Fault diagnosis of rolling bearings using a genetic algorithm optimized neural network

In rotary complex machines, collapse of a component may inexplicably occur usually accompanied by a noise or a disturbance emanating from other sources. Rolling bearings constitute a vital part in many rotational machines and the vibration generated by a faulty bearing easily affects the neighboring components. Continuous monitoring, fault diagnosis and predictive maintenance, is a crucial task to reduce the degree of damage and stopping time for a rotating machine. Analysis of fault-related vibration signal is a usual method for accurate diagnosis. Among the resonant demodulation techniques, a well-known resolution often used for fault diagnosis is envelope analysis. But, usually this method may not be adequate enough to indicate satisfactory results. It may require some auxiliary additional techniques. This study suggests some methods to extract features using envelope analysis accompanied by Hilbert Transform and Fast Fourier Transform. The proposed artificial neural network (ANN) based fault estimation algorithm was verified with experimental tests and promising results. Every test was initiated with a reference ANN architecture to avoid inappropriate classification during the evaluation of fitness value. Later, ANN model was modified using a genetic algorithm providing, an optimal skillful fast-reacting network architecture with improved classification results.     

特厚钢板的制造技术

为满足能源产业的各种大型装备对大单重特厚钢板的需求，重点从冶炼、铸造、轧制和热处理等方面，简要介绍了大单重特厚钢板的制造技术，供特厚钢板的制造者和使用者参考。     

Torque loss of type C40 FZG gears lubricated with wind turbine gear oils

Five fully formulated wind turbine gear oils were characterised. The gear oils have 320 ISO VG grade and different formulations: ester, mineral, PAO, PAG and mineral+PAMA.A back-to-back FZG test machine, with re-circulating power, was used and a torque-cell was included on the test rig in order to measure the torque loss. Eight thermocouples were included to monitor the temperatures in different locations of the test rig.Tests at 1.13, 2.26 and 6.79 m/s were performed for different FZG load stages: K1, K5, K7 and K9. Both gearboxes were jet-lubricated with an oil flow of 3 l/min. The input flow temperature was kept almost constant (80 ±1 °C).Friction generated between the meshing teeth, shaft seals and rolling bearing losses was predicted.     

碾压强化有限元建模及分析研究

碾压是强化金属表层的一种重要且很有发展潜力的强化方法,工件表层经碾压变形强化后会表层留有应力,能提高表层硬度和强度,同时还能改善工件表面粗糙度。对装备构件进行碾压模拟,模拟结果显示工件表层经碾压后产生较高应力且内部状态无明显变化,强化效果明显。接着改变下压量进行模拟,发现在一定范围内,随下压量增大,碾压强化效果愈好。     

农村民居防雷滚球半径合理性探析

针对农村民居的特点。分析其易遭受雷击的原因,提出应重视农村民居的防雷：推导农村民居防雷设计中的滚球半径的合理取值;建议在纬度45°以内地区小体量的建筑物防雷滚球半径可以参考使用75m。     

滚压加工工艺参数对粗糙度的影响分析

通过控制变量法,从实验的角度分析了滚压加工的主要工艺参数对滚压加工精度的影响,并从弹塑性力学的角度分析了加工机制。经过分析比较,指出在加工中过盈量对粗糙度的大小起着决定性作用。同时讨论了在过盈量一定时,进给量和滚压速度对粗糙度的影响。该研究为滚压加工的实际生产应用提供了有价值的参考。     

基于有限元和PSO-BP法的20辊轧机轧制板形预测

针对20辊轧机轧制板形受到多重因素影响、难以精确预测的问题,基于有限元和PSO-BP法,建立20辊轧机轧制板形质量预测模型。根据20辊轧机轧辊间的位置关系,基于有限元软件ANSYS/LS-DYNA,考虑轧辊弹性变形、板带塑性变形与摩擦等因素,建立20辊轧机辊系有限元模型,分析板宽、厚度、张力、速度等因素对板形指数的影响;综合考虑不同轧制板形影响因素,以板形指数作为板形质量衡量指标,基于BP神经网络建立轧制板形质量预测模型,采用粒子群算法优化BP神经网络板形质量预测模型的权值和阈值,提高板形预测精度。     

New Stress-Based Fatigue Life Models for Ball and Roller Bearings

New stress-based life models are introduced to define “dynamic stress capacity” in rolling bearings for the first time. The generalized stress capacity equations are formulated, for both point and line contacts, in terms of distinct geometrical and materials parameters while the empirical constants are now material independent. Life equations are first developed for individual rolling element to race contacts and then statistically combined to estimate lives of both races, rolling elements, and, finally, the whole bearings for both ball and roller bearings. An estimate of the empirical constant for the ball bearing equation is derived by regression analysis of available experimental data. The applicable constant for roller bearings is then derived by relating the ball and roller bearing constants to the fundamental subsurface fatigue hypothesis applicable to both point and line contacts. For AISI 52100 bearing steel at room temperature, life predictions with the new stress-based equations are in complete agreement with those currently provided by widely used load-based formulations, where the empirical constant contains the elastic properties of AISI 52100 bearing steel. In addition to these life equations based on the magnitude and depth of maximum orthogonal subsurface shear stress and the volume of material stressed, a new model that eliminates life dependence on the depth of maximum orthogonal shear stress and relates life to only the subsurface maximum shear stress and the stressed volume is presented. Though the predicted life estimates with the currently used and newly introduced life models are comparable in the contact stress range of 2 to 3 GPa, the new model provides significantly higher lives at low contact stresses.     

滚环DNA扩增技术及其应用

滚环扩增技术是一种等温信号扩增方法,DNA可在很短时间内实现指数扩增,因此,可用于痕量分子的检测.目前,该技术既可以扩增环状DNA、RNA,也可以扩增线性DNA,甚至全基因组DNA.目前,该技术主要用于全基因组扩增、核酸测序、单核苷酸多态性以及DNA芯片、蛋白质芯片分析等广泛领域.     

基于同步挤压提取变换的滚动轴承故障诊断研究

滚动轴承是大型机械设备的重要部件,起着非常重要的作用.当轴承发生故障时,如不及时修复或更换,将严重影响设备的寿命.时频分析方法是一种非常有效的故障特征提取工具,已得到广泛的应用;同时,时频分布的能量聚集性影响故障特征提取效果,因此,一种能量更加集中的时频分析方法对机械信号处理与故障诊断起着至关重要的作用.提出了一种全新...