Thermal deformation prediction based on the temperature distribution of the rotor in rotary air-preheater

Li-min, Wang; Deng, Lei; Tang, Chunli; Fan, Qing; Wang, Changxia; Che, Defu

doi:10.1016/j.applthermaleng.2015.07.021

Cited by 35 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At present, there are few relevant studies available. In [32] and [33], mathematical models based on thermal stress theory are adopted to analyze the thermal deformation of the air preheater rotor, which are typical KDMs. First, the finite difference method is used to calculate the temperature distribution of the air preheater.…”

Section: Application Backgroundmentioning

confidence: 99%

A Knowledge- and Data-Driven Soft Sensor Based on Deep Learning for Predicting the Deformation of an Air Preheater Rotor

Wang

Liu

2019

IEEE Access

View full text Add to dashboard Cite

In industrial processes, some important process variables cannot be measured directly by hardware sensors for technical or economic reasons. Soft sensors estimate these key variables using some other easily measured variables by building a mathematical model. A novel knowledge-and data-driven soft sensor is proposed in this paper to predict the deformation of an air preheater rotor in a thermal power plant boiler. Two submodels were constructed, including the knowledge-driven submodel, derived from all the available domain knowledge, and the data-driven submodel, constructed solely from the data. The two submodels were integrated with a mass balance model. A mathematical model based on technical expertise in predicting rotor deformation, named the Lab model, was used as the knowledge-driven submodel, and a deep learning model based on stacked autoencoders (SAE) was used as the data-driven submodel. To improve the performance of the model, the limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm was adopted to optimize the SAE parameters. The experimental results demonstrate that, compared with the common knowledge-driven (KDM) and data-driven (DDM) models, the proposed Lab-stacked autoencoders (L-SAE) model is able to provide a higher predictive accuracy for the air preheater rotor deformation and inherits the advantages of both the KDM and DDM. INDEX TERMS Deep learning, industrial process control, knowledge-and data-driven model, soft sensor.

show abstract

Section: Application Backgroundmentioning

confidence: 99%

A Knowledge- and Data-Driven Soft Sensor Based on Deep Learning for Predicting the Deformation of an Air Preheater Rotor

Wang

Liu

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The finite difference method (FDM) has been used in the design of RAPH by many manufacturers like Howden Global for a long time [11][12][13][14][15][16], but no shared code is available for free. Therefore, a program was developed by using a FDM to calculate the thermal performance of RAPH in our previous work [17]. The energy balance equation and the heat transfer equation can be expressed:…”

Section: Thermal Performance Calculationmentioning

confidence: 99%

Influence of operating conditions on ammonium bisulfate deposition in the rotary air preheater of coal-fired power plants

Wang¹,

Bu²,

He³

et al. 2019

THERM SCI

Self Cite

View full text Add to dashboard Cite

Original scientific paper https://doi.org/10.2298/TSCI180524213W To achieve the maximum NOx reduction in coal-fired power plant, excess ammonia is injected into the selective catalytic reduction reactor, which leads to the formation of ammonium bisulfate due to the reaction between ammonia escaping from the selective catalytic reduction reactor and SOx in the flue gas. Ammonium bisulfate can condense in the rotary regenerative air-preheater, which would adversely affect the safe and efficient operation of the air-preheater. An improved radian number is proposed to estimate the ammonium bisulfate deposition. The operating conditions or modes of the air-preheater, i. e., air-flow bypass, cold--end protection and different splitting fluid sector arrangements, are comparatively studied to analyze the temperature and ammonium bisulfate deposition distributions. The hot air re-circulation is not helpful to mitigate the ammonium bisulfate deposition in medium matrix layer. The splitting gas sector arrangement would cause more serious plugging problem, but the splitting air sector arrangements can alleviate the ammonium bisulfate deposition. To increase the air bypass rate is more effective than the splitting air sector arrangements to alleviate the plugging problem. The improved radian number is more reasonable to reflect the ammonium bisulfate deposition compared with the original radian number.

show abstract

“…In the air preheater, flue gas heat is absorbed by primary air and secondary air. However, considering the cost and security issues [33], air temperature cannot be increased without limitation. In this paper the primary air temperature (T pri air ) is set at 320 • C, the secondary air temperature (T sec air ) is set at 330 • C, which is in line with existing engineering experience.…”

Section: Causes Of Residual Heat Problemmentioning

confidence: 99%

How to Construct a Combined S-CO2 Cycle for Coal Fired Power Plant?

Sun

Han

et al. 2018

Entropy

View full text Add to dashboard Cite

It is difficult to recover the residual heat from flue gas when supercritical carbon dioxide (S-CO2) cycle is used for a coal fired power plant, due to the higher CO2 temperature in tail flue and the limited air temperature in air preheater. The combined cycle is helpful for residual heat recovery. Thus, it is important to build an efficient bottom cycle. In this paper, we proposed a novel exergy destruction control strategy during residual heat recovery to equal and minimize the exergy destruction for different bottom cycles. Five bottom cycles are analyzed to identify their differences in thermal efficiencies (ηth,b), and the CO2 temperature entering the bottom cycle heater (T4b) etc. We show that the exergy destruction can be minimized by a suitable pinch temperature between flue gas and CO2 in the heater via adjusting T4b. Among the five bottom cycles, either the recompression cycle (RC) or the partial cooling cycle (PACC) exhibits good performance. The power generation efficiency is 47.04% when the vapor parameters of CO2 are 620/30 MPa, with the double-reheating-recompression cycle as the top cycle, and RC as the bottom cycle. Such efficiency is higher than that of the supercritical water cycle power plant.

show abstract

Thermal deformation prediction based on the temperature distribution of the rotor in rotary air-preheater

Cited by 35 publications

References 18 publications

A Knowledge- and Data-Driven Soft Sensor Based on Deep Learning for Predicting the Deformation of an Air Preheater Rotor

A Knowledge- and Data-Driven Soft Sensor Based on Deep Learning for Predicting the Deformation of an Air Preheater Rotor

Influence of operating conditions on ammonium bisulfate deposition in the rotary air preheater of coal-fired power plants

How to Construct a Combined S-CO2 Cycle for Coal Fired Power Plant?

Contact Info

Product

Resources

About