掘进工作面是个噪声源集中且噪声频带宽、声压级高的作业场所，掘进机司机受噪声的影响，容易处于生理、心理和个体能力异常状态，增加不安全行为的可能性，导致人因事故发生。不安全状态是不安全行为产生的前提，是煤矿人因事故的险兆。因此，为识别该险兆，本文通过实验研究法，探究掘进机司机在噪声影响下表征指标变化，对掘进机司机的不安全状态进行预警，以完善煤矿安全管理，降低人因事故的发生。 首先，提出了研究假设并分析了噪声影响掘进机司机不安全状态的路径。通过文献调研，明确了基于噪声影响的掘进机司机不安全状态的概念，确定了心电指标心率、脑电指标（ERP）、个体能力指标（反应时间、正确率）和主观心理问卷为不安全状态表征指标。在此基础上，提出了研究假设，结合噪声效应理论，进行了噪声影响掘进机司机不安全状态的路径分析。 其次，从掘进机司机作业流程出发，设计并开展了基于噪声影响的掘进机司机不安全状态诱发实验，分析了噪声前后心电、脑电信号、心理指标和行为数据变化。以正常声音环境为对照组，噪声环境为实验组，进行了基于判别任务的实验研究。对采集数据进行预处理，应用 SPSS 软件进行统计学分析探究在噪声前后表征指标在任务过程中的变化，结果表明：在噪声影响下，被试人员心率均值升高，平均反应时间延长，正确率降低，ERP 成分中诱发了的 N1、N2 和 P3 波幅均显著增加，P2 波幅无显著变化，主观心理问卷得分变高，被试不安全状态风险增加。采用 Spearman 相关系数法确定各表征指标与主观心理问卷的关系，发现心率、N2 波幅、P3 波幅、反应时间和正确率与主观心理问卷具有显著相关性，这 6 个综合指标能有效表征掘进司机在噪声刺激下的不安全状态。 最后，进行综合表征指标分级，构建了掘进机司机不安全状态的模糊贝叶斯网络识别模型并实现了预警。基于模糊集理论，利用三角模糊数评估条件概率，实验数据评估先验概率，将掘进机司机不安全状态分为五个等级：优秀、良好、中、较差、差。噪声下掘进机司机不安全状态异常概率提升为 54%，风险等级提升“中”；一级指标中，对不安全状态影响程度由大到小为生理指标、心理指标、个体能力指标，二级指标中心率和主观心理问卷对不安全状态影响程度较大。根据识别结果，通过预警界面能实现预警信息发布，当司机处于不安全状态中，提示司机或管理层采取不同行动。 综上，本文设计的噪声下掘进机司机不安全状态诱发实验使被试产生了不同程度的不安全状态，不安全状态识别模型能准确输出当前掘进机司机的不安全状态大小，设计的预警方案能实现不安全状态的实时报警，完善了掘进机司机不安全状态的识别研究，并针对研究结果提出了干预措施，可为煤矿企业有效降低人因事故发生概率提供理论指导。

The heading face is a working place with concentrated noise source, wide noise frequency band and high sound pressure level. The driver of the roadheader is affected by noise, and is easy to be in an abnormal state of physiological,psychological and individual ability, which increases the possibility of unsafe behavior and leads to human accidents. Unsafe state is the premise of unsafe behavior and the danger sign of human accident in coal mine. Therefore, in order to identify the danger sign, this paper explores the change of the characterization index of the roadheader driver under the influence of noise through the experimental research method, and warns the unsafe state of the roadheader driver, so as to improve the coal mine safety management and reduce the occurrence of human accidents. Firstly, the research hypothesis was proposed and the path of noise affecting the unsafe state of the roadheader driver was analyzed. Through literature research, the concept of unsafe state of roadheader drivers based on the influence of noise was clarified, and the ECG index ( heart rate ), EEG index ( ERP ), individual ability index ( reaction time and accuracy ) and subjective psychological questionnaire were determined as the indicators of unsafe state. On this basis, the research hypothesis is put forward. And combined with the theory of noise effect, the path analysis of the influence of noise on the unsafe state of the roadheader driver is carried out. Secondly, starting from the operation process of the roadheader driver, the experiment of inducing the unsafe state of the roadheader driver based on the influence of noise was designed and carried out, and the changes of ECG, EEG, psychological index and behavior data before and after noise were analyzed. Taking the normal sound environment as the control group and the noise environment as the experimental group, an experimental study based on the discrimination task was carried out. The collected data were preprocessed, and SPSS software was used for statistical analysis to explore the changes of the characterization indexes before and after noise in the task process. The results showed that under the influence of noise, the average heart rate of the subjects increases, the average reaction time is prolonged, and the accuracy rate decreases. The amplitudes of N1, N2 and P3 induced by ERP components increase significantly, and the amplitude of P2 do not change significantly. The subjective psychological questionnaire score increases, and the risk of unsafe state of the subjects increases. Spearman correlation coefficient method is used to determine the relationship between each representation index and subjective psychological questionnaire. It is found that heart rate, N2 amplitude, P3 amplitude, reaction time and accuracy are significantly correlated with subjective psychological questionnaire. These six comprehensive indexes can effectively characterize the unsafe state of tunneling drivers under noise stimulation. Finally, the comprehensive characterization index was graded, and the fuzzy Bayesian network identification model of the unsafe state of the roadheader driver was constructed and the early warning was realized. Based on the fuzzy set theory, the triangular fuzzy number was used to evaluate the conditional probability, and the experimental data was used to evaluate the prior probability. The unsafe state of the roadheader driver was divided into five levels : excellent, good, medium, poor and poor. The abnormal probability of the unsafe state of the roadheader driver under noise is increased to 54 %, and the risk level is increased to ' medium '. Among the first-level indicators, the degree of influence on the unsafe state from large to small are physiological index, psychological index, individual ability index. Among the second-level indicators, heart rate and subjective psychological questionnaire have a greater impact on unsafe state. According to the identification results, the early warning information can be released through the early warning interface. When the driver is in an unsafe state, the driver or management is prompted to take different actions. In summary, the induced experiment of unsafe state of roadheader driver under noise designed in this paper makes the subjects produce different degrees of unsafe state. The identification model of the unsafe state can accurately output the unsafe state of the current roadheader driver. The designed early warning scheme can realize the real-time alarm of the unsafe state, improve the recognition research of the unsafe state of the roadheader driver, and put forward the intervention measures according to the research results, which can provide theoretical guidance for coal mine enterprises to effectively reduce the probability of human accidents.

[1] 袁亮. 煤炭工业碳中和发展战略构想[J]. 中国工程科学, 2023, 25(05): 103-110.

[2] 国家统计局. 中华人民共和国2023年国民经济和社会发展统计公报[N]. 人民日报, 2024-02-29.

[3] 程磊, 孙洁. 2016-2022年我国煤矿事故统计与规律分析[J]. 煤炭工程, 2023, 55 (11): 125-129.

[4] 田水承, 孙璐瑶, 唐艺璇, 等. 矿工不安全状态评价指标体系的构建与分析[J]. 西安科技大学学报, 2021, 41(03): 402-409.

[5] 雷柏伟, 吴兵, 程根银, 等. 煤矿井下主要设备噪声源测定分析研究[J]. 中国安全生产科学技术, 2011, 7(01): 72-75.

[6] 杨明, 贾改妮, 刘毛毛, 等. 我国煤矿噪声研究进展科学知识图谱分析[J]. 中国安全科学学报, 2022, 32(05): 1177-184.

[7] 付玉平, 陈兆波, 赵振保, 等. 煤矿安全事故的综合致因模型[J/OL]. 安全与环境学报, 2024-04-24.

[8] 李磊, 田水承. 煤矿工人不安全行为组合干预仿真研究[J]. 中国安全科学学报, 2016, 26(07): 23-28.

[9] Karen A B, P.Geoffirey W, Gregory E P. Predicting Safe Employee Behavior in the Steel Industry: Development and Test of a Sociotechnical Model[J]. Journal of Operations Management, 2000(18): 445-465.

[10] 张明媛, 徐琴. 施工工人不安全行为传播模型与干预效果分析[J]. 中国安全科学学报, 2021, 31(12): 1-9.

[11] Krause T R, Seymour K J, Sloat K C M, et al. Long Term Evaluation of A Behavior-based Method for Improving Safety Performance: A Meta-analysis of 73 Intermrupted Time-series Replications[J]. Safety Science, 1999, 32(1): 1-18.

[12] Konstantin C, Peter Y C, John R. The Effects of Error Management Climate and Safety Communication on Safety: A multi-level Study[J]. Accident Analysis and Prevention, 2010, 42(5): 1498-1506.

[13] 李丽, 赵营, 曹玉宽, 等. 民航机务维修人员不安全行为传播影响因素及作用研究[J]. 安全与环境学报, 2023, 23(12): 4435-4441.

[14] 莫俊文, 王锐锐. 基于HLM-BP的高海拔隧道施工人员不安全行为预警研究[J]. 铁道科学与工程学报, 2023, 20(03): 1116-1126.

[15] 石娟, 常丁懿, 郑鹏. 基于BP神经网络的建筑工人不安全行为预警模型[J]. 中国安全科学学报, 2022, 32(01): 27-33.

[16] 李红霞, 徐浩冉, 田水承. 基于随机森林的矿工不安全行为预测预警模型[J]. 中国安全科学学报, 2022, 32(12): 10-18.

[17] Ruihua X, Fan L. Risk Prediction and Early Warning for Air Traffic Controllers’ Unsafe Acts Using Association Rule Mining and Random Forest[J]. Safety Science, 2021, 135(1): 1-10.

[18] Patel D A, Jha K N. Evaluation of Construction Projects Based on The Safe Work Behavior of Co-employees Through a Neural Network Mode[J]. Safety Science, 2016, 89(1): 240-248.

[19] 白彦龙, 李海立, 陈昱, 等. 基于HFACS的煤矿一般事故人因分析[J]. 煤矿安全, 2021, 52(5): 250-255.

[20] 叶龙, 项芳芳, 沈梅, 等. 人的安全性评价研究[J]. 中国安全科学学报, 2003(10): 15-18+85.

[21] Lei C, Hongxia L, Shuicheng T. Application of AHP and DEMATEL for Identifying Factors Influencing Coal Mine Practitioners’ Unsafe State[J]. Sustainability, 2022, 14(21).

[22] 李国为, 田水承. 煤矿岗前人员不安全状态智能检测系统研究—以红柳林煤矿为例[J]. 中国安全生产科学技术, 2023, 19(02): 106-113.

[23] 田水承, 孙雯, 杨鹏飞, 等. 煤矿班组不安全状态影响因素及评价[J]. 西安科技大学学报, 2022, 42(03): 405-412.

[24] 程根银, 陈绍杰, 齐金龙, 等. 煤矿井下噪声对人的不安全行为影响分析研究[J]. 华北科技学院学报, 2014, 11(01): 89-93.

[25] 王娇琳. 环境噪声应激对人体生理心理影响的实验室研究[D]. 重庆: 重庆大学, 2006.

[26] 叶运莉, 李爱玲, 高绪芳. 噪声对工人心理影响的研究[J]. 泸州医学院学报, 2003, (04): 317-319.

[27] 马万赋, 王红. 噪声对女工心理健康水平的影响[J]. 工业卫生与职业病, 2001, (03): 172-173.

[28] 程根银, 陈绍杰, 魏志勇, 等. 井下噪声对人心理生理影响分析[J]. 西安科技大学学报, 2011, 31(06): 850-853.

[29] 陈义. 施工噪声对建筑工人生理、心理及不安全行为的影响研究[D]. 重庆: 重庆大学, 2020.

[30] Ulf L, Marianne F. Psychophysiological Reactions to Noise as Modified by Personal Control over Noise Intensity[J]. Biological Psychology, 1978, 6(01): 51-59.

[31] 景国勋, 王敏. 基于生理指标的噪声对作业人员认知绩效的影响研究[J]. 煤矿安全, 2021, 52(08): 243-247.

[32] 田水承, 张德桃. 高温联合噪声对矿工不安全行为的影响研究[J]. 煤矿安全, 2019, 50(02): 241-244.

[33] 卢才武, 高睿阳, 徐晓慧, 等. 基于脑电数据的不同噪声工况下矿工注意力研究[J]. 中国安全科学学报, 2023, 33(05): 35-41.

[34] Cho W H, Lee M S, Lee J K, et al. An Examination of The Effects of Various Noises on Physiological Sensibility Responses by Using Human EEG[J]. Journal of Mechanical Science and Technology, 2013, 27(12): 3589-3593.

[35] 戚作秋, 王宏, 常文文, 等. 生产性噪声对工作人员脑认知影响的ERP分析[J].东北大学学报(自然科学版), 2017, 38(11): 1590-1594+1600.

[36] 冯新怡. 施工噪声对工人危险识别影响机理的ERP实验研究[D]. 重庆: 重庆大学, 2021.

[37] 景国勋, 赵攀飞, 吕鹏飞, 等. 不同煤矿噪声暴露时间对视觉认知影响研究[J]. 安全与环境学报, 2018, 18(02): 615-618.

[38] Alain N, Veronique B, Patricia T, et al. Electroencephalogram and Cardiovascular Responses to Noise during Daytime Sleep in Shift Workers[J]. Eur J Appl Physiol Occup Physiol, 1993, 66(01): 76-84.

[39] Jinjing K, Ming Z, Xiaowei L, et al. Monitoring Distraction of Construction Workers Caused by Noise Using a Wearable Electroencephalography (EEG) Device[J]. Automation in Construction, 2021, 125: 103598.

[40] 姜劲, 焦学军, 张朕, 等. 利用fNIRs研究噪声环境下脑力负荷变化规律[J]. 航天医学与医学工程, 2016, 29(05): 339-346.

[41] 周敏, 王海明, 杨振珑, 等. 基于熵权-TOPSIS的成都市地铁TOD站点评价排序研究[J]. 铁道运输与经济, 2023, 45(04): 150-156.

[42] 田水承, 冯帅, 高晓颖, 等. 一线矿工不安全状态的熵权TOPSIS法评价[J]. 安全与环境学报, 2023, 23(11): 4049-4056.

[43] Nima K, Faisal K, Paul A. Safety Analysis in Process Facilities: Comparison of Fault Tree and Bayesian Network Approaches[J]. Re-liability Engineering and System Safety, 2011, 96(8).

[44] 秦岩, 盛武. 基于贝叶斯网络的煤矿顶板事故致因研究[J]. 矿业安全与环保, 2022, 49(03): 136-142.

[45] Xing T, Weipeng F, Shuaiqi Y. Application of Bayesian Approach to The Assessment of Mine Gas Explosion[J]. Loss Prev Process Ind, 2018, 54: 238-245.

[46] Esmaeil Z, Nima K, Valerio C. Safety Analysis of Process Systems Using Fuzzy Bayesian Network (FBN)[J]. Loss Prev Process Ind, 2019, 57: 7-16.

[47] Limao Z, Xiangguo W, Yawei Q, et al. Towards a Fuzzy Bayesian Network Based Approach for Safety Risk Analysis of Tunnel-Induced Pipeline Damage[J]. Risk analysis: an official publication of the Society for Risk Analysis, 2016, 36(2).

[48] Min L, Hetang W, Deming W, et al. Risk Assessment of Gas Explosion in Coal Mines Based on Fuzzy AHP And Bayesian Network[J]. Process Safety and Environmental Protection, 2020, 135(C).

[49] Jinhui Y, Jin Z, Liangshan S. Risk Assessment of Coal Mine Gas Explosion Based on Fault Tree Analysis and Fuzzy Polymorphic Bayesian Network: A Case Study of Wangzhuang Coal Mine[J]. Processes, 2023, 11: 2619.

[50] 陈星霖, 林卫东, 黄晓冬, 等. 基于模糊贝叶斯网络的超高层建筑火灾风险评估[J]. 安全与环境工程, 2023, 30(06): 40-47.

[51] 李敏, 林志军, 鲁义, 等. 基于模糊贝叶斯网络的煤矿瓦斯爆炸风险评估[J]. 煤炭学报, 2023, 48(S2): 626-637.

[52] Ping W, Jianliang M, Jianfeng H. Ensemble Classifier for Driver's Fatigue Detection Based on a Single EEG Channel[J]. Intelligent Transport Systems. IET, 2018, 12(10): 1322-1328.

[53] 孙勇, 钟卓玲, 李璐. 基于班组安全氛围的建筑工人不安全行为预测[J]. 中国安全生产科学技术, 2019, 15(8): 156-161.

[54] Eun J L, Byoung C K, Jae-Yeal N. Recognizing Pedestrian's Unsafe Behaviors in Far-infrared Imagery at Night[J]. Infrared Physics & Technology, 2016, 76: 261-270.

[55] 田水承, 匡秘姈, 丁洋. 风险偏好中介作用下矿工工作压力对不安全行为的影响[J]. 安全与环境学报, 2023, 23(01): 132-138.

[56] 孟远, 谢东海, 苏波, 等. 2010年—2019年全国煤矿生产安全事故统计与现状分析[J]. 矿业工程研究, 2020, 35(04): 27-33.

[57] 唐中华, 胡兰田, 阚伟华, 等. 矿山掘进工作面的噪声控制与防护[J]. 煤矿现代化, 2003, (01): 18.

[58] 彭佑多, 郭迎福, 李新, 等. 矿井掘进工作面及巷道环境噪声预测与控制研究状况[J]. 矿业工程研究, 2010, 25(04): 62-68.

[59] 胡杰. 煤巷掘进声发射监测信号噪声处理方法研究[J]. 煤炭工程, 2023, 55(07): 110-114.

[60] 殷雷宇. 掘进面噪声与矿工对险兆事件感知关系研究[D]. 西安: 西安科技大学, 2017.

[61] 刘媛媛. 煤矿操作者状态对不安全行为的影响研究[D]. 太原: 太原科技大学, 2015.

[62] 吴璐帆. 黄昏低照度条件下驾驶员心理负荷分析及建模[D]. 广州: 华南理工大学, 2019.

[63] Greg H, Annmarie M, Doreen M O. Event-Related Potentials, Emotion, and Emotion Regulation: An Integrative Review[J]. Developmental Neuropsychology, 2010, 35(2): 129-155.

[64] 李敏, 贾惠侨, 李开伟, 等. 噪声水平对人不安全行为的影响研究[J]. 中国安全科学学报, 2017, 27(03): 19-24.

[65] Broadbent D E. The Current State of Noise Research: Reply to Poulton [J]. Psychological Btilletin, 1978, 85(5): 1052-1067.

[66] 石尚霞. 施工噪声对脑力疲劳影响的ERP研究[D]. 重庆: 重庆大学, 2021.

[67] Peter A H, Joel S W. A Dynamic Model of Stress and Sustained Attention[J]. Journal of Human Performance in Extreme Environments, 2013.

[68] Mangun G R, Hillyard S A. Modulations of Sensory-evoked Brain Potentials Indicate Changes: Perceptual Processing During Visual-spatial Priming[J]. Journal of Experimental Psychology: Human Perception and Performance, 1991, 17(4): 1057-1074.

[69] Helen M M, Christoph K, Stephan G B, et al. Working Memory Load for Faces Modulates P300, N170, and N250r[J]. Journal of Cognitive Neuroscience, 2008, 20(6).

[70] Manfred H, Paul S, And Donald B L. Attention, Vigilance, and Cortical Evoked-potentials in Humans[J]. Science, 1964, 145(362): 180-182.

[71] Simon J T, Denis F, Catherine M. Speed of Processing in The Human Visual System[J]. Nature, 1996, 381(6582): 520-522.

[72] Brian F, Joan M, Lloyd T, et al. A Topographic Study of ERPs Elicited by Visual Feature Discrimination[J]. Brain Topography, 1997, 10(2): 133-143.

[73] Steven J, Steven A. Electro Physiological Correlates of Feature Analysis During Visual Search[J]. Psychophysiology, 2010, 31(3): 291-308.

[74] Davide R, David P, Rino R, et al. When People Matter More Than Money: An Erps Study[J]. Brain Research Bulletin, 2010, 81(4): 445-452.

[75] 叶贵, 陈俐莹, 冯新怡, 等. 噪声对建筑工人冒险行为的诱发机制研究[J]. 中国安全科学学报, 2020, 30(12): 16-23.

[76] 余凤琼, 袁加锦, 罗跃嘉. 情绪干扰听觉反应冲突的ERP研究[J]. 心理学报, 2009, 41(07): 594-601.

[77] Jonathan R, Cyma V P. Influence of Cognitive Control and Mismatch on The N2 Component of The ERP: A Review [J]. Psychophysiology, 2008, 45(1): 152-170.

[78] Jiajin Y, Qinglin Z, Antao C, et al. Are We Sensitive to Valence Differences in Emotionally Negative Stimuli? Electrophysiological Evidence from An ERP Study[J]. Neuropsychologia, 2007, 45(12): 2764-2771.

[79] Shedden J M, Nordgaard C L. ERP Time Course of Perceptual and Post-perceptual Mechanisms of Spatial Selection[J]. Cognitive Brain Research. 2001, 11(1): 59-75.

[80] Mennes M, Heidi W, Bea,van den B, et al. ERP Correlates of Complex Human Decision Making in A Gambling Paradigm: Detection and Resolution of Conflict[J]. Psychophysio-

logy, 2008, 45(5): 714-720.

[81] 陈俐莹. 基于ERP实验的噪声对建筑工人冒险行为影响研究[D]. 重庆: 重庆大学, 2021.

[82] 牛颖, 祁乐瑛, 王彩霞. 情绪对高海拔地区大学生双重认知控制影响的ERP研究[J]. 青海师范大学学报(自然科学版), 2023, 39(03): 48-54.

[83] Jenkins L, Tarnopolsky A, Hand D. Psychiatric Admissions and Aircraft Noise from London Airport: Four-year, Three-hospitals' Study[J]. Psychological Medicine. 1981, 11(4): 765-782.

[84] 谭鑫, 晏联璞, 熊巧巧. 基于眼动指标探讨噪声对航空维修人员工作记忆的影响[J]. 中国工业医学杂志, 2023, 36(06): 534-536.

[85] Andrew P S. Aircraft Noise Exposure, Noise Sensitivity, and Everyday Errors[J]. Environ-

ment and Behavior, 1986, 18(2).

[86] Helena J, Staffan H, Niklas H, et al. Open-plan Office Noise: Cognitive Performance and Restoration[J]. Journal of Environmental Psychology, 2011, 31(4): 373-382.

[87] Arnaud D, Terrence S, Scott M. Enhanced Detection of Artifacts in EEG Data Using Higher-Order Statistics and Independent Component Analysis[J]. Neuroimage, 2007, 34(4): 1443-1449.

[88] 成连华, 魏凯, 曹东强. 基于模糊贝叶斯网络的高层建筑火灾风险评估方法[J]. 科学技术与工程, 2023, 23(13): 5707-5714.

[89] ZadehL A. Fuzzy Set[J]. Information and Control, 1965, 8(3): 338-353.

[90] Anil K. Data Clustering: 50 Years Beyond K-Means[J]. Pattern Recognition Letters, 2010, 31(8): 651-666.

[91] 李世科. 基于K-均值聚类与贝叶斯判别的我国煤矿顶板灾害事故安全评价[J]. 中国矿业, 2020, 29(04): 131-135.

[92] 眭衍波, 陈龙, 裴华, 等. 煤矿矿工的人格、应激与心理健康状况调查[J]. 中国临床心理学杂志, 2003, 4: 273-275.

[93] 龚斌. 基于MCGS矿用带式输送机监控系统设计[J]. 建井技术, 2023, 44(01): 43-46+55.