A Novel Deep Learning Framework Based RNN-SAE for Fault Detection of Electrical Gas Generator

Abstract

The electrical generator is the key part of the electrical generation system for the oil and gas industry, and it is easy to fail, which disturbs the availability and reliability of the electrical generation in the power industry. Therefore, extracting and diagnosing the fault features from the process signals are useful to diagnose the status of the machine. Though, a common challenge in many applied applications is the practical knowledge about the risk of failure or historical records, which is totally unlabeled and difficult to be identified by traditional fault approaches. Hence, in the present study, a novel deep learning (DL) framework is proposed to fill the gap by balancing the three stages of fault feature extraction, fault detection, and parameter optimization based on the long short term memory-recurrent neural networks (RNN-LSTM), stacked autoencoders (SAE), and particle swarm optimization (PSO) techniques. The suggested framework focuses on failure detection through a sequence of numerous features for the unlabeled historical data and unknown anomaly. To validate the effectiveness of the proposed DL framework, an experiment for failure detection of the electrical generator was conducted for the data of risky environment at Yemen oil and gas plant. The experimental results compared with the earlier studies validate that, the DL framework can address the faults for vibration signals of the electrical generator in a well-diagnosis performance effectively. INDEX TERMSDeep learning (DL), Fault detection, Long short-term memory (LSTM), Oil and gas plant, Recurrent neural networks (RNN), Stacked autoencoders (SAE) This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.

Hybrid Deep Learning Model for Fault Detection and Classification of Grid-Connected Photovoltaic System

“…SAE has the excellent capability of performing dimensionality reduction on the input signal into any desired sizes by leveraging its hidden layer as a feature extractor, as well as can predict the output and the same input data without requiring labels. For this reason, SAE is able to automatically extract the significant fault features from input signals without requiring any data labeling and yet can offer better descriptions of fault features than the original data [51]. Fig.…”

Hovering Swarm Particle Swarm Optimization

“…A modified learning strategy is subsequently introduced to guide the search processes of all HSPSO main swarm members with better diversity preservation based on E Universal instead of historically best positions (e.g., personal and global best positions). For each i-th main swarm member, the d-th component of its new velocity is updated as: (8) where rand ∈ [0, 1] is a real-valued uniformly distributed random number; χ is a constriction factor used to prevent swarm explosion and it is set as 0.7298 based on the recommendation of [48]. Referring to the new velocity obtained, the position of each i-th main swarm member, i.e., X i ∈ X Main is updated using Eq.…”

“…searching of the best hyperparameters or network architectures of machine learning and deep learning frameworks in order to maximize their classification or regression accuracies [8]- [10]. Optimization is not only limited in the scientific and engineering domains, but it also prevalent in human daily lives such as determining the best investment portfolio that can lead to maximum profit [11], budget allocation in media planning to achieve the target level of reaching with minimum cost [12], and etc.…”

Data-Driven Forecasting and Modeling of Runoff Flow to Reduce Flood Risk Using a Novel Hybrid Wavelet-Neural Network Based on Feature Extraction

“…Moreover, Several researchers proposed novel methods to resolve different problems in a wide area of applications, such as a deep convolutional neural network for Classification underwater cable images [27], a hybrid approach of stacked autoencoders and long short term memory, for feature extraction and fault detection [28], the coevolutionary multi-objective particle swarm optimization approach for maintenance optimization [29].…”