Unsupervised Multimodal Anomaly Detection With Missing Sources for Liquid Rocket Engine

An intelligent fault diagnosis model for bearings with adaptive hyperparameter tuning in multi-condition and limited sample scenarios

Bearing fault diagnosis under multiple operating conditions is challenging due to the complexity of changing environments and the limited availability of training data. To address these issues, this paper presents an advanced diagnosis method using a hybrid Grey Wolf Algorithm (HGWA)-optimized convolutional neural network (CNN) and Bidirectional long short-term memory (BiLSTM) architecture. The proposed model leverages CNN for extracting spatial features and BiLSTM for capturing temporal dependencies. Through HGWA, hyperparameters are efficiently optimized, achieving 100% diagnostic accuracy across four operating conditions with the CWRU dataset. Additionally, the optimized CNN-BiLSTM model demonstrated high diagnostic accuracy when applied as a pre-trained model in new environments, even with minimal training data. The proposed model not only improves diagnostic performance but also enhances optimization efficiency, achieving faster results within the same time frame. This approach mitigates the challenges of manually tuning neural network hyperparameters and effectively addresses bearing fault diagnosis under constrained sample conditions, representing a meaningful contribution to the field of rolling bearing fault diagnostics.

Adaptive Intermediate Class-Wise Distribution Alignment: A Universal Domain Adaptation and Generalization Method for Machine Fault Diagnosis

Many transfer learning methods have been proposed to implement fault transfer diagnosis, and their loss functions are usually composed of task-related losses, distribution distance losses, and correlation regularization losses. The intrinsic parameters and trade-off parameters between losses, however, need to be tuned according to the specific diagnosis tasks; thus, the generalization abilities of these methods in multiple tasks are limited. Besides, the alignment goal of most domain adaptation (DA) mechanisms dynamically changes during the training process, which will result in loss oscillation, slow convergence and poor robustness. To overcome the above-mentioned issues, a novel and simple transfer learning diagnosis method named adaptive intermediate class-wise distribution alignment (AICDA) model is proposed, and it is established via the proposed AICDA mechanism, dynamic intermediate alignment (DIA) adaptive layer and AdaSoftmax loss. The AICDA mechanism develops an adaptive intermediate distribution as the alignment goal of multiple source domains and target domains, and it can simultaneously align the global and class-wise distributions of these domains. The DIA layer is designed to adaptively achieve domain confusion without the distribution distance loss and the correlation regularization loss. Meanwhile, to ensure the classification performance of the AICDA mechanism, AdaSoftmax loss is proposed for boosting the separability of Softmax loss. Finally, in order to evaluate the effectiveness and universality of the AICDA diagnosis model to the most degree, various multisource mixed fault transfer diagnosis tasks of wind turbine planetary gearboxes, including DA and domain generalization (DG), are implemented, and the experimental results indicate that our proposed AICDA model has a higher diagnosis accuracy and a stronger generalization ability than other state-of-the-art transfer learning methods.

PAFormer: Anomaly Detection of Time Series With Parallel-Attention Transformer

Time-series anomaly detection is a critical task with significant impact as it serves a pivotal role in the field of data mining and quality management. Current anomaly detection methods are typically based on reconstruction or forecasting algorithms, as these methods have the capability to learn compressed data representations and model time dependencies. However, most methods rely on learning normal distribution patterns, which can be difficult to achieve in real-world engineering applications. Furthermore, real-world time-series data is highly imbalanced, with a severe lack of representative samples for anomalous data, which can lead to model learning failure. In this article, we propose a novel end-to-end unsupervised framework called the parallel-attention transformer (PAFormer), which discriminates anomalies by modeling both the global characteristics and local patterns of time series. Specifically, we construct parallel-attention (PA), which includes two core modules: the global enhanced representation module (GERM) and the local perception module (LPM). GERM consists of two pattern units and a normalization module, with attention weights that indicate the relationship of each data point to the whole series (global). Due to the rarity of anomalous points, they have strong associations with adjacent data points. LPM is composed of a learnable Laplace kernel function that learns the neighborhood relevancies through the distributional properties of the kernel function (local). We employ the PA to learn the global-local distributional differences for each data point, which enables us to discriminate anomalies. Finally, we propose a two-stage adversarial loss to optimize the model. We conduct experiments on five public benchmark datasets (real-world datasets) and one synthetic dataset. The results show that PAFormer outperforms state-of-the-art baselines.

MIM-Graph: A multi-sensor network approach for fault diagnosis of HSR Bogie bearings at the IoT edge via mutual information maximization

The Internet of Things (IoT) is crucial in developing next-generation high-speed railways (HSRs). HSR IoT enables intelligent diagnosis of trains using multi-sensor data, which is critical for maintaining high speeds and ensuring passenger safety. Graph neural network (GNN)-based methods have gained popularity in HSR IoT research due to the ability to represent the sensor network as intuitive graphs. However, labeling monitoring data in the HSR scenario takes time and effort. To address this challenge, we propose a semi-supervised graph-level representation learning approach called MIM-Graph, which uses mutual information maximization to learn from a large amount of unlabeled data. First, the multi-sensor data is converted into association graphs based on their spatial topology. The unsupervised encoder is trained using global-local mutual maximization. The teacher-student framework transfers knowledge from the unsupervised encoder learned to the supervised encoder, which is trained using a small amount of labeled data. As a result, the supervised encoder learns distinguishable representations for intelligent diagnosis of HSR. We evaluate the proposed method using CWRU dataset and data from HSR Bogie test platform, and the experimental results demonstrate the effectiveness and superiority of MIM-Graph.

Single-Sensor Engine Multi-Type Fault Detection

Engine fault detection is conducive to improving equipment reliability and reducing maintenance costs. In practical scenarios, high-quality data is difficult to obtain. Usually, only single-sensor data is available. This paper proposes a fault detection method combining Variational Mode Decomposition (VMD) and Random Forest (RF). At first, the spectral energy distribution is obtained by decomposing and statistic the engine data of multiple working conditions. Based on the spectral energy distribution, the overall optimal mode number was identified, and the quadratic penalty term was optimized using SNR. The improved VMD (IVMD) improves mode aliasing and iterative efficiency and unifies feature dimensions. Decomposition of real signals demonstrates the effectiveness. The paper designs a feature vector composed of seven types of attributes, including unit bandwidth energy, center frequency, maximum singular value and so on. The feature vector is then fed to RF for classification. Features are selected in order of importance to classification to improve the training efficiency. By comparing with various algorithms, the proposed method has higher accuracy and faster training efficiency in single-speed, multi-speed and cross-speed single-sensor data diagnosis. The results show that the method has application prospects with little training data and low hardware requirements.

A Study Using Optimized LSSVR for Real-Time Fault Detection of Liquid Rocket Engine

Health monitoring and fault diagnosis of liquid rocket engine (LRE) are the most important concerning issue for the safety of rocket’s flying, especially for the man-carried aerospace engineering. Based on the sensor measurement signals of a certain type of hydrogen-oxygen rocket engine, this paper proposed a real-time fault detection approach using a genetic algorithm-based least squares support vector regression (GA-LSSVR) algorithm for the real-time fault detection of the rocket engine. In order to obtain effective training samples, the data is normalized in this paper. Then, the GA-LSSVR algorithm is derived through comprehensive considerations of the advantages of the Support Vector Regression (SVR) algorithm and Least Square Support Vector Regression (LSSVR). What is more, this paper provided the genetic algorithm to search for the optimal LSSVR parameters. In the end, the computational results of the suggested approach using the rocket practical experimental data are given out. Through the analysis of the results, the effectiveness and the detection accuracy of this presented real-time fault detection method using LSSVR GA-optimized is verified. The experiment results show that this method can effectively diagnose this hydrogen-oxygen rocket engine in real-time, and the method has engineering application value.