Multi-faults diagnosis of rolling bearings via adaptive customization of flexible analytical wavelet bases

Multi-faults detection is a challenge for rolling bearings due to the mode mixture and coupling of multiple fault features, as well as its easy burying in the complex, non-stationary structural vibrations and strong background noises. In this paper, a method based on the flexible analytical wavelet transform (FAWT) possessing fractional scaling and translation factors is proposed to identify multiple faults occurred in different components of rolling bearings. During the route of the proposed method, the proper FAWT bases are constructed via genetic optimization algorithm (GA) based on maximizing the spectral correlated kurtosis (SCK) which is firstly presented and proved to be efficient and effective in indicating interested fault mode. Via using the customized FAWT bases for each interested fault mode, the original vibration measurements are decomposed into fine frequency subbands, and the sensitive subband which enhances the signal-to-noise ratio (SNR) is selected to exhibit the fault signature on its envelope spectrum. The proposed method is tested via simulated signals, and applied to analyze the experimental vibration measurements from the running roller bearings subjected to outrace, inner-race and roller defects. The analysis results validate the effectiveness of the proposed method in identifying multi-faults occurred in different components of rolling bearings.     

含缺陷固体发动机两相流场计算方法研究

通过对国内外含缺陷固体发动机性能预示方法的分析比较，提出采用“N－S方程＋粒子仿真”方法来计算两相流动的新途径，并对某轴对称两相流动的流场进行仿真计算，计算结果表明，该计算方法可行，计算模型合理，能够较为准确地反映两相流中颗粒相对气体流动的影响。     

杯杯型复合挤压两种宏观缺陷并存分析

 通过杯杯型轴对称复合挤压两种宏观缺陷并存的上限分析表达式,研究了该变形方式下两种宏观缺陷并存区域与正挤部分、反挤部分变形程度和坯料相对余厚的关系。本文的模型及结论被实验结果所证实。     

大厚度铝合金飞行器结构的焊接

介绍了采用熔化极脉冲氦弧焊工艺焊接大厚度铝合金燃料箱的优越性。     

根据遗传算法的拉深模试冲缺陷智能诊断

总结了拉深模试冲时的缺陷及原因，建立原因表，应用遗传算法技术对拉深模试冲时的缺陷进行智能诊断，探讨了提高拉深模试冲时的缺陷诊断准确率的优化方法，描述了遗传算法的诊断过程。     

超声爬波无损检测方法的研究

本文介绍了超声无损检测中一种具有较好应用前景的波型──超声爬波。试验研究了爬波检测时缺陷定位、定性评定的方法，并给出了主要结论。     

Effect of interface debonding on matrix multicracking evolution of fiber-reinfroced ceramic-matrix composites

An analytical methodology was developed to investigate the effect of fiber/matrix interface debonding on matrix multicracking evolution of fiber-reinforced CMCs(ceramic-matrix composites). The Budiansky-Hutchinson-Evans shear-lag model was adopted to analyse the micro-stress field of the damaged composites. The critical matrix strain energy criterion, which presupposes the existence of an ultimate or critical matrix strain energy with matrix, was obtained to simulate the matrix multicracking evolution of CMCs. With the increase of the applied stress, the matrix multicracking and fiber/matrix interface debonding occurred to dissipate the additional energy entered into the composites. The fiber/matrix interface debonded length under matrix multicracking evolution was obtained by treating the interface debonding as a particular crack propagation problem. The conditions for no-debonding and debonding during the evolution of matrix multicracking were discussed in terms of two interfacial properties, i.e., the interface shear stress and interface debonded toughness. When the fiber/matrix interface was bonded, the matrix multicracking evolution was much more intense compared with the interface debonding; when the fiber/matrix interface was debonded, the matrix crack density increased with the increasing of interface shear stress and interface debonded energy. The theoretical results were compared with experimental data of unidirectional SiC/CAS(calcium alumina silicate), SiC/CAS-Ⅱ and SiC/borosilicate composites.      

2219铝合金搅拌摩擦焊接头缺陷补焊

对2219铝合金搅拌摩擦焊接头中出现的未焊透和孔洞缺陷进行一次、二次搅拌摩擦补焊实验。结果表明：在合适的补焊工艺参数下,可有效消除接头原有缺陷,获得成形美观,性能良好的接头;随补焊次数的增加,接头软化区域显著增加;含有上述两种缺陷接头一次补焊后拉伸性能显著提高,二次补焊接头相比于一次补焊接头拉伸性能有所降低;含有缺陷的原始接头拉伸时均于缺陷处起裂导致接头塑性较低,补焊后接头都断裂于后退侧热影响区与热机影响区交界处,呈韧性断裂模式。     

基于改进深度学习模型的焊缝缺陷检测算法

针对传统深度学习模型在进行焊缝缺陷检测时对小缺陷目标检测效果不理想问题,提出基于改进深度学习Faster RCNN模型的焊缝缺陷检测算法,算法通过多层特征网络提取多尺度特征图并共同作用于模型后续环节,以充分利用模型中的低层特征,增加细节信息;改进模型的区域生成网络,加入多种滑动窗口,从而优化了模型锚点的长宽比设置,提高检测能力。实验表明,改进Faster RCNN模型取得最优的缺陷检测结果,对于小缺陷目标仍取得较好的检测精度,从而验证了算法的有效性。     

基于知识图谱和自动机器学习的软件缺陷预测

不稳定和召回率低效的软件缺陷预测模型难以在行业领域应用,为解决稳定和高效各项性能评价指标的软件缺陷预测模型在工程实践应用的问题,提出了一种基于知识图谱和自动化机器学习的软件缺陷预测方法AutoKGGAS,首先获取软件缺陷预测模型数据,对知识建模、知识获取、知识融合、知识储存与知识计算等知识图谱构建技术研究,实现知识图谱...