Three-stage feature fusion method for fault diagnosis of rotating machinery based on multimodal data

Abstract

The present disclosure provides a three-stage feature fusion rotating machinery fault diagnosis method based on multi-modal data, obtains machine operating state parameter data, and obtains data of at least two modalities; the acquired modal data is respectively input into a preset In the neural network model, the final fault classification result is obtained; wherein, the preset neural network model includes at least three stages of first self-feature fusion, mutual feature fusion and second self-feature fusion in sequence; the present disclosure adopts one-dimensional convolutional neural network. The three-stage feature fusion method, including the network and the two-dimensional convolutional neural network, fuses multi-scale features and performs fault diagnosis. The two-dimensional convolutional neural network extracts the correlation between the feature maps, and the attention mechanism can The feature maps carry out different weight assignments, highlight important information, reduce redundant information, and greatly improve the performance of fault diagnosis.

Description

technical field [0001] The present disclosure relates to the technical field of mechanical fault diagnosis, in particular to a three-stage feature fusion method for fault diagnosis of rotating machinery based on multimodal data. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] With the continuous development of intelligent manufacturing, industrial systems are becoming more and more complex and non-linear, and the losses caused by equipment damage are also increasing. Early fault detection can not only eliminate faults before they cause huge economic losses, but also avoid major safety accidents. However, due to the complexity and nonlinearity of industrial systems, it is difficult to build an accurate model. Due to the continuous development of information science and technology, industrial systems have produced a large amount of opera...

AI Technical Summary

Problems solved by technology

However, despite the success of these intelligent methods, there are still two disadvantages: (1) These intelligent fault diagnosis methods need to be combined with feature extraction methods, resulting in a strong dependence on feature selection

However, data-level fusion requires a highly consistent data structure, and in decision-level fusion, when each classifier has a large decision-making conflict, the final classification result will be very unstable

Images