Abstract
We propose a method to integrate feature extraction and prediction as a single optimization task by stacking a three-layer model as a deep learning structure. The first layer of the deep structure is a Long Short Term Memory (LSTM) model which deals with the sequential input data from a group of assets. The output of the LSTM model is followed by meanpooling, and the result is fed to the second layer. The second layer is a neural network layer, which further learns the feature representation. The output of the second layer is connected to a survival model as the third layer for predicting asset health condition. The parameters of the three-layer model are optimized together via stochastic gradient decent. The proposed method was tested on a small dataset collected from a fleet of mining haul trucks. The model resulted in the “individualized” failure probability representation for assessing the health condition of each individual asset, which well separates the in-service and failed trucks. The proposed method was also tested on a large open source hard drive dataset, and it showed promising result.
Highlights
As the Internet-of-Things technology enables us to obtain a great amount of data to monitor physical assets, there is an increasing demand for determining asset health conditions in a variety of industries
Instead of doing feature extraction and survival analysis as two separate steps, we propose a novel ‘end-to-end’ deep learning structure by stacking Long Short Term Memory (LSTM), neural network, and survival analysis, and optimizing all the parameters together using stochastic gradient descent
The second layer (i) of LSTM decides what information to be stored in the current state
Summary
As the Internet-of-Things technology enables us to obtain a great amount of data to monitor physical assets, there is an increasing demand for determining asset health conditions in a variety of industries. A back-propagation neural network model was utilized to predict asset health condition using the identified key factor values. A support vector regression method was used to predict the cutting tool wear based on the reduce features. Tamilselvan et al (Tamilselvan & Wang, 2013) applied a deep learning classification method to diagnose electric power transformer health states. A deep convolutional neural network based regression approach was proposed by Babu et al (Babu, Zhao, & Li, 2016) to estimate remaining useful life of a sub-system or a system component. Instead of doing feature extraction and survival analysis as two separate steps, we propose a novel ‘end-to-end’ deep learning structure by stacking LSTM, neural network, and survival analysis, and optimizing all the parameters together using stochastic gradient descent
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
