The efficient processing of large amounts of data collected by the microseismic monitoring system(MMS),especially the rapid identification of microseismic events in explosions and noise,is essential for mine disaster ...The efficient processing of large amounts of data collected by the microseismic monitoring system(MMS),especially the rapid identification of microseismic events in explosions and noise,is essential for mine disaster prevention.Currently,this work is primarily performed by skilled technicians,which results in severe workloads and inefficiency.In this paper,CNN-based transfer learning combined with computer vision technology was used to achieve automatic recognition and classification of multichannel microseismic signal waveforms.First,data collected by MMS was generated into 6-channel original waveforms based on events.After that,sample data sets of microseismic events,blasts,drillings,and noises were established through manual identification.These datasets were split into training sets and test sets according to a certain proportion,and transfer learning was performed on AlexNet,GoogLeNet,and ResNet50 pre-training network models,respectively.After training and tuning,optimal models were retained and compared with support vector machine classification.Results show that transfer learning models perform well on different test sets.Overall,GoogLeNet performed best,with a recognition accuracy of 99.8%.Finally,the possible effects of the number of training sets and the imbalance of different types of sample data on the accuracy and effectiveness of classification models were discussed.展开更多
Main factors, which should be considered in the classification of dyke foundation, are discussed in this paper. Engineering conditions should be taken into account when the levee safety is appraised based on engineeri...Main factors, which should be considered in the classification of dyke foundation, are discussed in this paper. Engineering conditions should be taken into account when the levee safety is appraised based on engineering geologic appraisement and classification. On the basis of safety appraisement, dyke foundation may be classified with regard of suitable reinforcement measures. Examples are presented to illustrate the instructive significance of dyke foundation classification to dyke reinforcement design.展开更多
The paper discusses the framework for a risk-informed root cause analysis process.Such process enables scaling of the analysis performed based on the risk associated with the undesired event or condition,thereby creat...The paper discusses the framework for a risk-informed root cause analysis process.Such process enables scaling of the analysis performed based on the risk associated with the undesired event or condition,thereby creating tiers of analysis where the greater the risk,the more sophisticated the analysis.In a risk-informed root cause analysis process,a situation is normally not analyzed at a level less than what actually occurred.However,a situation may be investigated as though the consequence were greater than actually happened,especially if only slight differences in circumstances could result in a significantly higher consequence.While operational events or safety issues are normally expected to result only with negligible or marginal actual consequences,many of those would actually have certain potential to develop or propagate into catastrophic events.This potential can be expressed qualitatively or quantitatively.Risk-informing of root cause analysis relies on mapping the event or safety issue into a risk matrix which,traditionally,is a two-dimensional probability-consequence matrix.A new concept employed in the risk matrix for root cause analysis is that,while the probability reflects the observed or expected range of values(retaining,thus,its“traditional”meaning),the consequence reflects not only the observed or materialized impact(such as failure of equipment)but,also,its potential to propagate or develop into highly undesirable final state.The paper presents main elements of risk-informed root cause analysis process and discusses qualitative and quantitative aspects and approaches to determination of risk significance of operational events or safety issues.展开更多
基金the National Key R&D Program of China(No.2021YFC2900500).
文摘The efficient processing of large amounts of data collected by the microseismic monitoring system(MMS),especially the rapid identification of microseismic events in explosions and noise,is essential for mine disaster prevention.Currently,this work is primarily performed by skilled technicians,which results in severe workloads and inefficiency.In this paper,CNN-based transfer learning combined with computer vision technology was used to achieve automatic recognition and classification of multichannel microseismic signal waveforms.First,data collected by MMS was generated into 6-channel original waveforms based on events.After that,sample data sets of microseismic events,blasts,drillings,and noises were established through manual identification.These datasets were split into training sets and test sets according to a certain proportion,and transfer learning was performed on AlexNet,GoogLeNet,and ResNet50 pre-training network models,respectively.After training and tuning,optimal models were retained and compared with support vector machine classification.Results show that transfer learning models perform well on different test sets.Overall,GoogLeNet performed best,with a recognition accuracy of 99.8%.Finally,the possible effects of the number of training sets and the imbalance of different types of sample data on the accuracy and effectiveness of classification models were discussed.
文摘Main factors, which should be considered in the classification of dyke foundation, are discussed in this paper. Engineering conditions should be taken into account when the levee safety is appraised based on engineering geologic appraisement and classification. On the basis of safety appraisement, dyke foundation may be classified with regard of suitable reinforcement measures. Examples are presented to illustrate the instructive significance of dyke foundation classification to dyke reinforcement design.
文摘The paper discusses the framework for a risk-informed root cause analysis process.Such process enables scaling of the analysis performed based on the risk associated with the undesired event or condition,thereby creating tiers of analysis where the greater the risk,the more sophisticated the analysis.In a risk-informed root cause analysis process,a situation is normally not analyzed at a level less than what actually occurred.However,a situation may be investigated as though the consequence were greater than actually happened,especially if only slight differences in circumstances could result in a significantly higher consequence.While operational events or safety issues are normally expected to result only with negligible or marginal actual consequences,many of those would actually have certain potential to develop or propagate into catastrophic events.This potential can be expressed qualitatively or quantitatively.Risk-informing of root cause analysis relies on mapping the event or safety issue into a risk matrix which,traditionally,is a two-dimensional probability-consequence matrix.A new concept employed in the risk matrix for root cause analysis is that,while the probability reflects the observed or expected range of values(retaining,thus,its“traditional”meaning),the consequence reflects not only the observed or materialized impact(such as failure of equipment)but,also,its potential to propagate or develop into highly undesirable final state.The paper presents main elements of risk-informed root cause analysis process and discusses qualitative and quantitative aspects and approaches to determination of risk significance of operational events or safety issues.
