基于模糊理论和BN的燃气轮机健康状态评估方法

针对小样本条件下燃气轮机的健康状态评估问题，提出了基于模糊理论和近等式约束的贝叶斯网络的燃气轮机健康状态评估方法。用模糊理论整合专家先验知识，以近等式约束的形式将其融合到贝叶斯网络参数学习中，再通过贝叶斯网络模型得到燃气轮机健康状态。以某型燃气轮机为例进行仿真，结果表明，该型燃气轮机处于正常状态，与实际运行状态相符，验证了方法的可行性，具有一定的工程应用价值。

A Gas Turbine Health Evaluation Method Based on Fuzzy Theory and Bayesian Network

To evaluate the health status of gas turbine under small sample conditions, this paper proposes a Bayesian network health status evaluation method based on fuzzy theory and near-equality constraints. The expert priori knowledge was integrated with the fuzzy theory, which was fused into the Bayesian network parameter learning in the form of nearly equality constraint, and then the gas turbine health state was obtained through the Bayesian network model. Taking a certain type of gas turbine as an example, the simulation results show that this type of gas turbine is in normal state and consistent with the actual operation state, which verifies the feasibility of the method and has certain engineering application value.