多媒体设备故障信号优化检测仿真研究
|
摘要
针对当前多媒体设备故障信号检测方法未考虑故障信号隶属度,导致故障信号检测准确性系数低、收敛速度较慢等问题,提出基于模糊关系的多媒体设备故障信号优化检测方法。利用设备运行状态和设备状态变化幅值及设备状态信号采集的频率,构建设备信号采集频率的预测模型。对设备不同要素赋予不同权值,完成设备信号采集频率智能调整,实现多媒体设备信号自适应采集。将采集到的多媒体设备信号划分为振动信号和声发射信号两种,分别对两种信号的模糊状态进行提取,并得到该部分信号在设备中的隶属度值。通过模糊加权线性变换将得到的多媒体设备信号模糊关系矩阵及模糊特征向量等数据进行融合,利用决策规则判断融合后信号数据中的故障信号,完成设备故障信号优化检测。仿真表明,所提方法收敛速度快,故障信号检测准确性系数高。利用上述方法对设备故障进行检测,检测速度和精度方面均优于当前方法。
This paper proposes an optimal detection method for fault signals in multimedia equipment based on fuzzy relation. At first,the running state of equipment,the amplitude of equipment state change and the frequency of equipment state signal acquisition were used to build prediction model of signal acquisition frequency. Then,different weight values were given to different elements of the equipment and the intelligent adjustment of equipment signal acquisition frequency was finished to realize adaptive acquisition of multimedia equipment signal. Moreover,the collected multimedia equipment signals were divided into vibration signal and acoustic emission signal. The fuzzy state of the two signals was extracted and the membership value of this signal in equipment was obtained. The fuzzy relation matrix and fuzzy feature vector of multimedia equipment signals were obtained by fuzzy weighted linear transformation. Finally,the decision rule was used to judge fault signals in signal data after fusion. Thus,the optimal detection of fault signals in equipment was completed. Simulation results show that the proposed method has higher convergence rate and higher accuracy of detection than current methods.
This paper proposes an optimal detection method for fault signals in multimedia equipment based on fuzzy relation. At first,the running state of equipment,the amplitude of equipment state change and the frequency of equipment state signal acquisition were used to build prediction model of signal acquisition frequency. Then,different weight values were given to different elements of the equipment and the intelligent adjustment of equipment signal acquisition frequency was finished to realize adaptive acquisition of multimedia equipment signal. Moreover,the collected multimedia equipment signals were divided into vibration signal and acoustic emission signal. The fuzzy state of the two signals was extracted and the membership value of this signal in equipment was obtained. The fuzzy relation matrix and fuzzy feature vector of multimedia equipment signals were obtained by fuzzy weighted linear transformation. Finally,the decision rule was used to judge fault signals in signal data after fusion. Thus,the optimal detection of fault signals in equipment was completed. Simulation results show that the proposed method has higher convergence rate and higher accuracy of detection than current methods.
引文
[1]崔军立.用于多媒体网络节点的故障检测仿真[J].计算机仿真,2016,33(8):421-424.
[2]刘秀军,等.基于变压器铁芯接地线的电网故障暂态行波信号检测新方法[J].电力科学与技术学报,2016,31(3):57-64.
[3]李泽文,等.基于SR-ITD的故障行波检测方法[J].电力自动化设备,2017,37(2):121-125.
[4]崔伟成,等.基于果蝇优化算法的自适应随机共振轴承故障信号检测方法[J].振动与冲击,2016,35(10):96-100.
[5]贺利芳,等.基于幂函数型双稳随机共振的故障信号检测方法[J].仪器仪表学报,2016,37(7):1457-1467.
[6]王靖飞.河北低温区地表阻抗特性改变对电力电容器故障参数的影响.[J].科技通报,2017,1(33):114-118.
[7]魏艳鸣,海本斋.基于EMD和改进多重信号分类的感应电机故障检测方法[J].微特电机,2017,45(7):37-40.
[8]赵佳佳,等.基于概率与小波分析的故障检测方法及其应用[J].电网与清洁能源,2016,32(7):92-95.
[9]朱晓娟,等.基于小波能量矩的高阻接地故障检测方法[J].电力自动化设备,2016,36(12):161-168.
[10]刘国庆,史小春,廖强.基于神经网络分类算法的电机轴承故障检测方法[J].微特电机,2017,45(1):30-33.
[2]刘秀军,等.基于变压器铁芯接地线的电网故障暂态行波信号检测新方法[J].电力科学与技术学报,2016,31(3):57-64.
[3]李泽文,等.基于SR-ITD的故障行波检测方法[J].电力自动化设备,2017,37(2):121-125.
[4]崔伟成,等.基于果蝇优化算法的自适应随机共振轴承故障信号检测方法[J].振动与冲击,2016,35(10):96-100.
[5]贺利芳,等.基于幂函数型双稳随机共振的故障信号检测方法[J].仪器仪表学报,2016,37(7):1457-1467.
[6]王靖飞.河北低温区地表阻抗特性改变对电力电容器故障参数的影响.[J].科技通报,2017,1(33):114-118.
[7]魏艳鸣,海本斋.基于EMD和改进多重信号分类的感应电机故障检测方法[J].微特电机,2017,45(7):37-40.
[8]赵佳佳,等.基于概率与小波分析的故障检测方法及其应用[J].电网与清洁能源,2016,32(7):92-95.
[9]朱晓娟,等.基于小波能量矩的高阻接地故障检测方法[J].电力自动化设备,2016,36(12):161-168.
[10]刘国庆,史小春,廖强.基于神经网络分类算法的电机轴承故障检测方法[J].微特电机,2017,45(1):30-33.