Controlled laboratory experiments are proved to be a valuable tool for investigating changes in underground physical properties and the related response of surface geophysical signals.The self-potential(SP)method is w...Controlled laboratory experiments are proved to be a valuable tool for investigating changes in underground physical properties and the related response of surface geophysical signals.The self-potential(SP)method is widely used in mineral resource exploration due to its direct correlation with underground electrochemical gradients.This paper presented the design and construction of an experimental platform based on a multi-channel SP monitoring system.The proposed platform was used to monitor the anodizing corrosion process of different metal blocks from a laboratory perspective,record the real-time SP signal generated by the redox reaction,as well as investigate the geobattery mechanism associated with the natural polarization process of metal mineral resources.The experimental results demonstrate that the constructed SP monitoring platform effectively captures time-series SP signals and provides direct laboratory evidence for the geobattery model.The measured SP data were quantitatively interpreted using the simulated annealing algorithm,and the inversion results closely match the real model.This finding highlights the potential of the SP method as a promising tool for determining the location and spatial distribution of underground polarizers.The study holds reference value for the exploration and exploitation of mineral resources in both terrestrial and marine environments.展开更多
[Objective]Real-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases.Currently,various strategies have been propo...[Objective]Real-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases.Currently,various strategies have been proposed for monitoring cow ruminant behavior,including video surveillance,sound recognition,and sensor monitoring methods.How‐ever,the application of edge device gives rise to the issue of inadequate real-time performance.To reduce the volume of data transmission and cloud computing workload while achieving real-time monitoring of dairy cow rumination behavior,a real-time monitoring method was proposed for cow ruminant behavior based on edge computing.[Methods]Autono‐mously designed edge devices were utilized to collect and process six-axis acceleration signals from cows in real-time.Based on these six-axis data,two distinct strategies,federated edge intelligence and split edge intelligence,were investigat‐ed for the real-time recognition of cow ruminant behavior.Focused on the real-time recognition method for cow ruminant behavior leveraging federated edge intelligence,the CA-MobileNet v3 network was proposed by enhancing the MobileNet v3 network with a collaborative attention mechanism.Additionally,a federated edge intelligence model was designed uti‐lizing the CA-MobileNet v3 network and the FedAvg federated aggregation algorithm.In the study on split edge intelli‐gence,a split edge intelligence model named MobileNet-LSTM was designed by integrating the MobileNet v3 network with a fusion collaborative attention mechanism and the Bi-LSTM network.[Results and Discussions]Through compara‐tive experiments with MobileNet v3 and MobileNet-LSTM,the federated edge intelligence model based on CA-Mo‐bileNet v3 achieved an average Precision rate,Recall rate,F1-Score,Specificity,and Accuracy of 97.1%,97.9%,97.5%,98.3%,and 98.2%,respectively,yielding the best recognition performance.[Conclusions]It is provided a real-time and effective method for monitoring cow ruminant behavior,and the proposed federated edge intelligence model can be ap‐plied in practical settings.展开更多
The tire blowout or severe leakage real-time monitoring is one of key technologies for developing a tire blowout automatic braking system.An indirect real-time monitoring method to fuse analyses of tire vibration and ...The tire blowout or severe leakage real-time monitoring is one of key technologies for developing a tire blowout automatic braking system.An indirect real-time monitoring method to fuse analyses of tire vibration and effective radius is provided in this paper,and a monitoring system is developed.The calibration and related test results showthat the system can detect the tire blowout in low and middle vehicle speeds and the severe leakage in all speeds timely and accurately.展开更多
In view of characteristics of solar photovoltaic (PV) power station such as the decentralized layout and massive monitoring and control information, a solar PV power generation monitoring and control system has been d...In view of characteristics of solar photovoltaic (PV) power station such as the decentralized layout and massive monitoring and control information, a solar PV power generation monitoring and control system has been designed. The system is designed into three layers namely the sensor and actuator layer, the PLC field monitoring and control layer and the remote network monitoring and control layer. Through ZigBee wireless network, PROFIBUS and GPRS wireless network, the system makes the three layers exchange information rapidly, and the system supervises not only various operational parameters of the power generating system but also weather changes as a way to change the solar tracking strategy of the PV power generating system and reduce the operating energy consumption of the system. Through the hardware redundant design of PLC central controller and the upper computer, the solar PV power station can be more secure and reliable when running.展开更多
针对传统谐波责任划分方法需采用专门同步设备监测数据,且需基于等值电路模型划分谐波责任,工程应用较为复杂等不足,采用现有谐波监测装置非同步测量数据,提出一种综合考虑了数据非同步性、场景划分和数据相关性的谐波责任划分方法。首...针对传统谐波责任划分方法需采用专门同步设备监测数据,且需基于等值电路模型划分谐波责任,工程应用较为复杂等不足,采用现有谐波监测装置非同步测量数据,提出一种综合考虑了数据非同步性、场景划分和数据相关性的谐波责任划分方法。首先,对原始非同步监测数据集采用分段聚合近似算法进行降噪预处理,利用形状动态时间规整算法(shape dynamic time warping,ShapeDTW)实现数据匹配对齐;然后,利用点排序识别聚类结构的聚类算法(ordering points to identify the clustering structure,OPTICS)划分场景以处理电力系统中因负荷投切和无功补偿装置切换等情况导致的谐波责任变化;最后,基于相关性分析构建场景谐波责任和总谐波责任指标,在指标构建的过程中引入了场景时长占比这一因素以得到更加科学合理的总谐波责任值。通过仿真验证和电网实例验证,该方法能基于现有非同步性监测数据实现各用户合理时间尺度动态谐波责任划分,可为工程上的快速谐波责任划分提供一定的新思路和新方法。展开更多
为了提高利用监控和数据采集(supervisory control and data acquisition,SCADA)多变量长时间序列预测齿轮箱油温的精度,解决不同风电机组因处不同运行环境导致的数据分布不一致的问题,提出了一种基于多分支时间序列预测与迁移学习相结...为了提高利用监控和数据采集(supervisory control and data acquisition,SCADA)多变量长时间序列预测齿轮箱油温的精度,解决不同风电机组因处不同运行环境导致的数据分布不一致的问题,提出了一种基于多分支时间序列预测与迁移学习相结合的齿轮箱状态监测方法。首先,利用极致梯度提升(extreme gradient boosting,XGBoost)算法筛选输入参数组成原始序列,对其进行分解得到季节与趋势序列。其次,提出季节、趋势序列特征提取模块获取季节及趋势特征的序列,将其与经过Informer模型处理后的特征序列进行融合后输入进多层感知机映射成最终的预测值,以构建提出的多分支时间序列预测网络(multi-branch time series prediction network,MBFN)。最后,利用迁移学习并结合一分类向量支持机(one-class support vector machine,OCSVM)模型及滑动窗口构建齿轮箱的健康指数,完成齿轮箱状态监测。实验结果表明,所提出模型的MBFN显著提高了油温预测精度,优于常规时间序列预测模型,所使用的迁移策略能以较少数据适应不同数据的分布,进而实现对齿轮箱的状态监测,并且所提出的模型可以提前18.9 d发出齿轮箱故障预警。展开更多
基金Project(42174170)supported by the National Natural Science Foundation of China。
文摘Controlled laboratory experiments are proved to be a valuable tool for investigating changes in underground physical properties and the related response of surface geophysical signals.The self-potential(SP)method is widely used in mineral resource exploration due to its direct correlation with underground electrochemical gradients.This paper presented the design and construction of an experimental platform based on a multi-channel SP monitoring system.The proposed platform was used to monitor the anodizing corrosion process of different metal blocks from a laboratory perspective,record the real-time SP signal generated by the redox reaction,as well as investigate the geobattery mechanism associated with the natural polarization process of metal mineral resources.The experimental results demonstrate that the constructed SP monitoring platform effectively captures time-series SP signals and provides direct laboratory evidence for the geobattery model.The measured SP data were quantitatively interpreted using the simulated annealing algorithm,and the inversion results closely match the real model.This finding highlights the potential of the SP method as a promising tool for determining the location and spatial distribution of underground polarizers.The study holds reference value for the exploration and exploitation of mineral resources in both terrestrial and marine environments.
文摘[Objective]Real-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases.Currently,various strategies have been proposed for monitoring cow ruminant behavior,including video surveillance,sound recognition,and sensor monitoring methods.How‐ever,the application of edge device gives rise to the issue of inadequate real-time performance.To reduce the volume of data transmission and cloud computing workload while achieving real-time monitoring of dairy cow rumination behavior,a real-time monitoring method was proposed for cow ruminant behavior based on edge computing.[Methods]Autono‐mously designed edge devices were utilized to collect and process six-axis acceleration signals from cows in real-time.Based on these six-axis data,two distinct strategies,federated edge intelligence and split edge intelligence,were investigat‐ed for the real-time recognition of cow ruminant behavior.Focused on the real-time recognition method for cow ruminant behavior leveraging federated edge intelligence,the CA-MobileNet v3 network was proposed by enhancing the MobileNet v3 network with a collaborative attention mechanism.Additionally,a federated edge intelligence model was designed uti‐lizing the CA-MobileNet v3 network and the FedAvg federated aggregation algorithm.In the study on split edge intelli‐gence,a split edge intelligence model named MobileNet-LSTM was designed by integrating the MobileNet v3 network with a fusion collaborative attention mechanism and the Bi-LSTM network.[Results and Discussions]Through compara‐tive experiments with MobileNet v3 and MobileNet-LSTM,the federated edge intelligence model based on CA-Mo‐bileNet v3 achieved an average Precision rate,Recall rate,F1-Score,Specificity,and Accuracy of 97.1%,97.9%,97.5%,98.3%,and 98.2%,respectively,yielding the best recognition performance.[Conclusions]It is provided a real-time and effective method for monitoring cow ruminant behavior,and the proposed federated edge intelligence model can be ap‐plied in practical settings.
基金Sponsored by the Applied Foundation Research Project of Suzhou(SYFG0932)
文摘The tire blowout or severe leakage real-time monitoring is one of key technologies for developing a tire blowout automatic braking system.An indirect real-time monitoring method to fuse analyses of tire vibration and effective radius is provided in this paper,and a monitoring system is developed.The calibration and related test results showthat the system can detect the tire blowout in low and middle vehicle speeds and the severe leakage in all speeds timely and accurately.
基金sponsored by National Natural Science Foundation of China(50975020)National Major Program of Science and Tech-nique(2009ZX04014-101)Funding Project for Academic Human Resources Development in Institutions of Higher Learning under the Jurisdiction of Beijing Municipalipality(PHR20090518)
文摘In view of characteristics of solar photovoltaic (PV) power station such as the decentralized layout and massive monitoring and control information, a solar PV power generation monitoring and control system has been designed. The system is designed into three layers namely the sensor and actuator layer, the PLC field monitoring and control layer and the remote network monitoring and control layer. Through ZigBee wireless network, PROFIBUS and GPRS wireless network, the system makes the three layers exchange information rapidly, and the system supervises not only various operational parameters of the power generating system but also weather changes as a way to change the solar tracking strategy of the PV power generating system and reduce the operating energy consumption of the system. Through the hardware redundant design of PLC central controller and the upper computer, the solar PV power station can be more secure and reliable when running.
文摘针对传统谐波责任划分方法需采用专门同步设备监测数据,且需基于等值电路模型划分谐波责任,工程应用较为复杂等不足,采用现有谐波监测装置非同步测量数据,提出一种综合考虑了数据非同步性、场景划分和数据相关性的谐波责任划分方法。首先,对原始非同步监测数据集采用分段聚合近似算法进行降噪预处理,利用形状动态时间规整算法(shape dynamic time warping,ShapeDTW)实现数据匹配对齐;然后,利用点排序识别聚类结构的聚类算法(ordering points to identify the clustering structure,OPTICS)划分场景以处理电力系统中因负荷投切和无功补偿装置切换等情况导致的谐波责任变化;最后,基于相关性分析构建场景谐波责任和总谐波责任指标,在指标构建的过程中引入了场景时长占比这一因素以得到更加科学合理的总谐波责任值。通过仿真验证和电网实例验证,该方法能基于现有非同步性监测数据实现各用户合理时间尺度动态谐波责任划分,可为工程上的快速谐波责任划分提供一定的新思路和新方法。
文摘为了提高利用监控和数据采集(supervisory control and data acquisition,SCADA)多变量长时间序列预测齿轮箱油温的精度,解决不同风电机组因处不同运行环境导致的数据分布不一致的问题,提出了一种基于多分支时间序列预测与迁移学习相结合的齿轮箱状态监测方法。首先,利用极致梯度提升(extreme gradient boosting,XGBoost)算法筛选输入参数组成原始序列,对其进行分解得到季节与趋势序列。其次,提出季节、趋势序列特征提取模块获取季节及趋势特征的序列,将其与经过Informer模型处理后的特征序列进行融合后输入进多层感知机映射成最终的预测值,以构建提出的多分支时间序列预测网络(multi-branch time series prediction network,MBFN)。最后,利用迁移学习并结合一分类向量支持机(one-class support vector machine,OCSVM)模型及滑动窗口构建齿轮箱的健康指数,完成齿轮箱状态监测。实验结果表明,所提出模型的MBFN显著提高了油温预测精度,优于常规时间序列预测模型,所使用的迁移策略能以较少数据适应不同数据的分布,进而实现对齿轮箱的状态监测,并且所提出的模型可以提前18.9 d发出齿轮箱故障预警。
