In order to monitor the condition of the heat recovery steam generator (HRSG) and to ensure the healthy operation of the HRSG, the three-pressure main steam temperature and pressure prediction model was established by using the data from the healthy operation of HRSG and combining the three methods of principle component analysis (PCA), sparrow search algorithm (SSA) and long short-term memory (LSTM). PCA was used to reduce the input parameters of the model from 22 to 9 dimensions, and taking the reheat steam temperature prediction model as an example, it was concluded that the model with PCA dimensionality reduction reduced the hyperparameter optimization time by 11.3% compared with the model without PCA dimensionality reduction. Compared with the model without SSA, the value of coefficients of determination of these models is significantly improved, mean absolute error and root mean square error are significantly reduced, and the alarm threshold of the main steam temperature HRSG is determined according to the distribution of absolute error. Therefore, the condition monitoring model of HRSG based on PCA-SSA-LSTM has short training time and high prediction accuracy, and the model provides theoretical basis and technical support for fault monitoring and diagnosis of HRSG in gas turbine combined cycle power plants.

According to GB/T10184—2015, the calculation model of blast furnace gas boiler efficiency is constructed, and the calculation method of blast furnace gas boiler efficiency is analyzed. The results show that the calculation methods of gas moisture content and low-level calorific value are different due to the difference of gas benchmarks.Three methods for solving the excess air coefficient, actual flue gas volume and CO₂ content in the flue gas are proposed for blast furnace gas boilers, and a correction method for exhaust gas temperature of blast furnace gas boilers with gas heaters is proposed;The calculation of some formulas in the GB/T10184—2015 needs to be further discussed, and appropriate modifications can be made.

A new combined cooling, heating and power system is proposed based on solar photovoltaic, wind power, ground-source heat pump and energy storage unit (WSSH-CCHP) to improve the efficient utilization of renewable energy resources and the entire system energy efficiency. The comprehensive evaluation indexes are developed by using the analytic hierarchy process to account for the system performance of energy efficiency, economy and environment. The mixed integer linear programming (MILP) algorithm is employed to perform the optimization on the selection of equipment types, capacity allocation and system operation stratagem. A case study on an energy center in Jinan city is conducted to explore the optimal performance and operation characteristics of WSSH-CCHP. The obtained results indicate that the proposed system comprehensive performance is much better than the separate production system, which provide useful information for the development of CCHP system with wind-solar-storage and heat pump and the study on its integrated optimization and operation characteristics.

Under the background of the goal of “carbon peak and carbon neutrality”, environmental protection requirements are becoming increasingly stringent, and methanol as a recognized high-efficiency, clean and low-carbon fuel has received more and more attention. In order to analyze the feasibility of methanol for boiler fuel, a comprehensive evaluation model of methanol, coal, diesel and natural gas as boiler fuel was established, and the four indicators of energy saving, environmental protection, economy and sociality were considered through analytic hierarchy process (AHP) and entropy weight method (EWM), and comprehensive evaluation was carried out under five scenarios with different importance of each index. The following conclusions are drawn: the energy saving of methanol is better than that of other fuels, the environmental protection and economy are comparable to natural gas, and the social aspect is second only to coal, which is 3.2 times that of diesel and 2.2 times that of natural gas; in terms of importance, environmental factors first, economic factors and energy-saving factors second, social factors are the weakest importance (scenario 3); the comprehensive evaluation score of methanol as boiler fuel is 0.318 6, which has great advantages compared with natural gas (0.292 9), coal (0.232 4) and diesel (0.156 1).

Aiming at the problem that it is difficult to accurately and timely measure the inlet NOx concentration in the denitrification system of selective catalytic reduction (SCR) in thermal power plants, due to the excessive factors affecting the inlet NO_x concentration and the large delay and inertia of the system, the Max-Relevance and Min-Redundancy (mRMR) combined with Bayesian optimization (BO) algorithm is proposed, optimize the dynamic soft measurement model of NO_x concentration at the inlet of the SCR denitration system of the stacking ensemble model. Aiming at the problem of reduced prediction accuracy of static single model and asynchronous timing of auxiliary variables and inlet NOx concentration in the process of dynamic NO_x generation, the mRMR-BO combined with model was used to screen the auxiliary variables, Copula Entropy (CE) determined the delay of auxiliary variables, the BO combined with model determined the order of auxiliary variables, and TCN and LASSO were integrated by Stacking method. The auxiliary variables containing delay time and order information were used to construct a dynamic stacking ensemble soft measurement model, and the simulation results showed that the root mean square error, average absolute error, and average absolute percentage error of the integrated model compared with TCN and LASSO single networks were the smallest. Compared with the static ensemble model, the dynamic ensemble model has higher prediction accuracy and can achieve accurate soft measurement of the inlet NO_x concentration.

Aiming at the problems of pollution and high carbon emissions caused by island dependence on diesel energy supply, an islanded integrated energy system multi-objective planning optimization method considering carbon emission was proposed. Based on the construction of equipment model, the annual operation of the system was simulated hourly considering the influence of the climate fluctuation on the output of renewable energy devices, the life cycle costs and life cycle carbon dioxide emissions was taken as the optimization objectives, the multi-objective planning optimization model of islanded integrated energy system was constructed by combining with non-dominated sorting genetic algorithm II, the weighted arithmetic averaging operator was used to make decisions on the optimization results. An island area in Yantai was taken as an example, the influence of typical day and annual hourly data as input on planning results, the influence of investment changes in renewable energy devices and natural gas prices, as as well as wind power and photovoltaic installed capacity and battery capacity on optimization objectives were analyzed. By multi-objective planning optimization of the study area, the optimal capacity of each device under different target weights was obtained. The results showed that the configuration of renewable energy and battery can reduce the life cycle carbon dioxide emissions by 26.95% -55.96%. But when the life cycle carbon dioxide emissions weight was increased from 0.6 to 1, the carbon dioxide emissions were reduced by increasing the battery capacity. At this time, life cycle costs increased by 210.13% and life cycle carbon dioxide emissions only decreased by 8.59%. The proposed island integrated energy system planning method provides a reference for decision makers to balance low carbon cost and energy supply economy when planning islanded low carbon IES.

Taking a million kilowatt nuclear power half speed steam turbine generator set as the research object, a dynamic model of spring foundation bearing rotor is established by using the rotor dynamics professional analysis software ARMD. The dynamic characteristics of the shafting are obtained through dynamic calculation and analysis. The accuracy of the calculation model is verified by the coincidence of the field measured critical speed of the shafting and the calculated value. On this basis, the vibration response caused by the thermal imbalance of the seal pad of the generator is calculated. It is found that the vibration changes are mainly concentrated at the rotor of the generator, and the thermal imbalance of the seal pad is only the direct influence factor of the vibration fluctuation of the shaft system, but not the root cause. At the same time, the oil film stress of the seal pad under different operating conditions is analyzed, and it is found that the axial inclination has the greatest impact on the stress of the seal pad. Therefore, the processing and installation process shall be ensured during the maintenance and adjustment of the unit to prevent the shaft system deflection during the operation of the seal pad.

In the actual operation status of dry-type air-core reactor, the focus and difficulty of the fault diagnosis method is to reduce the false alarm rate and the missing alarm rate. About it, this paper proposes a weighted Naïve Bayes state evaluation method for a dry-type air-core reactor. First, a simulation model of a reactor inter-turn short circuit fault is established using multi-physical field coupling, and the effectiveness of the simulation method is validated by constructing a reactor operation test platform. Second, simulation and analysis of reactor current amplitude, current harmonics, impedance angle, and hot spot temperature under multiple operating conditions are performed to obtain the reactor’s normal and known fault sample sets. Finally, a weighted Naïve Bayes state evaluation model is developed using multi-state feature quantities. The example demonstrates that this method is effective for reactor operation state recognition and classification because it has high classification accuracy and requires fewer training samples.

The hybrid gas foil thrust bearings have excellent performance, but few studies have been reported on them. In this regard, a model of this bearings is proposed and a numerical research is carried out for the static and elasto-hydrodynamic characteristics. Based on MATLAB software, a steady fluid-structure interaction method was proposed for the numerical prediction of hybrid gas foil thrust bearings. The foil deformation, static load and frictional torque were calculated and analyzed at various rotating speeds, supply gas pressures and locations of air supply holes. The influences of operating parameters and locations of air supply holes on the static performance of hybrid gas foil thrust bearings were presented. The results show that: increasing the gas pressure has a small effect on the frictional torque, but increases the axial load of the bearing, and increasing the speed will lead to a significant increase in the frictional torque of the bearing. The location of the gas supply hole arrangement has a large effect on the static characteristics of the hybrid gas foil thrust bearings, so the location arrangement should be reasonably selected. The priority is given to the arrangement of the gas supply hole in the tilted area on the basis of meeting the bearing load requirements. The conclusions are of guidance for the design and application of hybrid gas foil thrust bearings.

Taking the gas fuel control valve of gas turbine as the research object, based on the computational fluid dynamics method, the flow field distribution and flow change rule of the gas fuel control valve under the actual operating conditions are studied, and the flow characteristic curve of the valve is fitted. The results show that the mass flow of the control valve at the same opening has nothing to do with the change of the pressure behind the valve, and is in a blocked flow state when the pressure in front of the valve is 2.650 MPa and the pressure ratio behind the valve to that in front of the valve is 0.49~0.78; Under the same pressure ratio, the discharge coefficient is approximately linear with the opening, which is consistent with the actual requirements of the project; There is a linear correlation between the flow coefficient and throat area. By optimizing the valve core profile, the linear curve of throat area with opening is improved, and the linearity of the flow characteristic curve is improved.