Search

This paper suggests an image gradient based method that determines the optimal image size for convolutional neural network (CNN)-based diagnosis of fluid-film rotorbearing systems. As distinct patterns improve the diagnosis performance, a criterion is defined to measure the intensity of patterns in an image. The proposed criterion is derived by segmenting an image by the size of the CNN filter and evaluating each segment through the use of image gradient analysis. Vibration signals from a testbed are used to demonstrate the proposed method. First, the signals are transformed into vibration images by using an omnidirectional regeneration technique. Then, vibration images of four different health states are analyzed using the suggested criterion. The analyzed results are compared to the performance of CNN based diagnosis. The results indicate that the proposed criterion can determine the optimal size range of the vibration image that gives the best performance for CNN-based diagnosis.

Recently, substantial research has explored the development of deep-learning-based methods to diagnose faults in rotating machinery. For these diagnosis methods, it is difficult to obtain high target diagnosis accuracy when the amount of labeled data obtained pertaining to the rotating machinery under study is insufficient or in cases involving a discrepancy in the distribution types found in the training and test data sets. To deal with this research need, the paper outlines a new method, a domain adaptation with semantic clustering (DASC), capable of diagnosing faults in rotating machinery. The method outlined in this research learns both domain-invariant and discriminative features. The method reduces the domain discrepancy by minimizing the domain-related loss. In addition, by defining an additional loss, which is called semantic clustering loss, and reducing it at multiple feature levels, the DASC method learns features that make samples better semantically clustered, according to their health conditions. Consequently, fault diagnosis performance for target rotating machinery can be enhanced through the use of the DASC approach. The effectiveness of the DASC approach is confirmed by examining various fault diagnosis situations with domain discrepancies across the source and target domains, using experimental data from three bearing systems. Also, various analyses are explored to better understand the advantages of the DASC method.

Despite the recent success of deep-learning-based fault diagnosis of rotating machinery, to enable accurate and robust diagnosis models, existing approaches proceed with the assumption that training and test data follow the same distribution. However, in practical industrial settings, variations in operating conditions and environmental noise can cause changes in the characteristics of the training and test data, called domain shift, resulting in performance degradation of the test data. To deal with these issues, this paper proposes an asymmetric inter-intra domain alignments (AIIDA) approach for fault diagnosis under various levels of domain shift. First, inter-domain alignment is conducted by minimizing the maximum mean discrepancy loss and domain adversarial loss. Next, intra-domain alignment is performed by adjusting the inconsistency loss. This approach allows the proposed AIIDA method to learn features that have lower inter-domain distance and higher intra-domain distance; thus, the fault diagnosis performance in the target domain can be significantly improved. Extensive experimental assessment that examines various scenarios across three bearing datasets is performed to validate the effectiveness of the proposed approach. Furthermore, a study comparing the proposed method with other existing methods demonstrates that the proposed method outperforms other methods.

This paper suggests label-based, mini-batch methods for convolutional neural network (CNN) based diagnosis of fluid-film bearing rotor systems. Rather than using random mini-batches in the training process, mini-batches are generated based on the label information. Label information is a critical factor for robust diagnosis. Five different types of label-based mini-batches are proposed and their performance is compared to the conventional random mini-batch method. In addition, sensitivity analysis of kernels in convolutional neural networks is suggested as a method to analyze the performance variation. A case study of a fluid-film bearing rotor system is used to show the effect of the proposed methods. The case study results indicate a wide range of performance variation among the proposed mini-batch methods. Of the examined methods, the equally labeled mini-batch approach presents the best performance. Moreover, the results of the kernel sensitivity analysis show that the use of properly sensitive kernels does positively affect the overall performance of the CNN.

Some anomaly states of journal bearing rotor systems are direction-oriented (e.g., rubbing, misalignment). In these situations, vibration signals vary according to the direction of the sensors and the health state. This makes diagnosis difficult with traditional diagnosis methods. This paper proposes an omnidirectional regeneration method to develop a robust diagnosis algorithm for rotor systems. The proposed method can generate vibration signals in arbitrary directions without using extra sensors. In this method, signals are generated around the entire circumference of the rotor to consider all possible directions. Then, the directionality of each state is proved by mathematically and is evaluated using a proposed metric. When a directional state is determined, the classification is carried out on all of the generated signals. When a non-directional state is found, the classification is performed on only one of the generated signals to minimize computational load without sacrificing accuracy. The proposed ODR method was validated using experimental data. The classification results show that the proposed method generally outperforms the conventional classification method. The results support the proposed concept of using ODR signals in diagnosis procedures for journal bearing systems.

Deep learning-based research has drawn much attention in the field of fault diagnosis of various mechanical systems due to its powerful performance. In deep learning-based methods, signals become the input for a deep learning algorithm. However, the performance of an algorithm can be diminished if there is significant noise in the data. To address the noise issue, this paper proposes a fault diagnosis method called multi-task learning of classification and denoising (MLCD). The proposed method is designed to make a fault diagnosis algorithm robust against the noise in vibration signals by learning the denoising task simultaneously with the classification. Given a noisy input, MLCD can improve test accuracy by implementing denoising as an auxiliary task, using hyperparameters chosen by Bayesian optimization. To validate the proposed MLCD method, it is integrated with the two most commonly used deep learning algorithms: long short-term memory and one-dimensional convolutional neural network. For a case study, these algorithms are tested to classify the states of a rotor testbed data. The results show that the proposed MLCD method extracts noise-robust and meaningful features; ultimately, this improves the fault diagnosis performance.

Although an injection molding is a promising method for inexpensive mass production of nanograting substrate for disposable guided mode resonance (GMR) protein sensor, the incomplete filling of nanocavities due to the thick solidified layer in conventional injection molding process may lower the sensitivity of label-free GMR protein sensor. In this study, an instant heating method at the filling stage during the injection molding process was investigated to improve the pattern transcribability of molded nanograting and the sensitivity of fabricated GMR protein sensor. Two types of injection molded nanograting with and without instant heating method were prepared and the effects of pattern fidelity on the performance of fabricated GMR protein sensor were analyzed by theoretical and experimental methods.