Fault diagnosis occupies a pivotal position within the domain of machine and equipment management.Existing methods,however,often exhibit limitations in their scope of application,typically focusing on specific types o...Fault diagnosis occupies a pivotal position within the domain of machine and equipment management.Existing methods,however,often exhibit limitations in their scope of application,typically focusing on specific types of signals or faults in individual mechanical components while being constrained by data types and inherent characteristics.To address the limitations of existing methods,we propose a fault diagnosis method based on graph neural networks(GNNs)embedded with multirelationships of intrinsic mode functions(MIMF).The approach introduces a novel graph topological structure constructed from the features of intrinsic mode functions(IMFs)of monitored signals and their multirelationships.Additionally,a graph-level based fault diagnosis network model is designed to enhance feature learning capabilities for graph samples and enable flexible application across diverse signal sources and devices.Experimental validation with datasets including independent vibration signals for gear fault detection,mixed vibration signals for concurrent gear and bearing faults,and pressure signals for hydraulic cylinder leakage characterization demonstrates the model's adaptability and superior diagnostic accuracy across various types of signals and mechanical systems.展开更多
Germplasm effect reflects the quantitative relation between production ability of germplasm elements and yield （quality） of a certain crop, which can be shown by mathematic function, namely, germplasm effect functio...Germplasm effect reflects the quantitative relation between production ability of germplasm elements and yield （quality） of a certain crop, which can be shown by mathematic function, namely, germplasm effect function. Germplasm effect of a crop variety is an aggregation of many effective factors, and is restrained by different effective factors; constant increase of any one effect of germplasm elements would lead to law of effect decline, therefore, possible modes of transgenic crops effect function were deduced according to the law of effect decline. The possible modes of single transgenic germplasm effect function and multi-transgenic germplasm effect regression equation were discussed, and the characteristics of germplasm effect regression equation were analyzed in this paper.展开更多
针对复杂海洋环境中的船舶辐射噪声信号去噪问题,该文提出了一种基于阿基米德优化算法优化变分模态分解联合小波阈值的非平稳水声信号去噪方法。首先,采用阿基米德优化算法对变分模态分解进行最优参数寻优,确定惩罚因子α和最佳模态分解...针对复杂海洋环境中的船舶辐射噪声信号去噪问题,该文提出了一种基于阿基米德优化算法优化变分模态分解联合小波阈值的非平稳水声信号去噪方法。首先,采用阿基米德优化算法对变分模态分解进行最优参数寻优,确定惩罚因子α和最佳模态分解数k。对原始水声信号进行变分模态分解,通过相关系数及其中心频率选择信号主导模态分量。结合小波阈值去噪对信号主导模态分量进行去噪后完成信号重构。仿真及实验结果表明:相比传统水声信号去噪方法,该文方法在复杂噪声环境下可有效提升信噪比12 d B,降低均方根误差80%,并在去噪的同时保持信号关键特征,具有更优的去噪性能。展开更多
煤炭开采沉陷动态预计对地表损害评估及土地复垦利用具有重要意义。当前主流预计方法是融合最大下沉量与时间函数构建动态模型,但其参数获取多依赖于相似地质条件工作面的既有参数,或利用稳定沉陷后的水准监测数据进行反演。针对缺乏相...煤炭开采沉陷动态预计对地表损害评估及土地复垦利用具有重要意义。当前主流预计方法是融合最大下沉量与时间函数构建动态模型,但其参数获取多依赖于相似地质条件工作面的既有参数,或利用稳定沉陷后的水准监测数据进行反演。针对缺乏相似地质条件参数时依赖稳定沉陷数据反演参数导致的沉陷预计时间滞后问题,提出了一种基于非稳沉数据和遗传算法(Genetic Algorithm,GA)的开采沉陷动态预计方法(Dynamic Subsidence Prediction via Genetic Algorithm with Unstable Data,DSP-GAUD)。该方法首先利用开采过程中的非稳沉样本数据,通过遗传算法反演参数,构建单点沉陷动态模型;继而基于单点预计结果优选并耦合模型;最终融合概率积分法建立了适用于全局动态预计的耦合模型。以皖北朱仙庄矿某工作面为例,对所提方法进行了试验,结果表明:(1)与传统方法相比,DSP-GAUD法的时效性提升51%以上,且沉陷初期预计结果均方根误差(Root Mean Squared Error,RMSE)和平均绝对误差(Mean Absolute Error,MAE)平均值均降低68%;(2)所构建的耦合动态预计模型融合了不同时间函数优势,动态预计精度优于单一函数模型,平均拟合优度R2达到0.96;(3)建立的最大下沉速度出现时间t1与切眼距关系模型,较基于稳定沉陷数据的关系模型适用性更强。该方法有效提升了开采沉陷预计的时效性和早期精度,对开采沉陷实时预计具有一定的应用价值。展开更多
文摘Fault diagnosis occupies a pivotal position within the domain of machine and equipment management.Existing methods,however,often exhibit limitations in their scope of application,typically focusing on specific types of signals or faults in individual mechanical components while being constrained by data types and inherent characteristics.To address the limitations of existing methods,we propose a fault diagnosis method based on graph neural networks(GNNs)embedded with multirelationships of intrinsic mode functions(MIMF).The approach introduces a novel graph topological structure constructed from the features of intrinsic mode functions(IMFs)of monitored signals and their multirelationships.Additionally,a graph-level based fault diagnosis network model is designed to enhance feature learning capabilities for graph samples and enable flexible application across diverse signal sources and devices.Experimental validation with datasets including independent vibration signals for gear fault detection,mixed vibration signals for concurrent gear and bearing faults,and pressure signals for hydraulic cylinder leakage characterization demonstrates the model's adaptability and superior diagnostic accuracy across various types of signals and mechanical systems.
文摘Germplasm effect reflects the quantitative relation between production ability of germplasm elements and yield （quality） of a certain crop, which can be shown by mathematic function, namely, germplasm effect function. Germplasm effect of a crop variety is an aggregation of many effective factors, and is restrained by different effective factors; constant increase of any one effect of germplasm elements would lead to law of effect decline, therefore, possible modes of transgenic crops effect function were deduced according to the law of effect decline. The possible modes of single transgenic germplasm effect function and multi-transgenic germplasm effect regression equation were discussed, and the characteristics of germplasm effect regression equation were analyzed in this paper.
文摘针对复杂海洋环境中的船舶辐射噪声信号去噪问题,该文提出了一种基于阿基米德优化算法优化变分模态分解联合小波阈值的非平稳水声信号去噪方法。首先,采用阿基米德优化算法对变分模态分解进行最优参数寻优,确定惩罚因子α和最佳模态分解数k。对原始水声信号进行变分模态分解,通过相关系数及其中心频率选择信号主导模态分量。结合小波阈值去噪对信号主导模态分量进行去噪后完成信号重构。仿真及实验结果表明:相比传统水声信号去噪方法,该文方法在复杂噪声环境下可有效提升信噪比12 d B,降低均方根误差80%,并在去噪的同时保持信号关键特征,具有更优的去噪性能。
文摘煤炭开采沉陷动态预计对地表损害评估及土地复垦利用具有重要意义。当前主流预计方法是融合最大下沉量与时间函数构建动态模型,但其参数获取多依赖于相似地质条件工作面的既有参数,或利用稳定沉陷后的水准监测数据进行反演。针对缺乏相似地质条件参数时依赖稳定沉陷数据反演参数导致的沉陷预计时间滞后问题,提出了一种基于非稳沉数据和遗传算法(Genetic Algorithm,GA)的开采沉陷动态预计方法(Dynamic Subsidence Prediction via Genetic Algorithm with Unstable Data,DSP-GAUD)。该方法首先利用开采过程中的非稳沉样本数据,通过遗传算法反演参数,构建单点沉陷动态模型;继而基于单点预计结果优选并耦合模型;最终融合概率积分法建立了适用于全局动态预计的耦合模型。以皖北朱仙庄矿某工作面为例,对所提方法进行了试验,结果表明:(1)与传统方法相比,DSP-GAUD法的时效性提升51%以上,且沉陷初期预计结果均方根误差(Root Mean Squared Error,RMSE)和平均绝对误差(Mean Absolute Error,MAE)平均值均降低68%;(2)所构建的耦合动态预计模型融合了不同时间函数优势,动态预计精度优于单一函数模型,平均拟合优度R2达到0.96;(3)建立的最大下沉速度出现时间t1与切眼距关系模型,较基于稳定沉陷数据的关系模型适用性更强。该方法有效提升了开采沉陷预计的时效性和早期精度,对开采沉陷实时预计具有一定的应用价值。
