A large amount of data is generated during steam turbine operation. In order to meet the requirements of high quality data driven by big data and simulation modeling, efficient data cleaning is very necessary. The semi-supervised data cleaning model of steam turbine is built by using the excellent nonlinear fitting ability of long and short memory layer for time series data. The model selects three boundary conditions of the unit as input to predict the cleaning data. Outliers are eliminated according to the residual difference between the predicted value and the actual value. Then, the predicted value of the model is used to fill the data to ensure the integrity of the data. The model is used to clean the data of a 650 MW unit in a power plant. To overcome the problems caused by sample imbalance in the selection of cleaning model indicators, the accuracy rate is improved and taken as the measurement index of cleaning effect. The results show that, the improved accuracy of the data cleaning model of the deep long and short memory network is higher than that of the other three common cleaning methods, which can effectively identify whether the data is abnormal, and can use the predicted value to fill the data to ensure the consistency of data before and after cleaning.

In the study, a computational fluid dynamics (CFD) model based on a 600 MW tangentially coal-fired boiler was established. According to orthogonal conditions (L₁₆(4⁵)), the heat flux distributions of the water-cooled wall under 100% BMCR, 75% THA, 50% THA and 35% BMCR loads were obtained. In addition, the factors also included: primary to secondary air rate, degree of air-staging, swing angles of burners and SOFA nozzles. Then, the spiral water-cooled wall temperature distributions under various conditions were calculated through coupling the heat absorption, temperature calculation and hydrodynamic characteristics of the water-cooled wall. Due to the discontinuity of orthogonal condition, the machine learning was used for predicting the spiral water-cooled wall temperature distribution within the range of parameters covered by orthogonal conditions. The results showed that a wall temperature peak up to 730 K would appear in the area among burner system. The heat transfer deterioration was easy to occur when the flame center height in furnace coincided with the phase change height of the working fluid during the boiler load adjusting process. The goodness of fit R² of the ensemble learning on the training set and the test set of the wall temperature data had reached 0.99, which could be used to predict the wall temperature of the boiler under wide load. At the same time, the machine learning established the mapping relationship between the wall temperature distribution and the operating parameters of the boiler. In the future study, the wall temperature safety of the water wall can be guaranteed by reasonably adjusting and optimizing the operating parameters through the optimization algorithm.

With the gradual increase in the proportion of new energy in the energy system, increasing the difficulty of AGC frequency regulation of thermal power units, energy storage systems combined with thermal power units AGC frequency regulation technology in China's power industry is developing rapidly. In this paper, the joint frequency modulation system of thermal power unit and energy storage system is studied for the problem of not considering the characteristics of unit variable load process and the lack of relevant evaluation system. Firstly, the thermal unit coal consumption, lifetime, environmental friendliness and energy storage lifetime models are established and uniformly transformed into cost terms during the thermal unit variable load process, thus constituting the corresponding evaluation system. Secondly, the system day-ahead operation optimization model is established, and the system load allocation strategy is further refined by considering the optimization results. Finally, the method proposed in this paper is verified by a case study. The results show that the optimal allocation strategy of joint frequency modulation load of thermal power unit and energy storage proposed in this paper can achieve the purpose of energy storage state management; and through the optimal selection of unit variable load rate and the coordinated response with the energy storage system, the process of unit load change is alleviated the problems of excessive environmental protection and rapid loss of lifespan.

In order to study the thermodynamic characteristics of oil-free scroll expander in detail, leakage and thermodynamic model are established based on the first law of thermodynamics and the equation of energy and mass balance. Through the established leakage model, different working condition parameters are further changed to study the changing trend of the leakage in the scroll expander. Under the comprehensive consideration of the influence of heat transfer and leakage on the thermodynamic model, the Euler method is used to solve the established thermodynamic model, pressure, temperature and mass variation of the working medium with the orbiting angle of the main shaft during one operation cycle of the scroll expander are obtained and analyzed. Finally, an experiment platform is set up to test and verify the established thermodynamic model of the scroll expander, which can provide a certain reference for the performance analysis of the scroll expander.

Aiming at the problem of inaccurate prediction of NO_x emission concentration when the current coal-gas boiler gas mixture is uncertain and changing, a combined online prediction method based on attention mechanism is proposed. First, the characteristic variables of the model are determined by combining the maximum information coefficient method with the Pearson correlation coefficient method; Secondly, vector autoregressive(VAR) model is constructed online with sliding time window for linearly correlated characteristic variables to realize the prediction of NO_x emission concentration under the input of multi-dimensional time series linear correlation variables For non-linear-related feature variables, the relationship between NO_x emission concentration is predicted by constructing an online Recurrent extreme learning machine(OR-ELM) model online learning. Finally, Attention Mechanism(AM) is used to dynamically weight the two forecasting models to achieve trend forecasting. Through field data verification, it shows that the VAR-OR-ELM combined online prediction model constructed in this paper can accurately predict the variation trend of NO_x emission concentration after 10 minutes. Combining prediction accuracy and prediction time, the combined prediction model is better than other single prediction models.

Conventional industrial steam turbines are usually equipped with quick-closing inlet valves to realize emergency shutdown of the turbine. In this paper, a negative pressure inlet condensing steam turbine was studied has low inlet parameters, large inlet steam volume flow and small pressure difference between inlet and exhaust steam ends. In order to reduce the intake pressure loss, the quick-closing inlet valves are not employed, but a redundant large-diameter rapid vacuum breaker valve is used at the exhaust end of the turbine. When the turbine needs emergency shutdown, open the quick vacuum breaker valve, so that the atmosphere quickly enters the exhaust end of the turbine, the pressure of the exhaust end of the turbine rapidly rises, In this paper, the steam turbine whose inlet and exhaust steam pressure difference is 40 kPa is studied, and the pressure difference between the inlet end and the exhaust end of the turbine could reach 0 within 4 seconds, so that the turbine is closed, and the purpose of emergency shutdown of the turbine is achieved.

The overheating of boiler heating surface seriously affects the safe operation of the power plant. It is of great significance for the safety of boiler to predict the tube temperature of heating surface and to take appropriate preventative measures. A data driven-based model for tube temperature prediction is proposed in this study. Firstly, the key variables affecting the tube temperature are selected by grey correlation analysis that affect the wall temperature of the heating surface, and a wall temperature prediction model based on long short term memory (LSTM) neural network is constructed. Then, the correlation feature coefficients under similar historical operating conditions are defined, and the predicted wall temperature obtained by the LSTM neural network is corrected to improve the model's prediction accuracy. Finally, an on-duty supercritical boiler with 600 MW capacity is taken as the case study. Results showed that the relative error of the proposed prediction model is within (−2.5%, 2.5%). The average relative error is 0.40%, and the average tube temperature prediction error is 2.24 ℃. It indicates that the proposed model is helpful for the tube temperature prediction of the boiler under complex operating conditions.

The proposal of the "dual carbon" has brought profound changes to the development of China's energy and power industry. As the leading enterprises in China's power industry, the five major power generation groups should play a demonstration and leading role, analyze and evaluate their low-carbon transformation achievements have important significance for the power generation industry to achieve the "dual carbon" goal as scheduled. This article uses the entropy weight TOPSIS method to conduct empirical research and analysis on the indicator data of the five major power generation groups in China from 2017 to 2021. The empirical results show that from a vertical dimension, it is found that the low-carbon transformation of the five power generation groups has achieved good results in 2017 to 2021, and the low-carbon transformation performance of each power generation group has shown an increasing trend year by year. This indicates the implementation of policies related to structural adjustment, emission reduction, and re transformation of the five power generation groups, achieved positive and significant results; from a horizontal perspective, the rankings of the five major power generation groups have been constantly changing from 2017 to 2021, indicating that each power generation group has made varying degrees of progress in low-carbon transformation.

The combustion of biomass will not increase carbon dioxide emissions, and the development of biomass coal coupled power generation technology is a feasible way to accelerate the transformation and upgrading of electricity. The compressed biomass and coal powder are ground in different coal mills without mixing, and are fed into the furnace by different burners. This method does not require additional biomass treatment equipment or setting up a biomass fuel treatment workshop, which can greatly save investment and factory space. The key limiting technical factor is whether the pulverizer of the power plant can effectively grind biomass Pellet fuel, and how to evaluate the adaptability of the existing pulverizer to the new coupling fuel. To this end, a medium speed coal mill experimental platform was built to analyze the adaptability of the medium speed coal mill in grinding biomass particles. The results show that the grinding output of the medium speed coal mill decreases when grinding wood chip biomass particles, and the effective output correction coefficient is 0.65~0.70; When the ZGM medium speed coal mill grinds sawdust particles, the loading force characteristics and separator characteristics both vary significantly at the particle size boundary of 0.2 mm. Therefore, the screening fineness R₂₀₀ and R₅₀₀ can be considered as the measurement standards for the uniformity of biomass particle materials ground by the coal mill; Compared with pulverized coal, the increase of loading force of milled biomass particles or the increase of rotating speed of the current separator has a large difference in the influence of fineness distribution, which needs further in-depth research.

Under the background of carbon peak and carbon neutralization, the importance of thermal power generation in northwest China has been further increased. Due to the high proportion of high alkali coal in this area, serious slagging and contamination come out easily in the process of burning high alkali coal in boiler. It's of vital importance to solve the problem of safe burning of high alkali coal ensuring the safety of electric power in China. The present situation of high-alkali coal combustion technology at home and abroad is introduced in this paper. With more than ten years' research, the high-alkali coal combustion technology in China has been improved remarkably, and the related achievements have been popularized and applied in the electric power industry. The blending ratio of high alkali coal in boiler has been increased from less than 60% to more than 90%, though the full burning of high alkali coal has not been realized yet. This paper introduces different technical routes to realize full burning of high alkali coal and analyzes the equipment parameters and operation of typical boilers burning high alkali coal. Generally speaking, pulverized coal boiler, fluidized bed boiler and liquid slag boiler have their own advantages and disadvantages in the adaptability to high alkali coal, with technical bottlenecks to be further studied and broken through. In order to ultimately solve the high alkali coal combustion problem, more new technologies need to be introduced.