Machine fault diagnosis with small sample based on variational information constrained generative adversarial network

In actual engineering scenarios, limited fault data leads to insufficient model training and over-fitting, which negatively affects the diagnostic performance of intelligent diagnostic models. To solve the problem, this paper proposes a variational information constrained generative adversarial network (VICGAN) for effective machine fault diagnosis. Firstly, by incorporating the encoder into the discriminator to map the deep features, an improved generative adversarial network with stronger data synthesis capability is established. Secondly, to promote the stable training of the model and guarantee better convergence, a variational information constraint technique is utilized, which constrains the input signals and deep features of the discriminator using the information bottleneck method. In addition, a representation matching module is added to impose restrictions on the generator, avoiding the mode collapse problem and boosting the sample diversity. Two rolling bearing datasets are utilized to verify the effectiveness and stability of the presented network, which demonstrates that the presented network has an admirable ability in processing fault diagnosis with few samples, and performs better than state-of-the-art approaches.     

Application of higher order spectral features and support vector machines for bearing faults classification

Condition monitoring and fault diagnosis of rolling element bearings timely and accurately are very important to ensure the reliability of rotating machinery. This paper presents a novel pattern classification approach for bearings diagnostics, which combines the higher order spectra analysis features and support vector machine classifier. The use of non-linear features motivated by the higher order spectra has been reported to be a promising approach to analyze the non-linear and non-Gaussian characteristics of the mechanical vibration signals. The vibration bi-spectrum (third order spectrum) patterns are extracted as the feature vectors presenting different bearing faults. The extracted bi-spectrum features are subjected to principal component analysis for dimensionality reduction. These principal components were fed to support vector machine to distinguish four kinds of bearing faults covering different levels of severity for each fault type, which were measured in the experimental test bench running under different working conditions. In order to find the optimal parameters for the multi-class support vector machine model, a grid-search method in combination with 10-fold cross-validation has been used. Based on the correct classification of bearing patterns in the test set, in each fold the performance measures are computed. The average of these performance measures is computed to report the overall performance of the support vector machine classifier. In addition, in fault detection problems, the performance of a detection algorithm usually depends on the trade-off between robustness and sensitivity. The sensitivity and robustness of the proposed method are explored by running a series of experiments. A receiver operating characteristic (ROC) curve made the results more convincing. The results indicated that the proposed method can reliably identify different fault patterns of rolling element bearings based on vibration signals.     

Modelling dislocation assisted tempering during rolling contact fatigue in bearing steels

Rolling contact fatigue in bearing steels is manifested by dark-etching regions, which are attributed to deformation induced tempering. In order to quantitatively explain this phenomenon, a model is suggested for martensite tempering assisted by dislocation glide during rolling contact fatigue. In the model, dislocations transport carbon from the matrix to carbide particles, provided that the carbon is located at a certain distance range from the dislocation contributing to the tempering process. By calculating the amount of carbon in the matrix, the kinetics of carbide thickening and hardness reduction are computed. It is found that the dark-etching region kinetics can be controlled by both bearing operation conditions (temperature and deformation rate) and microstructure (type, size, and volume fraction of carbides). The model is validated against tested bearings, and its limitations are discussed.     

On the thermally-induced seizure in bearings: A review

This paper presents a state-of-the-art survey of papers reported on the nature of a troublesome failure mode in bearings known as seizure. This mode of failure is thermally-induced and it occurs in both journal and rolling element bearings. To gain insight, particular attention is given to reported experimental observation, various mechanisms involved, and available prediction methodologies.     

攀钢1450热轧带钢厂精轧机组电动压下机构带钢压下时的动特性计算和探讨

从理论上和实践上对武钢１７００、鞍钢１７００改造前后、本钢１７００改造前后和攀钢１４５０精轧机组的电动压下机构在带钢压下时的动特性进行计算和探讨，得出有说服力的结论。主题词：     

中厚板轧制边部不均匀变形机理的探讨

通过分析宽中厚板轧制过程中的边部不均匀变形，探讨了其影响因素及大宽度板“切边纵裂”的产生原因，提出了解决问题的具体办法。     

Behaviors of concrete-filled steel tubular members subjected to combined loading

The present study is an investigation on the behaviors of concrete-filled thin-walled steel tubular members subjected to combined loading, such as compression and torsion, bending and torsion, compression, bending and torsion. ABAQUS software is used in this paper for the finite element analysis (FEA). A comparison of results calculated using this modeling shows generally good agreement with test results. The FEA modeling is then used to investigate the influence of important parameters that determine the ultimate strength of the composite members under combined loading, such as compression and torsion, bending and torsion, compression, bending and torsion. The parametric studies provide information for the development of formulae for calculating the ultimate strength of the composite members subjected to combined loading.     

一种新型的转炉炉底车

本文介绍了一种作业效率高、省时省力新型的转炉炉底车，其特点是转盘转动灵活，炉底车上项盘径向任意方向均能平稳倾斜一定角度，以保证炉底圆周所受项力均匀可靠，满足炉底安装要求。     

Evaluation of Laminated Circular Elastomeric Bearings

This paper evaluates the behavior and performance of laminated circular elastomeric bearings and compares them to those of square and rectangular bearings. The study included an experimental evaluation and a nationwide survey of state Department of Transportations on the use and performance of circular bearings and bearings in general in their states. The experimental investigation studied the bearings' behavior in compression, compression and rotation, and compression and shear. Results from this limited study showed that the three bearings have similar stress-strain behavior in compression and they are in agreement with the AASHTO LRFD guide stress–strain curves. In compression and rotation, the AASHTO LRFD substructure moments are slightly less than the measured values for circular bearings and rectangular bearings rotated about their strong axis for a compressive stress of 10.3?MPa (1.5?ksi) and slightly higher than those of rectangular bearings rotated about their weak axis. In compression and shear, the shear stiffness of circular and square bearings is in agreement with theoretical values within the range of design displacements. Results from the survey showed that many states are using circular bearings and more states would consider using them, however no maintenance or monitoring data were available on their short-term and long-term performance.     

GCr15轴承钢的热变形模拟试验研究

利用先进的Gleeble-2000热模拟试验机，对GCr15轴承钢某一轧制过程进行模拟试验，测定出GCr15轴承钢动态CCT曲线，并结合微观组织分析，制定合理的GCr15轴承钢轧后控制冷却工艺，以期达到提高GCr15轴承钢质量的最终目的。