The rapid and comprehensive determination of coal quality is of great significance for the optimization of boiler combustion and the digital transformation of coal-fired power plants. Laser-induced breakdown spectroscopy (LIBS) has the potential to be applied effectively in the rapid determination of coal quality. In order to meet the application goal of rapid coal inspection, 46 sets of spectral data of coal samples from different power plants were collected by the experimental device of coal particle flow LIBS, and the research of simultaneous rapid inspection of multiple indicators of coal quality by combining LIBS with machine learning was carried out systematically. In view of the considerable spectral fluctuations observed in the particle flow state, the number of single-pulse acquisitions was optimized. In addition, invalid spectral screening, spectral averaging and spectral normalization data preprocessing methods were established. Furthermore, four machine learning algorithms (PLSR, SVR, PSO-SVR, and LSTM) and four spectral feature inputs (full spectra, eigenbands, intensity integration, and PCA extraction) were compared in terms of their performance in predicting multiple indicators of coal quality. The results demonstrate that the uncertainty of the spectral signals can be maintained at a maximum of 5% when 200 single-pulse spectra are collected for spectral averaging in a single test. The PSO-SVR algorithm exhibits the most optimal prediction performance in the quantitative analysis of coal quality indicators, and the PCA algorithm reduces the dimensionality of the spectral data, which reduces the amount of model computation and at the same time improves the prediction performance of the model, and the model established by combining both of them has the best performance, the root mean square error (RMSEP) of the coal heat content is 0.289 MJ/kg, and the mean absolute error (MAE) is 0.231 MJ/kg. The coal carbon mass fraction, ash content and volatile matter content are also predicted satisfactorily, with the RMSEP of 0.987%, 1.310% and 1.612%, and the MAE of 0.839%, 1.014%, and 1.033%, respectively. The results show that, combined with appropriate machine learning algorithms, the LIBS technique can achieve simultaneous accurate and rapid determination of multiple indicators of coal quality, which has a broad application prospect in the scenario of efficient and clean coal utilization.

In order to study the effects of different drying conditions on crushing rate and pulverization rate of Baoqing lignite after drying, as well as the effects of different drying moistures on spontaneous combustion and explosion characteristics of the coal samples, several experiments were conducted, like the drying of raw coal, and the spontaneous combustion and explosion characteristics of coal samples with different moisture contents. The results show that, a drying furnace temperature above 300 ℃ and a higher heating terminal temperature can achieve a higher coal sample dehydration rate. Coal particles with smaller particle sizes tend to achieve higher dehydration rates and lower crushing rates. The pulverization rate of 6~13 mm coal particles is the highest under different drying conditions. Baoqing raw coal is a type of coal that is prone to spontaneous combustion. As the moisture content of the dried coal sample decreases, the spontaneous combustion tendency of the raw coal weakens and becomes a type of coal with moderate spontaneous combustion tendency. As the moisture content of the coal sample increases, the explosion tendency of the test coal sample decreases. As the fineness of coal powder R90 increases, the explosion tendency of coal powder decreases. Therefore, in the engineering application process of Baoqing lignite drying technology, the proportion of 6~13 mm coal particles should be reduced to lower the pulverization rate during the drying process. The air temperature during coal powder transportation should be appropriately reduced, or the fineness of coal powder should be appropriately increased to reduce the tendency for explosion.

To understand the inner wall temperature distribution characteristics of boiler heating surfaces during fast peaking operation, this study incorporates the coupling of non-uniform heat flux distribution on the combustion side with a multi-tube flow-resistance model on the working fluid side. This corrects the resistance and mass flow distribution among the rows of tubes in the superheater, forming a comprehensive heat transfer calculation model that couples the non-uniform heat flux on the flue gas side with the actual flow rate on the working fluid side, allowing for more accurate prediction of superheater temperatures. This model is applied to the calculation and analysis of wall temperature characteristics of a 660 MW counter-flow coal-fired boiler’s screen superheater at various loads and swirl angles. The study reveals that during deep load-following, the highest tube wall temperature at 30% load (868.4 K) exceeds that at 50% load (861.9 K), approaching the maximum temperature the material can withstand. The tube wall temperature at 50% load is higher than that at 75% load (849.7 K). Additionally, changes in swirl angle significantly affect the non-uniform distribution of flue gas and the working fluid temperature on the steam side. When the swirl angle is 45°, the high-temperature zone is primarily distributed at both ends of the tube screen. When the swirl angle is 15°, it concentrates in the middle front and middle rear regions. As the swirl angle increases, spatial heterogeneity of the flue gas field in the furnace enhances, leading to greater temperature non-uniformity across the superheater width. The research results can provide technical support for the design and retrofit of boilers during rapid load-following processes.

At present, foreign brands almost occupy the entire fan lubrication market share, and domestic oil products lack opportunities to enter the market. To demonstrate the feasibility of domestic substitution of lubricating oil for wind turbine gearboxes, the testing and analysis database for domestic gearbox lubricating oil and foreign competitors is established by adopting laboratory analysis to test the physical and chemical performance indicators (including kinematic viscosity, viscosity index, flash point, pour point, moisture, acid value, demulsibility, foam characteristics, liquid phase corrosion, and copper corrosion), tribological performance indicators (sucn as maximum seizure free load, sintering load, friction coefficient, wear spot diameter, comprehensive wear), and other lubricating oil performance indicators (like antioxidant performance, ferrography, infrared spectroscopy, and PQ index). The comprehensive performance of domestic gearbox lubricating oil products is systematically evaluated, and the feasibility study of domestic substitution of wind turbine lubricating oil is completed. The results indicate that there is not much difference in the basic performance indicators between domestic brand fan gearbox lubricating oil products and imported brands, and the substitution is feasible.

Biomass contains a high content of alkali metal elements, which can cause serious slagging problems during the combustion process. Coal gangue is a kind of bulk solid waste, and its resource utilization is an urgent need. In order to solve the problem of biomass combustion slagging and coal gangue utilization, coal gangue was used as an additive and mixed with sunflower straw for combustion. Physical and chemical characterization of the burned ash samples were carried out using thermogravimetric analysis (TG-DTG), inductively coupled plasma spectrometry (ICP-AES), and ash melting point tester. The effects of temperature and ratio on the combustion performance and slagging of mixed fuels were also investigated. The research results show that, during the combustion of sunflower straw, the addition of a small amount of gangue significantly increased the alkali metal content in the ash. More of these metals were converted into high-melting-point silica-aluminates, which were fixed in the ash samples, while the gaseous alkali metal content decreased. As a result, the tendency for slagging during combustion was reduced. At the same time, the sunflower straw reduced the ignition point and burnout temperature of the gangue, thereby promoting its combustion. The synergistic effect was obvious. When the proportion of coal gangue was 20%, the flammability index of the fuel reached 9.36×10^–4%/(min·℃), and the comprehensive combustion characteristics index reached 42.6×10^–7%/(min²·℃³). The combustion performance was optimal, with a softening temperature of 1 470 ℃, and the tendency for slagging was significantly reduced.

In order to solve the corrosion problem of direct air cooling condensers, the independently developed dynamic corrosion simulation test device is used to simulate the actual operating conditions of the initial condensate, and the alkalizing agent and oxidant with low vapor-liquid distribution coefficient are selected for the flow accelerated corrosion test of carbon steel. The results show that, both alkalizing agent and oxidant can effectively inhibit the accelerated corrosion of direct air-cooled condenser. The rapid change of water flow direction has little effect on the accelerated corrosion rate of flow. Under the same conditions, the flow accelerated corrosion rate of carbon steel in oxidant environment is much lower than that in alkalizer environment. When oxidant is added to the direct air-cooled condenser for anticorrosion, the production cost of a single unit can be saved by 523 700 yuan per year.

In China, Xinjiang province has vast reserves of high alkali coal resources. However, in coal-fired boilers, fouling and slagging on heating surface caused by alkali metals significantly limit the efficient utilization of the coals. Based on gas-phase alkali metal detection, combined with flue gas temperature monitoring, heat transfer calculation and other methods, slagging monitoring was carried out on the heating surface of a tangentially-fired boiler burning high alkali coal. The influence of air distribution on flame temperature, gas-phase alkali metal mass concentration and heating surface heat transfer in the furnace was analyzed, and a quantitative relationship between the gas-phase alkali metal mass concentration and the heating surface heat transfer was established. Preliminary monitoring of fouling and slagging on the heating surface was also conducted. The results indicate that, slag sample on the water wall side was quite different from that on the flue gas side. The covered water wall surface was loose and porous, while the flue gas side was dense and hard black coke. Significant macroscopic differences were observed, with sodium crystalline phases mainly in the form of feldspar. The highest alkali metal concentration were observed in the main combustion zone of the boiler. The higher the ratio of upper to lower secondary air, the higher the temperature and gaseous alkali metal concentration in the furnace. An increase in the average gaseous alkali metal concentration by 1 mg/m³ resulted in a decrease in the heat transfer of the water wall by 0.82×10⁸ kJ at 300 MW on a tangentially-fired boiler burning high alkali coal.

When thermal power units participate in deep peak loading, real-time acquisition of furnace temperature field is helpful to power plant boiler control and research of combustion process in the furnace. With the promotion of intelligent power generation, machine learning provides an important means for real-time acquisition of furnace temperature field. The principle and application of the three most commonly used online monitoring technologies of furnace temperature field, namely acoustic method, absorption spectral tomography and thermal radiation imaging, are summarized at first, and the advantages and disadvantages in the application of boiler furnace temperature measurement are reviewed. Then, the principle of the coupled machine learning and CFD prediction method is described in detail, indicating that the method is less affected in the harsh furnace environment, and the application research of the method in the combustion flame structure and parameters and the furnace temperature field is reviewed, demonstrating the feasibility of applying the method to the furnace temperature field, indicating it can accurately predict the furnace temperature field. Finally, the future development trend of furnace temperature field online monitoring technology and coupled machine learning and CFD prediction method is analyzed, so as to provide ideas for obtaining more accurate furnace temperature field in real time under the continuous advancement of intelligent construction of power station.

Peak regulation in thermal power plants is an inevitable trend under the development of new energy. Under this condition, the initial condensing zone of steam turbine moves forward and the corrosion of low pressure cylinder intensifies. Several methods such as electrochemical testing, sample weight loss and metal surface topography analysis (SEM, EDS, XRD, and so on) were used to study the pitting corrosion characteristics of 2Cr13 steel (the material of low pressure cylinder of the steam turbine) under the conditions of simulated initial setting zone, with different mass concentrations and different mass concentration ratios of Cl^– to SO₄^2– of three anions (Cl^–, SO₄^2– and CH₃COO^–). The test results showed that, the corrosion rate of 2Cr13 steel increased with the anions’ mass concentration, and the maximum corrosion rate (0.095 23 g/(m²·h)) occurred when was 2:1. Pitting corrosion was observed in all samples, and the number of pitting corrosion increased with the anions’ mass concentration. With the change of, Cl^– and SO₄^2– on the metal surface of 2Cr13 steel changed from site competitive adsorption effect to mutual synergistic effect, resulting in the intensification of uniform corrosion and pitting corrosion. The chloride ions and sulfate in the initial coagulation zone of steam turbine will accelerate the corrosion rate of 2Cr13 steel and the occurrence of point corrosion. In actual operation of power plant, measures should be taken to prevent the leakage of condenser tubes and the broken particles of positive resin should be effectively removed.

In order to solve the problems of difficult, high cost and poor accuracy of state-of-charge (SOC) estimation for vanadium redox flow batteries (VFB), a joint SOC estimation method is proposed, based on forgetting factor recursive least squares (FFRLS) and multiple innovation unscented Kalman filter (MIUKF). The FFRLS algorithm is used to identify the equivalent circuit model parameters of vanadium redox flow batteries online, and the MIUKF algorithm is used for SOC estimation, so as to achieve the purpose of accurately estimating the SOC of vanadium redox flow batteries. Finally, a 5 kW/30 kW·h vanadium redox flow battery is taken as experimental platform to verify the method. The experimental results show that, compared with the RLS-UKF algorithm and FFRLS-UKF algorithm, the FFRLS-MIUKF algorithm has lower mean square error and root mean square error in the charging and discharging phases, which are 0.003 7, 0.060 9 and 0.001 3, 0.036 3.