An Aero-Engine Quality Assessment Method Based on Particle Swarm Optimized Fermatean Fuzzy Structural Equation Model

XÜ Sining; WANG Yuhui; CHENG Xiangjun; YANG Qianjun; SHAN Zhifeng; TANG Xilang

doi:10.12382/bgxb.2025.0905

您当前的位置：

首页 >

文章列表页 >

An Aero-Engine Quality Assessment Method Based on Particle Swarm Optimized Fermatean Fuzzy Structural Equation Model

更新时间：2026-01-21

- An Aero-Engine Quality Assessment Method Based on Particle Swarm Optimized Fermatean Fuzzy Structural Equation Model
- Acta Armamentarii (2026)
- 作者机构：
  
  1. 空军工程大学装备管理与无人机工程学院,陕西,西安,710051
  2. 无人飞行器技术全国重点实验室,陕西,西安,710051
  3. 95866部队,河北,保定,071000
- 作者简介：
- 基金信息：
- DOI：10.12382/bgxb.2025.0905
  CLC： E926
- Received：13 October 2025，
  
  Published Online：05 January 2026，
- 稿件说明：
移动端阅览
徐思宁, 王育辉, 程湘钧, 等. 基于粒子群优化Fermatean模糊结构方程模型的航空发动机质量评估方法[J/OL]. 兵工学报, 2026(2026-01-05). https://doi.org/10.12382/bgxb.2025.0905.

XÜ S N, WANG Y H, CHENG X J, et al. An aero-engine quality assessment method based on particle swarm optimized fermatean fuzzy structural equation model[J/OL]. Acta Armamentarii, 2026(2026-01-05). https://doi.org/10.12382/bgxb.2025.0905. (in Chinese)
徐思宁, 王育辉, 程湘钧, 等. 基于粒子群优化Fermatean模糊结构方程模型的航空发动机质量评估方法[J/OL]. 兵工学报, 2026(2026-01-05). https://doi.org/10.12382/bgxb.2025.0905. DOI：

XÜ S N, WANG Y H, CHENG X J, et al. An aero-engine quality assessment method based on particle swarm optimized fermatean fuzzy structural equation model[J/OL]. Acta Armamentarii, 2026(2026-01-05). https://doi.org/10.12382/bgxb.2025.0905. (in Chinese) DOI：

摘要

针对航空发动机质量评估中不确定性信息处理不足与模型易陷局部最优的问题，提出一种融合Fermatean模糊结构方程模型（Structural Equation Modeling

SEM）与粒子群优化（Particle Swarm Optimization，PSO）的评估方法。首先，基于输入-过程-输出-环境（Input-Process-Output-Environment

IPO

E）模型构建含16项指标的评估体系，其中含3项模糊指标；其次，采用Fermatean模糊集理论处理模糊指标，结合专家打分完成去模糊化转换，并在此基础上构建Fermatean模糊SEM；最后引入PSO算法优化模型参数，提升模型的拟合度与解释力。以56台涡扇发动机数据为样本，与传统结构方程模型、层次分析法-逼近理想解排序（Analytic Hierarchy Process-Technique for Order Preference by Similarity to an Ideal Solution

AHP-TOPSIS）法、BP神经网络三类典型方法进行对比验证。研究结果表明：所提方法近似误差均方根（Root Mean Square Error of Approximation

RMSEA）为0.032、比较拟合指数（Comparative Fit Index

CFI）为0.99、评估准确度

=0.89，维修优先级识别准确率90.9%，留一交叉验证变异系数0.074，均优于对比方法；该方法能够有效处理航空发动机质量评估中的模糊性与复杂性，为装备质量管控与维修决策提供科学依据。

Abstract

Toaddress the issues of insufficient uncertainty information processing and local optimum entrapment in aero-engine quality assessment

an evaluation method integratingFermateanfuzzy structural equation model with particle swarm optimization algorithm is proposed. First

an assessment system comprising 16 indicators

including 3 fuzzy indicators

is established based on the IPO&E model. Second

Fermateanfuzzy set theory is employed to process fuzzy indicators

and defuzzification is completed through expert scoring integration

upon which aFermateanfuzzy structural equation model is constructed. Finally

particle swarm optimization algorithm is introduced for global optimization of model parameters to enhance model fitness and explanatory power. Using data from 56 turbofan engines as samples

comparative validation is conducted against traditional structural equation model

Analytic Hierarchy Process-Technique for Order Preference by Similarity to an Ideal Solution

and BP neural network. The results indicate that the proposed method achieves aroot mean square error of approximation (RMSEA) of 0.032

a Comparative Fit Index (CFI) of 0.99

an assessment accuracy of 0.89

a maintenance priority identification accuracyof 90.9%

and a leave-one-out cross-validation coefficient of variation of 0.074

all outperforming the comparative methods. This method effectively addresses the fuzziness and complexity in aero-engine quality assessment

providing a scientific basis for equipment quality control and maintenance decision-making.

关键词

Keywords

references

WANG Y T, LIU F, XI F, et al. Data driven comprehensive performance evaluation of aeroengines: a network dynamic approach[J]. Engineering, 2025, 46: 292-305.

LEI B Y, SHEN N, JI D Y, et al. A comprehensive review of key technologies for enhancing the reliability of aero-engines[J]. IEEE Access, 2024, 12: 148315 - 148331.

金向明,高德平,赵艳云,等.基于可靠性增长预测模型的航空发动机可靠性评估[J].航空动力学报, 2010, 25(6):1335-1339.

JIN X M, GAO D P, ZHAO Y Y, et al. Reliability assessment of aero-engine based on reliability growth prediction model[J]. Journal of Aerospace Power, 2010, 25(6): 1335-1339. (in Chinese).

李志平,孙泽锜,朱星宇,等.基于喘振/失速的航空发动机系统安全评估方法[J].航空动力学报,2025,40(8):488-499.

LI Z P, SUN Z Q, ZHU X Y, et al. Safety assessment method for aero-engine systems based on surge/stall[J]. Journal of Aerospace Power, 40(8): 488-499. (in Chinese).

ZHU R K, LIANG Q C, ZHAN H Y. Analysis of aero-engine performance and selection based on fuzzy comprehensive evaluation[J]. Procedia Engineering, 2017, 174: 1202-1207.

MA N, YANG F, TAO L F, et al. State-of-Health assessment for aero-engine based on density-distance clustering and fuzzy Bayesian risk[J]. IEEE Access, 2021, 9: 9996-10011.

CHEN Q, SHENG H L, LI J C, et al. Model-based improved advanced adaptive performance recovery control method for a commercial turbofan engine[J]. IEEE Transactions on Aerospace and Electronic Systems, 2023, 59(6): 7440-7454.

齐小刚,刘学星,张博孜,等.基于结构方程模型的武器装备体系涌现性度量模型[J].兵工学报,2020,41(2):406-416.

QI X G, LIU X X, ZHANG B Z, et al. Emergence measurement model of armament systems based on SEM[J]. Acta Armamentarii, 2020, 41(2): 406-416. (in Chinese).

GUNDUZ M, ELSHERBENY H A. Construction contract administration performance assessment tool by using a fuzzy structural equation model[J]. Sustainability, 2020, 12(2): 523.

ASHRAF S, ATTAULLAH, NAEEM M, et al. Novel information measures for Fermatean fuzzy sets and their applications to pattern recognition and medical diagnosis[J]. Computational Intelligence and Neuroscience, 2023, 2023(1): 9273239.

郑波.基于粒子群优化算法的航空发动机故障诊断与性能参数预测研究[D]. 成都:电子科技大学,2018.

ZHENG B. Research on aero-engine fault diagnosis and performance parameter prediction based on particle swarm optimization algorithm[D]. Chengdu: University of Electronic Science and Technology of China, 2018. (in Chinese).

罗兴华,耿佳,李明,等.航空发动机机载模型迭代计算优化方法研究[J].系统仿真学报,2022,34(12):2649-2658.

LUO X H, GENG J, LI M, et al. Research on iterative calculation optimization method for aero-engine on-board model[J]. Journal of System Simulation, 2022, 34(12): 2649-2658. (in Chinese).

游亮,王莉莉,蔡忠义,等.基于改进WNN的作战飞机维修保障能力评估方法[J].火力与指挥控制,2024,49(10):74-81.

YOU L, WANG L L, CAI Z Y, et al. Maintenance support capability evaluation method for combat aircraft based on improved WNN[J]. Fire Control & Command Control, 2024, 49(10): 74-81 (in Chinese).

WANG Z P, WANG Y, WANG X Z, et al. A novel digital twin framework for aeroengine performance diagnosis[J]. Aerospace, 2023, 10(9): 789.

LI J Y, ZHAO G, ZHANG P F, et al. A digital twin-based on-site quality assessment method for aero-engine assembly[J]. Journal of Manufacturing Systems, 2023, 71: 565-580.

陶飞, 孙清超, 孙惠斌, 等．航空发动机数字孪生工程:内涵与关键技术[J]. 航空学报, 2024, 45(21):630283.

TAO F, SUN Q C, SUN H B, et al. Aero-engine digital twin engineering:connotation and key technologies[J]. Acta Aeronautica et Astronautica Sinica,2024,45(21):630283. (in Chinese).

吕卫民,孙晨峰,任立坤,等.一种基于TCN-LGBM的航空发动机气路故障诊断方法[J].兵工学报,2024,45(1):253-263.

LÜ W M, SUN C F, REN L K, et al. An aero-engine gas path fault diagnosis method based on TCN-LGBM[J]. Acta Armamentarii, 2024, 45(1): 253-263. (in Chinese).

Performance requirements for aircraft gas turbine engine starting systems: ARP1210D [S]. Warrendale, PA, US: SAE, 2020.

Environmental engineering considerations and laboratory tests: MIL-STD-810H [S]. Washington, DC, US: DoD, 2019.

JÖRESKOG K G. A general method for estimating a linear structural equation system[J]. ETS Research Bulletin Series, 1970, 1970(2): i-41.

沈丙振,缪建明,李晓菲,等.基于改进结构方程模型的陆军武器装备体系作战能力评估模型[J].兵工学报,2021,42(11):2503-2512.

SHEN B Z, MIAO J M, LI X F, et al . Combat capability evaluation model for army weapon equipment system of systems based on improved structural equation model[J]. Acta Armamentarii, 2021, 42(11): 2503-2512 (in Chinese).

Senapati T, Yager R R. Fermatean fuzzy sets[J]. Journal of ambient intelligence and humanized computing, 2020, 11(2): 663-674.

YANG T, LIU C H, CÔTÉ R R P, et al. Evaluating the barriers to industrial symbiosis using a group AHP-TOPSIS model[J]. Sustainability, 2022, 14(11): 6815.

DAI W, HU J C, CHENG Y H, et al. RVFLN-based online adaptive semi-supervised learning algorithm with application to product quality estimation of industrial processes [J]. Journal of Central South University, 2019, 26(12): 3338-3350.

Views

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Non-parametric Modelling and Muzzle Velocity Prediction of Multi-stage Induction Coilgun based on PSO-RNN Algorithm

A Trajectory Tracking Control Method Incorporating Behavior Primitive Optimization and Game Coordination

A Gas Path Fault Diagnosis Method for Aero-engine Based on TCN-LGBM Model

Weapon-target Assignment with an Improved Multi-objective Particle Swarm Optimization Algorithm

A Planning Method of Equipment Support Task Based on Priority Ordering and Particle Swarm Optimization Algorithm

Related Author

Zhanfeng ZHENG

Lin LEI

Siyuan JI

Taotao QIN

Huiyan CHEN

Hai’ou LIU

Haijie GUAN

Junjie SONG

Related Institution

National Key Laboratory of Transient Physics, Nanjing University of Science and Technology

Zaozhuang Power Supply Company, State Grid Shandong Electric Power Company

State Grid Electric Power Research Institute Co., Ltd.

School of Mechanical Engineering, Beijing Institute of Technology

Zhengzhou Research Institute, Beijing Institute of Technology

Postal code：100089
Tel：010-68963060/68962718 Fax：010-68963025 Email：bgxb@cos.org.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05059581号-4 京公网安备11010802024360号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：44020

⁰