Optimum Design Of Thermodynamic System For Medium And Small Power Steam Turbines Based On Adaptive Genetic Algorithms

Steam turbines not only play a pivotal role in China's power supply,but are also widely used in marine machinery,industrial production and heating.The thermal system consists of numerous thermal devices.It is closely related to the fields of flow,heat transfer and heat work conversion.Therefore,it is of great practical significance to study and improve the efficiency of the steam turbine thermal system.At present,the level of software design and development in domestic steam turbine manufacturing field is uneven,and most of the existing steam turbine thermodynamic calculation software only has more accurate calculation results for a certain type of unit.In addition,the steam turbine manufacturers still have the shortcomings of unfriendly user interface and intuitive display of calculation results.Aiming at this problem,this paper establishes a general thermodynamic calculation model based on the conventional steam turbine thermodynamic calculation principle and engineering practice knowledge.On this basis,the improved adaptive genetic algorithm is coupled to realize the automatic optimization of some unit parameters.The following is a summary of the work in this paper:(1)Based on Fortran,the basic function module and aerodynamic loss model of steam turbine thermodynamic design calculation are realized.The thermodynamic calculation of the whole turbine can be completed according to the given thermodynamic parameters and mechanical parameters,and the efficiency of the final thermodynamic system can be evaluated.(2)Traditional design of geometric parameters of steam turbine mainly relies on original design experience and manual regulation,which not only occupies more human resources,but also is difficult to achieve optimal results.In order to solve this problem,it is necessary to combine the adaptive genetic algorithm with the thermodynamic calculation process.When using adaptive genetic algorithm,this paper finds that it is easy to fall into local optimum when the initial variation range of variables is limited.Therefore,this paper proposes an improved genetic algorithm based on the idea of iteration method.(3)A general software interface platform for thermal calculation and optimization design is developed by using Swing user interface component.The platform provides functions and interfaces for thermal calculation,design optimization and result display.(4)The experimental research shows that the optimized scheme of the developed platform has a certain improvement in the unit power and internal efficiency compared with the original manual adjustment and optimization design,thus validates the reliability and applicability of the software.The work and conclusions of this paper can provide a good reference for multi-objective optimization,genetic algorithm and thermal calculation.