An Intelligent Machinery Fault Diagnosis Method Based on GAN and Transfer Learning under Variable Working Conditions.

Intelligent fault diagnosis is of great significance to guarantee the safe operation of mechanical equipment. However, the widely used diagnosis models rely on sufficient independent and homogeneously distributed monitoring data to train the model. In practice, the available data of mechanical equipment faults are insufficient and the data distribution varies greatly under different working conditions, which leads to the low accuracy of the trained diagnostic model and restricts it, making it difficult to apply to other working conditions. To address these problems, a novel fault diagnosis method combining a generative adversarial network and transfer learning is proposed in this paper. Dummy samples with similar fault characteristics to the actual engineering monitoring data are generated by the generative adversarial network to expand the dataset. The transfer fault characteristics of monitoring data under different working conditions are extracted by a deep residual network. Domain-adapted regular term constraints are formulated to the training process of the deep residual network to form a deep transfer fault diagnosis model. The bearing fault data are used as the original dataset to validate the effectiveness of the proposed method. The experimental results show that the proposed method can reduce the influence of insufficient original monitoring data and enable the migration of fault diagnosis knowledge under different working conditions.

Evaluate the Fatigue Life of CFRC Subjected to Coupled Thermo-Mechanical Loading.

Mechanical properties of composites manufactured by high-temperature polymer polyether ether ketone (PEEK) with continuous reinforced fibers are closely dependent on ambient temperature variations. In order to effectively study fatigue failure behaviors of composites under the coupled thermo-mechanical loading, a well-established microscopic model based on a representative volume element (RVE) is proposed in this paper. Stiffness degradation behaviors of the composite laminates at room and elevated temperatures are firstly investigated, and their failure strengths are compared with experimental data. To describe the fatigue behaviors of composites with respect to complex external loading and ambient temperature variations, a new fatigue equation is proposed. A good consistency between theoretical results and experimental data was found in the cases. On this basis, the temperature cycling effects on the service life of composites are also discussed. Microscopic stress distributions of the RVE are also discussed to reveal their fatigue failure mechanisms.

O2O Method for Fast 2D Shape Retrieval.

A novel post-processing method, online to offline (O2O), to improve the efficiency of shape retrieval is proposed in this paper. The essence of this proposed method is to move more work that requires a lot of computation to offline. Based on this approach, the O2O rerank the retrieval result online with the help of the offline analysis. The result of offline analysis can be reused indefinitely, regardless of the query shape, as long as the database is unchanged. Therefore, O2O is very efficient and suitable for real-time applications. We evaluated our method for shape retrieval and recognition on five databases including MPEG-7 CE-1 Part B, Tari 1000, Animals, Kimia 99, and Swedish Plant Leaf. Our experimental results show that as a post-processing algorithm, O2O provides highly efficient and effective shape retrieval.

Sparsity-based signal extraction using dual Q-factors for gearbox fault detection.

Early detection of faults developed in gearboxes is of great importance to prevent catastrophic accidents. In this paper, a sparsity-based feature extraction method using the tunable Q-factor wavelet transform with dual Q-factors is proposed for gearbox fault detection. Specifically, the proposed method addresses the problem of simultaneously extracting periodic transients and high-resonance component from noisy data for the gearboxes fault detection purpose. Firstly, a sparse optimization problem is formulated to jointly estimate the useful components from the noisy observation. In order to promote wavelet sparsity, non-convex regularizations are employed in the cost function of the optimization problem. Then, a fast converging, computationally efficient iterative algorithm which termed SpaEdualQA (the sparsity-based signal extraction algorithm using dual Q-factors) is developed to solve the formulated optimization problem. The derivation of the proposed fast algorithm combines the split augmented Lagrangian shrinkage algorithm (SALSA) with majorization-minimization (MM). Finally, the effectiveness of the proposed SpaEdualQA is validated by analyzing numerical signals and real data collected from engineering fields. The results demonstrated that the proposed SpaEdualQA can effectively extract periodic transients and high-resonance component from noisy vibration signals.

An Intelligent Gear Fault Diagnosis Methodology Using a Complex Wavelet Enhanced Convolutional Neural Network.

As a typical example of large and complex mechanical systems, rotating machinery is prone to diversified sorts of mechanical faults. Among these faults, one of the prominent causes of malfunction is generated in gear transmission chains. Although they can be collected via vibration signals, the fault signatures are always submerged in overwhelming interfering contents. Therefore, identifying the critical fault's characteristic signal is far from an easy task. In order to improve the recognition accuracy of a fault's characteristic signal, a novel intelligent fault diagnosis method is presented. In this method, a dual-tree complex wavelet transform (DTCWT) is employed to acquire the multiscale signal's features. In addition, a convolutional neural network (CNN) approach is utilized to automatically recognise a fault feature from the multiscale signal features. The experiment results of the recognition for gear faults show the feasibility and effectiveness of the proposed method, especially in the gear's weak fault features.

Health State Monitoring of Bladed Machinery with Crack Growth Detection in BFG Power Plant Using an Active Frequency Shift Spectral Correction Method.

Power generation using waste-gas is an effective and green way to reduce the emission of the harmful blast furnace gas (BFG) in pig-iron producing industry. Condition monitoring of mechanical structures in the BFG power plant is of vital importance to guarantee their safety and efficient operations. In this paper, we describe the detection of crack growth of bladed machinery in the BFG power plant via vibration measurement combined with an enhanced spectral correction technique. This technique enables high-precision identification of amplitude, frequency, and phase information (the harmonic information) belonging to deterministic harmonic components within the vibration signals. Rather than deriving all harmonic information using neighboring spectral bins in the fast Fourier transform spectrum, this proposed active frequency shift spectral correction method makes use of some interpolated Fourier spectral bins and has a better noise-resisting capacity. We demonstrate that the identified harmonic information via the proposed method is of suppressed numerical error when the same level of noises is presented in the vibration signal, even in comparison with a Hanning-window-based correction method. With the proposed method, we investigated vibration signals collected from a centrifugal compressor. Spectral information of harmonic tones, related to the fundamental working frequency of the centrifugal compressor, is corrected. The extracted spectral information indicates the ongoing development of an impeller blade crack that occurred in the centrifugal compressor. This method proves to be a promising alternative to identify blade cracks at early stages.