Modeling for the bed temperature 2D-interval prediction of CFB boilers based on long-short term memory network

A dynamic nonlinear model used for controller design of a 600 MW supercritical circulating fluidized bed boiler-turbine unit

Modified active disturbance rejection control based on gain scheduling for circulating fluidized bed units

Circulating fluidized bed (CFB) is becoming the main coal combustion technique all over the world for its high combustion efficiency, low pollution, fuel flexibility and good load-following capability, but its combustion process characteristic is highly non-linear, time-varying, large time delay and multi-variable strong coupling. The conventional control proposal divides the bed temperature control system and main steam pressure control system into two separate PID single-loops without consideration of inter-circuit coupling, which results in low automatism operation rate and often manual operation required. To solve this problem, a multi-variable adaptive neural network decoupling controller with PID structure is introduced based on the principle of NN control and decoupling compensation. The decoupling and control capability of PID NN decoupling controller are from the NN cross-tie structure and the nonlinear mapping properties, as well as the PID style processing of the hidden layer node. The weights of the NN are learned and optimized by the particle swarm optimization (PSO) algorithm, which is known for its searching ability in the total parameter space concurrently and efficiently. These NN weights will not only eliminate the coupling relations between circuits, but also strengthen the PID-NN controller's adaptability. This multivariable decoupling control method is used to control the two-dimensional transfer function matrix of the bed temperature and main steam pressure system in the CFB combustion system. Simulation results show that the new control strategy could overcome nonlinear and strong coupling features of CFB combustion system in a wide range and is expected to have great potential for engineering application.

With the pollutant emission standards becoming increasingly stringent and considering the pressure of carbon neutral by 2060, the low pollutant emission potential of circulating fluidized bed (CFB) combustion technology needs to be further exploited, thus to promote the market competitiveness of CFB boilers; this is critical for the clean and efficient utilization of coal as well as for the energy transformation in China. In this article, we summarize the pollutant emission characteristics of CFB combustion, and review the development of major technologies for CFB boiler emission control. Based on the energy development strategies and corresponding policies in China, development suggestions are proposed for reducing pollutant emission of the CFB combustion technology. The most significant approach is to push the limits of original pollutant emission for CFB combustion by re-specifying the fluidization state and through in-furnace combustion adjustment, while the boiler thermal efficiency should be ensured. For the long-term development of coal energy, the new-generation CFB combustion technology with ultra-low emission should be researched and developed while combining with technologies such as supercritical/ultra-supercritical, intelligent operation, carbon capture, utilization, and storage, and energy storage technologies. The existing CFB boilers with small or medium capacity should also be upgraded. Considering the fuel flexibility of CFB combustion, biomass power generation should be promoted to realize low-cost and high-efficiency consumption of low-heat value fuels, urban refuse, industrial wastes, etc. The peak load regulation capacity and low pollutant emission property of the CFB boilers should be promoted to improve operation flexibility and renewable energy consumption. Moreover, the desulphurization ash produced in CFB combustion should be comprehensively utilized, and the N2O emission problem is also significant. The pollutant emission standards and related policies need to be formulated from an overall perspective to guide the healthy development of the energy industry.

Three-dimensional numerical simulation of coal and papermaking trash co-combustion in a circulating fluidized bed

Timely and accurate traffic flow prediction is the core of an intelligent transportation system. Canonical long short-term memory (LSTM) networks are guided by the mean square error (MSE) criterion, so it can handle Gaussian noise in traffic flow effectively. The MSE criterion is a global measure of the total error between the predictions and the ground truth. When the errors between the predictions and the ground truth are independent and identically Gaussian distributed, the MSE-guided LSTM networks work well. However, traffic flow is often impacted by non-Gaussian noise, and can no longer maintain an identical Gaussian distribution. Then, a $ {\overline{\delta }}_{relax} $-LSTM network guided by mixed correlation entropy and variable center (MCVC) criterion is proposed to simultaneously respond to both Gaussian and non-Gaussian distributions. The abundant experiments on four benchmark datasets of traffic flow show that the $ {\overline{\delta }}_{relax} $-LSTM network obtained more accurate prediction results than state-of-the-art models.

Hydrodynamic behaviour of aerogel powders in high-velocity fluidized beds

The interrelation between fuzzy logic and cluster renewal approaches for heat transfer modeling in a circulating fluidized bed (CFB) has been established based on a local furnace data. The furnace data have been measured in a 1296 t/h CFB boiler with low level of flue gas recirculation. In the present study, the bed temperature and suspension density were treated as experimental variables along the furnace height. The measured bed temperature and suspension density were varied in the range of 1131-1156 K and 1.93-6.32 kg/m3, respectively. Using the heat transfer coefficient for commercial CFB combustor, two empirical heat transfer correlation were developed in terms of important operating parameters including bed temperature and also suspension density. The fuzzy logic results were found to be in good agreement with the corresponding experimental heat transfer data obtained based on cluster renewal approach. The predicted bed-to-wall heat transfer coefficient covered a range of 109-241 W/(m2K) and 111-240 W/(m2K), for fuzzy logic and cluster renewal approach respectively. The divergence in calculated heat flux recovery along the furnace height between fuzzy logic and cluster renewal approach did not exceeded ±2%.

The migration behaviors of As, Se and Pb in ultra-low-emission coal-fired units were investigated and the effect of co-firing of sewage sludge and coal was explored in circulating fluidized-bed (CFB) boiler units. Samples of feed fuel including coal and sewage sludge, fly ash, bottom slag and desulfurization slurry were collected from five CFB units with a capacity between 150 MW and 350 MW and two pulverized coal boiler (PC) units with a capacity of 350 MW and 600 MW. The majority of As, Se and Pb in coal is released during coal combustion and enriched in fly ash. As, Se and Pb in fly ash and bottom slag are associated with inorganic matter, of which As, Se and Pb associated with silicates and aluminosilicates account for more than 60%. In the wet flue gas desulfurization (WFGD) unit, more than half of the As, Se and Pb migrates to the solid fraction and the concentrations of As, Se and Pb in fine solid particles are much higher than those in coarse solid particles and the liquid fraction. The proportions of exchangeable As, Se and Pb or associated with organic matter in gypsum are higher than those of fly ash and bottom slag. According to the two studied CFB units with blending ratios of sewage sludge below 10%, co-firing with sewage sludge has little effect on the migration and transformation characteristics of As, Se and Pb. Under a long-term acidic leaching environment, Pb in combustion by-products is in the range of low risk, while As and Se are in the range of medium risk.

Data-driven optimization of pollutant emission and operational efficiency for circulating fluidized bed unit

Investigation on lateral dispersion characteristics of fuel particles in dense phase zone of a large-scale circulating fluidized bed boiler under combustion conditions

Mixed incineration of municipal solid waste (MSW) in existing coal gangue power plant is a potentially high-efficiency and low-cost MSW disposal way. In this paper, the co-combustion and pollutants emission characteristic of MSW and coal gangue was investigated in a circulating fluidized bed (CFB) combustor. The effect of MSW blend ratio, bed temperature and excess air ratio was detailedly studied. The results show the NOx and HCl emission increases with the increasing MSW blend ratio and the SO2 emission decreases. With the increase of bed temperature, the CO emission decreases while the NOx and SO2 emission increases. The HCl emission is nearly stable in the temperature range of 850–950 °C. The increase of excess air ratio gradually increases the NOx emission but has no significant effect on the SO2 emission. The HCl emission firstly increases and then decreases with the increase of excess air ratio. For a typical CFB operating condition with excess air ratio of 1.4, bed temperature of 900 °C and MSW blend ratio of 10%, the original CO, NOx, SO2 and HCl emissions are 52, 181, 3373 and 58 mg/N m3 respectively.

A pressure balance model for a circulating fluidized bed (CFB) unit that incorporates a downer has been proposed. A comparison of the operation stability between a CFB downer and a CFB riser showed that, although only one critical operating gas velocity exists in the CFB riser for a given riser solids flux, there can be many critical gas velocities for the operation of a CFB downer. Therefore, it is possible to achieve high solids concentration in a CFB downer if appropriate operating conditions are used. Parameters that affect the solids concentration in the CFB downer have been studied using the model and have been validated with experimental data obtained from a special CFB unit that incorporates a downer. Measures to increase the solids concentration in the downer have been proposed.

A review of some operation and maintenance issues of CFBC boilers

With the increasing global focus on sustainable development, circulating fluidized bed (CFB) boilers, as highly efficient and low-pollution combustion equipment, play an important role in energy production and environmental protection. However, the combustion efficiency and emission control of CFB boilers still face challenges, and there is an urgent need for multi-objective optimization through advanced technologies to support the goal of sustainable development. This study proposes an intelligent framework integrating Bidirectional Temporal Convolutional Network (BiTCN) and Hybrid Dung Beetle Optimizer (HDBO) for multi-objective optimization of combustion efficiency and NOx/SO2 emissions in CFB boilers. The BiTCN model captures bidirectional temporal dependencies between dynamic parameters (e.g., air-coal ratio, bed temperature) and target variables through operational data analysis. Three key improvements are implemented in DBO: (1) Chaotic initialization via sequential pattern mining (SPM) enhances population diversity and spatial coverage; (2) The osprey optimization algorithm (OOA) hunting mechanism replaces the original rolling update strategy, improving global exploration; (3) t-Distribution perturbation is applied to foraging beetles in later iterations, leveraging its “sharp peak and thick tail” characteristics to dynamically balance exploitation and exploration. Experimental results demonstrate 0.5–1% combustion efficiency improvement and 15.1%/30% reductions in NOx/SO2 emissions for a typical CFB boiler.