As we all know, no matter how big the capacity of pure condensing unit is, the last stage exhaust steam contains huge residual heat, but eventually this part of heat will be released into the environment through the cooling tower, which will have a certain impact on the unit and the ecological environment. This paper aims to study the optimization of multi-pressure condenser combining artificial intelligence and deep learning algorithm. In this paper, Matlab is chosen as the modeling tool of condenser. According to the modular modeling concept of Matlab, the condenser model is divided into seven subsystems according to the structure. Based on the heat calculation and heat balance theory of condenser, seven subsystems are modeled by Simulink modeling platform, and then connected to establish the simulation model of single-pressure condenser in large power plant, and on this basis, the double-pressure condenser model is built. After determining the accuracy of condenser model, this paper uses the established model with certain accuracy to analyze the performance and economic benefits of different condenser tubes (including copper tubes). And stainless steel and titanium. Each material has significant differences in thermal conductivity, corrosion resistance and cost, among which titanium tube has the lowest thermal conductivity, the best corrosion resistance and the highest cost. In this paper, the investment cost, service life and operation performance of the tubes are comprehensively reviewed, the scope of each material is introduced in detail, and suggestions are put forward according to different design requirements, which provides a basis for the selection of condenser tubes.

Mayank Lakshmi. Optimization of Multi-pressure Condenser Combining Artificial Intelligence and Deep Learning Algorithm. Kinetic Mechanical Engineering (2022), Vol. 3, Issue 2: 46-55. https://doi.org/10.38007/KME.2022.030206.

[1] Yuan A , Gao L . Research on the Application of NLP Artificial Intelligence Tools in University Natural Language Processing. IOP Conference Series: Earth and Environmental Science, 2021, 714(4):042018 (9pp). https://doi.org/10.1088/1755-1315/714/4/042018

[2] Yoshitaka, BITO, Takashi, et al. Improved Support for Image Diagnosis by Artificial Intelligence. Medical Imaging and Information Sciences, 2019, 36(2):105-108.

[3] Albright B . Deep Learning and Design Engineering. Desktop Engineering, 2019, 24(7):26-28.

[4] Yu Y , Hussein R , Zaharchuk G , et al. Automated detection of arterial landmarks and vascular occlusions in patients with acute stroke receiving digital subtraction angiography using  deep learning. Journal of NeuroInterventional Surgery, 2022, 2018(N):1464-6.

[5] Cerrato P , Halamka J , Pencina M . A proposal for developing a platform that evaluates algorithmic equity and accuracy. BMJ Health And Care Informatics, 2022, 29(1):1351-63. https://doi.org/10.1136/bmjhci-2021-100423

[6] Wang P , Wang Y , Liu T , et al. Active learning-based multi-objective optimization for aerodynamic performance of a supercritical carbon dioxide turbine. Structural and Multidisciplinary Optimization, 2022, 65(9):1-16. https://doi.org/10.1007/s00158-022-03391-x

[7] Alotaibi G , Awawdeh M , Farook F F , et al. Artificial intelligence (AI) diagnostic tools: utilizing a convolutional neural network (CNN) to assess periodontal bone level radiographically—a retrospective study. BMC Oral Health, 2022, 22(1):1-7. https://doi.org/10.1186/s12903-022-02436-3

[8] Abdellatef E , Soliman R F , Omran E M , et al. Cancelable face and iris recognition system based on deep learning. Optical and Quantum Electronics, 2022, 54(11):1-21. https://doi.org/10.1007/s11082-022-03770-0

[9] Araz O . Optimization of three-element tuned mass damper based on minimization of the acceleration transfer function for seismically excited structur es. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2022, 44(10):1-14. https://doi.org/10.1007/s40430-022-03743-0

[10] Geneid A A , Atia M R A , Badawy A . Multi-objective optimization of vertical-axis wind turbine's blade structure using genetic algorithm. Journal of Engineering and Applied Science, 2022, 69(1):1-19. https://doi.org/10.1186/s44147-022-00150-z

[11] Bisoyi S K , Pal B K . Optimization of blasting parameters in opencast mine with the help of firefly algorithm and deep neural network. Sādhanā, 2022, 47(3):1-11. https://doi.org/10.1007/s12046-022-01956-6

[12] Aida-Zade K , Abdullayev V . Optimization of the Right-hand Sides of Multi-point and Integral Conditions of the Controlled Dynamic System. Bulletin of the Iranian Mathematical Society, 2021, 48(5):2033-2056. https://doi.org/10.1007/s41980-021-00628-1

[13] Kwon H J , Kwon H K . Computer aided engineering (CAE) simulation for the design optimization of gate system on high pressure die casting (HPDC) process. Robotics and Computer-Integrated Manufacturing, 2019, 55PB(FEB.):147-153. https://doi.org/10.1016/j.rcim.2018.01.003

[14] Zhang Z , Feng H , Zhao W , et al. The Technical Scheme Optimization of Nuclear Vessel Hydrostatic Test. IOP Conference Series: Earth and Environmental Science, 2021, 769(4):042051 (5pp). https://doi.org/10.1088/1755-1315/769/4/042051

[15] Junhua G U , Sun Z , Wang F , et al. Classification of benign and malignant pulmonary nodules based on multi-scale feature fusion. Journal of Shenzhen University Science and Engineering, 2021, 37(4):417-424. https://doi.org/10.3724/SP.J.1249.2020.04417

[16] Maruthappu M , Gao W , Lovejoy C A . Role of artificial intelligence and machine learning in haematology. Journal of Clinical Pathology, 2022, 68(N):143-4.

[17] Gao N . A Multi-Feature and Machine Learning Graded Pedestrian Detection Method. International Core Journal of Engineering, 2019, 5(12):57-62.

[18] Wijayati D T , Rahman M F W , Rahman Z , et al. A study of artificial intelligence on employee performance and work engagement: the moderating role of change leadership. International Journal of Manpower, 2022, 43(2):486-512. https://doi.org/10.1108/IJM-07-2021-0423