共查询到18条相似文献,搜索用时 140 毫秒
1.
2.
基于SIMULNK的单轴重型燃气轮机建模与仿真研究 总被引:1,自引:0,他引:1
通过面向对象的模块化建模方法,在MATLAB/SIMULINK软件中建立了燃气轮机部件模块库,并进行了燃气轮机系统变工况仿真研究。为了提高仿真精度,本文采用变比热容的计算方法,并考虑气体组分的变化对整个系统模型的影响,建立了一种考虑容积惯性和转动惯性的、非线性的单轴重型燃气轮机实时动态仿真模型。仿真结果表明,该模型设计合理、结构清晰,可应用于重型燃气轮机控制系统的研制和测试,并具有很好的通用性和扩展性。 相似文献
3.
4.
新型燃气轮机热参数故障诊断数学模型的研究和应用 总被引:1,自引:0,他引:1
介绍了一种新型燃气轮机热参数故障模型。与以往的热参数故障模型有所不同的是该模型对由故障导致的特性线移动所引起的性能变化及由部件匹配引起的性能变化进行了分离,提高了模型的准确性和精度。此外,本文推导出的故障矩阵可以用来解决由于测量参数的不足而导致的无法求解性能参数的问题。 相似文献
5.
6.
7.
8.
基于核主元分析的传感器故障检测 总被引:2,自引:0,他引:2
提出了一种新的火电机组传感器故障检测系统.传统的主元分析方法在非线性系统中不能很好的发挥作用.采用核主元分析方法提取系统的非线性冗余信息,建立核主元模型.并在输入空间对数据进行重构,通过最小化均方预测误差来选择合适的核函数和参数,对模型的建立过程进行指导.在线检测时,利用核主元模型,将实时数据投影到核主元空间,能够有效的去除系统的噪声.对重构残差采用序贯概率比检验方法进行检验,不仅能够诊断出传感器的漂移等明显故障,而且能够及时发现设备或者系统的早期故障.通过某电厂125MW机组真空系统的多传感器故障检测仿真实例,验证了该方法的有效性. 相似文献
9.
10.
11.
The present study investigates how sudden changes in fuel moisture affected the combustion characteristics of the fuel bed in a 4-MW reciprocating-grate furnace. The moisture content of the fuel fed to the furnace was monitored online using a near-infrared spectroscopy device, and the water vapor concentration in the flue gas was measured continuously. To obtain experimental data on fuel-bed conditions, the temperature and gas composition in the bed were measured using a probe. A simplified drying model was developed using the measured gas composition values as inputs. The model was then used to estimate the drying rate and to simulate the extent of the drying zone along the grate. Measurements indicated that a change in the moisture content of the fuel fed to the furnace was detected as a change in water vapor concentration in the flue gas with a delay of about 2 h. The model predicted that a portion of wet fuel would need about 2 h to become dry, in line with the measured time delay of the water vapor concentration change in the flue gas. Overall, there was good alignment between the measured and simulated results, supporting the validity of the model and the assumed mechanisms. 相似文献
12.
针对目前燃气轮机基于数据驱动的故障诊断技术诊断精度有待提升的问题,建立某型号燃气轮机的热力学模型并植入故障特征构造训练样本,在此基础上训练一种基于注意力机制的卷积神经网络与长短期记忆网络结合的神经网络模型。卷积层和注意力机制模块提取燃气轮机多维度的故障特征,长短期网络层进行时序动态故障参数处理。研究表明:相比于典型卷积神经网络,这种神经网络模型不仅能够识别多种故障的动态特征,对于各类故障的诊断能力均可达到93%以上,且加入注意力机制模块后对于不同的故障类型诊断准确率最高提升约3%。 相似文献
13.
14.
A phenomenological model of downdraft gasification under steady state operation is developed based on previously published values for the reaction kinetics in the reduction zone. The model predicts a product gas with a composition similar to that found experimentally, although the model over-predicts the methane concentration. The accuracy of the model is limited by the availability of data on the initial conditions at the top of the reduction zone. 相似文献
15.
16.
17.