Rotating machinery fault detection and diagnosis based on deep domain adaptation: A survey

In practical mechanical fault detection and diagnosis, it is difficult and expensive to collect enough large-scale supervised data to train deep networks. Transfer learning can reuse the knowledge obtained from the source task to improve the performance of the target task, which performs well on small data and reduces the demand for high computation power. However, the detection performance is significantly reduced by the direct transfer due to the domain difference. Domain adaptation (DA) can transfer the distribution information from the source domain to the target domain and solve a series of problems caused by the distribution difference of data. In this survey, we review various current DA strategies combined with deep learning (DL) and analyze the principles, advantages, and disadvantages of each method. We also summarize the application of DA combined with DL in the field of fault diagnosis. This paper provides a summary of the research results and proposes future work based on analysis of the key technologies.     

Variable structure multiple model fixed-interval smoothing

This paper focuses on fixed-interval smoothing for stochastic hybrid systems. When the truth-mode mismatch is encountered, existing smoothing methods based on fixed structure of model-set have significant performance degradation and are inapplicable. We develop a fixed-interval smoothing method based on forward- and backward-filtering in the Variable Structure Multiple Model (VSMM) framework in this paper. We propose to use the Simplified Equivalent model Interacting Multiple Model (SEIMM) in the forward and the backward filters to handle the difficulty of different mode-sets used in both filters, and design a re-filtering procedure in the model-switching stage to enhance the estimation performance. To improve the computational efficiency, we make the basic model-set adaptive by the Likely-Model Set (LMS) algorithm. It turns out that the smoothing performance is further improved by the LMS due to less competition among models. Simulation results are provided to demonstrate the better performance and the computational efficiency of our proposed smoothing algorithms.     

Efficient multi-objective CMA-ES algorithm assisted by knowledge-extraction-based variable-fidelity surrogate model

To accelerate the multi-objective optimization for expensive engineering cases, a Knowledge-Extraction-based Variable-Fidelity Surrogate-assisted Covariance Matrix Adaptation Evolution Strategy(KE-VFS-CMA-ES) is presented. In the first part, the KE-VFS model is established. Firstly, the optimization is performed using the low-fidelity surrogate model to obtain the Low-Fidelity Non-Dominated Solutions(LF-NDS). Secondly, aiming to obtain the High-Fidelity(HF) sample points located in promising are...     

Sea fog detection based on unsupervised domain adaptation

Sea fog detection with remote sensing images is a challenging task. Driven by the different image characteristics between fog and other types of clouds, such as textures and colors, it can be achieved by using image processing methods. Currently, most of the available methods are datadriven and relying on manual annotations. However, because few meteorological observations and buoys over the sea can be realized, obtaining visibility information to help the annotations is difficult. Considering t...     

Active,compact, wideband,receiving filtenna with power adaptation for space-limited wireless platforms

An active, compact, wideband, receiving filtenna with power adaptation for space-limited wireless platforms is presented. By organically combining a filtering antenna and a Variable Gain Amplifier (VGA), the proposed co-designed active filtenna is achieved. Its power adaptation is empowered by controlling gain of the VGA unit. A demonstrated prototype with a compact overall size is fabricated, assembled and measured. Good performances are achieved. Furthermore, in any condition, the proposed active filtenna displays outstanding impedance matching (|S₁₁| < ?10 dB) and high passband skirt selectivity at upper and lower stopbands (Selectivity ≥ 170 dB/GHz).     

Source free unsupervised domain adaptation for electro-mechanical actuator fault diagnosis

A common necessity for prior unsupervised domain adaptation methods that can improve the domain adaptation in unlabeled target domain dataset is access to source domain dataset and target domain dataset simultaneously. However, data privacy makes it not always possible to access source domain dataset and target domain dataset in actual industrial equipment simultaneously, especially for aviation component like Electro-Mechanical Actuator (EMA) whose dataset are often not shareable due to the data copyright and confidentiality. To address this problem, this paper proposes a source free unsupervised domain adaptation framework for EMA fault diagnosis. The proposed framework is a combination of feature network and classifier. Firstly, source domain datasets are only applied to train a source model. Secondly, the well-trained source model is transferred to target domain and classifier is frozen based on source domain hypothesis. Thirdly, nearest centroid filtering is introduced to filter the reliable pseudo labels for unlabeled target domain dataset, and finally, supervised learning and pseudo label clustering are applied to fine-tune the transferred model. In comparison with several traditional unsupervised domain adaptation methods, case studies based on low- and high-frequency monitoring signals on EMA indicate the effectiveness of the proposed method.