Search

Gearboxes operate in challenging environments, which leads to a heightened incidence of failures, and ambient noise further compromises the accuracy of fault diagnosis. To address this issue, we introduce a fault diagnosis method that employs singular value decomposition (SVD) and graph Fourier transform (GFT). Singular values, commonly employed in feature extraction and fault diagnosis, effectively encapsulate various fault states of mechanical equipment. However, prior methods neglect the inter-relationships among singular values, resulting in the loss of subtle fault information concealed within. To precisely and effectively extract subtle fault information from gear vibration signals, this study incorporates graph signal processing (GSP) technology. Following SVD of the original vibration signal, the method constructs a graph signal using singular values as inputs, enabling the capture of topological relationships among these values and the extraction of concealed fault information. Subsequently, the graph signal undergoes a transformation via GFT, facilitating the extraction of fault features from the graph spectral domain. Ultimately, by assessing the Mahalanobis distance between training and testing samples, distinct defect states are discerned and diagnosed. Experimental results on bearing and gear faults demonstrate that the proposed method exhibits enhanced robustness to noise, enabling accurate and effective diagnosis of gearbox faults in environments with substantial noise.

Gearboxes are utilized in practically all complicated machinery equipment because they have great transmission accuracy and load capacities, so their failure frequently results in significant financial losses. The classification of high-dimensional data remains a difficult topic despite the fact that numerous data-driven intelligent diagnosis approaches have been suggested and employed for compound fault diagnosis in recent years with successful outcomes. In order to achieve the best diagnostic performance as the ultimate objective, a feature selection and fault decoupling framework is proposed in this paper. That is based on multi-label K-nearest neighbors (ML-kNN) as classifiers and can automatically determine the optimal subset from the original high-dimensional feature set. The proposed feature selection method is a hybrid framework that can be divided into three stages. The Fisher score, information gain, and Pearson’s correlation coefficient are three filter models that are used in the first stage to pre-rank candidate features. In the second stage, a weighting scheme based on the weighted average method is proposed to fuse the pre-ranking results obtained in the first stage and optimize the weights using a genetic algorithm to re-rank the features. The optimal subset is automatically and iteratively found in the third stage using three heuristic strategies, including binary search, sequential forward search, and sequential backward search. The method takes into account the consideration of feature irrelevance, redundancy and inter-feature interaction in the selection process, and the selected optimal subsets have better diagnostic performance. In two gearbox compound fault datasets, ML-kNN performs exceptionally well using the optimal subset with subset accuracy of 96.22% and 100%. The experimental findings demonstrate the effectiveness of the proposed method in predicting various labels for compound fault samples to identify and decouple compound faults. The proposed method performs better in terms of classification accuracy and optimal subset dimensionality when compared to other existing methods.

Gearboxes are one of the most widely used speed and power transfer elements in rotating machinery. Highly accurate compound fault diagnosis of gearboxes is of great significance for the safe and reliable operation of rotating machinery systems. However, traditional compound fault diagnosis methods treat compound faults as an independent fault mode in the diagnosis process and cannot decouple them into multiple single faults. To address this problem, this paper proposes a gearbox compound fault diagnosis method. First, a multiscale convolutional neural network (MSCNN) is used as a feature learning model, which can effectively mine the compound fault information from vibration signals. Then, an improved hybrid attention module, named the channel–space attention module (CSAM), is proposed. It is embedded into the MSCNN to assign weights to multiscale features for enhancing the feature differentiation processing ability of the MSCNN. The new neural network is named CSAM-MSCNN. Finally, a multilabel classifier is used to output single or multiple labels for recognizing single or compound faults. The effectiveness of the method was verified with two gearbox datasets. The results show that the method possesses higher accuracy and stability than other models for gearbox compound fault diagnosis.

This paper established the system dynamics model for two kinds of tooth cracks of different depths of the sun gear and inner gear ring to study the influence mechanism of crack failure on the tooth root strain of the planetary gear transmission system. Combined with the finite element model of the inner gear ring, the tooth root strain of the ring was solved. Experiments verified the correctness of the solution method. The root strain under the crack fault of the sun gear and the tooth crack fault of the inner gear ring is analyzed, and the following conclusions are drawn: Periodic fault impact occurs in the strain signal of the tooth root of the inner gear ring during the crack fault of the sun gear root. The fault can be extracted by the fast spectral kurtosis method (FSK), and the fault components are used to determine whether the sun gear cracks. The Lempel–Ziv index showed a tendency to increase gradually during the process of solar wheel crack deepening, which could be used as the damage index of crack depth. The results can provide a basis and reference for fault diagnosis.

The technique for target detection based on a convolutional neural network has been widely implemented in the industry. However, the detection accuracy of X-ray images in security screening scenarios still requires improvement. This paper proposes a coupled multi-scale feature extraction and multi-scale attention architecture. We integrate this architecture into the Single Shot MultiBox Detector (SSD) algorithm and find that it can significantly improve the effectiveness of target detection. Firstly, ResNet is used as the backbone network to replace the original VGG network to improve the feature extraction capability of the convolutional neural network for images. Secondly, a multi-scale feature extraction (MSE) structure is designed to enrich the information contained in the multi-stage prediction feature layer. Finally, the multi-scale attention architecture (MSA) is fused onto the prediction feature layer to eliminate the redundant features’ interference and extract effective contextual information. In addition, a combination of Adaptive-NMS and Soft-NMS is used to output the final prediction anchor boxes when performing non-maximum suppression. The results of the experiments show that the improved method improves the mean average precision (mAP) value by 7.4% compared to the original approach. New modules make detection much more accurate while keeping the detection speed the same.

Wind turbines usually operate in harsh environments. The gearbox, the key component of the transmission chain in wind turbines, can easily be affected by multiple factors during the operation process and develop compound faults. Different types of faults can occur, coupled with each other and staggered interference. Thus, a challenge is to extract the fault characteristics from the composite fault signal to improve the reliability and the accuracy of compound fault diagnosis. To address the above problems, we propose a compound fault diagnosis method for wind turbine gearboxes based on multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) and parallel parameter optimized resonant sparse decomposition (RSSD). Firstly, the MOMEDA is applied to the preprocess, setting the deconvolution period with different fault frequency types to eliminate the interference of the transmission path and environmental noise, while decoupling and separating the different types of single faults. Then, the RSSD method with parallel parameter optimization is applied for decomposing the preprocessed signal to obtain the low resonance components, further suppressing the interference components and enhancing the periodic fault characteristics. Finally, envelope demodulation of the enhanced signal is applied to extract the fault features and identify the different fault types. The effectiveness of the proposed method was verified using the actual data from the wind turbine gearbox. In addition, a comparison with some existing methods demonstrates the superiority of this method for decoupling composite fault characteristics.

Further processing and the added value of potatoes are limited by irregular potatoes. An ellipse-fitting-based Hausdorff distance and intersection over union (IoU) method for identifying irregular potatoes is proposed to solve the problem. First, the acquired potato image is resized, translated, segmented, and filtered to obtain the potato contour information. Secondly, a least-squares fitting method fits the extracted contour to an ellipse. Then, the similarity between the irregular potato contour and the fitted ellipse is characterized using the perimeter ratio, area ratio, Hausdorff distance, and IoU. Next, the characterization ability of the four features is analyzed, and an identification standard of irregular potatoes is established. Finally, we discuss the algorithm’s shortcomings in this paper and draw the advantages of the algorithm by comparison. The experimental results showed that the characterization ability of perimeter ratio and area ratio was inferior to that of Hausdorff distance and IoU, and using Hausdorff distance and IoU as feature parameters can effectively identify irregular potatoes. Using Hausdorff distance separately as a feature parameter, the algorithm achieved excellent performance, with precision, recall, and F1 scores reaching 0.9423, 0.98, and 0.9608, respectively. Using IoU separately as a feature parameter, the algorithm achieved a higher overall recognition rate, with precision, recall, and F1 scores of 1, 0.96, and 0.9796, respectively. Compared with existing studies, the proposed algorithm identifies irregular potatoes using only one feature, avoiding the complexity of high-dimensional features and significantly reducing the computing effort. Moreover, simple threshold segmentation does not require data training and saves algorithm execution time.