基于SOM神经网络的燃气轮机状态评估方法
A State Assessment Method for Gas Turbines Based on SOM Neural Network
针对传统状态评估主观成分过多或评估模型不清晰问题，提出了一种基于自组织映射（SOM）神经网络的方法。建立SOM模型与健康度模型，通过SOM网络对燃气轮机退化数据进行训练，应用聚类健康度模型和修正健康度模型最终完成对燃气轮机退化数据集的健康度评估。通过退化数据的退化因子划分退化程度，根据退化程度验证评估模型精度。基于SOM网络的燃气轮机健康度评估方法具有很高的应用潜力，可以为燃气轮机的安全运行和维护提供有力的支持，同时也为其他类似问题的解决提供了参考。未来的研究可以进一步探索和优化该方法，以提高其性能和可靠性。
To solve the problem of too many subjective components or unclear assessment model in traditional state assessment, a method based on Self-organizing map (SOM) neural network is proposed. Establish SOM model and health degree model, train gas turbine degradation data through SOM network, apply cluster health degree model and modified health degree model to finally complete the health degree evaluation of gas turbine degradation dataset. Divide the degree of degradation through the degradation factors of the degradation data, and verify the accuracy of the evaluation model based on the degree of degradation. The health assessment method for gas turbines based on SOM network has high application potential, which can provide strong support for the safe operation and maintenance of gas turbines, and also provide reference for solving other similar problems. Future research can further explore and optimize this method to improve its performance and reliability.
屈东生;曹云鹏;李淑英;
哈尔滨工程大学 动力与能源工程学院,哈尔滨150006;哈尔滨工程大学 动力与能源工程学院,哈尔滨150006;哈尔滨工程大学 动力与能源工程学院,哈尔滨150006;
TK478
self-organizing map gas turbine health evaluation clustering health modified health
1-7 / 7
评论