Deep analysis of call detail log of the alarming information indicates that reasons except user equipment(UE)issue are usually ignored.To effectively reduce call drop rate in wideband code division multiple access(WCD...Deep analysis of call detail log of the alarming information indicates that reasons except user equipment(UE)issue are usually ignored.To effectively reduce call drop rate in wideband code division multiple access(WCDMA)mobile communication system,a novel method is presented.First,the reliable trace information is extracted to observe the distribution of all the exceptions from radio network controller(RNC)daily report.Then,the antenna angle of generalized clustering network in 024 base station’s c sector(GCN024C)for environmental test(ET)which is obtained from the radio frequency(RF)engineer is manually changed from 4° to 6°.Experimental results show that the proposed method can guarantee the key performance indicators(KPI)of WCDMA and have obvious effect on reducing call drop rate.展开更多
The Doppler weather radar fault judging system and remote monitoring platform were introduced.Through the real-time scanning of radar alarm information coding,the platform can realize dynamic monitoring and real-time ...The Doppler weather radar fault judging system and remote monitoring platform were introduced.Through the real-time scanning of radar alarm information coding,the platform can realize dynamic monitoring and real-time alarm of Doppler radar equipment components,so as to improve the reliability of equipment operation,and truly realize"unattended"remote monitoring.展开更多
Existing power grid fault diagnosis methods relyon manual experience to design diagnosis models, lack theability to extract fault knowledge, and are difficult to adaptto complex and changeable engineering sites. Consi...Existing power grid fault diagnosis methods relyon manual experience to design diagnosis models, lack theability to extract fault knowledge, and are difficult to adaptto complex and changeable engineering sites. Considering thissituation, this paper proposes a power grid fault diagnosismethod based on a deep pyramid convolutional neural networkfor the alarm information set. This approach uses the deepfeature extraction ability of the network to extract fault featureknowledge from alarm information texts and achieve end-to-endfault classification and fault device identification. First, a deeppyramid convolutional neural network model for extracting theoverall characteristics of fault events is constructed to identifyfault types. Second, a deep pyramidal convolutional neuralnetwork model for alarm information text is constructed, thetext description characteristics associated with alarm informationtexts are extracted, the key information corresponding to faultsin the alarm information set is identified, and suspicious faultydevices are selected. Then, a fault device identification strategythat integrates fault-type and time sequence priorities is proposedto identify faulty devices. Finally, the actual fault cases and thefault cases generated by the simulation are studied, and theresults verify the effectiveness and practicability of the methodpresented in this paper.展开更多
文摘Deep analysis of call detail log of the alarming information indicates that reasons except user equipment(UE)issue are usually ignored.To effectively reduce call drop rate in wideband code division multiple access(WCDMA)mobile communication system,a novel method is presented.First,the reliable trace information is extracted to observe the distribution of all the exceptions from radio network controller(RNC)daily report.Then,the antenna angle of generalized clustering network in 024 base station’s c sector(GCN024C)for environmental test(ET)which is obtained from the radio frequency(RF)engineer is manually changed from 4° to 6°.Experimental results show that the proposed method can guarantee the key performance indicators(KPI)of WCDMA and have obvious effect on reducing call drop rate.
文摘The Doppler weather radar fault judging system and remote monitoring platform were introduced.Through the real-time scanning of radar alarm information coding,the platform can realize dynamic monitoring and real-time alarm of Doppler radar equipment components,so as to improve the reliability of equipment operation,and truly realize"unattended"remote monitoring.
基金the National Natural Science Foundation of China(51877079).
文摘Existing power grid fault diagnosis methods relyon manual experience to design diagnosis models, lack theability to extract fault knowledge, and are difficult to adaptto complex and changeable engineering sites. Considering thissituation, this paper proposes a power grid fault diagnosismethod based on a deep pyramid convolutional neural networkfor the alarm information set. This approach uses the deepfeature extraction ability of the network to extract fault featureknowledge from alarm information texts and achieve end-to-endfault classification and fault device identification. First, a deeppyramid convolutional neural network model for extracting theoverall characteristics of fault events is constructed to identifyfault types. Second, a deep pyramidal convolutional neuralnetwork model for alarm information text is constructed, thetext description characteristics associated with alarm informationtexts are extracted, the key information corresponding to faultsin the alarm information set is identified, and suspicious faultydevices are selected. Then, a fault device identification strategythat integrates fault-type and time sequence priorities is proposedto identify faulty devices. Finally, the actual fault cases and thefault cases generated by the simulation are studied, and theresults verify the effectiveness and practicability of the methodpresented in this paper.
