHGF) is designed to retain the combustion optimization solutions with higher running safety. Meanwhile, the retained optimization solutions are integrated into an optimization cases base. Thereafter, case-based reasoning based on safety enhancement mechanism (CBRSEM) is designed to achieve the online combustion optimization for boiler. Finally, to confirm the effectiveness of the combination of IBBO-LSTM, INSGA-Ⅱ, IDHGF and CBRSEM, different online optimization methods (IBBO-LSTM-INSGA-Ⅱ, IBBO-LSTM-INSGA-Ⅱ-IDHGF, IBBO-LSTM-NSGA-Ⅱ-DHGF-CBR, IBBO-LSTM-NSGA-Ⅱ-IDHGF-CBR, IBBO-LSTM-NSGA-Ⅱ-DHGF-CBRSEM, IBBO-LSTM-NSGA-Ⅱ-IDHGF-CBRSEM, IBBO-LSTM-INSGA-Ⅱ-DHGF-CBR, IBBO-LSTM-INSGA-Ⅱ-IDHGF-CBR) are adopted to optimize a given combustion case. The proposed on-line combustion optimization approach for boiler received satisfied combustion optimization results that the growing for boiler efficiency was 0.653%, and the reduced concentration for NOx emission reached 22.891 mg/m3, and the operating safety raised from 5.592 to 6.913. In conclusion, IBBO-LSTM-INSGA-Ⅱ-IDHGF-CBRSEM can online offer the combustion optimization strategy to the boiler operators to improve boiler efficiency, reduce NOx emission and enhance the running safety of boiler, so that it is suitable for online application.

A novel three-stage multi-population evolutionary algorithm for constrained multi-objective optimization problems

Lots of real-world optimization problems are inherently constrained multi-objective optimization problems (CMOPs), but the existing constrained multi-objective optimization evolutionary algorithms (CMOEAs) often fail to balance convergence and diversity effectively. Therefore, a novel constrained multi-objective optimization evolutionary algorithm based on three-stage multi-population coevolution (CMOEA-TMC) for complex CMOPs is proposed. CMOEA-TMC contains two populations, called mainPop and helpPop, which evolve with and without consideration of constraints, respectively. The proposed algorithm divides the search process into three stages. In the first stage, fast convergence is achieved by transforming the original multi-objective problems into multiple single-objective problems. Coarse-grained parallel evolution of subpopulations in mainPop and guidance information provided by helpPop can facilitate mainPop to quickly approach the Pareto front. In the second stage, the objective function of mainPop changes to the original problem. Coevolution of mainPop and helpPop by sharing offsprings can produce solutions with better diversity. In the third stage, the mining of the global optimal solutions is performed, discarding helpPop to save computational resources. For CMOEA-TMC, the combination of parallel evolution, coevolution, and staging strategy makes it easier for mainPop to converge and maintain good diversity. Experimental results on 33 benchmark CMOPs and a real-world boiler combustion optimization case show that CMOEA-TMC is more competitive than the other five advanced CMOEAs.

Experimental Study on Combustion Optimization of Supercritical 600MW Quadrangle Tangential Boiler

Given the problems existing in the operation of supercritical 600MW boiler, such as spiral pipe water cooling wall outlet, superheater and reheater wall surface overtemperature easily, the superheater and reheater cooling water amount are too large under high load, and the low load cooling water amount is too small to meet the need of cold reheater heating, the boiler combustion optimization and adjustment are carried out. Through the boiler pulverized coal fineness, air distribution characteristics, swinging Angle of burner and furnace outlet is optimized, such as oxygen level superheater heating surface overtemperature problems are solved, such as the reheater desuperheating water flow under different load can meet the needs of heat supply, at the same time, it also improves the boiler efficiency, effectively improve the safety and economy of the unit.

Optimizing boiler combustion parameters based on evolution teaching-learning-based optimization algorithm for reducing NOx emission concentration.

How to reduce a boiler's NOx emission concentration is an urgent problem for thermal power plants. Therefore, in this paper, we combine an evolution teaching-learning-based optimization algorithm with extreme learning machine to optimize a boiler's combustion parameters for reducing NOx emission concentration. Evolution teaching-learning-based optimization algorithm (ETLBO) is a variant of conventional teaching-learning-based optimization algorithm, which uses a chaotic mapping function to initialize individuals' positions and employs the idea of genetic evolution into the learner phase. To verify the effectiveness of ETLBO, 20 IEEE congress on Evolutionary Computation benchmark test functions are applied to test its convergence speed and convergence accuracy. Experimental results reveal that ETLBO shows the best convergence accuracy on most functions compared to other state-of-the-art optimization algorithms. In addition, the ETLBO is used to reduce boilers' NOx emissions by optimizing combustion parameters, such as coal supply amount and the air valve. Result shows that ETLBO is well-suited to solve the boiler combustion optimization problem.

A novel online combustion optimization method for boiler combining dynamic modeling, multi-objective optimization and improved case-based reasoning

A new boiler combustion optimization method for online application is proposed based on data-driven and case-based reasoning principle. First, an improved constrained fuzzy association rule (ICFAR) is proposed to extract the boiler combustion rules from historical combustion data. Second, improved particle swarm optimization-based long short-term memory neutral network (IPSO-LSTM) is utilized to constructed an adaptive dynamic combustion model for boiler to adapt to time-variability of boiler combustion system. Whereafter, an improved multi-objective particle swarm optimization (IMOPSO) is designed to achieve the multi-objective combustion optimization of boiler with the goal of increasing boiler efficiency and decreasing NOx emission simultaneously. Case-based reasoning based on error correction mechanism (CBR_ECM) is applied to realize the boiler online combustion optimization. The effectiveness of proposed online combustion optimization technology for boiler is testified by applying it to an actual combustion process. The results illustrated that it could take less time to gain a series of excellent operating solutions based on proposed online combustion optimization method, the boiler efficiency increased by 0.082 % on average and the NOx emission reduced by 6.491 mg/m3 on average. Therefore, proposed online combustion optimization method for boiler has the ability to achieve the online combustion optimization of boiler.

Mechanism modeling of optimal excess air coefficient for operating in coal fired boiler

Optimization of excess air coefficient is extremely significant for boiler operating performance. Currently theoretical modeling of optimal excess air coefficient is still an intractable technical issue for pulverized coal boiler, limits further efficient utilization of coal. In this work, a mechanistic optimization model considering influence mechanisms was developed to model optimal excess air coefficient under partial boiler loads. To investigate efficiency of analyzed steam boiler, indirect method and individual boiler losses computation was applied. The accuracy of model results was verified at three different partial loads. Subsequently, modeling approach is used for a case study on 660 MW boiler. Influence mechanism between excess air coefficient and boiler operating parameters was graphically analyzed and meticulously discussed. Optimum energy efficiency and exergy efficiency of boiler were determined and given accurately.The developed model allows performing calculations for variable input conditions to determine total boiler efficiency and basic technical parameters. In addition, presented methods were applied to identify changing of boiler efficiency and basic boiler parameters during operation with different loads and burning different coal types. The results were presented in the form of coal consumption rate, total boiler efficiency and boiler losses as function of excess air coefficient, load and coal type. This work formulaically reveals evolution mechanism of boiler parameters and accurately determines the optimal excess air coefficient. It can be used as a means of boiler combustion optimization and adjustment.

Multi-objective modeling of boiler combustion based on feature fusion and Bayesian optimization

The physical field (temperature, gas concentration, etc.) inside the furnace is closely related to the boiler combustion optimization. A novel multi-objective prediction framework based on feature fusion is proposed to provide the basis for the online combustion optimization of coal-fired boilers. Firstly, the physical field information is obtained through the CFD, which presented a strong correlation between thermal efficiency and NOx generation. Then the eXtreme Gradient Boosting and Bayesian Optimization are used to construct the model according to the changes of the real-time physical field and operating conditions. The modeling results demonstrated that the prediction accuracy of thermal efficiency from the model with the fusion information can be improved by 1.49% compared with the model using the operational data. The prediction accuracy of thermal efficiency and NOx generation is improved by 2.57% and 0.13%, respectively, which indicated that the expression ability of the model improved by combing the typical real-time physical field information.

Online optimization of boiler operation based on information integration and case-based reasoning

ABSTRACT Boiler combustion optimization is a crucial method to deal with the profound load changing of coal-fired units, improve thermal power plant flexibility, and ensure unit operation safety, energy-saving, and environmental protection. However, the strong coupling, non-linearity, time-variation and timeliness of boiler combustion systems bring challenges to the online application of boiler combustion optimization technology in practical engineering. This work proposes a new multi-objective online combustion optimization framework based on information integration and case-based reasoning (II_CBR), and establishes the II_CBR system platform to serve a 330-MW coal-based power plant. The framework is combined offline database construction and online combustion optimization. The offline database integrates simulation feature information and operation parameter information, which provides richer informative knowledge. The online approach achieves the online calculation of the simulated feature information and combustion optimization. The results show that boiler efficiency increased by 0.31%, and the maximum reduction in NOx generation was 41.22 mg/Nm3, which indicates the proposed method is suitable for online real-time combustion optimization and supports power plant operators for flexible optimization. In addition, it improves boiler efficiency, reduces nitrogen oxide emissions, and provides new directions for deep load-changing coal-fired units.

기력발전 운영 환경 변화를 반영한 보일러 연소 최적화 기술의 소프트컴퓨팅적 접근 방법론 연구

In this paper, in order to evaluate the availability of the boiler combustion optimization of MPC technology for the current method of thermal power generation operation, two cases of experiment were implemented. Firstly, an experiment was performed using simulator linkage and actual process operation information. As a result, it was possible to obtain effects such as reducing overshooting when the target load was reached when linking the simulator. Secondly, an experiment was performed using actual operation information for optimizing combustion-related variables. However. the result of optimization by MPC solution was difficult to apply to actual process control. This is because the mechanical power generation control system is designed for the purpose of following the demand load, ① it is difficult to define a clear causal relationship between the process operation variables and nitrogen oxides and carbon monoxide, and ② data preprocessing techniques for handling disturbances and time delays. It could be confirmed that this was due to the inadequacy of the optimization technique among the multiple conflicting variables. To supplement this, soft-computing approaches including ① data linearization applying Bayesian optimization method, ② generalization of process situation prediction algorithm through application of multi-stage machine learning prediction structure and incremental data utilization, ③ global optimization method through combination of empirical-heuristic optimization algorithm are introduced to optimize the boiler combustion of thermal power plant.

Three-objective optimization of boiler combustion process based on multi-objective teaching–learning based optimization algorithm and ameliorated extreme learning machine

The combustion optimization problem of Circulation Fluidized Bed Boiler (CFBB) can be regarded as a constrained dynamic multi-objective optimization problem, so it has become a hot research to solve the problem for saving energy and reducing polluting gas. However, it is difficult to optimize the combustion process based on traditional optimization method due to a variety of complex characteristics of boiler, such as non-linearity, strong coupling , large lag. In order to address the boiler combustion optimization problem, a kind of multi-objective modified teaching–learning-based optimization (namely MMTLBO) is proposed. For the MMTLBO, a constrained mechanism is firstly introduced into MMTLBO. Finally, the MMTLBO and ameliorated extreme learning machine (AELM) are utilized to optimize the CFBB’s combustion process for increasing the thermal efficiency and reducing the NOx/SO2 emissions concentration. The AELM is used to establish the comprehensive model of the thermal efficiency and NOx/SO2 emissions. The model accuracy and standard deviation can arrive 10−2 and 10−4, separately. So the model shows high generalization ability and good stability. Based on the model, the MMTLBO is applied to optimize the boiler’s combustion process parameters. Experiment results show that the MMTLBO can find several groups reasonable combustion parameters which increase the thermal efficiency and reduce the NOx/SO2 emissions concentration. Therefore, the AELM and MMTLBO are the effective artificial intelligence algorithms.

Boiler Combustion Optimization of Vegetal Crop Residues from Greenhouses

This work presents an alternative for adding value to greenhouse crop residues, used for (1) heating and (2) as a CO2 source. Both options are focused on greenhouse agricultural production, but could be applied to other applications. The influence of factors, such as the air/fuel rate and turbulence inside the combustion chamber, is studied. Our results show that for pine pellets, olive pits, tomato-crop residues, and a blend of the latter mixed with almond prunings (75–25%), the thermal losses ranged from 19.5–53.1, 20.5–58.9, 39.9–95%, and 29.4–75.5%, respectively, while the NOX emissions were 30–247, 411–1792, and 361–2333 mg/Nm3, respectively. The above-mentioned blend was identified as the best set-up. The thermal losses were 39.2%, and the CO, NOX, and SO2 concentrations were 11,690, 906, and 1134 mg/Nm3, respectively (the gas concentration values were recalculated for 0% O2). Currently, no other work exists in the literature include a similar analysis performed using a boiler with a comparable thermal output (160.46 kW). The optimal configurations comply with the relevant local legislation. This optimization is important for future emission control strategies relating to using crop residues as a CO2 source. The work also highlights the importance of ensuring a proper boiler set-up for each case considered.

Case-based reasoning based on grey-relational theory for the optimization of boiler combustion systems

Boiler combustion optimization is an important method to improve the flexibility of thermal power units and ensures the stability of unit operation. However, time-variability of boiler combustion systems and time-consuming optimization methods pose great challenges for the use of boiler combustion optimization techniques because many optimization methods cannot be used online in practical engineering due to time constraints. In this paper, we propose a case-based reasoning optimization method based on grey-relational theory (GR-CBR) for online optimization of a boiler combustion system. After the introduction of the proposed algorithm, we discuss the potential of applying the proposed GR-CBR optimization method to a boiler combustion system; a case study of an existing fossil fuel power plant is conducted to demonstrate the feasibility of the proposed method. A least-squares support vector machine (LS-SVM) model of the boiler combustion process is established by using the real-time operation data of a 350-MW coal-based power plant. Based on the model, a non-linear global optimization algorithm is proposed to obtain the optimal case base and real-time data mining and online optimization are used to achieve efficient and stable boiler combustion optimization. The results of combining offline optimization with online querying show that this approach is suitable for online real-time combustion optimization, and provides support for power plant operators for optimization and condition monitoring to improve boiler efficiency, reduce NOx emissions, and ensure stable and efficient operation of the power system.

Combustion Optimization Test of “W” Flame Furnace Based on Orthogonal Experimental Design

This paper focuses on the selection ideas, test methods, test results and analysis of a “W” type flame furnace combustion test program. Under the electrical load of 300MW, 250MW, 200MW and 150MW, the orthogonal test method is adopted to change the “furnace outlet oxygen amount”, “secondary wind and grading wind distribution mode”, “burning air opening degree”, “secondary damper combination method” and “heat load distribution” of the boiler so as to make clear about the impact of various operating conditions on boiler efficiency and NOx emission level, and summarize the optimal operation mode of the boiler. The combustion adjustment can improve the economic and environmental protection of the boiler under different working conditions, which provides data support for equipment safety, environmental protection and economic operation, and provides reference for boiler combustion optimization test research and combustion optimization of the same type of furnace.

Optimization of Thermal Efficiency and Unburned Carbon in Fly Ash of Coal-Fired Utility Boiler via Grey Wolf Optimizer Algorithm

This paper focuses on improving thermal efficiency and reducing unburned carbon in fly ash by optimizing operating parameters via a novel high-efficient swarm intelligence optimization algorithm (grey wolf optimizer algorithm, GWO) for coal-fired boiler. Mathematical models for thermal efficiency and unburned carbon in fly ash of the discussed boiler are established by artificial neural network (ANN). Based on the ANN models, the grey wolf optimizer algorithm is used to obtain higher thermal efficiency and lower unburned carbon by optimizing the operating parameters. Meanwhile, the comparisons between GWO and particle swarm optimization (PSO) and genetic algorithm (GA) show that GWO has superior performance to GA and PSO regarding the boiler combustion optimization. The proposed method can accurately optimize the boiler combustion performance, and its validity and feasibility have been experimentally validated. Additionally, a run of optimization takes a less time period, which is suitable for the real-time optimization.

Combustion optimization of a boiler based on the chaos and Lévy flight vortex search algorithm

The boiler combustion optimization has attracted growing research interest of more and more researchers in thermal energy engineering field. To achieve combustion optimization objective, the combustion characteristics model of the boiler needs to be built, and the efficient optimization algorithm also needs to be found. Therefore, in this study, a logic self-map chaos and Lévy flight Vortex Search (I-VS) algorithm is proposed. Then, comparative study between the I-VS algorithm and some other state-of-the-art optimization algorithms is performed. Next, the combustion efficiency model is built based on fast learning network (FLN). The I-VS algorithm is used to optimize FLN, and then an I-VS-FLN model is built for predicting NOx emissions of a boiler. Experimental results show that the I-VS-FLN model has better generalization ability than five other models. Finally, the I-VS algorithm is used to tune the operating parameters of the boiler based on the FLN model and the I-VS-FLN model to achieve the combustion optimization objective.

Simulation and Research of Boiler Combustion Process Based On the Improved RBF Neural Network

Due to the use of time, machine wear degree, coal and other reasons, the original set parameters of the boiler have been unable to meet the control requirements, therefore using a large amount of data to build a real model of the power station based on the neural network, therefore, to establish a boiler combustion optimization neural network model by using of the power plant operating data. According to the shortcomings on RBF neural networks traditional training methods with slow convergence speed, easy to fall into the local minimum. Firstly, this paper Set the model to single input and single output system as the research object, optimize neural network by the particle swarm optimization algorithm. Finally, this modeling method is expanded to the multiple input multiple output system field. Use MATLAB to establish the simulation model and the simulation research, the simulation results show that improved method for combustion boiler system efficiency has been significantly improved, combustion efficiency of the entire system reached 94%, the accuracy of the system model was significantly better than ordinary neural network, system training error controls in less than 5% .We can see that the improved method is feasible and effective.

Numerical Simulation Study on Nitrogen Oxides Emissions of Power Plant

Modeling and optimization of NOx emissions is an important task of boiler combustion optimization. Nonlinear modeling techniques with adaptive mechanisms and the genetic algorithm for optimization are all used widely. The purpose of this study is to achieve successful application of modeling and optimization for NOx emissions of fossil-fired boilers. In this paper the adaptive modeling techniques and genetic algorithm will be integrated and applied on the NOx emission data of two different utility boiler units.

Target Values of Combustion Optimization in Coal Fire Boiler Based on Data Mining

In this paper, K-means clustering algorithm of data mining technology is applied to determine the targeted value. The historical operation data of 600MW unit boiler are studied to determine the boiler combustion optimization target values of different conditions. The normalized method is used for handling data, directly reflects the position of operation target value in the whole parameter range, provides guide for boiler combustion optimization.

Simulation of Supercharged Boiler Combustion Optimization Control Based on Radiant Energy Signal

According to the phenomenon that large lagging and the fluctuation of the fuel regulation of the supercharged boiler, the dynamic behavior of the steam pressure is simulated to study the internal pure delaying in this paper. The flame detector system was used to collect the real-time picture of the flame in the boiler furnace, and the radiant energy signal was introduced into the combustion control system. A combustion auxiliary duct pilot was added and some stimulation is studied. The results shows that with the change of the radiant energy signal, the new control system can change the supply of the fuel in 20 seconds and wipe off all the disturbance in 30 seconds and the amplitude of fluctuation is dramatically reduced.