Intelligent fault warning method of rotating machinery with intraclass and interclass infographic embedding

Abstract

Rotating machinery is widely used in industrial production facilities, and once a failure occurs, it can be catastrophic. Alerting to potential defects in time to prevent further equipment degradation is a challenging task. In this paper, a novel two-stage fault warning framework is proposed for early fault warning of rotating machinery. Specifically, a new method based on intra-class and inter-class neighborhood information graph embedding orthogonal discriminant projection (IINGEODP) is firstly adopted in this framework to extract the global distribution feature information and local geometric structure information of the data so that the homogeneous distance is compressed and the heterogeneous distance is distanced. Secondly, the minimum quantization error between the sample to be measured and the optimal winning neuron weight vector is calculated by self-organizingmap (SOM) to characterize the health state change, and combined with the Beta distribution self-learning technique to establish the fault warning threshold to circumvent the defects brought by the traditional fixation and it. Finally, the effectiveness of the proposed method is verified in the bearing and planetary gearbox test cases, and exciting conclusions are obtained under different working conditions in the gearbox case. Keywords: fault warning; feature extract; graph embedding; warning threshold

Fault detection of a reciprocating plunger pump with fault-free data based on an unsupervised feature encoder and minimum covariance determinant

“…Zhao and Zhang took the time-frequency image of the original signal as the input of the encoder and used parallel adversarial learning inference to train the encoder and decoder independently at the same time, so that the extracted features are similar to well-classified samples and the original signal is reconstructed [11]. Sun et al [19] conducted unsupervised training of a model based on the criterion of compressing homogeneous distance and distancing heterogeneous distance. Based on intra-class and inter-class neighborhood information graphs embedding orthogonal discriminant projection, the global distribution feature information and local geometric structure information of the data were extracted.…”

An interpretable RUL prediction method of aircraft engines under complex operating conditions using spatio-temporal features

“…Furthermore, adding an interpretability module, like the attention mechanism, has proven to be a highly effective way to improve the interpretability and accuracy of LSTM-based models in RUL prediction [12,13]. Some researchers have demonstrated that integrating attention with LSTM improves accuracy and interpretability, while also highlighting significant degradation aspects, which is crucial for improving RUL prediction performance [14][15][16].…”

Quantitative condition assessment method for rotating machinery using fuzzy neural network

“…Condition assessment includes evaluating mechanical operation, detecting anomalies, tracking degradation, and determining the degree of rotating machinery [9]. Faults in rotating machinery often start subtly and progress gradually over time [10]. Major accidents may occur if abnormalities are not detected in time.…”