Acoustic emission signal identification of different rocks based on SE-1DCNN-BLSTM network model

In order to study fracture mechanism of rocks in different brittle mineral contents,this study pro-poses a method to identify the acoustic emission signal released by rock fracture under different brittle miner-al content(BMC),and then determine the content of brittle matter in rock.To understand related interference such as the noises in the acoustic emission signals released by the rock mass rupture,a 1DCNN-BLSTM network model with SE module is constructed in this study.The signal data is processed through the 1DCNN and BLSTM networks to fully extract the time-series correlation features of the signals,the non-correlated features of the local space and the weak periodicity law.Furthermore,the processed signals data is input into the fully connected layers.Finally,softmax function is used to accurately identify the acoustic emission signals released by different rocks,and then determine the content of brittle minerals contained in rocks.Through experimental comparison and analysis,1DCNN-BLSTM model embedded with SE module has good anti-noise performance,and the recognition accuracy can reach more than 90 percent,which is better than the traditional deep network models and provides a new way of thinking for rock acoustic emission re-search.

Characteristics of acoustic emission signals in damp cracking coal rocks

A uniaxial load experiment on coal rocks at different stress rates was carried out, based on the characteristics of acoustic emission (AE) signals in cracking coal rocks, decomposition, de-noising and reconstruction for the AE signals through wavelet packet transform for solving the current problems created by the presence of noise in AE signals and the existing problems in AE signal processing. The results show that the various characteristics of AE signals in coal rocks cracking under different situations can be clearly reflected, after the AE signals are de-noised by the wavelet packet. Compared to dry coal rocks, the number of AE occurrences in damp coal rocks was significantly reduced, as well as the average amplitude. The number of AE occurrences in damp and dry coal rocks clearly increased with increases in the loading rate, but the largest amplitude of the AE signals in damp coal rocks has been reduced. There is no clear evidence of change in dry coal rocks.

Identification of acoustic emission signal in aluminum alloys spot welding based on fractal theory

The acoustic emission signal of aluminum alloys spot welding includes the information of forming nugget and is one of the important parameters in the quality control. Due to the nonlinearity of the signals, classic Euclidean geometry can not be applied to depict exactly. The fractal theory is implemented to quantitatively describe the characteristics of the acoustic emission signals. The experiment and calculation results show that the box counting dimension of acoustic emission signal, between 1 and 2, are distinctive from different nugget areas in AC spot welding. It is proved that box counting dimension is an effective characteristic parameter to evaluate spot welding quality. In addition, fractal theory can also be applied in other spot welding parameters, such as voltage, current, electrode force and so on, for the purpose of recognizing the spot welding quality.

Chaos analysis of acoustic emission signals in spot welding process

Based on chaos time series and fractal theory, acoustic emission signals were studied in the process of spot welding. According to calculating 8 welding parameters using phase space reconstruction method, the largest Lyapunov exponents were positive values and chaos characteristics were firstly discovered from acoustic emission signals in spot welding. In order to evaluate acoustic emission signal, Hausdorff dimension is put forward to analyze and estimate chaos characteristics. The experiment and calculation results indicate that the Hausdorff dimension of acoustic emission signal is significantly distinguishable in the nuggets with different welding parameters. This research provides a new method for measuring the resistance spot welding quality.

Combined optical fiber interferometric sensors for the detection of acoustic emission

A type of combined optical fiber interferometric acoustic emission sensor is proposed. The sensor can be independent on the laser source and make light interference by matching the lengths of two arms,so it can be used to monitor the health of large structure. Theoretical analyses indicate that the system can be equivalent to the Michelson interferometer with two optical fiber loop reflectors,and its sensitivity has been remarkably increased because of the decrease of the losses of light energy. PZT is powered by DC regulator to control the operating point of the system,so the system can accurately detect feeble vibration which is generated by ultrasonic waves propagating on the surface of solid. The amplitude and the frequency of feeble vibration signal are obtained by detecting the output light intensity of interferometer and using Fourier transform technique. The results indicate that the system can be used to detect the acoustic emission signals by the frequency characteristics.

Application of Acoustic Emission Technology in Offshore Platform Monitoring

As the offshore life and production base,the offshore platform plays an important role in offshore oil exploitation.The acoustic emission(AE)technology can be applied to damage detection and early warning of the offshore platform,and then can effectively guarantee the safe operation of the offshore platform,prevent accidents and casualties.The steel jacket offshore platform is currently the most widely used in shallow sea oil field of our country.Considering the complex structure of the steel jacket offshore platform and using AE technology,this paper has carried on research on effects of the pipe diameter size,the welding angle on the AE signal propagation characteristics,and at the same time,influence of the marine environment(seawater temperature,salinity)on the AE testing.These research contents have very important reference value for the application of the AE technology in offshore platform monitoring.

Effect of age on click-evoked otoacoustic emission A systematic review

OBJECTIVE：The aims of this study were to investigate the changes of the total intensity of transient evoked otoacoustic emission（TEOAE） and signal-to-noise ratio in various frequency bands as a function of aging,and to explore the role of age-related decline of cochlear outer hair cells.DATA SOURCES：The literature was searched using the PubMed database using ＇transient-evoked otoacoustic emissions＇ as a keyword.Articles were limited as follows：Species was ＇Humans＇;languages were ＇English and Chinese＇;publication date between 1990-01-01 and 2010-12-31.The references of the found were also searched to obtain additional articles.DATA SELECTION：Inclusion criteria：（1） Articles should involve the total TEOAE level or signal-to-noise ratio.（2） The measurement and analysis system used was Otodynamics ILO analysis system（ILO88,ILO92,ILO96 or ILO292）.（3） Studies involved groups of greater than 10 subjects and TEOAE results were from normally hearing ears.（4） If more papers from the same author or laboratory analyzed the same subjects,only one was used.MAIN OUTCOME MEASURES：The correlations of the age scale with the total level and signal-to-noise ratio of TEOAE was determined,respectively.RESULTS：（1） TEOAE total level gradually increased until 2 months of age,and then decreased with increasing age.Significant negative correlations between total TEOAE level and age were found（r =-0.885,P = 0.000）.（2） The most rapid decrease of TEOAE amplitude occurred at 1 year old.The total TEOAE level decreased about 4.25 dB SPL between 2 months to 1 year old,then about 0.26-0.52 dB SPL from 1 year to 10 years old,about 0.23 dB SPL from 11 years to 25 years old,and about 0.14 dB SPL from 26 years to 60 years old.（3） The signal-to-noise ratio in the frequency bands centered at 1.5,2,3 and 4 kHz decreased with increasing age after 2 months of age.Significant negative correlations between the signal-to-noise ratio and age were found for frequency bands ranging from 1.5 kHz to 4 kHz,with the highest correlations at 4 kHz（r =-0.890,P 〈 0.01）,then at 3 kHz（r =-0.889,P 〈 0.01）,at 2 kHz（r =-0.850,P 〈 0.01） and at 1.5 kHz（r =-0.705,P 〈 0.05）.Conversely,a positive correlation between the signal-to-noise ratio centered at 1 kHz and age was found,but was not statistically significant（r = 0.298,P = 0.374）.CONCLUSION：The total TEOAE response level decreased with increasing age after the first 2 months of age.The signal-to-noise ratio also decreased with increasing age in frequency bands above 1.5 kHz.The signal-to-noise ratio in higher frequencies decreased faster than in lower frequencies,leading to the maximum signal-to-noise ratio shift form 3.2-4.0 kHz in neonates to 1.5 kHz in adults,and further decreasing the total TEOAE response level.The age-related TEOAE spectrum peak shift is most likely because the outer hair cells functioning in higher frequencies are more prone to damage than those for lower frequencies.

CE/FCC认证中Spectrum Emission Mask与Band Edge的测试解析

在CE/FCC认证中,无线通信终端的杂波信号都是重点测试指标,而相邻信道的杂波信号最不容易察觉,所以在每一个国家都有着严格的规定,但是检测的方式却有些不大一样。Spectrum Emission Mask(频谱发射模板)测量单个信道的杂波信号是否有超出规定的框架范围,而Band Edge(频带边沿)是检查整个频宽高低信道的杂波信号是否有超出规定的框架范围。

基于模态理论和改进GMM的声发射源识别研究

基于模态声发射信号理论,提出了一种利用声学对数倒谱统计参数作为声发射信号特征参数的分析与提取方法。从声发射信号多模态特性出发,提出了一个基于改进高斯混合模型的声发射源信号识别系统。理论分析和实验结果表明,该方法能准确地判断声发射信号源,不仅能够应用于突发型声发射信号的识别,而且可以应用于连续型声发射信号的识别。

基于随机森林法的铣刀磨损状态监测

针对机床加工过程中铣削刀具状态监测困难,以及单传感器监测法存在信息不全的问题,提出了一种利用随机森林完成多传感器信息融合的刀具磨损状态监测研究方法。在不同的切削参数下,以声发射传感器和振动传感器为信号采集元件,多方位采集信号,并对信号进行时域、频域、小波包分析,提取其对刀具状态敏感的共计23个特征量,构建随机森林模型对铣刀状态进行监测。实验结果表明,该研究方法识别刀具准确率达90.0%,具有可行性。

基于奇异谱分析和辛几何模态分解的短期碳排放预测模型

在短时期内对碳排放水平进行评估和规划,对制定精准的减排目标和有效的政策措施可以起到辅助作用。将奇异谱分析分解法(Singular spectrum analysis decomposition,SSAD)和辛几何模态分解(Symplectic geometry mode decomposition,SGMD)组合成新型的二次信号分解法,并应用于每日碳排放量预测。在对原始序列进行二次分解之后,利用快速傅里叶变换对子序列进行重构,并应用偏自相关函数来选择合适的输入变量。最后,利用麻雀搜索算法(Sparrow search algorithm,SSA)对长短期记忆网络(Long short-term memory network,LSTM)进行优化,建立了SSAD-SGMD-SSA-LSTM模型。通过与其他模型进行对比实验,发现SSAD-SGMD二次分解更加适合碳排放时间序列预处理,并且可以进一步提高预测精度。SSAD-SGMD模型与集成经验模态分解和变分模态分解相结合的二次分解模型相比,模型的可决系数R2提高了1.83%,平均绝对百分比误差(Mean absolute percentage error,MAPE)有所降低,均方根误差(Root mean square error,RMSE)降低了43.16%。此外,经过SSA优化后的LSTM模型,R2提高了1.49%,MAPE有所降低,RMSE降低了38.64%。所提出的模型能够有效提升短期碳排放预测的准确性。

基于ZOA优化VMD-IAWT岩石声发射信号降噪算法

针对岩石破裂过程中产生的声发射(AE)信号夹杂大量噪声的问题,提出了一种基于斑马优化算法(ZOA)改进变分模态分解(VMD)并与改进的自适应小波阈值(IAWT)联合的声发射信号降噪算法。利用ZOA算法优选出影响VMD分解效果的模态个数K和二次惩罚因子α;通过相关系数将分解出的IMFs划分为有效分量、含噪分量和剔除分量;针对小波阈值(WT)降噪算法不具备自动调整小波基以及软、硬阈值函数存在偏差大和不连续的弊端,提出了IAWT算法去除IMFs中的噪声分量,并与有效分量合并重构,得到降噪后的AE信号。通过模拟和实测AE信号验证并与现有降噪算法对比,结果表明ZOA-VMD-IAWT降噪算法适合处理AE信号,信号的时频特征得以保留。研究结果可为岩石AE信号理论及实际工程应用提供参考。

基于迁移学习和CNN-LSTM的水轮机空化状态识别方法

针对水轮机空化声发射信号中包含较多噪声、依赖人工降噪与特征提取以及深度学习模型准确率极度依赖海量训练数据的问题,提出一种基于迁移学习和卷积神经网络-长短时记忆网络(CNN-LSTM)的水轮机空化状态识别方法。首先,将数据输入CNN中提取隐含特征;然后,在LSTM中提取特征隐含的时序信息并输出空化类型,通过训练网络参数建立基于CNN-LSTM的空化状态识别模型;最后,引入迁移学习对类似工况进行空化状态识别。结果表明:该模型能准确识别出3种不同的水轮机空化类型,其平均识别准确率达到较高水平;与传统深度学习模型相比,该模型在极少样本学习任务中的识别准确率具有明显优势。

声发射法检测输气管道泄漏的研究综述

声发射法检测管道泄漏是目前的热点方法,研究涉及泄漏信号的产生与传播、信号拾取与处理、基于信号的智能识别与定位等。通过介绍声发射检测定位原理及一些基本规律,详细分析小波分析、局域均值分解、经验模态分解、变分模态分解在处理泄漏信号时的优劣,探讨人工智能在处理管道泄漏声发射信号中的应用,总结管道泄漏的模态研究、相关试验研究,来理清基于声发射的管道泄漏检测现状及展望未来发展。

基于FPGA-PCIe的声发射信号采集系统硬件设计

论文描述了以EP2C5Q208C8N、AD7621以及CH368为核心的声发射数据采集系统的硬件设计,主要提到了系统的实现原理、硬件模块的组成及相应的电路设计。通过Altera公司的Modelsim仿真对模块电路整体工作的过程进行验证,最后采用GWINSTEK函数发生器产生的无直流偏置幅值为4 Vpp、频率为200 kHz正弦波验证系统的硬件指标,验证发现硬件指标可以满足声发射信号采集所需的16 bit分辨率,3MSPS采样率设计要求。

输气管道泄漏声发射信号的数值模拟及应用

声发射信号常用于管道泄漏检测中。目前主要采用实验结合信号分析的方法对管道泄漏声发射信号进行研究,对于管道泄漏声发射信号数值模拟的研究较少。为了研究输气管道泄漏的流固耦合振动响应特性,建立了泄漏管道三维模型,采用单向瞬态流固耦合的方法对模型进行有限元模拟分析,模拟管道发生泄漏时管道振动的声发射信号。通过实验声发射传感器记录管壁振动产生的声发射信号。结果表明:数值模拟结果与实验结果的误差为0.3%,其结果吻合较好。并将声发射模拟信号应用于小波基选取方面,为后续的泄漏检测研究提供理论参考。

基于优化SVM模型的立铣刀在机崩刃监测技术研究

随着加工精度要求不断提高,切削过程中,对刀具在机磨损或崩刃状态进行在机实时监测的需求日益增加。本文以声发射和主轴功率为监测信号,通过提取时域、频域和时频域的有效特征,构建了基于融合信号的平底立铣刀在机崩刃SVM监测模型;采用网格搜索、粒子群和遗传算法优化SVM模型参数,并在实际切削环境中,将平底立铣刀的崩刃监测效果进行对比。结果表明:基于遗传算法优化的SVM模型对铣刀崩刃状态监测效果最佳。

高速铁路信号系统碳排放边界划分及分析

准确量化高速铁路信号系统的碳排放量,对高速铁路碳排放核算及低碳化发展有重要意义。本文提出在计算其碳排放时需要综合考虑信号系统相关关联活动的思路,并划分信号系统的碳排放边界;提出基于能源消耗的信号系统碳排放计算方法,进一步利用碳流理论分析计算信号系统内各设备的相关碳流指标;最后以甘肃省兰州西高铁站为例进行分析,验证本文所提方法的可行性和有效性。结果显示,控制及监测系统的碳排放主要与电力碳排放因子有关,维护保养电码化设备所产生的碳排放平均仅有0.12 kgCO_(2)·d^(-1);信号系统各设备间的平均支路碳流密度为0.0076 kgCO_(2)·kWh^(-1),各设备的节点碳势与支路碳流密度相等。结论表明,各子系统的碳排放量主要和其能耗类型有关,电能消耗引起的间接碳排放是信号系统碳排放的主要组成部分,信号系统相关活动引起的直接碳排放与一次能源消耗成正比。

密封端面声发射信号降噪处理技术研究

针对利用声发射技术监测密封端面摩擦状态,受到轴承、电机等部件摩擦产生背景噪声对密封端面摩擦信号的干扰,导致获取密封端面声发射信号信噪比不高的问题,文章提出的基于经验小波变换和相对熵(EWT-KLD)的滤波降噪方法,对采集到的原始信号进行滤波降噪处理,以提高密封端面摩擦产生声发射信号的信噪比。通过试验验证,该方法可适用于不同工况、不同介质、不同摩擦状态的声发射信号进行降噪,提高50 kHz以上声发射信号的信噪比,尤其是密封端面微弱摩擦产生信号的信噪比,有效地提高了密封端面摩擦声发射检测的精度和灵敏度,对于早期密封端面摩擦监测的作用尤为明显,使得密封端面摩擦状态累积变化过程的监测更准确。

A signal coordination algorithm for two adjacent intersections based on approximate dynamic programming

To reduce vehicle emissions in road networks, a new signal coordination algorithm based on approximate dynamic programming （ADP） is developed for two intersections. Taking the Jetta car as an experimental vehicle, field tests are conducted in Changchun Street of Changchun city and vehicle emission factors in complete stop and uniform speed states are collected. Queue lengths and signal light colors of approach lanes are selected as state variables, and green switch plans are selected as decision variables of the system. Then the calculation model of the optimization index during the planning horizon is developed based on the basis function method of the ADP. The temporal-difference algorithm is employed to update the weighting factor vector of the approximate function. Simulations are conducted in Matlab and the results show that the established algorithm outperforms the conventional coordination algorithm in reducing vehicle emissions by 8.2%. Sensitive analysis of the planning horizon length on the evaluation index is also conducted and the statistical results show that the optimal length of the planning horizon is directly proportional to the traffic load.