Nowadays, the measurement technology of multichannel information fusion provides a solid research foundation for digital and intelligent fault diagnosis of mechatronics equipment. To implement the rapid fusion of multi-channel data and intelligent diagnosis, a new fault diagnosis method for multichannel motor-rotor system via Multi-manifold Deep Extreme Learning Machine (MDELM) algorithm is firstly proposed in this paper. Specifically, the designed MDELM algorithm is divided into two main components: i). unsupervised self-taught feature extraction via the designed Extreme Learning Machine based-Modified Sparse Filtering (ELM-MSF) feature extractor; ii). semi-supervised fault classification via the designed Multimanifold Extreme Learning Machine (MELM) classifier with multi-manifold constraints to mine the intra-class and inter-class discriminant feature information. Experimental and industrial data from motor-rotor system demonstrates the superiority of the proposed method and algorithms. Compared with other fault diagnosis methods, the designed MDELM algorithm has better learning efficiency, and it is more suitable for intelligent diagnosis of multi-channel data fusion.

Remaining useful life (RUL) prediction, allowing for mechanical predictive maintenance, reduces unplanned and expensive maintenance greatly. One of the great challenges of data-driven RUL prediction is to extract the features that describe the actual degradation process. This paper presents a health indicator (HI) construction method based on a sparse auto-encoder with regularization (SAEwR) model for rolling bearings. This paper includes two modules, HI construction and RUL prediction. In the stage of the HI construction, the original features are compressed and extracted by the SAEwR model. The extracted features are sorted according to the trendability, and the features with large trendability are selected to construct the HI by using minimum quantization error. In the module of RUL prediction, the maximum likelihood estimation method is used to estimate the parameters of the prediction model, and a particle filter-based RUL prediction with degradation model is proposed. The proposed method is benchmarked with variational auto-encoder, auto-encoder methods and principal component analysis. The data from PRONOSTIA and ABLT-1A platform support the value of our approach.

Intelligent diagnosis of mechanical faults is an important means to guarantee the safe maintenance of equipment. Cross domain diagnosis may lack sufficient measurement data as support, and this bottleneck is particularly prominent in high-end manufacturing. This paper presents a few-shot fault diagnosis methodology based on meta transfer learning for gearbox. To be specific, firstly, the subtasks for transfer diagnosis are constructed, and then joint distribution adaptation is conducted to align the two domain distributions; secondly, through adaptive manifold regularization, the data of target working condition is further utilized to explore the potential geometric structure of the data distribution. Meta stochastic gradient descent is explored to dynamically adjust the model’s parameter based on the obtained task information to obtain better generalization performance, ultimately to achieve transfer diagnosis of gearbox faults with few samples. The effectiveness of the approach is supported by the experimental datasets of the gearbox.

Intelligent mechanical fault diagnosis is a crucial measure to ensure the safe operation of equipment. To address the issue of model collapse in domain adversarial training and the problem posed by different training samples having different transferability not considered in transfer tasks, this article proposes a weighted entropy minimization based deep conditional adversarial diagnosis approach of rotating machines under variable working conditions. First, the features of vibration signals in the source domain and target domain are extracted by a weight-sharing one-dimensional deep convolution neural network. The feature vectors and category prediction vectors are then fused by multilinear mapping to carry out adversarial training in domain adaptation. The entropy of the output of the domain discrimination model provides the index by which to measure the transferability of training samples. The transferability weights of samples are applied to the entropy minimization loss to eliminate the influence of these samples that are hard to transfer in adversarial domain adaptation. Experimental datasets under variable working conditions support the value of our approach.

The gearbox of large-scale mechanical equipment operates under complex working conditions, and its operation and maintenance are crucial to ensure safe production. This paper proposes a fault diagnosis method for gearboxes under variable operating conditions with few-shot data to address the scarcity of data for specific fault types. Firstly, several fault diagnosis tasks are constructed under variable operating conditions. These deep features of different tasks are extracted by a deep convolutional neural network. In the training process, the model adaptively adjusts its parameters and inner loop learning rate, enabling it to acquire domain invariant features. The Batch Spectral Shrinkage is presented to reduce the impact of negative transfer and catastrophic forgetting on model optimization during knowledge transfer. The loss function is reconstructed using the weight balance strategy to mitigate the distribution discrepancy between the source and target domains. Consequently, the Meta-SGD transfer neural network framework enables a fault diagnosis model for gearboxes under variable operating conditions with few-shot data. The experimental datasets of the gearbox verify the effectiveness of the proposed fault diagnosis framework.