Research on Classification and Identification of Crack Faults in Steam Turbine Blades Based on Supervised Contrastive Learning DOI Creative Commons
Qinglei Zhang, Longfei Tang,

Jiyun Qin

et al.

Entropy, Journal Year: 2024, Volume and Issue: 26(11), P. 956 - 956

Published: Nov. 6, 2024

Steam turbine blades may crack, break, or suffer other failures due to high temperatures, pressures, and high-speed rotation, which seriously threatens the safety reliability of equipment. The signal characteristics different fault types are slightly different, making it difficult accurately classify faults rotating directly through vibration signals. This method combines a one-dimensional convolutional neural network (1DCNN) channel attention mechanism (CAM). 1DCNN can effectively extract local features time series data, while CAM assigns weights each highlight key features. To further enhance efficacy feature extraction classification accuracy, projection head is introduced in this paper systematically map all sample into normalized space, thereby improving model's capacity distinguish between distinct types. Finally, optimization supervised contrastive learning (SCL) strategy, model better capture subtle differences Experimental results show that proposed has an accuracy 99.61%, 97.48%, 96.22% task multiple crack at three speeds, significantly than Multilayer Perceptron (MLP), Residual Network (ResNet), Momentum Contrast (MoCo), Transformer methods.

Language: Английский

An investigation into the correlation between operating conditions and non-equilibrium condensation in supersonic nozzles: Focusing on supercooled, saturated, and superheated vapor states DOI

Leyla Iraj,

Iman Bazari,

Nima Khoshnazar

et al.

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(3)

Published: March 1, 2025

Non-equilibrium condensation (NQC) is a critical process within supersonic nozzle, leading to thermodynamic losses and significant alterations in the flow structure. The release of latent heat during NQC results increased pressure, temperature, reduction Mach number. This study investigates influence different input vapor types—superheated, saturated, supercooled—on structure two-phase regimes nozzle. A compressible model employed simulate behavior. Results reveal that type has profound impact on pattern. Supercooled associated with gradual pressure increase converging section, whereas saturated superheated vapors exhibit abrupt surges at throat diverging section. Furthermore, supercooled demonstrates higher mass fraction liquid larger droplet radii compared vapors. Saturated exhibits highest rate, while experiences loss. Superheated vapor, other hand, entropy production. Compared 10-degree 1.33% decrease 9.06% loss, reductions frictional thermal production by 3.61% 2.56%, respectively.

Language: Английский

Citations

2
Numerical study of the impact of hot steam injection in the condensation flow through the low-pressure stage of steam turbine DOI

Samaneh Masoumi,

Esmail Lakzian, Heuy Dong Kim

et al.

Thermal Science and Engineering Progress, Journal Year: 2024, Volume and Issue: 53, P. 102698 - 102698

Published: June 13, 2024

Language: Английский

Citations

6
Two-phase Flow Characteristics and Leakage in the Shaft Seal of Steam Screw Expanders DOI
Yafen Tian, Zebin Wang, Zhixiang Liu

et al.

International Journal of Refrigeration, Journal Year: 2025, Volume and Issue: 172, P. 214 - 227

Published: Feb. 1, 2025

Language: Английский

Citations

0
Numerical analysis of saturated steam injection effects on steam turbine performance considering condensation losses and turbine stage efficiency DOI Creative Commons

Leyla Iraj,

Mahdi Tamimi,

Ali Jahangiri

et al.

International Communications in Heat and Mass Transfer, Journal Year: 2025, Volume and Issue: 164, P. 108876 - 108876

Published: March 23, 2025

Language: Английский

Citations

0
Progress in the research on non-equilibrium condensation of the compressor in the supercritical CO2 closed Brayton cycle system DOI

Xinzhe Zhang,

Bin Yu, Guoju Li

et al.

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(4)

Published: April 1, 2025

The supercritical carbon dioxide (S-CO2) closed Brayton cycle holds significant promise for revolutionizing the future of efficient and comprehensive new energy utilization. However, compressor operation in this is characterized by rapid pressurization, which induces substantial fluctuations temperature pressure, potentially triggering non-equilibrium condensation S-CO2. This phenomenon disrupts flow field within compressor, thereby decreasing overall performance system. Therefore, exploring mechanism great significance improving work summarizes various improvement types S-CO2 systems engineering applications across fields. Subsequently, it reviews development theories compressors, focusing on nucleation growth models. In addition, current research status characteristics under high-speed high-pressure conditions summarized, based convergent-divergent nozzle experiments simulations. systematically progress system from perspectives, such as origin technological bottleneck, nature scientific problem, state research. By reviewing blade humidity control method condensation, proposed that technology active multi-objective coordination should be direction further findings analysis can provide a reference design blades

Language: Английский

Citations

0
Prediction of condensation shock in supersonic nozzle: Comparison between high-pressure and low-pressure conditions at different of superheating degree DOI
Yanyu Zhang,

Fengrong Liu,

Shanshan Liu

et al.

Chemical Engineering Science, Journal Year: 2025, Volume and Issue: unknown, P. 121818 - 121818

Published: May 1, 2025

Language: Английский

Citations

0
Failure mechanism of sulfur transport jacketed pipeline induced by the combined effects of steam erosion and wet sulfur corrosion DOI
Jingjing Jiang, Lihua Huang,

Zicheng Peng

et al.

Engineering Failure Analysis, Journal Year: 2025, Volume and Issue: unknown, P. 109749 - 109749

Published: May 1, 2025

Language: Английский

Citations

0
Research on Classification and Identification of Crack Faults in Steam Turbine Blades Based on Supervised Contrastive Learning DOI Creative Commons
Qinglei Zhang, Longfei Tang,

Jiyun Qin

et al.

Entropy, Journal Year: 2024, Volume and Issue: 26(11), P. 956 - 956

Published: Nov. 6, 2024

Steam turbine blades may crack, break, or suffer other failures due to high temperatures, pressures, and high-speed rotation, which seriously threatens the safety reliability of equipment. The signal characteristics different fault types are slightly different, making it difficult accurately classify faults rotating directly through vibration signals. This method combines a one-dimensional convolutional neural network (1DCNN) channel attention mechanism (CAM). 1DCNN can effectively extract local features time series data, while CAM assigns weights each highlight key features. To further enhance efficacy feature extraction classification accuracy, projection head is introduced in this paper systematically map all sample into normalized space, thereby improving model's capacity distinguish between distinct types. Finally, optimization supervised contrastive learning (SCL) strategy, model better capture subtle differences Experimental results show that proposed has an accuracy 99.61%, 97.48%, 96.22% task multiple crack at three speeds, significantly than Multilayer Perceptron (MLP), Residual Network (ResNet), Momentum Contrast (MoCo), Transformer methods.

Language: Английский

Citations

0