Neural Network Signal Integration from Thermogas-Dynamic Parameter Sensors for Helicopters Turboshaft Engines at Flight Operation Conditions

Abstract

The article's main provisions are the development and application of a neural network method for helicopter turboshaft engine thermogas-dynamic parameter integrating signals. This allows you to effectively correct sensor data in real time, ensuring high accuracy and reliability of readings. A neural network has been developed that integrates closed loops for the helicopter turboshaft engine parameters, which are regulated based on the filtering method. This made achieving almost 100% (0.995 or 99.5%) accuracy possible and reduced the loss function to 0.005 (0.5%) after 280 training epochs. An algorithm has been developed for neural network training based on the errors in backpropagation for closed loops, integrating the helicopter turboshaft engine parameters regulated based on the filtering method. It combines increasing the validation set accuracy and controlling overfitting, considering error dynamics, which preserves the model generalization ability. The adaptive training rate improves adaptation to the data changes and training conditions, improving performance. It has been mathematically proven that the helicopter turboshaft engine parameters regulating neural network closed-loop integration using the filtering method, in comparison with traditional filters (median-recursive, recursive and median), significantly improve efficiency. Moreover, that enables reduction of the errors of the 1st and 2nd types: 2.11 times compared to the median-recursive filter, 2.89 times compared to the recursive filter, and 4.18 times compared to the median filter. The achieved results significantly increase the helicopter turboshaft engine sensor readings accuracy (up to 99.5%) and reliability, ensuring aircraft efficient and safe operations thanks to improved filtering methods and neural network data integration. These advances open up new prospects for the aviation industry, improving operational efficiency and overall helicopter flight safety through advanced data processing technologies.

Keywords: error; filtration; helicopter turboshaft engine; integration; neural network; sensor.

Figure 1

Diagram of closed loops for regulating helicopter turboshaft engine parameters (W_reg is regulator transfer function, W_FMU is fuel dispenser model transfer function, W_TE is helicopter turboshaft engine model transfer function): (a) gas–generator rotor rpm, (b) gas temperature in front of the compressor turbine, (c) free turbine rotor speed (author’s research, based on [44]).

Figure 2

Dynamic compensation diagram in closed loops for regulating helicopter turboshaft engine parameters: (a) gas–generator rotor rpm, (b) gas temperature in the compressor turbine front, (c) free turbine rotor speed (author’s research, based on [44,47,48]).

Figure 3

Adaptive device diagram for noise suppression with the helicopter turboshaft engine parameters signal components passage to the reference input (according to B. Widrow and S. Stearns) [56].

Figure 4

Dynamic compensation diagram in closed loops for regulating the helicopter turboshaft engine parameters with an adaptive noise suppression device with the component signals passage to the reference input: (a) gas–generator rotor rpm, (b) gas temperature in the compressor turbine front, (c) free rotor speed turbines (author’s research).

Figure 5

Diagram for integrating closed loops for regulating helicopter turboshaft engine parameters using the filtration method (author’s research).

Figure 6

The developed neural network architecture, which implements the closed-loop integration for regulating the helicopter turboshaft engines’ parameters using the filtering method (author’s research).

Figure 7

Derivative ReLU functions diagrams: (a) traditional ReLU max(0, x); (b) proposed Smooth ReLU with adjustment (22) (author’s research).

Figure 8

Cluster analysis results: (a) training sample of the parameter n_TC, (b) test sample of the parameter n_TC, (c) training sample of the parameter $T_G^{*}$, (d) test sample of the parameter $T_G^{*}$, (e) training sample of the parameter n_FT, (f) test sample of the n_FT parameter (author’s research).

Figure 9

The influence diagram for the number of epochs passed on the resulting error (author’s research). (a) Training for the 320 epochs (b) Training from 320 to 1000 epochs.

Figure 10

Accuracy metric diagram (author’s research).

Figure 11

Loss function diagram (author’s research).

Figure 12

Initial diagram of the n_TC gas–generator rotor rpm signal (author’s research).

Figure 13

Resulting diagram of the n_TC gas–generator rotor rpm signal (author’s research).

Figure 14

The n_TC gas–generator rotor rpm signal spectrum diagram: (a) Original signal (b) Filtered signal (author’s research).

Figure 15

The n_TC gas–generator rotor rpm signal repetition period diagram: (a) Original signal (b) Filtered signal (author’s research).

Figure 16

The n_TC gas–generator rotor rpm signal signal-to-noise ratio diagram: (a) Original signal (b) Filtered signal (author’s research).

Figure 17

Signal histogram for the n_TC gas–generator rotor rpm estimates: (a) Original signal (b) Filtered signal (author’s research).

Figure 18

The spectrum histogram for the n_TC gas–generator rotor rpm signal estimates: (a) Original signal (b) Filtered signal (author’s research).

Figure 19

The sequence histogram for the gas–generator rotor rpm signal n_TC estimates: (a) Original signal (b) Filtered signal (author’s research).

Figure 20

The n_TC gas–generator rotor rpm signal signal/noise estimates histogram: (a) Original signal (b) Filtered signal (author’s research).

Figure 21

Noise dispersion diagram of the n_TC gas–generator rotor rpm signal (author’s research).