Multiple Convolutional Recurrent Neural Networks for Fault Identification and Performance Degradation Evaluation of High-Speed Train Bogie

A pruning-aware dynamic slimmable network using meta-gradients for high-speed train bogie bearing fault diagnosis

Although intelligent fault diagnosis achieves remarkable achievements, computation efficiency is a commonly ignored problem in existing studies. Pruning network networks enable us to find compact models that not only retain the diagnosis accuracy, but also consume fewer computation resources for training and inference. However, current studies are inefficient in building a saliency criterion for parameter importance evaluation. In this paper, we identify a pruning-aware dynamic slimmable network which uses the meta-gradients to select unnecessary parameters to prune. The slimmable network is designed with two sub-networks, called the classifier and the evaluator to generate meta-gradients for parameter pruning. And an iterative pruning algorithm is proposed to improve computation efficiency while retaining diagnosis performance. Our method is verified on a high-precision bogie fault simulation experimental data set and achieves state-of-art performance in terms of accuracy and efficiency compared with existing studies.

Explainable Graph Wavelet Denoising Network for Intelligent Fault Diagnosis

Deep learning (DL)-based intelligent fault diagnosis methods have greatly promoted the development of the field of fault diagnosis due to their powerful feature extraction ability for handling massive monitoring data. However, most of them still suffer from the following three limitations. First, many existing DL-based intelligent diagnosis methods cannot extract proper discriminative features from signals with strong noise. Second, the interactions or relationships between signals are ignored, while they mainly focus on extracting temporal features from the signal. Third, owing to their black-box nature, the learned features lack interpretability, which hinders their application in the industry. To tackle these issues, an explainable graph wavelet denoising network (GWDN) is proposed to achieve intelligent fault diagnosis under noisy working conditions in this article. In GWDN, the collected signals are first transformed into graph-structured data to consider the interactions among signals. Then, the graph wavelet denoising convolution (GWDConv) is proposed based on the discrete graph wavelet frame, which allows GWDN to achieve multiscale feature extraction for graph-structured data and realize signal denoising. Extensive experiments are implemented to verify the efficacy of the proposed GWDN, and the experimental results show that GWDN can achieve state-of-the-art performance among the comparison methods. Besides, by using the square envelope spectrum to analyze the extracted features of GWDConv, we find that it can well retain the fault-related components of the signal and realize signal denoising, which further proves that GWDN is explainable.

Physics-Constraint Variational Neural Network for Wear State Assessment of External Gear Pump

Most current data-driven prognosis approaches suffer from their uncontrollable and unexplainable properties. To address this issue, this article proposes a physics-constraint variational neural network (PCVNN) for wear state assessment of the external gear pump. First, a response model of the pressure pulsation of the gear pump is constructed via a spectral method, and a compound neural network is utilized to extract features from the pressure pulsation signal. Then, the response model is formulated into an objective function to softly constrain the learning process of the neural network, forcing the learned features to have explicit physics meaning. Meanwhile, to characterize the system uncertainty, the variational inference is utilized to extend a Kullback-Leibler (KL) divergence into the objective function. Finally, the wear state is evaluated based on the distance of learned physics features. Experimental results on an external gear pump validate the merits of the proposed method in explainable representation learning and system uncertainty estimation. It also offers a controllable and explainable perspective to understand the dynamic behavior of the system.

Unsupervised Multimodal Anomaly Detection With Missing Sources for Liquid Rocket Engine

To achieve reliable and automatic anomaly detection (AD) for large equipment such as liquid rocket engine (LRE), multisource data are commonly manipulated in deep learning pipelines. However, current AD methods mainly aim at single source or single modality, whereas existing multimodal methods cannot effectively cope with a common issue, modality incompleteness. To this end, we propose an unsupervised multimodal method for AD with missing sources in LRE system. The proposed method handles intramodality fusion, intermodality fusion, and decision fusion in a unified framework composed of multiple deep autoencoders (AEs) and a skip-connected AE. Specifically, the first module restores missing sources to construct a complete modality, thus advancing the secondary reconstruction. Different from vanilla reconstruction-based methods, the proposed method minimizes reconstruction loss and meanwhile maximizes the dissimilarity of representations in two latent spaces. Utilizing reconstruction errors and latent representation discrepancy, the anomaly score is acquired. At decision level, the model performance can be further enhanced via anomaly score fusion. To demonstrate the effectiveness, extensive experiments are carried out on multivariate time-series data from static ignition of several LREs. The results indicate the superiority and potential of the proposed method for AD with missing sources for LRE.

A Dimensionality-Reducible Operational Optimal Control for Wastewater Treatment Process

Operational optimal control (OOC) is an essential component of wastewater treatment process (WWTP). The control variables usually are high-dimensional, nonlinear, and strongly coupled, which can easily fail traditional optimization control methods. Mathematically, these operational variables usually are in the unknown low-dimensional space embedded in the high-dimensional space. Therefore, the OOC problem of WWTP can be resolved as an optimization challenge involving low-dimensional space, and the unknown low-dimensional space is presented in the form of a set of controlled variables in a high-dimensional space, which is normal in real-world industries. Here, a dimension-reducible data-driven optimization control framework for WWTP is proposed. Considering the difficulty in elucidating the whole space of set points, a neural network is designed to approximate the constraint relationship between control variables. The search process is based on optimization methods in low-dimensional space embedded into Euclidean spaces. Furthermore, the convergence of the process is ensured via mathematical analysis. Finally, the experimental simulation of wastewater treatment revealed that this approach is effective for an optimal solution in control systems.

Intelligent Fault Diagnosis of Gearbox Under Variable Working Conditions With Adaptive Intraclass and Interclass Convolutional Neural Network

The industrial gearboxes usually work in harsh and variable conditions, which results in partial failure of gears or bearings. Accordingly, the continuous irregular fluctuations of gearbox under variable conditions maybe increase the intraclass difference and reduce the interclass difference for the monitored samples. To this end, a new intelligent fault diagnosis method of gearbox based on adaptive intraclass and interclass convolutional neural network (AIICNN) under variable working conditions is proposed. The core of the proposed algorithm is to apply the designed intraclass and interclass constraints to improve the distribution differences of samples. Meanwhile, the adaptive activation function is added into the 1-D convolutional neural network (1dCNN) to enlarge the heterogeneous distance and narrow the homogeneous distance of samples. Specifically, the training sample subset with intraclass and interclass spacing fluctuations under variable conditions is first converted into frequency domain through the fast Fourier transform (FFT), and the designed AIICNN algorithm is employed for model training. Afterward, the testing subset is provided to the trained AIICNN algorithm for fault diagnosis. The experimental data of the planetary gearbox test rig verify the feasibility of the proposed diagnosis method and algorithm. Compared with other methods, this method can eliminate the difference of sample distribution under variable conditions and improve its diagnostic generalization.

Research on Performance Degradation Estimation of Key Components of High-Speed Train Bogie Based on Multi-Task Learning

The safe and comfortable operation of high-speed trains has attracted extensive attention. With the operation of the train, the performance of high-speed train bogie components inevitably degrades and eventually leads to failures. At present, it is a common method to achieve performance degradation estimation of bogie components by processing high-speed train vibration signals and analyzing the information contained in the signals. In the face of complex signals, the usage of information theory, such as information entropy, to achieve performance degradation estimations is not satisfactory, and recent studies have more often used deep learning methods instead of traditional methods, such as information theory or signal processing, to obtain higher estimation accuracy. However, current research is more focused on the estimation for a certain component of the bogie and does not consider the bogie as a whole system to accomplish the performance degradation estimation task for several key components at the same time. In this paper, based on soft parameter sharing multi-task deep learning, a multi-task and multi-scale convolutional neural network is proposed to realize performance degradation state estimations of key components of a high-speed train bogie. Firstly, the structure takes into account the multi-scale characteristics of high-speed train vibration signals and uses a multi-scale convolution structure to better extract the key features of the signal. Secondly, considering that the vibration signal of high-speed trains contains the information of all components, the soft parameter sharing method is adopted to realize feature sharing in the depth structure and improve the utilization of information. The effectiveness and superiority of the structure proposed by the experiment is a feasible scheme for improving the performance degradation estimation of a high-speed train bogie.

Coarse-to-Fine: Progressive Knowledge Transfer-Based Multitask Convolutional Neural Network for Intelligent Large-Scale Fault Diagnosis

In modern industry, large-scale fault diagnosis of complex systems is emerging and becoming increasingly important. Most deep learning-based methods perform well on small number of fault diagnosis, but cannot converge to satisfactory results when handling large-scale fault diagnosis because the huge number of fault types will lead to the problems of intra/inter-class distance unbalance and poor local minima in neural networks. To address the above problems, a progressive knowledge transfer-based multitask convolutional neural network (PKT-MCNN) is proposed. First, to construct the coarse-to-fine knowledge structure intelligently, a structure learning algorithm is proposed via clustering fault types in different coarse-grained nodes. Thus, the intra/inter-class distance unbalance problem can be mitigated by spreading similar tasks into different nodes. Then, an MCNN architecture is designed to learn the coarse and fine-grained task simultaneously and extract more general fault information, thereby pushing the algorithm away from poor local minima. Last but not least, a PKT algorithm is proposed, which can not only transfer the coarse-grained knowledge to the fine-grained task and further alleviate the intra/inter-class distance unbalance in feature space, but also regulate different learning stages by adjusting the attention weight to each task progressively. To verify the effectiveness of the proposed method, a dataset of a nuclear power system with 66 fault types was collected and analyzed. The results demonstrate that the proposed method can be a promising tool for large-scale fault diagnosis.

Resource-Aware Distributed Differential Evolution for Training Expensive Neural-Network-Based Controller in Power Electronic Circuit

The neural-network (NN)-based control method is a new emerging promising technique for controller design in a power electronic circuit (PEC). However, the optimization of NN-based controllers (NNCs) has significant challenges in two aspects. The first challenge is that the search space of the NNC optimization problem is such complex that the global optimization ability of the existing algorithms still needs to be improved. The second challenge is that the training process of the NNC parameters is very computationally expensive and requires a long execution time. Thus, in this article, we develop a powerful evolutionary computation-based algorithm to find a high-quality solution and reduce computational time. First, the differential evolution (DE) algorithm is adopted because it is a powerful global optimizer in solving a complex optimization problem. This can help to overcome the premature convergence in local optima to train the NNC parameters well. Second, to reduce the computational time, the DE is extended to distribute DE (DDE) by dispatching all the individuals to different distributed computing resources for parallel computing. Moreover, a resource-aware strategy (RAS) is designed to further efficiently utilize the resources by adaptively dispatching individuals to resources according to the real-time performance of the resources, which can simultaneously concern the computing ability and load state of each resource. Experimental results show that, compared with some other typical evolutionary algorithms, the proposed algorithm can get significantly better solutions within a shorter computational time.

Feature-Level Attention-Guided Multitask CNN for Fault Diagnosis and Working Conditions Identification of Rolling Bearing

Accurate and real-time fault diagnosis (FD) and working conditions identification (WCI) are the key to ensuring the safe operation of mechanical systems. We observe that there is a close correlation between the fault condition and the working condition in the vibration signal. Most of the intelligent FD methods only learn some features from the vibration signals and then use them to identify fault categories. They ignore the impact of working conditions on the bearing system, and such a single-task learning method cannot learn the complementary information contained in multiple related tasks. Therefore, this article is devoted to mining richer and complementary globally shared features from vibration signals to complete the FD and WCI of rolling bearings at the same time. To this end, we propose a novel multitask attention convolutional neural network (MTA-CNN) that can automatically give feature-level attention to specific tasks. The MTA-CNN consists of a global feature shared network (GFS-network) for learning globally shared features and K task-specific networks with feature-level attention module (FLA-module). This architecture allows the FLA-module to automatically learn the features of specific tasks from globally shared features, thereby sharing information among different tasks. We evaluated our method on the wheelset bearing data set and motor bearing data set. The results show that our method has a better performance than the state-of-the-art deep learning methods and strongly prove that our multitask learning mechanism can improve the results of each task.

A Vibration Fault Identification Framework for Shafting Systems of Hydropower Units: Nonlinear Modeling, Signal Processing, and Holographic Identification

The shafting systems of hydropower units work as the core component for the conversion of water energy to electric energy and have been running for a long time in the hostile hydraulic–mechanical–electrical-coupled environment—their vibration faults are frequent. How to quickly and accurately identify vibration faults to improve the reliability of the unit is a key issue. This study proposes a novel shafting vibration fault identification framework, which is divided into three coordinated stages: nonlinear modeling, signal denoising, and holographic identification. A nonlinear dynamical model of bending–torsion coupling vibration induced by multiple excitation vibration sources of the shafting system is established in the first stage. The multi-stage signal denoising method combines Savitzky–Golay (SG) smoothing filtering, singular value decomposition (SVD), and variational mode decomposition (VMD). SG-SVD-VMD is used for the guide bearing the vibration signals in the second stage. Further, the holospectrum theory is innovatively introduced to obtain the holospectra of the simulated and measured signals, and the shafting vibration faults of the real unit are identified by comparing the holospectrum of the measured signal with the simulated signal. These results show that the shafting nonlinear model can effectively reflect the vibration characteristics of the coupled vibration source and reveal the influence and fault characteristics of each external excitation on the shafting vibration. The shafting vibration faults of operating units can be identified by analyzing the holospectra of the shafting simulation signals and measuring the noise reduction signals. Thus, this framework can guide the safe and stable operation of hydropower units.

Railway Track Inspection Using Deep Learning Based on Audio to Spectrogram Conversion: An on-the-Fly Approach

The periodic inspection of railroad tracks is very important to find structural and geometrical problems that lead to railway accidents. Currently, in Pakistan, rail tracks are inspected by an acoustic-based manual system that requires a railway engineer as a domain expert to differentiate between different rail tracks' faults, which is cumbersome, laborious, and error-prone. This study proposes the use of traditional acoustic-based systems with deep learning models to increase performance and reduce train accidents. Two convolutional neural networks (CNN) models, convolutional 1D and convolutional 2D, and one recurrent neural network (RNN) model, a long short-term memory (LSTM) model, are used in this regard. Initially, three types of faults are considered, including superelevation, wheel burnt, and normal tracks. Contrary to traditional acoustic-based systems where the spectrogram dataset is generated before the model training, the proposed approach uses on-the-fly feature extraction by generating spectrograms as a deep learning model's layer. Different lengths of audio samples are used to analyze their performance with each model. Each audio sample of 17 s is split into 3 variations of 1.7, 3.4, and 8.5 s, and all 3 deep learning models are trained and tested against each split time. Various combinations of audio data augmentation are analyzed extensively to investigate models' performance. The results suggest that the LSTM with 8.5 split time gives the best results with the accuracy of 99.7%, the precision of 99.5%, recall of 99.5%, and F1 score of 99.5%.

Performance Degradation Estimation of High-Speed Train Bogie Based on 1D-ConvLSTM Time-Distributed Convolutional Neural Network

High-speed train bogies are essential for the safety and comfort of train operation. The performance of the bogie usually degrades before it fails, so it is necessary to detect the performance degradation of a high-speed train bogie in advance. In this paper, with two key dampers on the bogie taken as experimental objects (lateral damper and yaw damper), a novel 1D-ConvLSTM time-distributed convolutional neural network (CLTD-CNN) is proposed to estimate the performance degradation of a high-speed train bogie. The proposed CLTD-CNN is an encoder-decoder structure. Specifically, the encoder part of the proposed structure consists of a time-distributed 1D-CNN module and a 1D-ConvLSTM. The decoder part consists of a 1D-ConvLSTM and a simple time-CNN with residual connections. In addition, an auxiliary training part is introduced into the structure to support CLTD-CNN in learning the performance degradation trend characteristic, and a special input format is designed for this structure. The whole structure is end-to-end and does not require expert knowledge or engineering experience. The effectiveness of the proposed CLTD-CNN is tested by the high-speed train CRH380A under different performance states. The experimental results demonstrate the superiority of CLTD-CNN. Compared to other methods, the estimation error of CLTD-CNN is the smallest.