For planetary gear has the characteristics of small volume, light weight and large transmission ratio, it is widely used in high speed and high power mechanical system. Poor working conditions result in frequent failures of planetary gear. A method is proposed for diagnosing faults in planetary gear based on permutation entropy of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) Adaptive Neuro-fuzzy Inference System (ANFIS) in this paper. The original signal is decomposed into 6 intrinsic mode functions (IMF) and residual components by CEEMDAN. Since the IMF contains the main characteristic information of planetary gear faults, time complexity of IMFs are reflected by permutation entropies to quantify the fault features. The permutation entropies of each IMF component are defined as the input of ANFIS, and its parameters and membership functions are adaptively adjusted according to training samples. Finally, the fuzzy inference rules are determined, and the optimal ANFIS is obtained. The overall recognition rate of the test sample used for ANFIS is 90%, and the recognition rate of gear with one missing tooth is relatively high. The recognition rates of different fault gears based on the method can also achieve better results. Therefore, the proposed method can be applied to planetary gear fault diagnosis effectively.

Poor working environment leads to frequent failures of planetary gear trains. However, complex structure and variable transmission make the vibration signal strongly non-linear and non-stationary, which brings big problems to fault diagnosis. A method of planetary gear fault diagnosis via feature image extraction based on multi central frequencies and vibration signal frequency spectrum is proposed. The original vibration signal is decomposed by variational mode decomposition (VMD), and four components with narrow bands and independent central frequencies are decomposed. In order to retain the feature spectrum of the original vibration signal as far as possible, the corresponding feature bands are intercepted from the frequency spectrum of original vibration signal based on the central frequency of each component. Then, the feature images of fault signals are constructed as the inputs of the convolution neural network (CNN), and the parameters of the neural network are optimized by sample training. Finally, the optimized CNN is used to identify fault signals. The overall fault recognition rate is up to 98.75%. Compared with the feature bands extracted directly from the component spectrums, the extraction method of the feature bands proposed in this paper needs fewer iterations under the same network structure. The method of planetary gear fault diagnosis proposed in this paper is effective.

Considering the difficulty of selecting sensitive fault features in bearing health diagnosis, a fault diagnosis method based on complete center frequency distribution feature (CCFDF) is proposed. By making full use of the sensitivity of the center frequency to the signal spectrum distribution in variational mode decomposition (VMD) and extracting the complete distribution feature of the center frequency under different parameter combinations, CCFDF can effectively characterize the difference in bearing vibration signals under different health conditions and avoid the parameter setting problem in VMD. Finally, two groups of experimental data are used to verify the effectiveness of the method, and the recognition accuracy was 99% and 97%, respectively. Therefore, this method can effectively characterize the difference characteristics of different signals and achieve the final bearing fault diagnosis.

Various kinds of sensing data can be acquired for smart fault detection. Each signal source has spatial attributes and strong correlations exist between different data sources. However, most of the existing fault detection models are established in the vector domain, which would destroy the structure information embedded within multisource data. Besides, the nonideal data, especially strong-noise data and mislabeled data, will seriously affect the fault detection performance. Therefore, a matrix-form one-class model called robustness one-class support matrix machine (ROCSMM) is proposed for industrial gearbox fault detection under multisource nonideal data. ROCSMM extends the traditional one-class support vector machine to the matrix domain, which can retain the topological structure information of multisource data while improving the fault detection performance. Besides, an adaptive weight generation strategy is designed for ROCSMM according to the prior distribution of matrix samples. This strategy can eliminate the negative impact of nonideal data on ROCSMM to the greatest extent and improve the model's robustness. The experimental results indicate that the proposed model is superior to other cutting-edge models in the fault detection of industrial gearboxes.

As the supporting unit of rotating machinery, bearing can ensure efficient operation of the equipment. Therefore, it is very important to monitor the status of bearings accurately. A bearing fault diagnosis mothed based on Multipoint Optimal Minimum Local Mean Entropy Deconvolution Adjusted (MOMLMEDA) and Long Short-Term Memory (LSTM) is proposed. MOMLMEDA is an improved algorithm based on Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA). By setting the local kurtosis mean as a new selection criterion, it can effectively avoid the interference of false kurtosis caused by noise and improve the accuracy of optimal kurtosis position. The optimal filter designed by optimal kurtosis position has periodic and amplitude characteristics, which are used as the fault feature in this paper. However, this feature has temporal characteristics and cannot be used as input of general neural network directly. LSTM is selected as the classification network in this paper. It can effectively avoid the influence of the temporal problem existing in feature vectors. Accurate diagnosis of bearing faults is realized by training classification neural network with samples. The overall recognition rate is up to 93.50%.

Large electromechanical equipment typically operates under low-speed, heavy-duty conditions, significantly increasing the likelihood of bearing failures. The reduced speed diminishes the frequency of fault impacts per unit time, rendering them prone to being obscured within intricate vibration signals. To address this challenge, a novel fault weak feature extraction method is proposed for low-speed, heavy-duty operations. Initially, Improved Variational Modal Decomposition (IVMD) is employed to efficiently isolate the primary signal components from diverse signals and reconstruct them. Subsequently, a Stacking Autoencoder (SAE) is leveraged to extract higher-order features from each reconstructed signal spectrum, markedly enhancing the discriminative power between distinct signals. Lastly, Random Forest (RF) is utilized to establish a precise mapping between these higher-order features and fault category labels, enabling effective diagnosis of bearing health status. This integrated method effectively tackles the difficulties of weak fault feature extraction and classification under low-speed, heavy-duty conditions. Experimental data validates the method’s accuracy, achieving a remarkable 97% success rate.