In engineering applications, the effectiveness of rotating machinery fault diagnosis is often disturbed by both vibration noise and labeling noise. Vibration noise makes it more difficult for the model to extract a potential fault impact feature, while labeling noise makes the feature extraction go in the wrong direction through error backpropagation. Both of these factors lead to a decrease in fault diagnosis accuracy. Hence, an adaptive symmetric loss in dynamic wide-kernel ResNet (AS-DWResNet) is proposed to solve the rotating machinery fault diagnosis under noisy labels. Firstly, wider convolution kernels are designed for branch convolution to enhance the extraction of vibration features. Secondly, a parallel network structure is constructed to fully and accurately extract the fault features by dynamically weighting different branches to improve the basic diagnostic performance of the network in the background of vibration noise. Thirdly, an improved adaptive symmetric cross-entropy (ASCE) loss function is adapted to reduce the effect of label noise in training datasets and hyperparameters in loss functions. The experimental results show that in the background of vibration noise and severe noisy labels, the proposed method still keeps more than 99.08% accuracy and has stronger noise robustness and stability than other networks and loss functions.

In recent years, supervised deep learning methods have proven to be feasible and advanced for fault diagnosis. They do, however, rely on large amounts of accurately labeled data. It is challenging to accurately label incipient or secondary fault signals in the presence of operational background noise, resulting in noisy labels. This study presents a bidirectional guidance method that enables deep networks to diagnose faults robustly with the ability to label noise tolerance. First, the proposed method uses discrete wavelet packet transform to preprocess vibration signals before feeding them into the deep convolutional network. Second, a bidirectional loss function is proposed to significantly improve the robustness of the model in the case of noisy labels. Third, a fast cosine decay strategy of the learning rate is designed to further boost the recognition performance of the model under severe noisy labels. The proposed method is applied to testbed experiments and wind turbines fault diagnosis. The experimental results demonstrate that it outperforms other cutting-edge methods in fault diagnosis with severely noisy labels.

Purpose: Many users build personal projects in co-innovation community to accomplish their innovations. However, very few projects from such communities are successful and understanding of this phenomenon is limited. The purpose of this paper is to identify the factors facilitating user projects success in online co-innovation communities. Design/methodology/approach: Based on the theories of persuasion and diffusion of innovation (DOI), a conceptual model is proposed to explain how project success likelihood is affected by the creator, project and user participation characteristics. Then, the model and hypotheses are tested through binary logistic regression on a secondary data set of 572 projects collected from a typical user co-innovation community, Local Motors. Findings: The results show that creator characteristics (prior success rate), project characteristics (project popularity, length and duration) and user participation characteristics (participation users and degree) have significant and positive impacts on project success likelihood. The number of prior projects, which can hardly represent the creator’s credibility in open and unrestricted situations, has no significant influence on the project success likelihood. Practical implications: This study offers project creators the keys to increase their projects successful possibility. Besides, this study recommends a new way to attract users and helps to identify creative and effective users for community practitioners. Originality/value: This study expands the research scope in online co-innovation community by focusing on user personal projects. In addition, it combines persuasion theory and DOI theory to add the holistic understanding of user project success likelihood.

It is crucial to recognize unknown faults for the intelligent fault diagnosis of bogie mechanical transmission components. This is essential to ensure the safety of trains in long-term service. However, the unknown faults are hardly represented accurately because of the influence of vibration signals multipath propagation. This results in a challenge to efficiently construct open-set decision boundaries (OSDB). An open-set fault diagnosis (OSFD) method based on multichannel feature-enhanced placeholder learning is proposed to improve diagnostic reliability. It utilizes the multichannel vibration signals collected by sensors located at different positions to construct a placeholder learning network based on the association of multichannel features. It can effectively improve the association of unknown class presentations and boost the effect of unknown fault identification. Besides, the placeholder learning network based on dummy classifier enhancement is proposed to strengthen the representations of known classes and ensure the generalization of OSDB. The proposed approach is validated with case studies constructed by high-speed train bogie fault datasets and the data challenge public datasets of PHM-Beijing 2024. The results demonstrate that the proposed method can enhance the effectiveness of OSFD.

Accurate fault diagnosis of bogie bearings is beneficial for ensuring safe operation of railway trains. With the development of detection technology and optimization of maintenance strategies, increasingly detailed undetected or previously ignored faults are being found. However, most of the existing fault diagnosis methods are based on the closed-set hypothesis and fewer consider the occurrence of unknown faults in the future. The features of these unknown faults may overlap with the distribution of known faults, which inevitably affects the judgment of the model. This study proposes an open-set diagnosis method for unknown bogie bearing faults by a hybrid open score relation network (HOSRN). First, an auxiliary feature module is added based on the relation network framework, and the prototype centre cross-entropy loss is introduced to enhance the feature extraction capability of the module. Second, a hybrid open score is constructed, based on the outputs of the modules, to simulate the distribution of known and unknown samples. Third, the open score of the training set is used to establish an adaptive threshold, which is used as the criterion for rejecting the unknown samples. Finally, the effectiveness of the proposed method is validated in three rolling bearing datasets, and the results show that the proposed method outperforms the comparison open-set diagnosis method.