Correlation of Performance, Exhaust Gas Temperature and Speed of a Spark Ignition Engine Using Kiva4

The objective of this study was to investigate performance characteristics of a spark ignition engine, particularly, the correlation between performance, exhaust gas temperature and speed, using Kiva4. Test data to validate kiva4 simulation results were conducted on a 3-cylinder, four-stroke Volkswagen (VW) Polo 6 TSI 1.2 gasoline engine. Three different tests were, therefore, carried out. In one set, variations in exhaust gas temperature were studied by varying the engine load, while keeping the engine speed constant. In another test, exhaust gas temperature variations were studied by keeping the engine at idling whilst varying the speeds. A third test involved studying variations in exhaust gas temperature under a constant load with variable engine speeds. To study variations in exhaust gas temperatures under test conditions, a basic grid/mesh generator, K3PREP, was employed to write an itape17 file comprising of a 45° asymmetrical mesh. This was based on the symmetry of the combustion chamber of the engine used in carrying out experimental tests. Simulations were therefore performed based on the input parameters established in the conducted tests. Simulations with the kiva4 code showed a significant predictability of the performance characteristics of the engine. This was evident in the appreciable agreement obtained in the simulation results when compared with the test data, under the considered test conditions. A percentage error, between experimental results and results from simulations with the kiva4 code of only between 2% to 3% was observed.

A step parameters prediction model based on transfer process neural network for exhaust gas temperature estimation after washing aero-engines

The prediction of Exhaust Gas Temperature Margin(EGTM)after washing aeroengines can provide a theoretical basis for airlines not only to evaluate the energy-saving effect and emission reduction,but also to formulate reasonable maintenance plans.However,the EGTM encounters step changes after washing aeroengines,while,in the traditional models,a persistence tendency exists between the prediction results and the previous data,resulting in low accuracy in prediction.In order to solve the problem,this paper develops a step parameters prediction model based on Transfer Process Neural Networks(TPNN).Especially,“step parameters”represent the parameters that can reflect EGTM step changes.They are analyzed in this study,and thus the model concentrates on the prediction of step changes rather than the extension of data trends.Transfer learning is used to handle the problem that few cleaning records result in few step changes for model learning.In comparison with Long Short-Term Memory(LSTM)and Kernel Extreme Learning Machine(KELM)models,the effectiveness of the proposed method is verified on CFM56-5B engine data.

Remaining Useful Life Prediction for Aero-Engines Combining Sate Space Model and KF Algorithm

The key to failure prevention for aero-engine lies in performance prediction and the exhaust gas temperature margin(EGTM)is used as the most important degradation parameter to obtain the operating performance of the aero-engine.Because of the complex environment interference,EGTM always has strong randomness,and the state space based degradation model can identify the noisy observation from the true degradation state,which is more close to the actual situations.Therefore,a state space model based on EGTM is established to describe the degradation path and predict the remaining useful life(RUL).As one of the most effective methods for both linear state estimation and parameter estimation,Kalman filter(KF)is applied.Firstly,with EGTM degradation data,state space model approach is used to set up a state space model for aero-engine.Secondly,RUL of aero-engine is analyzed,and expected RUL and distribution of RUL are determined.Finally,the sate space model and KF algorithm are applied to an example of CFM-56aero-engine.The expected RUL is predicted,and corresponding probability density distribution(PDF)and cumulative distribution function(CDF)are given.The result indicates that the accuracy of RUL prediction reaches 7.76%ahead 580 flight cycles(FC),which is more accurate than linear regression,and therefore shows the validity and rationality of the proposed method.