Uneingeschränkter Zugang

Research on the fault diagnosis method of offshore oil and gas field equipment combined with deep reinforcement learning

 und   
26. März 2025

Zitieren
COVER HERUNTERLADEN

Figure 1.

Multisource heterogeneous data model
Multisource heterogeneous data model

Figure 2.

Fault diagnosis process based on DDPG-SDAE
Fault diagnosis process based on DDPG-SDAE

Figure 3.

Nose-free pulse signal
Nose-free pulse signal

Figure 4.

The noise extraction effect of different algorithms
The noise extraction effect of different algorithms

Figure 5.

MAE of various algorithms under SNR
MAE of various algorithms under SNR

Figure 6.

Simulation signal time domain waveform
Simulation signal time domain waveform

Figure 7.

The upper and lower envelope of different algorithms
The upper and lower envelope of different algorithms

Figure 8.

Fault diagnosis of different models
Fault diagnosis of different models

Figure 9.

Fault diagnosis migration results of different models
Fault diagnosis migration results of different models

Different migration task descriptions

Describe Source domain Target domain Migration task
The single-transmitter migration task Sensor 1 Sensor 3 1→3
Sensor 2 Sensor 3 2→3
Sensor 1 Sensor 2 1→2
Sensor 3 Sensor 2 3→2
Sensor 2 Sensor 1 2→1
Sensor 3 Sensor 1 3→1
Multi-sensor migration task Sensor 1+2 Sensor 3 1+2→3
Sensor 1+3 Sensor 2 1+3→2
Sensor 2+3 Sensor 1 2+3→1
Sprache:
Englisch
Zeitrahmen der Veröffentlichung:
1 Hefte pro Jahr
Fachgebiete der Zeitschrift:
Biologie, Biologie, andere, Mathematik, Angewandte Mathematik, Mathematik, Allgemeines, Physik, Physik, andere