基于声发射技术的聚乙烯自增强复合材料损伤模式识别研究
|
摘要
超高分子量聚乙烯(UHMWPE)纤维是一类具有高度取向伸直链结构的高性能有机纤维,具有轴向比强度、比模量高,韧性、耐磨性能和抗冲击性能优异,以及抗化学腐蚀性、电绝缘性和生物相容性等特点,广泛应用于各类行业。近年来随着热塑性复合材料的快速发展,其结构在工程领域中的应用已越来越广泛,其中基于"One Polymer Composites"概念的PE自增强复合材料,由于化学相容性改善了界面性能,并更好地发挥了纤维的综合性能。同时,原料丰富、价格低廉及回收便利性,使其相对其它复合材料在成本和性能等方面更具竞争优势而受到广泛的重视。对PE自增强复合材料损伤机理的研究是保证其服役过程的安全以及合理设计的基础。在对玻纤、碳纤增强热固性复合材料损伤机理的研究表明,声发射(Acoustic emission, AE)技术能够为材料损伤过程提供丰富和实时的信息,是进行材料损伤机制研究的有效工具。目前该领域已有的研究工作主要集中于热固性复合材料,而针对热塑性复合材料的研究尚不多见。PE自增强复合材料是典型的热塑性复合材料,本文将采用AE技术对其损伤过程的AE特征进行研究,以建立损伤机制和AE信号的关系并对损伤源进行分类和鉴别,为工程实际应用中基于AE技术的热塑性复合材料损伤机制鉴别提供简便有效的方法。
纤维增强复合材料的损伤机理十分复杂,包括纤维断裂、基体开裂、界面脱粘、分层等。为了揭示PE自增强复合材料各种不同损伤机制的AE时域和频域特征,建立损伤机制和AE信号的对应关系,实现对AE信号的分类和鉴别,并最终建立基于神经网络方法的AE信号模式识别系统,本文主要开展了以下研究工作。首先,针对热塑性基体复合材料的破坏特点,采用简单模型试样来激发产生预期损伤模式的AE信号,结合模型试样在损伤过程中的力学性能变化并通过FFT讨论典型损伤模式AE信号的时域和频率特征；其次,根据简单模型试样的破坏过程研究了AE信号的聚类分析,包括相似性测度、聚类变量的选择、聚类结果的确认,以此建立PE自增强复合材料典型损伤模式AE信号分类方法,并比较常用判别分析方法对典型损伤模式AE信号的判别效果；最后,建立实现PE自增强复合材料损伤AE信号分类和识别的神经网络系统,并比较多种优化算法对神经网络性能的影响。
实验结果表明模型试样的拉伸破坏过程包括多种不同的损伤机制,伴随损伤过程的AE响应能较好地反映出损伤过程的阶段性特征。基体试样AE活动性低、信号数量少,损伤机制包括塑性变形和断裂；90°单层板产生不同程度的界面损伤AE信号；0°和[+45°/-45°]层合板结构复杂、损伤源多,AE活动性高、信号数量多,前者产生纤维断裂信号,后者产生层内剪切和层间损伤信号。基体塑性变形、界面初始损伤等破坏程度低的损伤机制,AE信号幅度低、持续时间短。基体断裂、界面脱粘、纤维断裂和分层等破坏程度严重的损伤机制,AE信号幅度高、持续时间长。从损伤进程上看,各试样早期损伤基本伴随持续时间短的低幅度信号,而持续时间长的高幅度信号主要发生在断裂阶段。AE信号的FFT分析表明,非损伤信号和损伤信号以及各类损伤信号间都具有不同的频率特征。虽然不同损伤机制的AE信号时域和频率参数存在差异,但其分布范围存在重叠,使得仅通过时域或频率参数进行损伤源的鉴别尚存在困难。
伴随复合材料损伤过程的AE信号是多种损伤模式的混合信号。因此,对AE信号进行聚类分析的目的是建立典型损伤机制和AE信号的对应关系。为了获得可靠的聚类结果,分别对基体、90°单向层合板、纤维束试样、反对称层合板等简单模型试样破坏过程的AE信号进行聚类分析。首先,通过对8个常用AE信号参数进行变量聚类分析表明,不同损伤机制AE信号参数分为3类时,类内相似程度较大,类间相似度较小,且相似关系一致,分别从中选择幅度、峰值频率和持续时间作为模式特征,并采用k-means算法对各类模型试样的AE信号进行了聚类分析,结合SEM观察对聚类结果进行了验证,以此建立8种典型损伤机制的AE信号训练样本。以聚类分析的结果对AE信号进行了判别分析,模式特征组间均值相等的假设检验证明,各模式特征对AE信号判别均产生有效作用。此外,以识别正确率比较了欧氏、马氏距离判别法和k近邻法的判别效果,实验结果表明,马氏距离判别法对损伤AE信号具有较好的判别效果,超过90%的识别正确率说明以幅度、峰值频率和持续时间作为模式特征,可以实现不同损伤机制AE信号的模式识别。不同判别方法的判别错误均来自于基体断裂和界面脱粘,以及基体塑性变形-1和界面损伤之间的相互误判。各典型损伤信号在模式空间中的分布情况说明,当各类别信号的相互分离程度较好时识别率较好,而当各类别信号间存在重叠时就会出现相互的误判,从而导致识别正确率的降低。虽然通过聚类和判别分析的模式识别方法可以实现对AE信号的分类和识别,但是整个分析流程相对复杂、效率低且操作上不够方便。
为进一步提高对AE信号源机制的分类和鉴别准确率和数据分析操作的便利性,更好地适应工程实际应用的需要,本课题进一步研究了基于神经网络技术的AE信号模式识别,包括分别建立竞争型SOC网络和多层前向BP网络实现对AE信号的聚类和识别。通过对相同数据集分别进行SOC网络分类和聚类分析的对比发现,两种方法分类的一致性达到98%以上,说明SOC网络对于AE信号的聚类分析是可行的和有效的。在相同结构的BP网络和实验数据的前提下,对标准BP算法及其改进算法的训练过程和识别正确率进行了比较,实验结果表明：标准BP算法训练时间长,训练结果易受到不同的网络初始值的影响,识别率最低,几乎没有实际应用价值。基于启发式的改进算法中,有动量可变学习速度法和弹性梯度下降法均能在一定程度上提高识别率,同时也能改善训练速度。基于标准数值优化的改进算法中Levenberg-Marquardt算法具有最佳的训练效果,该算法最适合作为BP网络的训练算法。
Ultra high molecular weight polyethylene (UHMWPE) fiber is a kind of high performance organic fiber with highly oriental extended-chain. It has been widely used in many fields for high specific strengthen, high specific modulus, excellent toughness, well abrasion resistance and excellent anti-impact performance, fine chemical resistance, insulation and biocompatibility. With rapid development of thermoplastic composite materials in recent years, their structures were used in more and more engineering fields. Based on "one polymer composites", the interface of PE self-reinforced composites and general performances of fiber were improved due to chemical compatibility. Meanwhile, it has more competitive advantage than other composites such as low price, rich resource and convenient recycle. Research on damage mechanisms of PE self-reinforced composites are important to the assurance of safety of the composites in service and obtain the optimal structure design. Results of damage mechanisms on glass-fiber, carbon-fiber reinforced thermoset composites revealed acoustic emission (AE) is an effective tools which can provide rich and real information during damage progress. Up to now, researches mostly focus on thermoset composites and rarely focus on thermoplastic composites. PE self-reinforced composites is a typical thermoplastic composites, this study will investigate its AE characteristic during damage progress based on AE technology. Then, correlation between damage mechanisms and AE signals will be established and damage mechanisms will be classified and identified. This study can provide a convenient and effective method for damage mechanisms identified on thermoplastic composites based on AE technology during real applications.
Damage mechanisms of fiber reinforced composites are very complicated including fiber breakage, matrix crack, interface debonding and delamination. In order to reveal AE feature of time domain and frequency domain generated from different damage mechanisms of PE self-reinforced composites and establish correlation between damage mechanisms and AE signals to classify and identify AE signals, and finally establish AE signal pattern recognition system based on artificial neural networks, this study mainly include following research work. Firstly, according to damage characteristic of thermoplastic composites, using model sample with simple structure to generate AE signals of desired damage mode, analyze AE features of time domain and frequency domain of typical damage mechanisms based on mechanical performance change and Fast Fourier transformation (FFT). Secondly, according to damage process of model sample with simple structure, the cluster analysis on AE signals were investigated including selection of similarity measure and cluster variables and validation of cluster results. Cluster analysis method of AE signals on typical damage modes was established. Results of several common methods on discriminant analysis were compared. Finally, artificial neural networks for AE signal classification and identification on PE self-reinforced composites were established and performance of neural networks due to some optimal algorithms was also compared.
The experiment revealed damage process of model sample including different damage mechanisms and AE response can reflect features of different damage stage. Matrix sample has small number of signals and poor AE activities, the damage mechanisms including plastic deformation and fracture.90°laminate generate interface damage signals with different degree. Due to complicated structure and more damage,0°laminate and [+45°/-45°] laminates have more AE signals and high AE activities. The former mainly generate AE signals from fiber breakage, the later mainly generate AE signals from in-layer shear and interlayer damage. AE signals from damage mechanisms with small degree destruction such as matrix plastic deformation and interface initial damage are low amplitude and short duration. However, AE signals from big degree destruction such as matrix fracture, interface debonding, fiber breakage and delamination are high amplitude and long duration. According to damage process, AE signals from early damage of all kinds of specimen are all low amplitude with short duration, while high amplitude with long duration AE signals mainly generated at the moment of material fracture. The results of FFT analysis on AE signals revealed different frequency features between non-damage signals and damage signals as well as among different damage mechanisms. The difference from various damage mechanisms is obvious both on time domain and frequency domain. However, the overlap of distribution results in identification difficulty when only using parameters of time domain or frequency domain.
AE signals from damage process of composites are hybrid signals with many different damage modes. The purpose of cluster analysis on AE signals is to establish correlation between typical damage mechanisms and AE signals. For obtaining reliable cluster results, simple model specimens such as pure matrix,90°unidirectional laminate, fiber bundle and [+45°/-45°] laminates were used to generate expected damage mechanisms. Firstly, the results of variable cluster analysis on 8 AE parameters revealed similarity within groups is better than similarity between groups and relation of similarity is same when all parameters were divided into 3 groups. Therefore, amplitude, peak frequency and duration selected from each group can be used as pattern features. Then, based on k-means algorithms, sample cluster analysis on all kinds of model specimens were performed to establish AE training set with 8 typical kinds of damage mechanisms. Cluster results were validated by SEM of each model specimen. According to cluster results, discriminant analysis on AE signals was also performed. The result of hypothesis test on mean equal among different model showed each pattern features were effective for discriminant analysis. Furthermore, discriminant effects of Euclidean distance, Mahalanobis distance and k nearest neighbor discriminance were compared with percentage of right identification. The results revealed Mahalanobis distance discriminance has the best effect. Percentage of right identification over 90% showed different damage mechanisms can be divided with pattern features including amplitude, peak frequency and duration. The main error of identification resulted from different discriminances were all come from identification mistake between matrix fracture and interface debonding as well as matrix plastic deformation-1 and interface damage. Distribution of AE signal in pattern space from typical damages showed better right identification resulted from better separability and identification mistake will take place when overlap each other. Classification and identification of AE signal can be realized by cluster and discriminant analysis. However, these methods are complicated in process, poor efficiency and inconvenient to real application.
In order to improving classification and identification, convenience of data analysis and more fit for demand of real application, this study investigated pattern recognition of AE signal based on artificial neural networks. These work included establishing self-organizing competitive (SOC) and error back-propagation (BP) network to realize classification and identification respectively. According to the classification results from SOC network and cluster analysis to the same data set, the classification consistency of two methods is over 98%. Therefore, SOC network is a feasible and effective tool for cluster analysis of AE signals. Based on the same data set and the same architecture of BP network, the right identification percentage with standard BP training algorithm and other improved training algorithms were compared. The results revealed standard BP algorithms is unfit for real application due to long training time, low identification and easy effected by initial value of network. Among heuristic improved method, both BP algorithm with momentum and adaptive learning rate and resilient BP algorithm can improve identification effect and accelerate training process. Among standard numerical optimal improved methods, Levenberg-Marquardt algorithm has the best training effect. It is the best algorithms to training BP networks to identify different damage mechanisms with AE signals.
纤维增强复合材料的损伤机理十分复杂,包括纤维断裂、基体开裂、界面脱粘、分层等。为了揭示PE自增强复合材料各种不同损伤机制的AE时域和频域特征,建立损伤机制和AE信号的对应关系,实现对AE信号的分类和鉴别,并最终建立基于神经网络方法的AE信号模式识别系统,本文主要开展了以下研究工作。首先,针对热塑性基体复合材料的破坏特点,采用简单模型试样来激发产生预期损伤模式的AE信号,结合模型试样在损伤过程中的力学性能变化并通过FFT讨论典型损伤模式AE信号的时域和频率特征；其次,根据简单模型试样的破坏过程研究了AE信号的聚类分析,包括相似性测度、聚类变量的选择、聚类结果的确认,以此建立PE自增强复合材料典型损伤模式AE信号分类方法,并比较常用判别分析方法对典型损伤模式AE信号的判别效果；最后,建立实现PE自增强复合材料损伤AE信号分类和识别的神经网络系统,并比较多种优化算法对神经网络性能的影响。
实验结果表明模型试样的拉伸破坏过程包括多种不同的损伤机制,伴随损伤过程的AE响应能较好地反映出损伤过程的阶段性特征。基体试样AE活动性低、信号数量少,损伤机制包括塑性变形和断裂；90°单层板产生不同程度的界面损伤AE信号；0°和[+45°/-45°]层合板结构复杂、损伤源多,AE活动性高、信号数量多,前者产生纤维断裂信号,后者产生层内剪切和层间损伤信号。基体塑性变形、界面初始损伤等破坏程度低的损伤机制,AE信号幅度低、持续时间短。基体断裂、界面脱粘、纤维断裂和分层等破坏程度严重的损伤机制,AE信号幅度高、持续时间长。从损伤进程上看,各试样早期损伤基本伴随持续时间短的低幅度信号,而持续时间长的高幅度信号主要发生在断裂阶段。AE信号的FFT分析表明,非损伤信号和损伤信号以及各类损伤信号间都具有不同的频率特征。虽然不同损伤机制的AE信号时域和频率参数存在差异,但其分布范围存在重叠,使得仅通过时域或频率参数进行损伤源的鉴别尚存在困难。
伴随复合材料损伤过程的AE信号是多种损伤模式的混合信号。因此,对AE信号进行聚类分析的目的是建立典型损伤机制和AE信号的对应关系。为了获得可靠的聚类结果,分别对基体、90°单向层合板、纤维束试样、反对称层合板等简单模型试样破坏过程的AE信号进行聚类分析。首先,通过对8个常用AE信号参数进行变量聚类分析表明,不同损伤机制AE信号参数分为3类时,类内相似程度较大,类间相似度较小,且相似关系一致,分别从中选择幅度、峰值频率和持续时间作为模式特征,并采用k-means算法对各类模型试样的AE信号进行了聚类分析,结合SEM观察对聚类结果进行了验证,以此建立8种典型损伤机制的AE信号训练样本。以聚类分析的结果对AE信号进行了判别分析,模式特征组间均值相等的假设检验证明,各模式特征对AE信号判别均产生有效作用。此外,以识别正确率比较了欧氏、马氏距离判别法和k近邻法的判别效果,实验结果表明,马氏距离判别法对损伤AE信号具有较好的判别效果,超过90%的识别正确率说明以幅度、峰值频率和持续时间作为模式特征,可以实现不同损伤机制AE信号的模式识别。不同判别方法的判别错误均来自于基体断裂和界面脱粘,以及基体塑性变形-1和界面损伤之间的相互误判。各典型损伤信号在模式空间中的分布情况说明,当各类别信号的相互分离程度较好时识别率较好,而当各类别信号间存在重叠时就会出现相互的误判,从而导致识别正确率的降低。虽然通过聚类和判别分析的模式识别方法可以实现对AE信号的分类和识别,但是整个分析流程相对复杂、效率低且操作上不够方便。
为进一步提高对AE信号源机制的分类和鉴别准确率和数据分析操作的便利性,更好地适应工程实际应用的需要,本课题进一步研究了基于神经网络技术的AE信号模式识别,包括分别建立竞争型SOC网络和多层前向BP网络实现对AE信号的聚类和识别。通过对相同数据集分别进行SOC网络分类和聚类分析的对比发现,两种方法分类的一致性达到98%以上,说明SOC网络对于AE信号的聚类分析是可行的和有效的。在相同结构的BP网络和实验数据的前提下,对标准BP算法及其改进算法的训练过程和识别正确率进行了比较,实验结果表明：标准BP算法训练时间长,训练结果易受到不同的网络初始值的影响,识别率最低,几乎没有实际应用价值。基于启发式的改进算法中,有动量可变学习速度法和弹性梯度下降法均能在一定程度上提高识别率,同时也能改善训练速度。基于标准数值优化的改进算法中Levenberg-Marquardt算法具有最佳的训练效果,该算法最适合作为BP网络的训练算法。
Ultra high molecular weight polyethylene (UHMWPE) fiber is a kind of high performance organic fiber with highly oriental extended-chain. It has been widely used in many fields for high specific strengthen, high specific modulus, excellent toughness, well abrasion resistance and excellent anti-impact performance, fine chemical resistance, insulation and biocompatibility. With rapid development of thermoplastic composite materials in recent years, their structures were used in more and more engineering fields. Based on "one polymer composites", the interface of PE self-reinforced composites and general performances of fiber were improved due to chemical compatibility. Meanwhile, it has more competitive advantage than other composites such as low price, rich resource and convenient recycle. Research on damage mechanisms of PE self-reinforced composites are important to the assurance of safety of the composites in service and obtain the optimal structure design. Results of damage mechanisms on glass-fiber, carbon-fiber reinforced thermoset composites revealed acoustic emission (AE) is an effective tools which can provide rich and real information during damage progress. Up to now, researches mostly focus on thermoset composites and rarely focus on thermoplastic composites. PE self-reinforced composites is a typical thermoplastic composites, this study will investigate its AE characteristic during damage progress based on AE technology. Then, correlation between damage mechanisms and AE signals will be established and damage mechanisms will be classified and identified. This study can provide a convenient and effective method for damage mechanisms identified on thermoplastic composites based on AE technology during real applications.
Damage mechanisms of fiber reinforced composites are very complicated including fiber breakage, matrix crack, interface debonding and delamination. In order to reveal AE feature of time domain and frequency domain generated from different damage mechanisms of PE self-reinforced composites and establish correlation between damage mechanisms and AE signals to classify and identify AE signals, and finally establish AE signal pattern recognition system based on artificial neural networks, this study mainly include following research work. Firstly, according to damage characteristic of thermoplastic composites, using model sample with simple structure to generate AE signals of desired damage mode, analyze AE features of time domain and frequency domain of typical damage mechanisms based on mechanical performance change and Fast Fourier transformation (FFT). Secondly, according to damage process of model sample with simple structure, the cluster analysis on AE signals were investigated including selection of similarity measure and cluster variables and validation of cluster results. Cluster analysis method of AE signals on typical damage modes was established. Results of several common methods on discriminant analysis were compared. Finally, artificial neural networks for AE signal classification and identification on PE self-reinforced composites were established and performance of neural networks due to some optimal algorithms was also compared.
The experiment revealed damage process of model sample including different damage mechanisms and AE response can reflect features of different damage stage. Matrix sample has small number of signals and poor AE activities, the damage mechanisms including plastic deformation and fracture.90°laminate generate interface damage signals with different degree. Due to complicated structure and more damage,0°laminate and [+45°/-45°] laminates have more AE signals and high AE activities. The former mainly generate AE signals from fiber breakage, the later mainly generate AE signals from in-layer shear and interlayer damage. AE signals from damage mechanisms with small degree destruction such as matrix plastic deformation and interface initial damage are low amplitude and short duration. However, AE signals from big degree destruction such as matrix fracture, interface debonding, fiber breakage and delamination are high amplitude and long duration. According to damage process, AE signals from early damage of all kinds of specimen are all low amplitude with short duration, while high amplitude with long duration AE signals mainly generated at the moment of material fracture. The results of FFT analysis on AE signals revealed different frequency features between non-damage signals and damage signals as well as among different damage mechanisms. The difference from various damage mechanisms is obvious both on time domain and frequency domain. However, the overlap of distribution results in identification difficulty when only using parameters of time domain or frequency domain.
AE signals from damage process of composites are hybrid signals with many different damage modes. The purpose of cluster analysis on AE signals is to establish correlation between typical damage mechanisms and AE signals. For obtaining reliable cluster results, simple model specimens such as pure matrix,90°unidirectional laminate, fiber bundle and [+45°/-45°] laminates were used to generate expected damage mechanisms. Firstly, the results of variable cluster analysis on 8 AE parameters revealed similarity within groups is better than similarity between groups and relation of similarity is same when all parameters were divided into 3 groups. Therefore, amplitude, peak frequency and duration selected from each group can be used as pattern features. Then, based on k-means algorithms, sample cluster analysis on all kinds of model specimens were performed to establish AE training set with 8 typical kinds of damage mechanisms. Cluster results were validated by SEM of each model specimen. According to cluster results, discriminant analysis on AE signals was also performed. The result of hypothesis test on mean equal among different model showed each pattern features were effective for discriminant analysis. Furthermore, discriminant effects of Euclidean distance, Mahalanobis distance and k nearest neighbor discriminance were compared with percentage of right identification. The results revealed Mahalanobis distance discriminance has the best effect. Percentage of right identification over 90% showed different damage mechanisms can be divided with pattern features including amplitude, peak frequency and duration. The main error of identification resulted from different discriminances were all come from identification mistake between matrix fracture and interface debonding as well as matrix plastic deformation-1 and interface damage. Distribution of AE signal in pattern space from typical damages showed better right identification resulted from better separability and identification mistake will take place when overlap each other. Classification and identification of AE signal can be realized by cluster and discriminant analysis. However, these methods are complicated in process, poor efficiency and inconvenient to real application.
In order to improving classification and identification, convenience of data analysis and more fit for demand of real application, this study investigated pattern recognition of AE signal based on artificial neural networks. These work included establishing self-organizing competitive (SOC) and error back-propagation (BP) network to realize classification and identification respectively. According to the classification results from SOC network and cluster analysis to the same data set, the classification consistency of two methods is over 98%. Therefore, SOC network is a feasible and effective tool for cluster analysis of AE signals. Based on the same data set and the same architecture of BP network, the right identification percentage with standard BP training algorithm and other improved training algorithms were compared. The results revealed standard BP algorithms is unfit for real application due to long training time, low identification and easy effected by initial value of network. Among heuristic improved method, both BP algorithm with momentum and adaptive learning rate and resilient BP algorithm can improve identification effect and accelerate training process. Among standard numerical optimal improved methods, Levenberg-Marquardt algorithm has the best training effect. It is the best algorithms to training BP networks to identify different damage mechanisms with AE signals.
引文
[1]肖长发.超高相对分子质量聚乙烯,高分子通报,2004(8)：74-88.
[2]Smith P, Lemstra PJ, Kalb B, Pennings AJ. Ultrahigh-strength polyethylene filaments by solution spinning and hot drawing.Polymer Bulletin,1979,1:733-736.
[3]Smith P, Lemstra PJ.Ultra high strength polyethylene filaments by solution spinning/drawing. Journal of Materials Science,1980,15(2):505-514.
[4]Smith P, Lemstra PJ.Ultra high strength polyethylene filaments by solution spinning/drawing 2:influence of solvent on the draw ability.Macromolecular chemistry and physics, 1979,180:2983-2986
[5]Smith P, Lemstra PJ.Ultra high strength polyethylene filaments by solution spinning/drawing 3:influence of drawing temperature.Polymer,1980,21(11):1341:1343.
[6]李涛.国内外超高分子质量聚乙烯纤维的开发应用进展.合成纤维,2007(8)：26-28.
[7]晏雄.产业用纺织品.上海：东华大学出版社,2003.
[8]蔡忠龙,冼杏娟.超高模聚乙烯纤维增强复合材料．北京：科学出版社,1997.
[9]宋俊,肖长发.UHMWPE纤维的表面改性研究进展.纺织导报,2006(12)：46-48.
[10]Yoichiro M,Michael JR,Lawrence TD. Sulfonation of UHMW-PE fibers for adhesion promotion in epoxy polymers. Journal of adhesion science and technology,2002,16, (12):1669-1685.
[11]Salehi KA,James JS, Zhong WH.Improvement of interfacial adhesion between UHMWPE fiber and epoxy matrix using functionalized graphitic nanofibers. Journal of composite materials,2007,41 (10):1163-1176.
[12]Capiati NJ, Porter RS. The concept of one polymer composites modelled with high density polyethylene. J Mater Sci,1975,10:1671-1677.
[13]Mead W T, Porter RS. The preparation and tensile properties of polyethylene composites. Journal of applied polymer science.1978,(22):3249-3265.
[14]Marias C, Feillard P. Manufacturing and mechanical characterization of unidirectional polyethylene-fiber/polyethylene-matrix composites. Composite science and technology, 1992(45):247-255.
[15]Rolel D, Yavin E, Wachtel E, Wagner HD. Experimental study of transcrystallinity in UHMWPE/LLDPE composites. Composties interfaces,1993(3):225-242.
[16]Amer MS, Ganapathiraju S. Effects of processing parameters on axial stiffness of self-reinforced polyethylene composites. Journal of applied polymer science, 2001(81):1136-1141.
[17]沈观林,胡更开.复合材料力学．北京：清华大学出版社,2006.9.
[18]袁振明,马羽宽,何泽云.AE技术及其应用．北京：机械工业出版社,1985.
[19]许凤旌,陈积懋.AE技术在复合材料发展中的应用.机械工程材料,1997,21,(4)：30-34.
[20]Fdoyle J.Wave propagation in structures. New York Berlin Heidelberg:Springer-Verlag,1997.
[21]Hill R, Okoroafor EU, Pristo AM.Acoustic emission wave propagation model and issues of damage induction in composites. Ultrasonics.1996,34:321-325.
[22]Bohse J. Acoustic emission characteristics of micro-failure processes in polymer blends and composites.Composite science and technology,2000,60:1213-1226.
[23]耿荣生,沈功田,刘时风.AE信号处理和分析技术.无损检测,2002,(1)：23-28.
[24]沈功田,耿荣生,刘时风.AE信号的参数分析方法.无损检测.2002,(2)：72-77.
[25]Jeng JS, Ono K, Yang JM. Fracture mechanism studies of carbon fiber reinforced thermoplastic composites by acoustic emission.Progress in acoustic emission(IV). Kobe, Japan,1988.
[26]Shiva M, Ishida T, Kishi T.Acoustic emission evaluation of araldite reinforced aluminum laminate. Progress in Acoustic Emission(IV). Kobe, Japan,1988.
[27]Yamaguchi K,Oyaizu H,Hirai J et al. Recognition of fracture modes in fiber reinforced plastics by acoustic emission waveform parameters.Progress in Acoustic Emission(IV) Kobe, Japan,1988.
[28]Barre S, Benzeggagh ML. On the use of acoustic emission to investigate damage mechanisms in glass-fiber-reinforced polypropylene. Composite science and technology,1994,52:369-376.
[29]Kumosa M, Hull D, Price N. Acoutic emission from stress corrosion cracks in aligned GRP. J Mater Sci,1987,22:331-336.
[30]Gioradano M,Calabro A, Esposito C, Amore AD, Nicolais L, An acoustic emission characterization of the failure modes in polymer composite materials.Composite science and technology,1998,58:1923-1928.
[31]Yu YH, Choi JH, Kweon JH,Kim DH.A study on the failure detection of composite materials using an acoustic emission.Composite Structures,2006,75:163-169.
[32]Woo SC, Goo NS.Analysis of the bending fracture process for piezoelectric composite actuators using dominant frequency bands by acoustic emission.Composite science and technology,2007,67:1499-1508.
[33]耿荣生,沈功田,刘时风.模态声发射基本理论.无损检测,2002,24,(7)：302-306.
[34]耿荣生,沈功田,刘时风.模态声发射.无损检测,2002,24,(8)：341-345.
[35]Gorman MR.Plate wave acoustic emission.JASA,1991,90(1):358-364.
[36]Gorman MR, Ziola SM.Plate waves produced by transverse matrix cracking. Ultrasonics,1991,(29):245-251.
[37]Prosser WH,Gorman MR.Plate mode velocities in garaphite/epoxy plates, JASA.1994, 96(2):902-907.
[38]Prosser WH,Jackson KE,Kellas S,Smith BT,McKeon J,Friedman A.Advanced waveform based acoustic emission detection of matrix cracking in composites.Materials evaluation,1995,53(9):1052-1058.
[39]Mikael J, Peter G.Broad-band transient recording and characterization of acoustic emission events in composite laminates. Composite science and technology,2000,60:2803-2818.
[40]Mikael J.Waveform based clustering and classification of AE transients in composite laminates using principal component analysis. NDT&E Int,2002,35(3):367-376.
[41]Christian UG, Florian F, Jochen HK, et al. Improvements of AE technique using wavelet algorithms, coherence functions and automatic data analysis. Construction and building materials,2004,18:203-213.
[42]Velayudham A, Krishnamurthy R, Soundarapandian T. Acoustic emission based drill condition monitoring during drilling of glass/phonetic polymeric composite using wavelet packet transform. Materials science and engineering:A,2005(412):141-145.
[43]Qi G. Wavelet-based AE characterization of composite materials. NDT&E International,2003(3):133-144
[44]Pappas YZ, Markopoulos YP. Failure mechanisms analysis of 2D carbon/carbon using acoustic emission monitoring. NDT&E International,1998(31):157-163.
[45]Moevus M, Godin N, R'Mili M, et al. Analysis of damage mechanisms and associated acoustic emission in two SiCf/[Si-B-C] composites exhibiting different tensile behaviours. Part Ⅰ:Damage patterns and acoustic emission activity. Compos Sci Technol,2008, 68:1250-1257
[46]Moevus M, Godin N, R'Mili M, et al. Analysis of damage mechanisms and associated acoustic emission in two SiCf/[Si-B-C] composites exhibiting different tensile behaviours.Part Ⅱ:Unsupervised acoustic emission data clustering. Compos Sci Technol,2008,68:1258-1265.
[47]Kostopoulos V, Loutas T, Dassios K. Fracture behavior and damage mechanisms identification of SiC/glass ceramic composites using AE monitoring. Compos Sci Technol, 2007,67:1740-1746.
[48]Kostopoulos V, Loutas T H. On the identification of the failure mechanisms in oxide/oxide composites using acoustic emission. NDT & E International,2003,36(8):571-580.
[49]Bhat C, Bhat MR. Acoustic emission characterization of failure modes in composites with ANN. Composite Structures,2003,61(3):213-220.
[50]Philippidis TP, Nikolaidis VN, Anastassopoulos AA. Damage characterization of carbon/carbon laminates using neural network techniques on AE signals. NDT & E International 1998,31:329-340.
[51]Huguet S, Godin N. Use of acoustic emission to identify damage modes in glass fibre reinforced polyester. Composite Science and Technology,2002,62(10-11):1433-1444.
[52]BarHN, Bhat MR, Murthy CRL. Identification of failure modes in GFRP using PVDF sensors:ANN approach. Composite Structures 2004; 65:231-237.
[53]Godin N, Huguet S. Integration of the Kohonen's self-organising map and k-means algorithm for the segmentation of the AE data collected during tensile tests on cross-ply composite. NDT & E International,2005,38(4):299-309.
[54]Godin N, Huguet S. Clustering of acoustic emission signals collected during tensile tests on unidirectional glass/polyester composite using supervised and unsupervised classifiers. NDT & E International,2004,37(4):253-264.
[55]张慧萍,庄兴民,晏雄,高小玲.聚乙烯自增强复合材料的制备及力学性能.高分子材料科学与工程,2004,20(1)：121-124,128.
[56]张慧萍,庄兴民,晏雄,高小玲.聚乙烯自增强复合材料的热分析.高分子材料科学与工程,2004,20(6)：176-179.
[57]庄兴民,晏雄.UHMWPE/HDPE层合板拉伸损伤扩展的有限元数值模拟.复合材料学报,2005(5)：141-146.
[58]杨璧玲,张慧萍,张同华,庄兴民,晏雄.含材料非线性的热塑性聚乙烯自增强复合材料逐渐损伤分析.材料工程,2009,11：65-68,98
[59]Zhuang XM, Yan X.Investigation of damage mechanisms in self-reinforced polyethylene composites by acoustic emission. Composite Science and Technology,2006,66:444-449.
[60]庄兴民,张慧萍,晏雄.聚乙烯自增强复合材料损伤过程的AE特征.复合材料学报,2006(2)： 82-87.
[61]张同华,杨壁玲,彭永超等.基于AE检测技术的PE/PE自增强复合材料破损机理分析.材料工程,2007(1)：56-59,64
[62]Yang BL, Yan X. Identification of damage mechanisms in self-reinforced polyethylene composites by using pattern recognition techniques on AE data. Nondestructive testing and evaluation,2009,24:251-260.
[63]杨璧玲,张同华,张慧萍,周晓鸥,晏雄.基于AE信号模式识别的UHMWPE/LDPE复合材料损伤机理分析.复合材料学报,2008,25(2)：35-40．
[64]杨明纬,马云中,刘哲军.声发射检测.北京：机械工业出版社,2005.
[65]杨瑞峰,马铁华.声发射技术研究及应用进展.中北大学学报(自然科学版),2006,7(5)：456-471.
[66]AEwin software users manual(rev.1.90).Physical acoustics corporation,New Jersey,USA,2004.
[67]Bussiba A, Kupiec M, Piat R, Bohlke T.Fracture characterization of C/C composites under various stress modes by monitoring both mechanical and acoustic responses. Carbon,2008,46:618-630.
[68]王旭,晏雄.聚乙烯自增强复合材料损伤行为的声发射特征.纺织学报,2010,3：27-31.
[69]Renner K, Yang MS, Moczo J, Choi HJ, Pukanszky B.Analysis of the debonding process in polypropylene model composites.European polymer journal 2005,41:2520-2529.
[70]. - ,北京： ,2004.
[71]Wang X, Zhang HP, Yan X. Frequency spectral analysis on AE signals of damage mechanisms in PE/PE composites.ICAFPM, Shanghai, China,2009,278-281.
[72]Ramirez-Jimenez CR, Papadakis N, Reynolds N, Gan TH, Purnell P, Pharaoh P. Identification of failure modes in glass/polypropylene composites by means of the primary frequency content of the acoustic emission event. Compos Sci Technol,2004,64: 1819-1827.
[73]Wang X, Zhang HP, Yan X.Frequency features of acoustic emission on failure mechanisms in PE self-reinforced laminates, Proceedings of the second international conference on advanced textile materials and manufacturing technology, Hangzhou, China,2010,501-505.
[74]． ．北京： ,2005.
[75]北京：科学出版社,2006.
[76]Pipes RB, Pagano NJ. Interlaminar stresses in composite laminates under uniform axial extension. Journal of composite materials,1970,4,(4):538-548.
[77]Pagano NJ, Pipes RB. Some observations on the interlaminar strength of composite laminates. International journal of mechanical sciences,1973,15,(8):679-686.
[78]孙即祥,姚伟,滕书华,模式识别北京：国防工业出版社,2009.
[79]Yang BL, Zhuang XM, Zhang TH, Yan X.Damage mode identification for the clustering analysis of AE signals in thermoplastic composites, J Nondestruct Eval,2009,28:163-168.
[80]Yang BL, Wang X, Zhang HP, Yan X.Using clustering of acoustic emission signals on damage mechanisms analysis of quasi-isotropic self-reinforced polyethylene composites. ICAFPM, Shanghai, China,2007,423-425.
[81]Wang X, Yang BL, Zhang HP, Yan X, Use of acoustic emission to identify damage modes in UHMWPE/LDPE laminates.ICAFPM, Shanghai, China,2007,245-247.
[82]Wang X, Zhang TH, Yan X, Acoustic emission characteristic of damage modes on UHMWPE/LDPE laminates. Proceedings of the fiber society 2009 spring conference, Shanghai, China,2009,629-632.
[83]张立军,任英华.多元统计分析实验.北京：中国统计出版社,2009．
[84]孙亮,禹晶.模式识别原理.北京：北京工业大学出版社,2009.
[85]杨淑莹.模式识别与智能计算-matlab技术实现,北京：电子工业出版社,2008.
[86]李金宗.模式识别导论,北京：高等教育出版社,1994.
[87]Johnson RA, Wichern DW著,陆璇,叶俊译.实用多元统计分析(第6版),北京：清华大学出版社,2008.
[88]王静龙.多元统计分析,北京：科学出版社,2008.
[89]董长虹.Matlab神经网络与应用(第2版),北京：国防工业出版社,2007.
[90]Martin TH, Howard BD, Mark HB神经网络设计,北京：机械工业出版社,2002.
[91]Widrow B, Hoff ME.Adaptive switching circuits. IRE WESCON Convention Record, 4:96-104,1960.
[92]Werbos PJ. Beyond regression:New tools for prediction and analysis in the behavioral sciences. Ph.D Thesis, Harvard University, Cambridge,MA,1974.
[93]苏高利,邓芳萍.论基于Matlab语言BP神经网络的改进算法.科技通报,2003,19(2)：130-135.
[94]Demuth H, Beale M, Hagan Martin.Neural network toolbox 6 user's guide.The Math Works Inc.,2007
[95]Battiti R. First and second order methods for learning:Between steepest descent and Newton's method. Neural Computation,1992,4 (2):141-166.
[96]Hagan MT,Menhaj M. Training feedforward networks with the Marquardt algorithm.IEEE transactions on neural networks.1994,5 (6):989～993.
[97]周开利,康耀红．神经网络模型及其matlab仿真程序设计.北京：清华大学出版社,2005.7
[2]Smith P, Lemstra PJ, Kalb B, Pennings AJ. Ultrahigh-strength polyethylene filaments by solution spinning and hot drawing.Polymer Bulletin,1979,1:733-736.
[3]Smith P, Lemstra PJ.Ultra high strength polyethylene filaments by solution spinning/drawing. Journal of Materials Science,1980,15(2):505-514.
[4]Smith P, Lemstra PJ.Ultra high strength polyethylene filaments by solution spinning/drawing 2:influence of solvent on the draw ability.Macromolecular chemistry and physics, 1979,180:2983-2986
[5]Smith P, Lemstra PJ.Ultra high strength polyethylene filaments by solution spinning/drawing 3:influence of drawing temperature.Polymer,1980,21(11):1341:1343.
[6]李涛.国内外超高分子质量聚乙烯纤维的开发应用进展.合成纤维,2007(8)：26-28.
[7]晏雄.产业用纺织品.上海：东华大学出版社,2003.
[8]蔡忠龙,冼杏娟.超高模聚乙烯纤维增强复合材料．北京：科学出版社,1997.
[9]宋俊,肖长发.UHMWPE纤维的表面改性研究进展.纺织导报,2006(12)：46-48.
[10]Yoichiro M,Michael JR,Lawrence TD. Sulfonation of UHMW-PE fibers for adhesion promotion in epoxy polymers. Journal of adhesion science and technology,2002,16, (12):1669-1685.
[11]Salehi KA,James JS, Zhong WH.Improvement of interfacial adhesion between UHMWPE fiber and epoxy matrix using functionalized graphitic nanofibers. Journal of composite materials,2007,41 (10):1163-1176.
[12]Capiati NJ, Porter RS. The concept of one polymer composites modelled with high density polyethylene. J Mater Sci,1975,10:1671-1677.
[13]Mead W T, Porter RS. The preparation and tensile properties of polyethylene composites. Journal of applied polymer science.1978,(22):3249-3265.
[14]Marias C, Feillard P. Manufacturing and mechanical characterization of unidirectional polyethylene-fiber/polyethylene-matrix composites. Composite science and technology, 1992(45):247-255.
[15]Rolel D, Yavin E, Wachtel E, Wagner HD. Experimental study of transcrystallinity in UHMWPE/LLDPE composites. Composties interfaces,1993(3):225-242.
[16]Amer MS, Ganapathiraju S. Effects of processing parameters on axial stiffness of self-reinforced polyethylene composites. Journal of applied polymer science, 2001(81):1136-1141.
[17]沈观林,胡更开.复合材料力学．北京：清华大学出版社,2006.9.
[18]袁振明,马羽宽,何泽云.AE技术及其应用．北京：机械工业出版社,1985.
[19]许凤旌,陈积懋.AE技术在复合材料发展中的应用.机械工程材料,1997,21,(4)：30-34.
[20]Fdoyle J.Wave propagation in structures. New York Berlin Heidelberg:Springer-Verlag,1997.
[21]Hill R, Okoroafor EU, Pristo AM.Acoustic emission wave propagation model and issues of damage induction in composites. Ultrasonics.1996,34:321-325.
[22]Bohse J. Acoustic emission characteristics of micro-failure processes in polymer blends and composites.Composite science and technology,2000,60:1213-1226.
[23]耿荣生,沈功田,刘时风.AE信号处理和分析技术.无损检测,2002,(1)：23-28.
[24]沈功田,耿荣生,刘时风.AE信号的参数分析方法.无损检测.2002,(2)：72-77.
[25]Jeng JS, Ono K, Yang JM. Fracture mechanism studies of carbon fiber reinforced thermoplastic composites by acoustic emission.Progress in acoustic emission(IV). Kobe, Japan,1988.
[26]Shiva M, Ishida T, Kishi T.Acoustic emission evaluation of araldite reinforced aluminum laminate. Progress in Acoustic Emission(IV). Kobe, Japan,1988.
[27]Yamaguchi K,Oyaizu H,Hirai J et al. Recognition of fracture modes in fiber reinforced plastics by acoustic emission waveform parameters.Progress in Acoustic Emission(IV) Kobe, Japan,1988.
[28]Barre S, Benzeggagh ML. On the use of acoustic emission to investigate damage mechanisms in glass-fiber-reinforced polypropylene. Composite science and technology,1994,52:369-376.
[29]Kumosa M, Hull D, Price N. Acoutic emission from stress corrosion cracks in aligned GRP. J Mater Sci,1987,22:331-336.
[30]Gioradano M,Calabro A, Esposito C, Amore AD, Nicolais L, An acoustic emission characterization of the failure modes in polymer composite materials.Composite science and technology,1998,58:1923-1928.
[31]Yu YH, Choi JH, Kweon JH,Kim DH.A study on the failure detection of composite materials using an acoustic emission.Composite Structures,2006,75:163-169.
[32]Woo SC, Goo NS.Analysis of the bending fracture process for piezoelectric composite actuators using dominant frequency bands by acoustic emission.Composite science and technology,2007,67:1499-1508.
[33]耿荣生,沈功田,刘时风.模态声发射基本理论.无损检测,2002,24,(7)：302-306.
[34]耿荣生,沈功田,刘时风.模态声发射.无损检测,2002,24,(8)：341-345.
[35]Gorman MR.Plate wave acoustic emission.JASA,1991,90(1):358-364.
[36]Gorman MR, Ziola SM.Plate waves produced by transverse matrix cracking. Ultrasonics,1991,(29):245-251.
[37]Prosser WH,Gorman MR.Plate mode velocities in garaphite/epoxy plates, JASA.1994, 96(2):902-907.
[38]Prosser WH,Jackson KE,Kellas S,Smith BT,McKeon J,Friedman A.Advanced waveform based acoustic emission detection of matrix cracking in composites.Materials evaluation,1995,53(9):1052-1058.
[39]Mikael J, Peter G.Broad-band transient recording and characterization of acoustic emission events in composite laminates. Composite science and technology,2000,60:2803-2818.
[40]Mikael J.Waveform based clustering and classification of AE transients in composite laminates using principal component analysis. NDT&E Int,2002,35(3):367-376.
[41]Christian UG, Florian F, Jochen HK, et al. Improvements of AE technique using wavelet algorithms, coherence functions and automatic data analysis. Construction and building materials,2004,18:203-213.
[42]Velayudham A, Krishnamurthy R, Soundarapandian T. Acoustic emission based drill condition monitoring during drilling of glass/phonetic polymeric composite using wavelet packet transform. Materials science and engineering:A,2005(412):141-145.
[43]Qi G. Wavelet-based AE characterization of composite materials. NDT&E International,2003(3):133-144
[44]Pappas YZ, Markopoulos YP. Failure mechanisms analysis of 2D carbon/carbon using acoustic emission monitoring. NDT&E International,1998(31):157-163.
[45]Moevus M, Godin N, R'Mili M, et al. Analysis of damage mechanisms and associated acoustic emission in two SiCf/[Si-B-C] composites exhibiting different tensile behaviours. Part Ⅰ:Damage patterns and acoustic emission activity. Compos Sci Technol,2008, 68:1250-1257
[46]Moevus M, Godin N, R'Mili M, et al. Analysis of damage mechanisms and associated acoustic emission in two SiCf/[Si-B-C] composites exhibiting different tensile behaviours.Part Ⅱ:Unsupervised acoustic emission data clustering. Compos Sci Technol,2008,68:1258-1265.
[47]Kostopoulos V, Loutas T, Dassios K. Fracture behavior and damage mechanisms identification of SiC/glass ceramic composites using AE monitoring. Compos Sci Technol, 2007,67:1740-1746.
[48]Kostopoulos V, Loutas T H. On the identification of the failure mechanisms in oxide/oxide composites using acoustic emission. NDT & E International,2003,36(8):571-580.
[49]Bhat C, Bhat MR. Acoustic emission characterization of failure modes in composites with ANN. Composite Structures,2003,61(3):213-220.
[50]Philippidis TP, Nikolaidis VN, Anastassopoulos AA. Damage characterization of carbon/carbon laminates using neural network techniques on AE signals. NDT & E International 1998,31:329-340.
[51]Huguet S, Godin N. Use of acoustic emission to identify damage modes in glass fibre reinforced polyester. Composite Science and Technology,2002,62(10-11):1433-1444.
[52]BarHN, Bhat MR, Murthy CRL. Identification of failure modes in GFRP using PVDF sensors:ANN approach. Composite Structures 2004; 65:231-237.
[53]Godin N, Huguet S. Integration of the Kohonen's self-organising map and k-means algorithm for the segmentation of the AE data collected during tensile tests on cross-ply composite. NDT & E International,2005,38(4):299-309.
[54]Godin N, Huguet S. Clustering of acoustic emission signals collected during tensile tests on unidirectional glass/polyester composite using supervised and unsupervised classifiers. NDT & E International,2004,37(4):253-264.
[55]张慧萍,庄兴民,晏雄,高小玲.聚乙烯自增强复合材料的制备及力学性能.高分子材料科学与工程,2004,20(1)：121-124,128.
[56]张慧萍,庄兴民,晏雄,高小玲.聚乙烯自增强复合材料的热分析.高分子材料科学与工程,2004,20(6)：176-179.
[57]庄兴民,晏雄.UHMWPE/HDPE层合板拉伸损伤扩展的有限元数值模拟.复合材料学报,2005(5)：141-146.
[58]杨璧玲,张慧萍,张同华,庄兴民,晏雄.含材料非线性的热塑性聚乙烯自增强复合材料逐渐损伤分析.材料工程,2009,11：65-68,98
[59]Zhuang XM, Yan X.Investigation of damage mechanisms in self-reinforced polyethylene composites by acoustic emission. Composite Science and Technology,2006,66:444-449.
[60]庄兴民,张慧萍,晏雄.聚乙烯自增强复合材料损伤过程的AE特征.复合材料学报,2006(2)： 82-87.
[61]张同华,杨壁玲,彭永超等.基于AE检测技术的PE/PE自增强复合材料破损机理分析.材料工程,2007(1)：56-59,64
[62]Yang BL, Yan X. Identification of damage mechanisms in self-reinforced polyethylene composites by using pattern recognition techniques on AE data. Nondestructive testing and evaluation,2009,24:251-260.
[63]杨璧玲,张同华,张慧萍,周晓鸥,晏雄.基于AE信号模式识别的UHMWPE/LDPE复合材料损伤机理分析.复合材料学报,2008,25(2)：35-40．
[64]杨明纬,马云中,刘哲军.声发射检测.北京：机械工业出版社,2005.
[65]杨瑞峰,马铁华.声发射技术研究及应用进展.中北大学学报(自然科学版),2006,7(5)：456-471.
[66]AEwin software users manual(rev.1.90).Physical acoustics corporation,New Jersey,USA,2004.
[67]Bussiba A, Kupiec M, Piat R, Bohlke T.Fracture characterization of C/C composites under various stress modes by monitoring both mechanical and acoustic responses. Carbon,2008,46:618-630.
[68]王旭,晏雄.聚乙烯自增强复合材料损伤行为的声发射特征.纺织学报,2010,3：27-31.
[69]Renner K, Yang MS, Moczo J, Choi HJ, Pukanszky B.Analysis of the debonding process in polypropylene model composites.European polymer journal 2005,41:2520-2529.
[70]. - ,北京： ,2004.
[71]Wang X, Zhang HP, Yan X. Frequency spectral analysis on AE signals of damage mechanisms in PE/PE composites.ICAFPM, Shanghai, China,2009,278-281.
[72]Ramirez-Jimenez CR, Papadakis N, Reynolds N, Gan TH, Purnell P, Pharaoh P. Identification of failure modes in glass/polypropylene composites by means of the primary frequency content of the acoustic emission event. Compos Sci Technol,2004,64: 1819-1827.
[73]Wang X, Zhang HP, Yan X.Frequency features of acoustic emission on failure mechanisms in PE self-reinforced laminates, Proceedings of the second international conference on advanced textile materials and manufacturing technology, Hangzhou, China,2010,501-505.
[74]． ．北京： ,2005.
[75]北京：科学出版社,2006.
[76]Pipes RB, Pagano NJ. Interlaminar stresses in composite laminates under uniform axial extension. Journal of composite materials,1970,4,(4):538-548.
[77]Pagano NJ, Pipes RB. Some observations on the interlaminar strength of composite laminates. International journal of mechanical sciences,1973,15,(8):679-686.
[78]孙即祥,姚伟,滕书华,模式识别北京：国防工业出版社,2009.
[79]Yang BL, Zhuang XM, Zhang TH, Yan X.Damage mode identification for the clustering analysis of AE signals in thermoplastic composites, J Nondestruct Eval,2009,28:163-168.
[80]Yang BL, Wang X, Zhang HP, Yan X.Using clustering of acoustic emission signals on damage mechanisms analysis of quasi-isotropic self-reinforced polyethylene composites. ICAFPM, Shanghai, China,2007,423-425.
[81]Wang X, Yang BL, Zhang HP, Yan X, Use of acoustic emission to identify damage modes in UHMWPE/LDPE laminates.ICAFPM, Shanghai, China,2007,245-247.
[82]Wang X, Zhang TH, Yan X, Acoustic emission characteristic of damage modes on UHMWPE/LDPE laminates. Proceedings of the fiber society 2009 spring conference, Shanghai, China,2009,629-632.
[83]张立军,任英华.多元统计分析实验.北京：中国统计出版社,2009．
[84]孙亮,禹晶.模式识别原理.北京：北京工业大学出版社,2009.
[85]杨淑莹.模式识别与智能计算-matlab技术实现,北京：电子工业出版社,2008.
[86]李金宗.模式识别导论,北京：高等教育出版社,1994.
[87]Johnson RA, Wichern DW著,陆璇,叶俊译.实用多元统计分析(第6版),北京：清华大学出版社,2008.
[88]王静龙.多元统计分析,北京：科学出版社,2008.
[89]董长虹.Matlab神经网络与应用(第2版),北京：国防工业出版社,2007.
[90]Martin TH, Howard BD, Mark HB神经网络设计,北京：机械工业出版社,2002.
[91]Widrow B, Hoff ME.Adaptive switching circuits. IRE WESCON Convention Record, 4:96-104,1960.
[92]Werbos PJ. Beyond regression:New tools for prediction and analysis in the behavioral sciences. Ph.D Thesis, Harvard University, Cambridge,MA,1974.
[93]苏高利,邓芳萍.论基于Matlab语言BP神经网络的改进算法.科技通报,2003,19(2)：130-135.
[94]Demuth H, Beale M, Hagan Martin.Neural network toolbox 6 user's guide.The Math Works Inc.,2007
[95]Battiti R. First and second order methods for learning:Between steepest descent and Newton's method. Neural Computation,1992,4 (2):141-166.
[96]Hagan MT,Menhaj M. Training feedforward networks with the Marquardt algorithm.IEEE transactions on neural networks.1994,5 (6):989～993.
[97]周开利,康耀红．神经网络模型及其matlab仿真程序设计.北京：清华大学出版社,2005.7