Rock Burst Precursor Electromagnetic Radiation Signal Recognition Method and Early Warning Application Based on Recurrent Neural Networks

Di, Yangyang; Wang, Enyuan

doi:10.1007/s00603-020-02314-w

Cited by 44 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the most popularly used techniques to detect warning signals prior to sudden changes are recurrent neural networks. Recurrent neural networks have been used to study a variety of critical phenomena including epileptic seizures [89], heart failure onset [90], financial crises [91], rock bursts [92], abnormal increases in infectious diseases [93] etc. Apart from recurrent neural networks, other machine learning tools such as decision trees [94], convolutional neural networks [95], random forests [96] etc.…”

Section: Prediction Of Transitions Using Machine Learning Methodsmentioning

confidence: 99%

Early warning signals for critical transitions in complex systems

George¹,

Kachhara²,

Ambika³

2021

Preprint

View full text Add to dashboard Cite

In this review, we present the different measures of early warning signals that can indicate the occurrence of critical transitions in complex systems. We start with the mechanisms that trigger critical transitions, how they relate to warning signals and the methods used to detect early warning signals (EWS) for sudden transitions or tipping. We discuss briefly a few applications in real systems in this context, like transitions in ecology, climate and environment, medicine, epidemics, finance and engineering. Towards the end, we mention the issues in detecting EWS in specific applications and our perspective on future trends in this area, especially related to sudden transitions in the dynamics of connected systems on complex networks.

show abstract

Section: Prediction Of Transitions Using Machine Learning Methodsmentioning

confidence: 99%

Early warning signals for critical transitions in complex systems

George¹,

Kachhara²,

Ambika³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The fracture-induced electromagnetic radiation (FEMR) signal recognition model based on bidirectional long short-term memory recurrent neural networks (bi-directional LSTM RNN) had a good response to the occurrence of rockburst and can capture rockburst information in advance in order to realize the automatic/intelligent discrimination of rockburst precursory [156].…”

Section: Machine Learningmentioning

confidence: 99%

Development of Rockburst Research: A Comprehensive Review

Wang

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

Rockburst is a difficult problem in underground resource development and infrastructure construction. With scientific and technological progress, more research technologies and methods to prevent rockburst have been proposed and applied. Research content has become more comprehensive, and positive progress and achievements have been made. However, due to the complexity of rockburst control factors and the sudden occurrence of rockburst, the occurrence mechanism and accurate prediction of occurrence intensity and time are still difficult worldwide problems. In this paper, the research development and achievements of rockburst are reviewed. Firstly, various definitions and types of rockburst are briefly summarized. Then, research progress and achievements in four aspects are comprehensively reviewed, including methods and techniques of rockburst research (theoretical research, numerical simulation, physical model tests and in situ monitoring), mechanism of rockburst, classification and prediction of rockburst (empirical criteria, in situ monitoring, mathematical model approaches and rockburst chart) and prevention and control of rockburst. Of particular significance is that the classification and prediction with prevention and control are summarized in detail. Finally, limitations, deficiencies and some promising directions for future research are listed.

show abstract

“…The abovementioned research is somewhat to investigate the early‐warning information of rock materials based on surface monitoring technology, such as deformation localization field, infrared radiation temperature field, and EMR spectrum zone. In addition, previous studies on early‐warning signals of rock failure have been limited to a single response index 21–24 . To quantitatively characterize the precursor characteristics, multi‐parameters should be used to explore the early‐warning information of rock failure.…”

Section: Introductionmentioning

confidence: 99%

Early‐warning signal recognition methods in flawed sandstone subjected to uniaxial compression

Lei

Berto

et al. 2022

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

To investigate the precursor information related to rock fracturing, a series of indoor uniaxial compression tests are conducted on flawed sandstone. Four methods of identifying potential precursors to rock catastrophic failure, namely, cumulative acoustic emission (AE) activity, AE b-value, inter-event time function, and critical slowing down, are discussed. The results show that the four precursory identification methods can reasonably identify the earlywarning signal, subcritical failure, and final catastrophic failure of flawed sandstone involving the whole loading process. The minimum b-value is correspondingly obtained when the specimen approaches failure. The inter-event rate of AE multi-parameters shows a significant increase, following a power law distribution. By comparison with the other three precursor identification methods, the time intervals of AE parameters-based variance between the precursory signal and its corresponding tripping points become increasingly shortened. Additionally, the precursory characteristics of variance of AE multiparameters are more accurate and reliable than that of autocorrelation coefficient.

show abstract

Rock Burst Precursor Electromagnetic Radiation Signal Recognition Method and Early Warning Application Based on Recurrent Neural Networks

Cited by 44 publications

References 41 publications

Early warning signals for critical transitions in complex systems

Early warning signals for critical transitions in complex systems

Development of Rockburst Research: A Comprehensive Review

Early‐warning signal recognition methods in flawed sandstone subjected to uniaxial compression

Contact Info

Product

Resources

About