A Fuzzy Fusion Rotating Machinery Fault Diagnosis Framework Based on the Enhancement Deep Convolutional Neural Networks

Some artificial intelligence algorithms have gained much attention in the rotating machinery fault diagnosis due to their robust nonlinear regression properties. In addition, existing deep learning algorithms are usually dependent on single signal features, which would lead to the loss of some information or incomplete use of the information in the signal. To address this problem, three kinds of popular signal processing methods, including Fast Fourier Transform (FFT), Short-Time Fourier Transform (STFT) and directly slicing one-dimensional data into the two-dimensional matrix, are used to create four different datasets from raw vibration signal as the input data of four enhancement Convolutional Neural Networks (CNN) models. Then, a fuzzy fusion strategy is used to fuse the output of four CNN models that could analyze the importance of each classifier and explore the interaction index between each classifier, which is different from conventional fusion strategies. To show the performance of the proposed model, an artificial fault bearing dataset and a real-world bearing dataset are used to test the feature extraction capability of the model. The good anti-noise and interpretation characteristics of the proposed method are demonstrated as well.

Fusion Domain-Adaptation CNN Driven by Images and Vibration Signals for Fault Diagnosis of Gearbox Cross-Working Conditions

The vibration signal of gearboxes contains abundant fault information, which can be used for condition monitoring. However, vibration signal is ineffective for some non-structural failures. In order to resolve this dilemma, infrared thermal images are introduced to combine with vibration signals via fusion domain-adaptation convolutional neural network (FDACNN), which can diagnose both structural and non-structural failures under various working conditions. First, the measured raw signals are converted into frequency and squared envelope spectrum to characterize the health states of the gearbox. Second, the sequences of the frequency and squared envelope spectrum are arranged into two-dimensional format, which are combined with infrared thermal images to form fusion data. Finally, the adversarial network is introduced to realize the state recognition of structural and non-structural faults in the unlabeled target domain. An experiment of gearbox test rigs was used for effectiveness validation by measuring both vibration and infrared thermal images. The results suggest that the proposed FDACNN method performs best in cross-domain fault diagnosis of gearboxes via multi-source heterogeneous data compared with the other four methods.

Vibration Separation Methodology Compensated by Time-Varying Transfer Function for Fault Diagnosis of Non-Hunting Tooth Planetary Gearbox

Due to planetary movement of planet gears, the vibration signal perceived by a stationary sensor is modulated and difficult to diagnose. This paper proposed a vibration separation methodology compensated by a time-varying transfer function (TVTF-VS), which is a further development of the vibration separation (VS) method in the diagnosis of non-hunting tooth planetary gearboxes. On the basis of VS, multi-teeth VS is proposed to extract and synthesize the meshing signal of a planet gear using a single transducer. Considering the movement regularity of a planetary gearbox, the time-varying transfer function (TVTF) is represented by a generalized expression. The TVTF is constructed using a segment of healthy signal and an evaluation indicator is established to optimize the parameters of the TVTF. The constructed TVTF is applied to overcome the amplitude modulation effect and highlight fault characteristics. After that, experiments with baseline, pitting, and compound localized faults planet gears were conducted on a non-hunting tooth planetary gearbox test rig, respectively. The results demonstrate that incipient failure on a planet gear can be detected effectively, and relative location of the local faults can be determined accurately.

A hybrid deep-learning model for fault diagnosis of rolling bearings under strong noise environment

Aiming at the problem that the signal of rolling bearing is interfered by strong noise in practical engineering environment, which leads to the decline of the diagnosis accuracy of intelligent diagnosis model. This paper proposes a novel hybrid model (CDAE-BLCNN). First, the rolling bearing vibration signal containing noise was input into the Convolutional Denoising Auto-Encoder (CDAE), which denoises the signal through unsupervised learning, and then outputs the reconstructed data. Secondly, a hybrid neural network (BLCNN) composed of multi-scale wide convolution kernel block (MWCNN) and bidirectional long-short-term memory network (BiLSTM) was used to extract intrinsic fault features from the reconstructed signal and diagnose fault types. The analysis results demonstrate that the proposed hybrid deep learning model achieves higher detection accuracy even under different noise and various rotating speed. Compared with other models, there is a high fault recognition rate, robustness, and generalization ability, which may be favorable to practical applications.

A Characterization Method for Pavement Structural Condition Assessment based on the Distribution Parameter of the Vehicle Vibration Signal

A pavement structural survey plays a vital role in road maintenance and management. This study was intended to explore the feasibility of a non-stop pavement structure assessment method by analyzing the vibration data from a vehicle sensor. In this study, three falling weight deflectometer (FWD) tests and four vehicle vibration tests were conducted on five pavement structures. The FWD test results show that the continuously reinforced composite pavement has a higher structural stiffness than the semi-rigid base asphalt pavement. According to the statistical distribution of vehicle acceleration, a distribution parameter, the peak probability density (PPD), was proposed. The correlation coefficient (−0.722) of the center deflection (D1) and PPD indicates a strong correlation between the two variables. Therefore, PPD is strongly correlated with pavement structural stiffness. This study proposed a novel characterization method for pavement structural conditions based on the distribution parameter of the vehicle vibration signal.

Rolling Bearing Fault Diagnosis Based on Component Screening Vector Local Characteristic-Scale Decomposition

The fault vibration signal of a bearing has nonstationary and nonlinear characteristics and can be regarded as the combination of multiple amplitude- and frequency-modulation components. The envelope of a single component contains the fault characteristics of a bearing. Local characteristic-scale decomposition (LCD) can decompose the vibration signal into a series of multiple intrinsic scale components. Some components can clearly reflect the running state of a bearing, and fault diagnosis is conducted according to the envelope spectrum. However, the conventional LCD takes a single-channel signal as the research object, which cannot fully reflect the characteristic information of the rotor, and the analysis results based on different channel signals of the same section will be inconsistent. To solve this problem, based on full vector spectrum technology, the homologous dual-channel information is fused. A vector LCD method based on cross-correlation coefficient component selection is given, and a simulation analysis is completed. The effectiveness of the proposed method is verified by simulated signals and experimental signals of a bearing, which provides a method for bearing feature extraction and fault diagnosis.