To overcome some drawbacks of Viterbi algorithm （VA）, such as exponential growing complexity of decoding, and its poor performance under bad channel conditions, some available known information must be used as cons...To overcome some drawbacks of Viterbi algorithm （VA）, such as exponential growing complexity of decoding, and its poor performance under bad channel conditions, some available known information must be used as constrained condition and apriori knowledge for decoding. A new constrained VA is proposed by adding con- straint bits directly for conventional codec. Compared with the conventional VA, under the bad channel condi- tion, the proposed scheme can improve the peak signal to noise ratio （PSNR） of the decoding image 2--10 dB by changing the number of constrained bits. Experimental results show that it is an efficient error-controlling way for the transmission of set partitioning in hierarchical trees （SPIHT） coded image.展开更多
结合旋转机械启停阶段振动信号的特点,提出一种基于Viterbi算法的Gabor阶比跟踪(Gabor order tracking based on Viterbi,V_GOT)算法,此算法采用Viterbi算法代替了传统的Gabor阶比跟踪(Gabor order tracking,GOT)算法中的时频滤波技术。...结合旋转机械启停阶段振动信号的特点,提出一种基于Viterbi算法的Gabor阶比跟踪(Gabor order tracking based on Viterbi,V_GOT)算法,此算法采用Viterbi算法代替了传统的Gabor阶比跟踪(Gabor order tracking,GOT)算法中的时频滤波技术。V_GOT算法和传统的GOT算法相比,其能够对复杂机械振动信号产生的邻近阶比和交叉阶比分量进行有效的跟踪和分离,并且具有计算量小、精度高、无需转速计等硬件和用纯软件的方法实现等优点。详细讨论了V_GOT技术的基本原理、算法及进行阶比跟踪的实现过程,另外,对偶函数对Gabor阶比跟踪结果的影响进行了深入的研究。采用仿真和实际试验对V_GOT算法进行了验证,试验结果表明该方法能够在时频域准确地提取幅值和复杂频率变化的阶比,适合于复杂旋转机械振动响应特征提取。展开更多
针对航空发动机的突发故障,提出了一种基于多状态混合高斯隐马尔科夫模型(mixture of Gaussian-hidden Markov model,简称MOG-HMM)和Viterbi算法相结合的预测方法。首先,根据航空发动机突发故障的历史监测数据建立多状态MOG-HMM模型,确...针对航空发动机的突发故障,提出了一种基于多状态混合高斯隐马尔科夫模型(mixture of Gaussian-hidden Markov model,简称MOG-HMM)和Viterbi算法相结合的预测方法。首先,根据航空发动机突发故障的历史监测数据建立多状态MOG-HMM模型,确定状态数、状态转移矩阵、观察值概率分布以及最终的突发故障状态;然后,对新采集的观测数据,通过Viterbi算法解码出该观测数据对应的当前状态;最后,计算该状态到达突发故障状态的时间间隔,从而可以对突发故障进行预测。仿真和实验结果表明,该方法能够实现对突发故障的预测,并且符合标准预测指标的要求。展开更多
文摘To overcome some drawbacks of Viterbi algorithm （VA）, such as exponential growing complexity of decoding, and its poor performance under bad channel conditions, some available known information must be used as constrained condition and apriori knowledge for decoding. A new constrained VA is proposed by adding con- straint bits directly for conventional codec. Compared with the conventional VA, under the bad channel condi- tion, the proposed scheme can improve the peak signal to noise ratio （PSNR） of the decoding image 2--10 dB by changing the number of constrained bits. Experimental results show that it is an efficient error-controlling way for the transmission of set partitioning in hierarchical trees （SPIHT） coded image.
文摘结合旋转机械启停阶段振动信号的特点,提出一种基于Viterbi算法的Gabor阶比跟踪(Gabor order tracking based on Viterbi,V_GOT)算法,此算法采用Viterbi算法代替了传统的Gabor阶比跟踪(Gabor order tracking,GOT)算法中的时频滤波技术。V_GOT算法和传统的GOT算法相比,其能够对复杂机械振动信号产生的邻近阶比和交叉阶比分量进行有效的跟踪和分离,并且具有计算量小、精度高、无需转速计等硬件和用纯软件的方法实现等优点。详细讨论了V_GOT技术的基本原理、算法及进行阶比跟踪的实现过程,另外,对偶函数对Gabor阶比跟踪结果的影响进行了深入的研究。采用仿真和实际试验对V_GOT算法进行了验证,试验结果表明该方法能够在时频域准确地提取幅值和复杂频率变化的阶比,适合于复杂旋转机械振动响应特征提取。
文摘针对航空发动机的突发故障,提出了一种基于多状态混合高斯隐马尔科夫模型(mixture of Gaussian-hidden Markov model,简称MOG-HMM)和Viterbi算法相结合的预测方法。首先,根据航空发动机突发故障的历史监测数据建立多状态MOG-HMM模型,确定状态数、状态转移矩阵、观察值概率分布以及最终的突发故障状态;然后,对新采集的观测数据,通过Viterbi算法解码出该观测数据对应的当前状态;最后,计算该状态到达突发故障状态的时间间隔,从而可以对突发故障进行预测。仿真和实验结果表明,该方法能够实现对突发故障的预测,并且符合标准预测指标的要求。
