A High-Dimensional and Small-Sample Submersible Fault Detection Method Based on Feature Selection and Data Augmentation

Abstract

The fault detection of manned submersibles plays a very important role in protecting the safety of submersible equipment and personnel. However, the diving sensor data is scarce and high-dimensional, so this paper proposes a submersible fault detection method, which is made up of feature selection module based on hierarchical clustering and Autoencoder (AE), the improved Deep Convolutional Generative Adversarial Networks (DCGAN)-based data augmentation module and fault detection module using Convolutional Neural Network (CNN) with LeNet-5 structure. First, feature selection is developed to select the features that have a strong correlation with failure event. Second, data augmentation model is conducted to generate sufficient data for training the CNN model, including rough data generation and data refiners. Finally, a fault detection framework with LeNet-5 is trained and fine-tuned by synthetic data, and tested using real data. Experiment results based on sensor data from submersible hydraulic system demonstrate that our proposed method can successfully detect the fault samples. The detection accuracy of proposed method can reach 97% and our method significantly outperforms other classic detection algorithms.

Bearing Fault Numerical Model for the Closed-slot Rotor Submersible Motor

“…The supporting force of guide bearings is provided by a rotating water film in the internal clearance, which is different from that of rolling bearings. However, the bearing fault is a critical issue in submersible motors [3][4] . To ensure the safe operation of the motor, it is necessary to study the guide bearing fault mechanism and diagnosis.…”

Diffusion‐UDA: Diffusion‐based unsupervised domain adaptation for submersible fault diagnosis

“…Introduction: As a manned submersible that is capable of reaching the depth of 7,000 m, the Jiaolong usually works in the extreme deep-sea environments. Therefore, timely and accurate fault diagnosis is crucial to ensure the safety of both the personnel and the equipment while Jiaolong is on mission [1,2]. Due to the intricate structure of the submersible, the inconsistency between the failure systems and the sensor signals during the mission becomes a considerable challenge.…”