BAM网络在飞机空中特情处置中的应用

提出了将BAM网络用于飞机空中特情处置的方法，探讨了利用BAM网络映射飞机上故障代码信息与特性处置措施的关系，实现对飞行员进行正确操纵提示，具体实现方法表明，这种方法可以高效地完成类似任务，为进一步开展将神经网络应用于飞机故障诊断，特情处置等研究提供了一种有效的方法。     

Stability analysis of BAM neural networks with time-varying delays

Some new criteria for the global asymptotic stability of the equilibrium point for the bi-directional associative memory neural networks with time varying delays are presented. The obtained results present the structure of linear matrix inequality which can be solved efficiently. The comparison with some previously reported results in the literature demonstrates that the results in this paper provide one more set of criteria for determining the stability of the bi-directional associative memory neural networks with delays.     

Stability analysis of BAM neural networks with time-varying delays

Some new criteria for the global asymptotic stability of the equilibrium point for the bi-directional associative memory neural networks with time varying delays are presented. The obtained results present the structure of linear matrix inequality which can be solved efficiently. The comparison with some previously reported results in the literature demonstrates that the results in this paper provide one more set of criteria for determining the stability of the bi-directional associative memory neural networks with delays.     

多重训练BAM算法中强化系数的解析求取

从ＢＡＭ的能量函数出发推导出强化系数的解析解形式。在强化系数的作用下，ＢＡＭ网将被强化矢量对存储在皮知矢量对为中心Ｈｅｍｍｉｎｇ距离为１的邻域里的能量最小点，人而保证了该矢量对的正确联想。给出了根据此解析算式编制的算法和计算实例。     

BAM神经网络的稳定性分析

本文研究了BAM神经网络的稳定性问题,通过构造新的Lyapunov泛函,给出了此类系统平衡点渐近稳定的充分条件,并举例说明了结果的有效性和保守性.该充分条件对丰富和完善了神经网络的稳定性理论体系,具有积极的意义.     

具有变系数和变时滞的BAM神经网络的全局指数稳定性的新判据

研究了一类具有变系数和变时滞的联想记忆神经网络的全局指数稳定性。通过选择适当的Lyapunov-krasovskii泛函,利用不等式技巧给出了联想记忆神经网络的全局指数稳定性的新判据。     

分布时滞模糊BAM神经网络模型的指数稳定性

详细介绍了一类具分布时滞的模糊BAM（Bi·direction Associate Memory）神经网络模型．在合适的条件下,通过数学分析技巧和压缩映像原理,证明了模型平衡点的存在唯一性;通过构造Liapunov泛函,利用Lipschitz激励函数性质,获得了平衡点的指数稳定性．     

牛肾上腺髓质8-22肽在福尔马林持续性痛中对吗啡耐受的调制

观察椎管内注射感觉神经元特异性受体选择性激动剂牛肾上腺髓质8-22肽(bovine adrenal medulla 8-22,BAM8-22)在福尔马林引起的持续性痛中对吗啡耐受的影响.结果表明,吗啡(20 μg)在正常大鼠中能显著抑制福尔马林引起的痛行为,多次应用吗啡导致耐受后,其抑制痛行为的能力大大减弱(P＜0.001);吗啡耐受后,BAM8-22(0.1nmol)能翻转吗啡的耐受效应,福尔马林引起第2期抬足/舔爪持续时间和抖动次数分别减少了39.4％ (P＜0.001)和25.3％(P＜0.05).每天椎管内联合应用BAM8-22(0.1 nmol)和吗啡(20峭)不影响吗啡耐受的形成,但隔天给予BAM8-22则能有效延缓吗啡耐受的形成,福尔马林引起第2期缩足舔爪和抖动分别为14.7 min和234.5次,与吗啡耐受鼠相比,分别减少了41.0％ (P＜0.001)和24.8％(P＜0.05).然而,BAM8-22并没有完全翻转或抑制吗啡的耐受(P＜0.001).此外,连续6d给予BAM8-22后会降低吗啡在福尔马林持续痛中的抗伤害作用.证明在福尔马林引起的持续性痛中,SNSR受体参与了调制阿片受体的敏感性.同时,提示在持续性痛中,通过BAM8-22延缓或翻转吗啡耐受是利用阿片受体治疗持续性痛的有效方法.     

Application of MBAM Neural Network in CNC Machine Fault Diagnosis

In ruder to improve the bidirectional associative memory (BAM) performance, a modified BAM medei(MBAM) is used to enhance neural netwcrk(NN)‘s memory capacity and error correction capability, theoretical analysis and experment results illuminate that MBAM performs much better than the original BAM. The MBAM is used in computer numeric control(CNC) machine fault diagnosis, it not only can complete fault diagnosis correctly but also have fairly high error correction capability for disturbed Input Information sequence. Moreover MBAM model is a more convenient and effective method of solving the problem of CNC electric system fault diagnosis.     

基于FTA与BAM神经网络融合的飞机故障诊断方法

飞机由大量彼此关联的组件组合而成,其大规模特性使得基于故障树(FTA)和基于神经网络的故障诊断方法在应用于其故障诊断时分别存在空间爆炸问题和训练样本整理困难问题.本文融合故障树和BAM神经网络,由故障树归纳出系统所有的故障模式,整理出BAM神经网络所需的具有规范性、独立性、正交性的训练样本,然后用BAM神经网络实现飞机故障的快速和准确诊断.实验评估结果表明,融合方法有良好的可扩展性,而且故障判别率提升了20%.