In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring ...approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM) has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks(LSTMs) are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods.
This paper introduces a novel deep learning-based algorithm that integrates a long short-term memory (LSTM)-based auto-encoder (AE) network with support vector machine (SVM) for electrocardiogram ...(ECG) arrhythmias classification. The LSTM-based AE network (LSTM-AE) is used to learn the features from ECG arrhythmias signals, and the SVM is used to classify those signals from the learned features. The LSTM-AE consists of an encoder model, which extracts high-level feature information from ECG arrhythmias signals through LSTM network, and a decoder model which outputs reconstruct ECG arrhythmias signals from high-level features through LSTM network. Experiments show that the proposed method can learn better features than the traditional method without any prior knowledge, presenting a good potential for the ECG arrhythmias classification. In the classification of five heartbeats types, including normal, left bundle branch block (LBBB), right bundle branch block (RBBB), atrial premature complexes (APC), premature ventricular contractions (PVC), the proposed method achieved average accuracy, sensitivity, and specificity of 99.74%, 99.35%, and 99.84%, respectively, in the beat-based cross-validation approach, and 85.20%, 62.99%, and 90.75%, respectively, in the record-based cross-validation approach, in public MIT-BIH Arrhythmia Database. While based on the Advancement of Medical Instrumentation (AAMI) standards, the proposed method achieved average accuracy, sensitivity, and specificity of 99.45%, 98.63%, and 99.66%, respectively, in the beat-based cross-validation approach.
This paper presents an enhanced particle filter (PF) approach for predicting remaining useful life (RUL) of rolling bearings. In the presented approach, particles in each recursive step are used to ...determine an alterable importance density function and the backpropagation neutral network is utilized to improve the particle diversity before resampling. Based on the enhanced PF, the framework of online rolling bearing RUL prediction is designed and a multiorder autoregressive model is used to construct the dynamic model for PF. Case studies performed on a simulation example and two test-to-failure experiments indicate that the presented approach can accurately predict the RUL of rolling bearings and it can achieve better performance than the traditional PF-based approach and commonly used support vector regression approach.
In modern industries, machine health monitoring systems (MHMS) have been applied wildly with the goal of realizing predictive maintenance including failures tracking, downtime reduction, and assets ...preservation. In the era of big machinery data, data-driven MHMS have achieved remarkable results in the detection of faults after the occurrence of certain failures (diagnosis) and prediction of the future working conditions and the remaining useful life (prognosis). The numerical representation for raw sensory data is the key stone for various successful MHMS. Conventional methods are the labor-extensive as they usually depend on handcrafted features, which require expert knowledge. Inspired by the success of deep learning methods that redefine representation learning from raw data, we propose local feature-based gated recurrent unit (LFGRU) networks. It is a hybrid approach that combines handcrafted feature design with automatic feature learning for machine health monitoring. First, features from windows of input time series are extracted. Then, an enhanced bidirectional GRU network is designed and applied on the generated sequence of local features to learn the representation. A supervised learning layer is finally trained to predict machine condition. Experiments on three machine health monitoring tasks: tool wear prediction, gearbox fault diagnosis, and incipient bearing fault detection verify the effectiveness and generalization of the proposed LFGRU.
•We conduct a detailed review of the applications of recent deep learning models on machine health monitoring tasks and provide our own insights into these models.•Practical studies about ...conventional machine learning models and deep learning models on a challenging tool wear prediction have been given. Related data and code have also been open to public.•We present current deep learning works on machine health monitoring in a well-organized way to facilitate researchers to catch this topic and provide discussions about the future direction in this research topic.
Since 2006, deep learning (DL) has become a rapidly growing research direction, redefining state-of-the-art performances in a wide range of areas such as object recognition, image segmentation, speech recognition and machine translation. In modern manufacturing systems, data-driven machine health monitoring is gaining in popularity due to the widespread deployment of low-cost sensors and their connection to the Internet. Meanwhile, deep learning provides useful tools for processing and analyzing these big machinery data. The main purpose of this paper is to review and summarize the emerging research work of deep learning on machine health monitoring. After the brief introduction of deep learning techniques, the applications of deep learning in machine health monitoring systems are reviewed mainly from the following aspects: Auto-encoder (AE) and its variants, Restricted Boltzmann Machines and its variants including Deep Belief Network (DBN) and Deep Boltzmann Machines (DBM), Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). In addition, an experimental study on the performances of these approaches has been conducted, in which the data and code have been online. Finally, some new trends of DL-based machine health monitoring methods are discussed.
A primary challenge in fault diagnosis is to extract multiple components entangled within a noisy observation. Therefore, this paper describes and analyzes a novel framework, based on convex ...optimization, for simultaneously identifying multiple features from superimposed signals. This work adequately exploits the underlying prior information that multiple faults with similar frequency spectrum have different morphological waveforms that can be sparsely represented over the union of redundant dictionaries. Within this framework, prior information is formulated into regularization terms, and a sparse optimization problem, which can be solved through the alternating direction method of multipliers (ADMM), is proposed. Meanwhile, the convergence and computational complexity of the proposed iterative framework are profoundly investigated. Moreover, sensitivity analyses and adaptive selection rules for the regularization parameters are described in detail through a set of comprehensive numerical studies. The proposed framework is validated through performing the diagnosis of multiple faults for gearbox in a wind farm. The comparison with respect to the state of the art in the field is illustrated in detail, which highlights the superiority of the proposed framework.
A convolutional discriminative feature learning method is presented for induction motor fault diagnosis. The approach firstly utilizes back-propagation (BP)-based neural network to learn local ...filters capturing discriminative information. Then, a feed-forward convolutional pooling architecture is built to extract final features through these local filters. Due to the discriminative learning of BP-based neural network, the learned local filters can discover potential discriminative patterns. Also, the convolutional pooling architecture is able to derive invariant and robust features. Therefore, the proposed method can learn robust and discriminative representation from the raw sensory data of induction motors in an efficient and automatic way. Finally, the learned representations are fed into support vector machine classifier to identify six different fault conditions. Experiments performed on a machine fault simulator indicate that compared with the current state-of-the-art methods, the proposed method shows significant performance gains, and it is effective and efficient for induction motor fault diagnosis.
This paper presents a signal analysis technique for machine health monitoring based on the Hilbert-Huang Transform (HHT). The HHT represents a time-dependent series in a two-dimensional (2-D) ...time-frequency domain by extracting instantaneous frequency components within the signal through an Empirical Mode Decomposition (EMD) process. The analytical background of the HHT is introduced, based on a synthetic analytic signal, and its effectiveness is experimentally evaluated using vibration signals measured on a test bearing. The results demonstrate that HHT is suited for capturing transient events in dynamic systems such as the propagation of structural defects in a rolling bearing, thus providing a viable signal processing tool for machine health monitoring
This paper investigates the usage of permutation entropy for working status characterization of rotary machines. As a statistical measure, the permutation entropy describes complexity of a time ...series or signal measured on a physical system through phase space reconstruction, and takes into account non-linear behavior of the time series, as often seen in vibration signals of rotary machines. Thus it can be served as a viable tool for detecting dynamic changes of the machine working status. The effect of embedded dimension and time delay on calculation of the permutation entropy value has been studied, and the validity of the permutation entropy for detecting dynamic change of a physical system is studied through a well known non-linear system, the Logistic Map. Comparison with other complexity measures using a numerically formulated signal has also been investigated. Experimental results on bearing vibration analysis have then confirmed that the permutation entropy provides an effective measure for monitoring the working status of rolling bearings.
► We investigate permutation entropy for status characterization of rotary machines. ► Embedded dimension at 6 and time delay at 3 provide reasonable PE calculation. ► PE provides an effective measure for monitoring working status of rolling bearings.
Prediction of material removal rate (MRR) during chemical mechanical polishing is critical for product quality control. Complexity involved in polishing makes it challenging to accurately predict MRR ...based on physical models. A data-driven technique based on Deep Belief Network (DBN) is investigated to reveal the relationship between MRR and polishing operation parameters such as pressure and rotational speeds of the wafer and pad. The effect of network structure and learning rate on the accuracy of predicted MRR is studied using particle swarm optimization algorithm. With an optimized network structure, the performance of DBN is experimentally verified, under varying operation conditions.