“…As the related research of this method has been relatively mature, please refer to the literature. [16][17][18][19] Principle of PSC variables are treated as optimization variables to maximize the performance of the engine. In the optimization process, the safe operation of the engine must be ensured, so the constraint conditions of the engine need to be considered, which is described as follows.…”
Section: Adaptive Modulementioning
confidence: 99%
“…As the related research of this method has been relatively mature, please refer to the literature. 16–19 Figure 6.Structure of the adaptive module.…”
Section: On-board Modelmentioning
confidence: 99%
“…The simplex algorithm is a general optimization algorithm, and the related research has been relatively mature. For more details, Refs 16, 17. can be referred.…”
Section: Principle Of Pscmentioning
confidence: 99%
“…9,10 At present, most scholars use the piecewise linear model (PLM) or component level model (CLM) as the on-board model for PSC. [11][12][13][14][15][16][17] The PLM has good realtime performance. However, when PLM is applied to the large flight envelope, it needs to store a large number of interpolation data tables, which makes it difficult to ensure the accuracy of the model.…”
In order to improve the real-time performance of performance seeking control (PSC), a neural network-propulsion system matrix(NN-PSM) on-board model is proposed and applied to PSC. First, based on NN-PSM, a large-envelope, multi-variable on-board adaptive model is established. The PSM is extracted through a small deviation linearization method. The neural network is used to map the relationship between the flight conditions, engine control parameters, and the engine performance parameters, and designed a Kalman filter to estimate engine health parameters in real-time. Then, four PSC mode of maximum thrust, minimum fuel consumption, minimum high-pressure turbine inlet temperature, and minimum infrared radiation intensity are designed using LP optimization algorithm as optimize algorithm. Finally, the simulation results show that NN-PSM has much higher precision than Compact Propulsion System Model (CPSM). The PSC simulations show that compared with the PSC based on the conventional CPSM, the proposed method has much better real-time performance and get better engine performance, such as more thrust, less specific fuel consumption, and less turbine inlet temperature.
“…As the related research of this method has been relatively mature, please refer to the literature. [16][17][18][19] Principle of PSC variables are treated as optimization variables to maximize the performance of the engine. In the optimization process, the safe operation of the engine must be ensured, so the constraint conditions of the engine need to be considered, which is described as follows.…”
Section: Adaptive Modulementioning
confidence: 99%
“…As the related research of this method has been relatively mature, please refer to the literature. 16–19 Figure 6.Structure of the adaptive module.…”
Section: On-board Modelmentioning
confidence: 99%
“…The simplex algorithm is a general optimization algorithm, and the related research has been relatively mature. For more details, Refs 16, 17. can be referred.…”
Section: Principle Of Pscmentioning
confidence: 99%
“…9,10 At present, most scholars use the piecewise linear model (PLM) or component level model (CLM) as the on-board model for PSC. [11][12][13][14][15][16][17] The PLM has good realtime performance. However, when PLM is applied to the large flight envelope, it needs to store a large number of interpolation data tables, which makes it difficult to ensure the accuracy of the model.…”
In order to improve the real-time performance of performance seeking control (PSC), a neural network-propulsion system matrix(NN-PSM) on-board model is proposed and applied to PSC. First, based on NN-PSM, a large-envelope, multi-variable on-board adaptive model is established. The PSM is extracted through a small deviation linearization method. The neural network is used to map the relationship between the flight conditions, engine control parameters, and the engine performance parameters, and designed a Kalman filter to estimate engine health parameters in real-time. Then, four PSC mode of maximum thrust, minimum fuel consumption, minimum high-pressure turbine inlet temperature, and minimum infrared radiation intensity are designed using LP optimization algorithm as optimize algorithm. Finally, the simulation results show that NN-PSM has much higher precision than Compact Propulsion System Model (CPSM). The PSC simulations show that compared with the PSC based on the conventional CPSM, the proposed method has much better real-time performance and get better engine performance, such as more thrust, less specific fuel consumption, and less turbine inlet temperature.
“…Most data-driven prediction methods are implemented based on neural networks, which include Artificial Neural Networks(ANNs), 10 , 11 Support Vector Machine(SVM), 12–14 Random Forest (RF), 15 , 16 Extreme Learning Machine(ELM), 17 , 18 etc. In recent years, most scholars have used artificial features to extract features and combined them with neural networks to achieve bearing RUL prediction.…”
The prediction of the remaining useful life (RUL) of rolling bearings is an important means to ensure the rotating machinery's safe operation. At present, most of the proposed methods use direct prediction based on bearing vibration signals, which not only have low prediction accuracy but also time-consuming. This paper proposes a staged prediction method, and the regularized learning machine (RELM) based on the proposed sensitive degradation feature is applied to predict RUL of the bearing with high accuracy and speed. Firstly, the relative root mean square value (RRMS) is used to divide the degradation stages of rolling bearings. Secondly, the RRMS indicator is used for multi-step time series prediction in the normal phase of the bearing. Thirdly, in the bearing's degradation stage, the Pearson Correlation Coefficient (PCC) Combined Entropy Weight Method (EWM) feature selection criterion is proposed to predict the RUL of the rolling bearing. Finally, the sensitive degradation feature of the bearing vibration signals is input into RELM to predict the RUL. The bearing data sets of PHM Challenging 2012 are used to verify the effectiveness of the proposed method. Three comparative experiments have been verified to prove the accuracy and rapidity of the proposed method in time series forecasting.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
