Xiufeng Zhang, Haikuan Zhang, Haitao Li, Guoying Li, Shanshan Xue, Haichen Yin, Yang Chen, Fei Han
{"title":"基于岩爆预测指数特征自动挖掘的自监督岩爆风险预测算法","authors":"Xiufeng Zhang, Haikuan Zhang, Haitao Li, Guoying Li, Shanshan Xue, Haichen Yin, Yang Chen, Fei Han","doi":"10.3389/feart.2024.1459879","DOIUrl":null,"url":null,"abstract":"The rockburst risk prediction based on microseismic (MS) data is an important research task in deep mine safety prevention. However, the lack of systematic research on explicit prediction indexes and the waste of a large amount of unlabeled data are still two main problems that hinder the development of rockburst prediction. In this paper, the acoustic emission (AE) event distribution at each coal rock deformation and failure stage is studied based on the laboratory experiment. The spatial-temporal evolution of rockburst in MS data of coal mine fields is explored. Based on systematic research of the AE and MS distribution features considering the physical logic of coal rock mass failure, nine different rockburst prediction indexes are employed to describe the MS data features before rockburst. Then, according to the rockburst prediction indexes, a new self-supervision rockburst risk prediction algorithm is constructed, consisting of the pre-trained model and fine-tuning model with the same encoder and decoder structure. The pre-trained model is trained with unlabeled MS data to automatically learn rockburst prediction index features by reconstructing the masked indexes. Based on the pre-trained encoder and decoder parameters, the fine-tuning model is trained with the labeled MS data to predict rockburst risk. A large number of experiments show that the proposed rockburst prediction self-supervision algorithm is far superior to previous algorithms, by effectively utilizing unlabeled data. The ablation experiment also proves the validity of the studied rockburst prediction indexes.","PeriodicalId":12359,"journal":{"name":"Frontiers in Earth Science","volume":"55 1","pages":""},"PeriodicalIF":2.0000,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A self-supervision rockburst risk prediction algorithm based on automatic mining of rockburst prediction index features\",\"authors\":\"Xiufeng Zhang, Haikuan Zhang, Haitao Li, Guoying Li, Shanshan Xue, Haichen Yin, Yang Chen, Fei Han\",\"doi\":\"10.3389/feart.2024.1459879\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The rockburst risk prediction based on microseismic (MS) data is an important research task in deep mine safety prevention. However, the lack of systematic research on explicit prediction indexes and the waste of a large amount of unlabeled data are still two main problems that hinder the development of rockburst prediction. In this paper, the acoustic emission (AE) event distribution at each coal rock deformation and failure stage is studied based on the laboratory experiment. The spatial-temporal evolution of rockburst in MS data of coal mine fields is explored. Based on systematic research of the AE and MS distribution features considering the physical logic of coal rock mass failure, nine different rockburst prediction indexes are employed to describe the MS data features before rockburst. Then, according to the rockburst prediction indexes, a new self-supervision rockburst risk prediction algorithm is constructed, consisting of the pre-trained model and fine-tuning model with the same encoder and decoder structure. The pre-trained model is trained with unlabeled MS data to automatically learn rockburst prediction index features by reconstructing the masked indexes. Based on the pre-trained encoder and decoder parameters, the fine-tuning model is trained with the labeled MS data to predict rockburst risk. A large number of experiments show that the proposed rockburst prediction self-supervision algorithm is far superior to previous algorithms, by effectively utilizing unlabeled data. The ablation experiment also proves the validity of the studied rockburst prediction indexes.\",\"PeriodicalId\":12359,\"journal\":{\"name\":\"Frontiers in Earth Science\",\"volume\":\"55 1\",\"pages\":\"\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2024-08-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Earth Science\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.3389/feart.2024.1459879\",\"RegionNum\":3,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"GEOSCIENCES, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Earth Science","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.3389/feart.2024.1459879","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
摘要
基于微震(MS)数据的岩爆风险预测是深部矿井安全预防的一项重要研究任务。然而,缺乏明确预测指标的系统研究和大量无标注数据的浪费仍是阻碍岩爆预测发展的两大问题。本文以实验室实验为基础,研究了各煤岩变形和破坏阶段的声发射(AE)事件分布。探讨了煤矿井田 MS 数据中岩爆的时空演化规律。在系统研究 AE 和 MS 分布特征的基础上,结合煤岩体崩落的物理逻辑,采用九种不同的岩爆预测指标来描述岩爆前 MS 数据特征。然后,根据岩爆预测指标,构建了一种新的自监督岩爆风险预测算法,该算法由预训练模型和具有相同编码器和解码器结构的微调模型组成。预训练模型使用无标注的 MS 数据进行训练,通过重构掩蔽指数自动学习岩爆预测指数特征。在预训练编码器和解码器参数的基础上,使用标注的 MS 数据训练微调模型,以预测岩爆风险。大量实验表明,所提出的岩爆预测自监督算法有效利用了未标记数据,远远优于之前的算法。烧蚀实验也证明了所研究的岩爆预测指标的有效性。
A self-supervision rockburst risk prediction algorithm based on automatic mining of rockburst prediction index features
The rockburst risk prediction based on microseismic (MS) data is an important research task in deep mine safety prevention. However, the lack of systematic research on explicit prediction indexes and the waste of a large amount of unlabeled data are still two main problems that hinder the development of rockburst prediction. In this paper, the acoustic emission (AE) event distribution at each coal rock deformation and failure stage is studied based on the laboratory experiment. The spatial-temporal evolution of rockburst in MS data of coal mine fields is explored. Based on systematic research of the AE and MS distribution features considering the physical logic of coal rock mass failure, nine different rockburst prediction indexes are employed to describe the MS data features before rockburst. Then, according to the rockburst prediction indexes, a new self-supervision rockburst risk prediction algorithm is constructed, consisting of the pre-trained model and fine-tuning model with the same encoder and decoder structure. The pre-trained model is trained with unlabeled MS data to automatically learn rockburst prediction index features by reconstructing the masked indexes. Based on the pre-trained encoder and decoder parameters, the fine-tuning model is trained with the labeled MS data to predict rockburst risk. A large number of experiments show that the proposed rockburst prediction self-supervision algorithm is far superior to previous algorithms, by effectively utilizing unlabeled data. The ablation experiment also proves the validity of the studied rockburst prediction indexes.
期刊介绍:
Frontiers in Earth Science is an open-access journal that aims to bring together and publish on a single platform the best research dedicated to our planet.
This platform hosts the rapidly growing and continuously expanding domains in Earth Science, involving the lithosphere (including the geosciences spectrum), the hydrosphere (including marine geosciences and hydrology, complementing the existing Frontiers journal on Marine Science) and the atmosphere (including meteorology and climatology). As such, Frontiers in Earth Science focuses on the countless processes operating within and among the major spheres constituting our planet. In turn, the understanding of these processes provides the theoretical background to better use the available resources and to face the major environmental challenges (including earthquakes, tsunamis, eruptions, floods, landslides, climate changes, extreme meteorological events): this is where interdependent processes meet, requiring a holistic view to better live on and with our planet.
The journal welcomes outstanding contributions in any domain of Earth Science.
The open-access model developed by Frontiers offers a fast, efficient, timely and dynamic alternative to traditional publication formats. The journal has 20 specialty sections at the first tier, each acting as an independent journal with a full editorial board. The traditional peer-review process is adapted to guarantee fairness and efficiency using a thorough paperless process, with real-time author-reviewer-editor interactions, collaborative reviewer mandates to maximize quality, and reviewer disclosure after article acceptance. While maintaining a rigorous peer-review, this system allows for a process whereby accepted articles are published online on average 90 days after submission.
General Commentary articles as well as Book Reviews in Frontiers in Earth Science are only accepted upon invitation.