基于LSTM神经网络的燃气轮机排温预测方法

针对燃气轮机气路性能退化的周期性与非线性特点,提出一种基于长短期记忆(Long-Short Term Memory,LSTM)神经网络的燃气轮机排气温度趋势预测方法.利用标准化与归一化数据预处理方法提取排气温度数据中的退化特征,减小了环境和工况变化对退化特征的影响;通过滑窗法提取一定长度的历史数据,增强LSTM模型的泛...     

基于时间序列模型的燃气轮机气路性能退化预测

针对燃气轮机实际运行过程中压气机积垢导致的性能退化与定期清洗维护问题,提出一种基于时间序列模型的燃气轮机气路性能退化预测方法。并在燃气轮机建模仿真基础上,以燃气轮机排气温度为例,对时间序列模型在燃气轮机气路性能退化预测中的应用进行了有效性评估。研究结果表明,使用该方法可将燃气轮机气路性能参数随压气机积垢程度的变化转化为时间序列趋势预测问题,可以有效地实现燃气轮机气路性能退化趋势预测,进而实现压气机的视情清洗维护。该方法为燃气轮机在线健康状态监测与诊断提供了一种思路,具有一定的工程应用价值。     

基于滤波阵列的燃气轮机气路故障诊断研究

针对燃气轮机故障诊断过程中诊断精度不足,卡尔曼滤波易出现“弥散”现象的问题,提出了一种基于滤波阵列的燃气轮机气路故障诊断方法。该方法首先构建了一组基于健康参数调度的平衡流形展开模型阵列,然后结合平方根容积卡尔曼滤波对气路部件健康参数进行了实时估计,最后通过隔离因子实现了对故障部件的检测与隔离。仿真表明：该方法有效解决了卡尔曼滤波在故障诊断过程中出现“弥散”现象的问题,针对燃气轮机气路部件突变故障,能够有效实现故障的检测、隔离与估计。     

燃气轮机预测及诊断方法研究进展

针对燃气轮机气路性能退化趋势预测和部件剩余寿命预测方法的最新研究进展进行了综述。随着故障预测精度和可靠性要求的提高,传统的故障预测方法已经不能满足燃气轮机故障预测需求。因此需要在传统预测方法及模型的基础上进行改进,以适应不同环境下燃气轮机故障预测及诊断的需求。     

基于Markov决策过程的舰船燃气轮机运行与维护成本建模

针对燃气轮机性能退化特性和维护保养策略分析,考虑机组的随机故障失效和退化失效,运用Mark·ov决策过程方法,提出了基于状态的燃气轮机运行与维护成本模型.通过算例分析,验证了模型的可行性,并比较了三种不同保养策略的可用度和经济性.     

高温材料在发电燃气轮机中的应用和发展

介绍了当前世界四大燃气轮机制造商热端部件使用的各种高温材料和我国燃气轮机用高温材料的现状,通过分析热部件工作环境对材料性能的要求,提出了热部件材料选择的原则。结合国内外燃气轮机用高温合金的发展和应用现状,提出了我国重型燃气轮机高温材料发展的目标和方向。     

一种基于多运行工况点的强鲁棒性燃气轮机非线性气路诊断方法

通常准确的气路测量信息对于获取准确的衰退特征从而实现准确的燃气轮机气路诊断至关重要。由于气路传感器同部件一样,其性能也可能会衰退甚至发生故障,而产生一定的测量偏差并引起误导性的诊断结果。为解决诊断准确性高度依赖气路传感器可靠性的问题,本文提出了一种基于高斯数据调和原理与多运行工况点相结合的非线性气路诊断方法。该方法能有效地降低部件健康参数对传感器测量偏差的敏感性,适用于存在测量偏差的离线气路诊断情况。     

基于改进型强跟踪卡尔曼滤波的燃气轮机组气路故障诊断研究

针对燃气轮机组气路故障诊断易受时变噪声干扰以及突变故障诊断精度不高等问题,本文提出一种基于改进型强跟踪卡尔曼滤波的燃气轮机组气路故障诊断方法。该算法通过引入气路部件先验知识,合理分配各通道的调节作用,从而提高了气路故障诊断的精度以及动态响应速度。以PG9171E型燃气轮机为研究对象,分别利用EKF(扩展卡尔曼滤波)、STF(强跟踪滤波)以及ISTF(改进型强跟踪滤波)对常见气路故障进行诊断,结果表明ISTF算法同时兼具良好的响应速度以及较高的精度。     

燃气轮机异常检测技术研究进展

考虑燃气轮机结构组成复杂、旋转部件服役环境恶劣以及多类型故障容易耦合等特点,如何提高系统/设备的异常检测性能是实现燃气轮机状态监测与健康维护的关键。本文概述了燃气轮机异常检测技术的发展历程,分别从气路性能参数、振动参数、油液分析/静电监测、多源信息融合等方面综述了燃气轮机异常检测方法的国内外研究进展。在此基础上,针对目前研究存在的问题与不足,从有效提高建模精度、解决气路分析方程欠定问题、丰富异常特征数据库、增加数据源信息、强化多源信息融合模式和深度挖掘隐含信息等多个角度展望了燃气轮机异常检测技术的发展方向。     

燃气轮机异常检测技术的研究进展

考虑燃气轮机结构组成复杂、旋转部件服役环境恶劣以及多类型故障容易耦合等特点,如何提高系统/设备的异常检测性能是实现燃气轮机状态监测与健康维护的关键。本文概述了燃气轮机异常检测技术的发展历程,分别从气路性能参数、振动参数、油液分析/静电监测、多源信息融合等方面综述了燃气轮机异常检测方法的国内外研究进展。在此基础上,针对目前研究存在的问题与不足,从有效提高建模精度、解决气路分析方程欠定问题、丰富异常特征数据库、增加数据源信息、强化多源信息融合模式、深度挖掘隐含信息等多个角度分析了燃气轮机异常检测技术的发展方向。     

Nonlinear design-point performance adaptation approaches and their comparisons for gas turbine applications

Accurate performance simulation and understanding of gas turbine engines is very useful for gas turbine manufacturers and users alike and such a simulation normally starts from its design point. When some of the engine component parameters for an existing engine are not available, they must be estimated in order that the performance analysis can be started. Therefore, the simulated design point performance of an engine may be slightly different from its actual performance. In this paper, two nonlinear gas turbine design-point performance adaptation approaches have been presented to best estimate the unknown component parameters and match available design point engine performance, one using a nonlinear matrix inverse adaptation method and the other using a Genetic Algorithm-based adaptation approach. The advantages and disadvantages of the two adaptation methods have been compared with each other. In the approaches, the component parameters may be compressor pressure ratios and efficiencies, turbine entry temperature, turbine efficiencies, engine mass flow rate, cooling flows, and bypass ratio, etc. The engine performance parameters may be thrust and SFC for aero engines, shaft power, and thermal efficiency for industrial engines, gas path pressures, temperatures, etc. To select the most appropriate to-be-adapted component parameters, a sensitivity bar chart is used to analyze the sensitivity of all potential component parameters against the engine performance parameters. The two adaptation approaches have been applied to a model gas turbine engine. The application shows that the sensitivity bar chart is very useful in the selection of the to-be-adapted component parameters, and both adaptation approaches are able to produce good quality engine models at design point. The comparison of the two adaptation methods shows that the nonlinear matrix inverse method is faster and more accurate, while the genetic algorithm-based adaptation method is more robust but slower. Theoretically, both adaptation methods can be extended to other gas turbine engine performance modelling applications.     

Nonlinear design-point performance adaptation approaches and their comparisons for gas turbine applications

Accurate performance simulation and understanding of gas turbine engines is very useful for gas turbine manufacturers and users alike and such a simulation normally starts from its design point. When some of the engine component parameters for an existing engine are not available, they must be estimated in order that the performance analysis can be started. Therefore, the simulated design point performance of an engine may be slightly different from its actual performance. In this paper, two nonlinear gas turbine design-point performance adaptation approaches have been presented to best estimate the unknown component parameters and match available design point engine performance, one using a nonlinear matrix inverse adaptation method and the other using a Genetic Algorithm-based adaptation approach. The advantages and disadvantages of the two adaptation methods have been compared with each other. In the approaches, the component parameters may be compressor pressure ratios and efficiencies, turbine entry temperature, turbine efficiencies, engine mass flow rate, cooling flows, and by-pass ratio, etc. The engine performance parameters may be thrust and SFC for aero engines, shaft power, and thermal efficiency for industrial engines, gas path pressures, temperatures, etc. To select the most appropriate to-be-adapted component parameters, a sensitivity bar chart is used to analyze the sensitivity of all potential component parameters against the engine performance parameters. The two adaptation approaches have been applied to a model gas turbine engine. The application shows that the sensitivity bar chart is very useful in the selection of the to-be-adapted component parameters, and both adaptation approaches are able to produce good quality engine models at design point. The comparison of the two adaptation methods shows that the nonlinear matrix inverse method is faster and more accurate, while the genetic algorithm-based adaptation method is more robust but slower. Theoretically, both adaptation methods can be extended to other gas turbine engine performance modelling applications.     

Energetic and exergetic performance analyses of a combined heat and power plant with absorption inlet cooling and evaporative aftercooling

In this paper, exergy method is applied to analyze the gas turbine cycle cogeneration with inlet air cooling and evaporative aftercooling of the compressor discharge. The exergy destruction rate in each component of cogeneration is evaluated in detail. The effects of some main parameters on the exergy destruction and exergy efficiency of the cycle are investigated. The most significant exergy destruction rates in the cycle are in combustion chamber, heat recovery steam generator and regenerative heat exchanger. The overall pressure ratio and turbine inlet temperature have significant effect on exergy destruction in most of the components of cogeneration. The results obtained from the analysis show that inlet air cooling along with evaporative aftercooling has an obvious increase in the energy and exergy efficiency compared to the basic gas turbine cycle cogeneration. It is further shown that the first-law efficiency, power to heat ratio and exergy efficiency of the cogeneration cycle significantly vary with the change in overall pressure ratio and turbine inlet temperature but the change in process heat pressure shows small variation in these parameters.     

基于正交试验的低速机增压器涡轮排气壳性能优化研究

为提升船用低速机涡轮增压器性能,对增压器涡轮排气壳底部流道结构进行参数化,设计并开展了以效率为优化目标的四因素三水平正交试验优化设计和增压器整机性能试验。首先,采用CFD数值模拟方法对不同参数组合的涡轮气动性能进行了计算,然后对涡轮排气壳底部流道结构参数开展了灵敏度分析,同时针对不同参数组结构开展了内部流场对比分析,明确结构因素对流动的影响机理;在此基础上对优化后方案开展了涡轮特性分析,最后在低速双燃料机平台上开展增压器整机试验验证。分析研究表明：在涡轮进气壳、喷嘴环和涡轮叶片等通流部件结构不变的前提下,涡轮排气壳排气方向轴向长度对涡轮整级效率的影响最大,优化后效率明显提升,设计点总压损失系数降低0.3874,静压恢复系数提升0.537,总静效率提升1.85%,其余工况总静效率最大提升2.4%。试验结果表明：优化后涡轮增压器整机效率在主机燃油模式和燃气模式下的全工况范围内效率均有提升,最大提升幅度分别达到1.4%和2.1%,涡轮性能和增压器整机性能改善明显。     

GA-based design-point performance adaptation and its comparison with ICM-based approach

Accurate performance simulation and estimation of gas turbine engines is very useful for gas turbine manufacturers and users alike and such a simulation normally starts from its design-point. When some of the engine component parameters for an existing engine are not available, they must be estimated in order that the performance analysis can be started. Therefore, the simulated design-point performance of an engine may be slightly different from its actual performance. In this paper, a Genetic Algorithm (GA) based non-linear gas turbine design-point performance adaptation approach has been presented to best estimate the unknown component parameters and match available design-point engine performance. In the approach, the component parameters may be compressor pressure ratios and efficiencies, turbine entry temperature, turbine efficiencies, engine mass flow rate, cooling flows, by-pass ratio, etc. The engine performance parameters may be thrust and SFC for aero engines, shaft power and thermal efficiency for industrial engines, gas path pressures and temperatures, etc. To select the most appropriate to-be-adapted component parameters, a sensitivity analysis is used to analyze the sensitivity of all potential component parameters against the engine performance parameters. The adaptation approach has been applied to an industrial gas turbine engine to test the effectiveness of the approach. The approach has also been compared with a non-linear Influence Coefficient Matrix (ICM) based adaptation method and the advantages and disadvantages of the two adaptation methods have been compared with each other. The application shows that the sensitivity analysis is very useful in the selection of the to-be-adapted component parameters and the GA-based adaptation approach is able to produce good quality engine models at design-point. Compared with the non-linear ICM-based method, the GA-based performance adaptation method is more robust but slower in computation and relatively less accurate.     

Energy and exergy analyses of an integrated SOFC and coal gasification system

This paper examines an integrated gasification and solid oxide fuel cell (SOFC) system with a gas turbine and steam cycle that uses heat recovery of the gas turbine exhaust. Energy and exergy analyses are performed with two different types of coal. For the two different cases, the energy efficiency of the overall system is 38.1% and 36.7%, while the exergy efficiency is 27% and 23.2%, respectively. The effects of changing the reference temperature on the exergy destruction and exergy efficiency of different components are also reported. A parametric study on the effects of changing the pressure ratio on the component performance is presented.     

Optimal design of the regenerative gas turbine engine with isothermal heat addition

A regenerative gas turbine engine, with isothermal heat addition, working under the frame of a Brayton cycle has been analyzed. With the purpose of having a more efficient small-sized gas turbine engine, the optimization has been carried out numerically using the maximum power (MP) and maximum power density (MPD) method. The effects of internal irreversibilities have been considered in terms of the isentropic efficiencies of the turbine and compressor and of the regenerator efficiency. The results summarized by figures show that the regenerative gas turbine engine, with isothermal heat addition, designed according to the maximum power density condition gives the best performance and exhibits highest cycle efficiencies.     

展弦比对船用燃气轮机低压压气机跨音级性能影响研究

为了揭示展弦比对压气机跨声速级气动性能的影响机理,进一步提高舰船燃气轮机低压压气机的气动性能,采用数值模拟方法研究了展弦比对某船用燃气轮机低压压气机跨声速级气动性能的影响.结果表明:展弦比对压气机性能的影响受到扭曲规律和反动度等参数选择的影响,对于不同的扭曲方式和反动度分别存在着效率最优展弦比和喘振裕度最优展弦比,且在...     

Thermodynamic analysis of an integrated power generation system driven by solid oxide fuel cell

A new integrated power generation system driven by the solid oxide fuel cell (SOFC) is proposed to improve the conversion efficiency of conventional energy by using a Kalina cycle to recover the waste heat of exhaust from the SOFC-GT. The system using methane as main fuel consists an internal reforming SOFC, an after-burner, a gas turbine, preheaters, compressors and a Kalina cycle. The proposed system is simulated based on the developed mathematical models, and the overall system performance has been evaluated by the first and second law of thermodynamics. Exergy analysis is conducted to indicate the thermodynamic losses in each components. A parametric analysis is also carried out to examine the effects of some key thermodynamic parameters on the system performance. Results indicate that as compressor pressure ratio increases, SOFC electrical efficiency increases and there is an optimal compressor pressure ratio to reach the maximum overall electrical efficiency and exergy efficiency. It is also found that SOFC electrical efficiency, overall electrical efficiency and exergy efficiency can be improved by increasing air flow rate. Also, the largest exergy destruction occurs in the SOFC followed by the after-burner, the waste heat boiler, the gas turbine. The compressor pressure ratio and air flow rate have significant effects on the exergy destruction in some main components of system.     

Thermal performance analysis of gas turbine engines based on different compressor configurations

In this study, the performance of several gas turbine engines has been investigated using computational modelling based on the actual manufacturer's data. Further, the study focuses on evaluating the impact of varying the configuration of the compressor on overall engine performance based on the first and second laws of thermodynamics. The results confirm that the main source of irreversibilities occurs in the combustion chamber in all cases. The exergetic efficiency of the gas turbine engine significantly varies with compressor configurations, type of compressors, load variation, climatic condition, and isentropic efficiency. The engine capacity and high‐pressure turbine inlet temperature govern the gas turbine performance, and higher values are more favourable. The gas turbine exergetic efficiency drops off when the power setting adjusted at part‐load and at high ambient temperature. The most optimal gas turbine performance is located at the single axial compressor case, followed by the axial‐centrifugal compressor and then the centrifugal–centrifugal compressor.