Acoustic emission source localization technique based on least squares support vector machine by using FBG sensors

An intelligent acoustic emission (AE) source localization technique by using fiber Bragg grating (FBG) sensors was investigated. Four FBGs sensing network was established for detecting the AE signal. And power intensity demodulation method was initialized employing narrow-band tunable laser. The intelligent AE source localization method was proposed based on wavelet transform, cross-correlation analysis, and least squares support vector machines (LS-SVM). LS-SVM modal’s input is signal time difference and output is AE source position. The location experiments were carried out on a 500 mm × 500 mm × 2 mm aluminum alloy plate. The results showed that the AE source position abscissa and ordinate localization errors are all less than 10 mm. The maximum and average localization errors are 8.65 and 6.78 mm, respectively. The research results provided a novel method for AE source localization by using FBG sensors.     

基于近场波束形成法的声发射源定位研究

引入近场波束形成法处理声发射信号,研究在小区域布置少量传感器来实现声发射源定位的新方法.首先,利用板波理论进行声发射信号传播特性研究,对比了板中声发射信号与空气中声波传播的差异性,分析了波束形成法应用于声发射源定位的问题.并在板上进行断铅实验,验证了近场波束形成法进行声发射源定位的有效性.最后,在旋转机械碰摩模拟实验台上进行了碰摩实验,利用波束形成法进行碰摩声发射源定位,所提出的方法能有效地定位旋转机械初始碰摩位置.所得结果可为声发射源定位提供一种新途径.     

Fracture source location in thin plates using the wavelet transform of dispersive waves

A new signal processing approach was presented for acoustic emission source location using the dispersive waves in a thin plate. For wave propagation in dispersive media, the accuracy of source location can be improved by using the arrival times of a single frequency component in the output signals at an array of sensors. The wavelet transform (WT) was used to resolve this problem. By utilizing the time-frequency data of the WT, the frequency-dependent arrival time traveling with the group velocity was shown to be easily determined. Experiments were performed using a lead break as the simulated fracture source on the surface of an aluminum plate. Two plate modes corresponding to the S(0) and A(0) Lamb waves were identified, and their group velocities were accurately measured. The source location results based on the WT method agreed well with the true locations. The WT method was also compared with the cross correlation technique, and both methods provide similar results.     

基于材料选型优化的金属-复合材料组合结构-声辐射优化

基于金属铺层假设,以结构材料属性和材料铺层数量为设计变量,建立了基于金属-复合材料的材料选型结构-声辐射优化设计模型。以钢-纤维增强复合材料组合结构为例,开展了多设计变量、多约束条件的结构-声辐射优化研究。最后,采用遗传算法进行求解,实现了结构材料的转换。数值算例表明,通过金属-复合材料组合结构的材料选型优化,可以有效降低钢-纤维增强复合材料结构的振动和声辐射。文中的研究方法为结构材料的分布优化提供了一种可行有效的思路。     

Solving initial and boundary value problems using learning automata particle swarm optimization

In this article, the particle swarm optimization (PSO) algorithm is modified to use the learning automata (LA) technique for solving initial and boundary value problems. A constrained problem is converted into an unconstrained problem using a penalty method to define an appropriate fitness function, which is optimized using the LA-PSO method. This method analyses a large number of candidate solutions of the unconstrained problem with the LA-PSO algorithm to minimize an error measure, which quantifies how well a candidate solution satisfies the governing ordinary differential equations (ODEs) or partial differential equations (PDEs) and the boundary conditions. This approach is very capable of solving linear and nonlinear ODEs, systems of ordinary differential equations, and linear and nonlinear PDEs. The computational efficiency and accuracy of the PSO algorithm combined with the LA technique for solving initial and boundary value problems were improved. Numerical results demonstrate the high accuracy and efficiency of the proposed method.     

基于改进PSO算法的结构损伤检测

结构的损伤检测常转化为求解约束优化问题,针对粒子群算法容易出现早熟问题,增大算法后期的粒子位置的改变量,从而增加粒子位置的差异,因而能够增强其在求解约束优化问题时抵抗局部极小的能力。两层刚架单损伤和多损伤识别的数值结果和收敛曲线表明了改进后的粒子群算法优于传统的带惯性因子的粒子群算法。三层框架结构的4种损伤工况的试验研究进一步说明了该算法应用于结构损伤检测领域的有效性。     

碎片云撞击声发射信号能量特征小波包分析

利用小波包分析技术对碎片云撞击载荷作用下铝合金板声发射信号的能量分布特征进行了研究。首先,介绍了碎片云撞击信号的获取方案及撞击引起的损伤情况;其次,对获取的声发射信号进行小波包分析,得到了信号在频率带上能量分布特征图。最后,讨论了碎片云撞击损伤特征与声发射信号能量分布的关系。分析结果发现,对于相同质量的弹丸,随着其破碎程度的提高,形成的碎片云对后板的损伤程度减少;弹丸具有的初始速度越大,弹丸破碎越完全,碎片云撞击声发射信号中的能量越小;当弹丸破碎程度低时,碎片云撞击引起的声发射信号能量集中在约488kHz以下;弹丸破碎程度越高,信号中488kHz以上的能量所占总能量的比例越大。     

A surrogate-assisted particle swarm optimization algorithm based on efficient global optimization for expensive black-box problems

Evolutionary algorithms cannot effectively handle computationally expensive problems because of the unaffordable computational cost brought by a large number of fitness evaluations. Therefore, surrogates are widely used to assist evolutionary algorithms in solving these problems. This article proposes an improved surrogate-assisted particle swarm optimization (ISAPSO) algorithm, in which a hybrid particle swarm optimization (PSO) is combined with global and local surrogates. The global surrogate is not only used to predict fitness values for reducing computational burden but also regarded as a global searcher to speed up the global search process of PSO by using an efficient global optimization algorithm, while the local one is constructed for a local search in the neighbourhood of the current optimal solution by finding the predicted optimal solution of the local surrogate. Empirical studies on 10 widely used benchmark problems and a real-world structural design optimization problem of a driving axle show that the ISAPSO algorithm is effective and highly competitive.     

Optimization of Positioning of an Acoustic Emission Sensor for Monitoring Hot Forging

Optimization of a sensor location for effective characterization of a hot forging process using acoustic emission (AE) signals is discussed in this paper. Acoustic emission signals generated during forging operations on an aluminium alloy were recorded using three sensors simultaneously by mounting them on the top bolster, bottom bolster, and bottom die of the press. The AE signals with maximum sensitivity could be detected with a sensor attached to the bottom die in preference to the other positions. Using AE parameters, the forging process could be differentiated into three regions, i.e., 1) yielding of the workpiece material, 2) intermediate deformation region, and 3) filling of the die. The results show that the optimum position of the AE sensor for monitoring hot forging is found to be the bottom die of the forging press.     

结构拓扑优化中敏度过滤技术研究

为了抑制连续体结构拓扑优化结果中的棋盘格和灰度单元问题,借鉴粒子群优化算法中粒子状态的更新方法,提出一种改进的敏度更新技术.以结构的柔度最小为优化目标,构建了基于固体各项同性微惩罚结构的结构拓扑优化模型,根据结构的力学响应分析,采用优化准则法进行设计变量更新,进行载荷作用下二维连续体结构的拓扑优化设计,得到了材料在设计域内的最优分布.通过与已有敏度过滤技术的对比分析,验证了文中方法的正确性和有效性．     

Leakage Locating in Underground High Pressure Gas Pipe by Acoustic Emission Method

Detecting gas leakage accurately in urban high-pressure natural gas pipelines is a great problem all over the world. Gas leakage may lead to pollution and severe environmental damages; therefore, in order to minimize the leakage problem, it is necessary to maintain pipelines. Acoustic emission is a technique to detect leakage in urban pipelines. Leakage in high-pressure pipes radiates acoustic emission signals that are transferred through the pipe walls. This paper proposes a leakage detection algorithm combined with wavelet transform, filtering and cross-correlation techniques to locate leakage source in urban gas pipes. The major noise of acoustic emission signals is removed through the wavelet transform and filtering technique. After removing the noise, the time difference between the signals recorded at two sensors is precisely computed using cross-correlation function. Experiments are carried out with continuous leakage source and a linear array of two sensors positioned in two sides of the leakage source. To study the accuracy of the proposed algorithm, several tests were carried out changing the source-sensor distance, and a percentage error less than 5 % was found in the leakage detection.     

基于阻尼材料拓扑分布的结构-声辐射优化

基于拓扑优化思想,提出一种人工材料假设,建立了阻尼材料铺设的拓扑优化数学模型。在阻尼材料用量一定的情况下实现阻尼材料最优分布,达到减振降噪之目的。采用遗传算法进行求解,进行了阻尼材料和人工材料的转换,实现了阻尼材料的拓扑优化。数值算例表明:所提方法在减振降噪设计中具有可行性和有效性,有较好的工程应用价值,可为阻尼材料的敷设提供一种可行有效的思路。     

基于智能算法的啤酒灌装生产线设备选型研究

目的以啤酒灌装生产线为研究对象,基于粒子群智能算法,实现啤酒灌装生产线所需设备的快速选型,且使设备的利用率最大化。方法建立啤酒灌装生产线所需设备的数据库,利用Matlab软件编写粒子群智能算法,对啤酒灌装生产线的相关设备进行多目标优化,实现快速智能寻优。结果在客户要求的约束条件下,当初始化100个种群、迭代次数为8000时,生产线平衡率高达90%以上,满足了客户要求。结论文中验证了粒子群智能算法的可靠性,并得到了客户满意的求解方案。该智能算法在生产线布局初期具有很强的柔性,可以快速解决啤酒灌装生产线建厂初期设备的快速选型问题。     

Drilling path optimization by the particle swarm optimization algorithm with global convergence characteristics

Drilling path optimization is one of the key problems in holes-machining. This paper presents a new approach to solve the drilling path optimization problem belonging to discrete space, based on the particle swarm optimization (PSO) algorithm. Since the standard PSO algorithm is not guaranteed to be global convergent or local convergent, based on the mathematical model, the algorithm is improved by adopting the method to generate the stop evolution particle once again to obtain the ability of convergence on the global optimization solution. Also, the operators are proposed by establishing the Order Exchange Unit (OEU) and the Order Exchange List (OEL) to satisfy the need of integer coding in drilling path optimization. The experimentations indicate that the improved algorithm has the characteristics of easy realization, fast convergence speed, and better global convergence capability. Hence the new PSO can play a role in solving the problem of drilling path optimization.     

The characteristics of acoustic emission from a hole in a composite laminate

Holes in composite laminates are sources for the onset of delamination and matrix cracking. Early discovery of delamination growth makes it possible to repair the damage. Monitoring of acoustic emission and analyzing the signals may enable the recognition of the onset of delamination and its location by using a few sensors and calculation of arrival times. It is shown that acoustic emission signals originating from holes can be characterized by using a ‘pattern recognition’ scheme. Thus the acoustic emission which results from the presence of a hole can be differentiated from that generated by fiber breakage.     

基于PSO改进深度置信网络的滚动轴承故障诊断

针对深度置信网络(Deep Belief Network,DBN)用于轴承故障诊断时,网络层结构调试比较费时等问题,提出一种基于粒子群优化(Particle Swarm Optimization,PSO)的DBN算法,以及基于该算法的轴承故障诊断模型。该模型利用PSO算法优选DBN网络结构,并通过自适应时刻估计法微调模型参数,随后运用具有最优结构的DBN模型直接从原始振动信号中提取低维故障特征,并将其输入到Soft-max分类器中识别轴承的故障模式。该算法与支持向量机、BP神经网络、DBN、堆叠降噪自编码等方法进行对比分析,实验结果表明,PSO改进的DBN算法具有更高的准确率以及更好的鲁棒性。     

基于时频分析和改进差分进化的多点泄漏定位方法

当管道同时发生多个泄漏点时,多个泄漏点的声波信号出现混叠,从而影响泄漏声信号的传播和衰减规律。在多点泄漏声波信号混叠的情况下,传统的泄漏定位方法无法对多个泄漏点进行有效定位。为此,提出了一种基于时频分析和改进差分进化的多点泄漏定位方法。由于变分模态分解(variational mode decomposing, VMD)的分解模态个数对特征提取有影响,因此采用能量函数估计分解模态个数,从而对VMD改进。然后采用改进VMD对多点泄漏声波信号进行处理。另外,通过时频分析(time-frequency analysis, TFA)估计多个泄漏点数量,从而得到多点泄漏的定位函数。差分进化(differential evolution, DE)算法易陷入局部最优,在进化后期收敛速度较慢,采用粒子群优化(particle swarm optimization, PSO)算法提高DE的全局收敛速度,并通过改进的差分进化算法估计多个泄漏点的位置。在管道现场进行多点泄漏的模拟试验,试验结果表明该方法能够准确地估计多点泄漏位置,泄漏定位的最小误差为18 m。     

基于遗传算法和拓扑优化的结构多孔洞损伤识别

鉴于拓扑优化和遗传算法在结构损伤识别中各自的优点,本文将遗传算法、有限元和拓扑优化三种方法相结合,提出了一种用于二维结构多损伤识别的新方法。这种方法将拓扑优化的设计变量和遗传算法的参数统一化,将拓扑优化中的目标函数和约束方程与遗传算法的适应度函数联系起来,并以拓扑优化的约束方程作为控制条件参与整个遗传运算的控制。采用二进制编码遗传算法代替连续变量拓扑优化的方式对发生孔洞损伤形式的二维结构进行损伤识别,避免了利用连续变量拓扑优化进行损伤识别时参数阈值的确定可能给识别结果带来的不良影响。通过对两个二维结构模型的多损伤识别仿真计算,结果显示本方法能够很好地识别二维结构中多个位置的损伤,对于仅用拓扑优化法很难识别的轻微孔洞损伤情况,该方法也能得出与实际情况吻合良好的结果。     

滚动轴承故障非接触多传感器声信号融合方法

摘　要：针对移动滚动轴承非接触声发射检测中,一个故障源信号可能被多个传感器采集,致使这些声信号包含故障信息不完整且存在重叠的问题,综合考虑声波传播理论、多传感器声信号时差关系、滚动轴承典型故障撞击频率等,建立滚动轴承故障非接触多传感器声信号融合方法。建立滚动轴承故障非接触多传感器声发射检测试验台,分别采集移动滚动轴承滚动体、外圈和内圈故障声信号。采用融合方法对同声源信号进行处理,利用信号相似理论证明了融合信号与故障源信号的相似程度高于各传感器声信号。采用声发射累计撞击计数法对融合处理后的滚动轴承不同故障声信号进行分析。结果表明,该融合算法能有效地处理多传感器接收的同声源信号,可利用融合后信号进行准确的故障识别。     

基于优化匹配追踪稀疏分解的微弱超声回波提取

为提高低信噪比环境中微弱超声回波信号的提取性能,提出优化的匹配追踪(Matching Pursuit,MP)稀疏分解的超声回波提取算法。该算法将具有连续空间搜索能力的粒子群优化(Particle Swarm Optimization,PSO)算法引入到MP稀疏分解中,以缓解原子集的遍历有限性需求与超完备性之间的矛盾,通过改进粒子群算法的参数自适应设置及MP算法的目标函数和重构函数,实现自适应的PSO-MP稀疏分解算法,并建立了连续伽柏(Gabor)原子集,提高了最优原子与不同参数超声回波信号的匹配程度,最后由最优原子集通过重构函数对回波信号进行重构,实现对回波的降噪和准确提取。实验结果表明,该算法显著降低了计算量,效果优于已有小波阈值等算法且具有较好鲁棒性。