Search

The remaining useful life forecast (RUL) of rolling bearings, a crucial part of offshore equipment, is one of the most troublesome equipment because it may avoid equipment failure and lessen equipment failure loss. This paper proposes a method to build CNN-BIGRU bearing health indicators based on the SE attention mechanism, and combines primary linear regression to predict the RUL of bearings in order to address the issues of low accuracy and poor generalization performance in the current bearing RUL prediction. The proposed method combines the spatial feature extraction capability of convolutional neural networks with the temporal feature extraction capability of bidirectional gated recurrent units, allowing it to effectively use feature information from the spatial and temporal dimensions of vibration signals to improve prediction accuracy and stability. The suggested technique is validated in this research using experimental data from the 2012 IEEE PHM Challenge for the whole life cycle bearing. The experimental findings reveal that the approach can more accurately estimate the RUL of the bearing than the standard model, proving the usefulness and viability of the suggested method.

machinery fault diagnosis is an attractive but challenging task, especially for low-speed conditions. Therefore, a new discriminative approach that introduces robust principle component analysis (RPCA) and multi-kernel to deep neural networks is proposed to perform intelligent fault diagnosis. Firstly, RPCA is applied to extract fault signals from extreme background noise based on its sensitivity to grossly corrupted data. Secondly, two cascaded MKPCA stages with additional robustness to distortions in feature extraction are used to enhance the energy of spectrum symptom and overcome the tricky issues of low-speed machinery. Especially, the multi-kernel is introduced into the basic PCA filters to learn the data-adapting convolution filter and gain additional robustness to nonlinearity in the signal. Finally, the proposed method is demonstrated on signals from laboratory tests (with a slightly damaged defect in a bearing) and structural fault data, outperforming those of traditional machine learning and classical deep learning methods. Moreover, hidden information of the network is visualized to analyse the reasons for its high performance.

To realize an automatic diagnosis of rotating machinery structure faults, this paper presents a novel fault diagnosis model based on adaptive multiband filter and stacked autoencoders (SAEs). First, to solve the problem where the actual rotating frequency and its harmonics cannot be accurately extracted in engineering applications, an improved adaptive multiband filtering method is designed. This method takes the theoretical rotating frequency as the search center, extracts the maximum within the positive and negative deviation as the actual rotating frequency, and sets a threshold according to the actual value to realize multiband filtering. This method can effectively remove background noise and accurately extract the actual rotating frequency and its harmonics. Second, an unsupervised SAE multiclassification model is established to realize an automatic diagnosis of fault types. This model can automatically extract the in-depth features of the filtered signal and improve the fault classification accuracy. Third, engineering and comparative experiments were carried out to verify the effectiveness and superiority of this model. Results show that the proposed automatic diagnosis model can extract the characteristic components abundantly and accurately recognize rotating machinery structural faults.

Thermally conductive and electrically insulating h-BN/MVQ and h-BN/SiCw/MVQ composites were prepared by internal mixing and two roll mixing, using 1-dimensional (1D) silicon carbide whiskers (SiCw)...

Improvement of the food value of rice straw is urgently required in rice crop growing areas to mitigate pollution caused by rice straw burning and enhance the supply of high-quality forages for ruminants. The aims of the present study were to compare the effects of fresh corn Stover and rice straw co-fermented with probiotics and enzymes on rumen fermentation and establish the feasibility of increasing the rice straw content in ruminant diets and, by extension, reducing air pollution caused by burning rice straw. Twenty Simmental hybrid beef cattle were randomly allotted to two groups with ten cattle per group. They were fed diets based either on rice straw co-fermented with probiotics and enzymes or fresh corn Stover for 90 days. Rumen fluid was sampled with an esophageal tube vacuum pump device from each animal on the mornings of days 30, 60, and 90. Bacterial diversity was evaluated by sequencing the V4–V5 region of the 16S rRNA gene. Metabolomes were analyzed by gas chromatography/time-of-flight mass spectrometry (GC–TOF/MS). Compared to cattle fed fresh corn Stover, those fed rice straw co-fermented with probiotics and enzymes had higher (P P Ruminococcus, Saccharofermentans, Pseudobutyrivibrio, Treponema, Lachnoclostridium, and Ruminobacter, and higher (P 2-utilizing bacteria, and feed energy conversion efficiency in the rumen.

The fluctuation of decision parameters will deviate from the optimal decision, which will have significant impact on the optimization performance of chemical processes. To reduce optimization performance deterioration caused by fluctuation of decision parameters in chemical processes, a multi-objective robust optimization scheme is developed to assess performance robustness. In addition, based on the model that maps decision parameters to objective performance through neural network, a new robustness evaluation metric is created as the fitness value of the multi-objective evolutionary algorithm (for improving the strength Pareto evolutionary algorithm (SPEAII)) to elaborate the relationship between robustness and fluctuation. The efficacy of the proposed method is verified with HCN production process application by comparing with genetic algorithm (GA) and weighted single-objective robust optimization.

Since the raw signal collected from the sliding bearing is contaminated with background noise, and it is difficult to obtain high-precision results for the traditional methods due to the low signal-to-noise ratio (SNR). Therefore, a stepwise intelligent diagnosis method based on statistical filter and stacked auto-encoder (SAE) that is established with several auto-encoders is proposed to identify several faults of sliding bearing in a rotor system. Firstly, the statistical filter is utilized to reduce the interference information for the different abnormal states and to increase the SNR. Secondly, the stepwise intelligent diagnosis based on SAE is performed to learn the useful fault features, and it can automatically complete the fault diagnosis which is contributed with the superiority binary classification to fully mine the relationship between the fault characteristics and the health condition of bearing. Finally, the diagnosis of the oil whirl and structural faults in a rotor system is cited as an example to demonstrate the effectiveness of proposed method. It can effectively illustrate the advantages of the stepwise diagnosis method to obtain the maximum diagnostic accuracy.

In this paper, a 2D off-grid small compact model of vertical axis wind turbine was established. The sliding grid technology, the RNG turbulence model and the Coupld algorithm was applied to simulate the unsteady value of the model's aerodynamic performance. Through the analysis on the flow field at difference moments, the rules about velocity fields, vortices distributions and the wind turbine's total torque were obtained. The results show that: the speed around wind turbine blades have obvious gradient, and the velocity distribution at different times show large differences in the computional domain. In the rotating domain vorticity is large. With away from the rotation domain, vorticity reduced quickly. In the process of rotating for vertical axis wind turbine, the wind turbine's total torque showed alternating positive and negative changes.