•Surveys on recent applications of artificial intelligence techniques to rotating machinery fault diagnosis.•Provides a guidance of how to choose and use artificial intelligence techniques in ...engineering.•Describes the artificial intelligence techniques applications and rotating machinery fault diagnosis trends.
Fault diagnosis of rotating machinery plays a significant role for the reliability and safety of modern industrial systems. As an emerging field in industrial applications and an effective solution for fault recognition, artificial intelligence (AI) techniques have been receiving increasing attention from academia and industry. However, great challenges are met by the AI methods under the different real operating conditions. This paper attempts to present a comprehensive review of AI algorithms in rotating machinery fault diagnosis, from both the views of theory background and industrial applications. A brief introduction of different AI algorithms is presented first, including the following methods: k-nearest neighbour, naive Bayes, support vector machine, artificial neural network and deep learning. Then, a broad literature survey of these AI algorithms in industrial applications is given. Finally, the advantages, limitations, practical implications of different AI algorithms, as well as some new research trends, are discussed.
Intelligent spindles are core components of the next-generation of intelligent/smart machine tools in the Industry 4.0 Era. The purpose of this paper is to clarify the concept of intelligent spindles ...and provide an in-depth review of the state-of-the-art of related technologies. A new integrated concept for intelligent spindles is proposed, followed by descriptions of required characteristics, key enabling technologies and expected intelligent functions. Relevant research that may be beneficial to the development of intelligent spindles is reviewed from six thrust areas, which include monitoring and control of tool condition, chatter, spindle collision, temperature/thermal error, spindle balance, and spindle health. Finally, current limitations and challenges are discussed, and future trends of intelligent spindles are prospected from various perspectives.
Display omitted
•A new integrated concept for intelligent spindles is proposed.•Previous research works related with intelligent spindles are reviewed.•Future trends of intelligent spindles are prospected.
Deep learning (DL) based methods have swept the field of mechanical fault diagnosis, because of the powerful ability of feature representation. However, many of existing DL methods fail in ...relationship mining between signals explicitly. Unlike those deep neural networks, graph convolutional networks (GCNs) taking graph data with topological structure as input is more efficient for data relationship mining, making GCN to be powerful for feature representation from graph data in non-Euclidean space. Nevertheless, existing GCNs have two limitations. First, most GCNs are constructed on unweighted graphs, considering importance of neighbors as the same, which is not in line with reality. Second, the receptive field of GCNs is fixed, which limits the effectiveness of GCNs for feature representation. To address these issues, a multireceptive field graph convolutional network (MRF-GCN) is proposed for effective intelligent fault diagnosis. In MRF-GCN, data samples are converted into weighted graphs to indicate differences in relationship of data samples. Moreover, MRF-GCN learns not only features from different receptive field, but also fuses learned features as an enhanced feature representation. To verify the efficacy of MRF-GCN for machine fault diagnosis, case studies are implemented, and the results show that MRF-GCN can achieve superior performance even under imbalanced dataset.
Bearing faults are one of the most common inducements for machine failures. Therefore, it is very important to perform bearing fault diagnosis reliably and rapidly. However, it is fundamental but ...difficult to extract impulses buried in heavy background noise for bearing fault diagnosis. In this paper, a novel adaptive enhanced sparse period-group lasso (AdaESPGL) algorithm for bearing fault diagnosis is proposed. The algorithm is based on the proposed enhanced sparse group lasso penalty, which promotes the sparsity within and across groups of the impulsive feature of bearing faults. Moreover, a periodic prior is embedded and updated dynamically through each iteration of the optimization procedure. Additionally, we formed a deterministic rule about how to set the parameters adaptively. The main advantage over conventional sparse representation methods is that AdaESPGL is parameter free (forming a deterministic rule) and rapid (extracting the impulsive information directly from the time domain). Finally, the performance of AdaESPGL is verified through a series of numerical simulations and the diagnosis of a motor bearing. Results demonstrate its superiority in extracting periodic impulses in comparison to other state-of-the-art methods.
It is always a primary challenge in fault diagnosis of a wind turbine generator to extract fault character information under strong noise and nonstationary condition. As a novel signal processing ...method, sparse representation shows excellent performance in time-frequency analysis and feature extraction. However, its result is directly influenced by dictionary, whose atoms should be as similar with signal's inner structure as possible. Due to the variability of operation environment and physical structure in industrial systems, the patterns of impulse signals are changing over time, which makes creating a proper dictionary even harder. To solve the problem, a novel data-driven fault diagnosis method based on sparse representation and shift-invariant dictionary learning is proposed. The impulse signals at different locations with the same characteristic can be represented by only one atom through shift operation. Then, the shift-invariant dictionary is generated by taking all the possible shifts of a few short atoms and, consequently, is more applicable to represent long signals that in the same pattern appear periodically. Based on the learnt shift-invariant dictionary, the coefficients obtained can be sparser, with the extracted impulse signal being closer to the real signal. Finally, the time-frequency representation of the impulse component is obtained with consideration of both the Wigner-Ville distribution of every atom and the corresponding sparse coefficient. The excellent performance of different fault diagnoses in a fault simulator and a wind turbine proves the effectiveness and robustness of the proposed method. Meanwhile, the comparison with the state-of-the-art method is illustrated, which highlights the superiority of the proposed method.
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.
This paper presents a new time-frequency (TF) analysis method called matching synchrosqueezing wavelet transform (MSWT) to signals with fast varying instantaneous frequency (IF). The original ...synchrosqueezing wavelet transform (SWT) can effectively improve the readability of TF representation (TFR) of signals with slowly varying IF. However, SWT still suffers from TF blurs for signals with fast varying IF. Moreover, the variable operating conditions of the aeroengine always make the vibration a signal with fast varying IF, especially when it comes to significant speed changes, which results in the obscure TFR for aeroengine vibration monitoring. In this paper, the MSWT introduces a chirp rate estimation into a comprehensive IF estimation to match the TF structure of the signals with fast varying IF and thus to achieve a highly concentrated TFR as the standard TF reassignment methods. Most importantly, the MSWT retains the reconstruction benefit like the SWT. The proposed MSWT is validated by both numerical simulation and applications in a bat echolocation signal analysis. Finally, a case study of a dual-rotor turbofan engine is given to illustrate the effectiveness of the proposed method for aeroengine vibration monitoring.
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.
On-line health status monitoring, a key part of prognostics and health management, provides various benefits, such as preventing unexpected failure and improving safety and reliability. In this ...paper, a data-driven approach for health status assessment is presented. A novel method based on discriminative deep belief networks (DDBN) and ant colony optimization (ACO) is used to predict health status of machine. DDBN is a new paradigm that utilizes a deep architecture to combine the advantages of deep belief networks and discriminative ability of back-propagation strategy. DDBN works through a greedy layer-by-layer training with multiple stacked restricted Boltzmann machines, which preserves information well when embedding features from high-dimensional space to low-dimensional space. However, selecting the parameters of DDBN is quite challenging. To address the problem, ACO is introduced to DDBN in this paper. By optimization, the structure of DDBN model is determined automatically without prior knowledge and the performance is enhanced. To evaluate the proposed approach, two case studies were carried out, which shows that it can achieve a good result. The performance of this model is also compared with support vector machine. It is concluded that the proposed method is very promising in the field of prognostics.
Broad learning system (BLS) is widely used in intelligent fault diagnosis (IFD) since its high computation efficiency and incremental learning ability. However, its applicability is limited to the ...single-task learning scenario in which only one diagnosis task needs to be learned. Generally, a machinery system contains multiple critical components that need to be diagnosed. The fault data of different components will be collected at different times for model training. It is essentially a task-incremental learning scenario in which the diagnosis model needs to learn a series of diagnosis task for different components at different times. Existing BLS methods cannot meet this requirement due to the catastrophic forgetting issue. Therefore, this paper proposes a task-incremental broad learning system (TiBLS) for multi-component IFD. The TiBLS is developed as a multi-head configuration with a series of BLS blocks to learn different diagnosis tasks sequentially. Then, the catastrophic forgetting is prevented via parameter isolation. Finally, the structure-incremental learning ability is developed for the TiBLS to enhance the diagnosis performance of each task without retraining. In this way, the TiBLS will gain more and more functions to diagnose different components over time. The experiment validation is implemented on a simulated machinery system including three critical components. The diagnosis accuracies of the three tasks are 94.75%, 93.02%, and 92.00%, respectively. The training times of the three tasks are 22.2 s, 34.5 s, and 7.6 s, respectively. The satisfying results demonstrate that the TiBLS is an effective and efficient method for multi-component IFD.