煤矿辅助运输是煤矿生产系统的重要环节，运输状况直接关系到煤矿企业的安全和发展。无轨胶轮车驾驶员作为参与运输工作的主要人员，由于复杂的工作环境和单调的工作内容，极易产生疲劳。疲劳是导致不安全状态的主要因素，而不安全状态是不安全行为发生的前提和基础，研究不安全状态预警是将不安全行为防治“关口前移”，从而防止人因事故发生。因此，应用理论分析、实验研究、模型构建的方法，开展无轨胶轮车驾驶员不安全状态预警模型研究，及时检测驾驶员的不安全状态，有助于预防煤矿事故发生，对煤矿交通人因事故防治具有重要意义。本文主要研究内容和结论如下：

（1）设计实施了无轨胶轮车驾驶员体-脑疲劳诱发实验，并成功诱发出不同程度等级的体-脑疲劳。通过对当前疲劳检测的国内外研究现状、无轨胶轮车驾驶员工作环境和工作内容的梳理，设计了采用长时间跑步运动负荷增加后的单调重复按键行为来模拟无轨胶轮车驾驶员体力疲劳和部分脑力疲劳的产生。在诱发过程中采用KSS量表、RPE量表和心率来实时记录疲劳诱发情况，并在诱发过程中采用E-prime软件记录被试的行为数据指标，同时使用脑电设备同步记录被试脑电信号的变化。

（2）揭示了在无轨胶轮车驾驶员体-脑疲劳的发展过程中，其脑电信号特征以及行为数据的变化规律。运用SPSS25.0软件对诱发疲劳过程中RPE分数、心率以及诱发疲劳后所采集到的行为能力指标进行处理。结果表明，在疲劳诱发过程中，被试的RPE分数和心率的变化趋势一致，且显著增加。在疲劳恢复过程中，被试的RPE分数仍大于疲劳诱发前，表明体-脑疲劳诱发成功。体-脑疲劳诱发后，被试重复按键行为的平均反应时和错误率增加。通过MATLAB软件对脑电数据进行处理，结果表明疲劳诱发后，δ波在F7、FT7、T7、TP7通道所在的颞区会显著减少，θ波在F7、P6通道所在的颞区会显著性增加，ɑ波在全脑会增加，β波在FPZ、AF3、F1通道所在的大脑额区会显著减少。

（3）基于A/M值和K-means聚类进行了无轨胶轮车驾驶员体-脑疲劳等级划分。结合所采集到的脑电信号特征值运用专注度和放松度分数A/M值划分体-脑疲劳等级；通过记录的RPE分数和行为能力指标运用K-means聚类法划分体-脑疲劳等级，两次分级结果一致。将无轨胶轮车驾驶员体-脑疲劳分为三个等级：正常工作状态、中度疲劳状态、重度疲劳状态。

（4）构建了无轨胶轮车驾驶员不安全状态预警模型，并对其效能进行了评估。运用XGBoost算法，选取体-脑疲劳后有显著性变化的指标作为模型的输入值，划分的三个疲劳等级作为输出值，构建预警模型，并对该模型进行训练和测试，模型训练集的正确率为100%，测试集的正确率为90.48%。引入模型测试混淆矩阵对本研究不安全状态预警模型进行评价，结果显示此预警模型对各级不安全状态预警整体性能较好。且经过实例应用验证表明：此预警模型可以很好的对无轨胶轮车驾驶员不安全状态进行预警。

综上，本研究通过设计疲劳诱发实验，量化并提取体-脑疲劳的脑电数据特征，构建不安全状态预警模型，实现了对无轨胶轮车驾驶员不安全状态准确、可靠的预警，为煤矿监管部门、煤矿企业等遏制不安全行为形成提供了理论依据和技术支撑。

Coal mine auxiliary transportation is an important part of coal mine production system, and the transportation condition is directly related to the safety and development of coal mine enterprises. As the main personnel involved in the transportation work, the driver of trackless rubber wheelbarrow is very prone to fatigue due to the complex working environment and monotonous work content. Fatigue is the main factor leading to the unsafe state, and the unsafe state is the premise and basis of the occurrence of unsafe acts, the study of the unsafe state early warning is the prevention and control of unsafe acts, “the gate forward”, so as to prevent accidents due to human factors. Therefore, it is of great significance to carry out the research on the early warning model of the unsafe state of the driver of trackless rubber wheelbarrow to detect the unsafe state of the driver in time, which can help to prevent the occurrence of accidents in coal mines, and has great significance to the prevention and control of human-caused accidents in coal mine transportation. The main research contents and conclusions of this paper are as follows:

(1)The body-brain fatigue inducing experiment for trackless rubber wheelbarrow drivers was designed and implemented, and body-brain fatigue of different degree levels was successfully induced. By sorting out the current domestic and international research status of fatigue detection, the working environment and work content of trackless rubber-wheeled vehicle drivers, we designed to use the monotonous repetitive key-pressing behavior after the increase of the long-time running exercise load to simulate the generation of physical fatigue and part of the cerebral fatigue of trackless rubber-wheeled vehicle drivers. The KSS scale, RPE scale and heart rate were used to record the fatigue induced situation in real time during the induction process, and E-prime software was used to record the behavioral data indexes of the subjects during the induction process, while the changes of the EEG signals of the subjects were synchronously recorded using the EEG equipment.

(2)The changing rules of EEG signal characteristics as well as behavioral data in the development of body-cerebral fatigue in trackless rubber wheelbarrow drivers were revealed. SPSS25.0 software was used to process the RPE scores and heart rate during the process of induced fatigue as well as the behavioral ability indexes collected after the fatigue was induced. The results showed that during the fatigue-inducing process, the subjects' RPE scores and heart rates showed consistent trends and significant increases. During fatigue recovery, the subjects' RPE scores were still greater than those before fatigue induction, indicating that the body-brain fatigue induction was successful. After the body-brain fatigue was induced, the average reaction time and error rate of the subjects' repeated key press behavior increased. The EEG data were processed by MATLAB software, and the results showed that after fatigue evocation, the δ wave would be significantly reduced in the temporal area where the F7, FT7, T7, and TP7 channels are located, the θ wave would be significantly increased in the temporal area where the F7 and P6 channels are located, the ɑ wave would be increased in the whole brain but the effect would be insignificant, and the β wave would be significantly reduced in the frontal area of the brain where the FPZ, AF3, and F1 channels are located.

(3)Body-brain fatigue classification of trackless rubber wheelbarrow drivers was carried out based on A/M values and K-means clustering. The A/M values of concentration and relaxation scores were used to classify the body-brain fatigue grades by combining the characteristic values of the collected EEG signals, and the K-means clustering method was used to classify the body-brain fatigue grades by using the recorded RPE scores and behavioral ability indexes, and the results of the two classifications were consistent. The body-brain fatigue of trackless rubber wheelbarrow drivers was categorized into three grades: normal working state, moderate fatigue state, and severe fatigue state.

(4)An early warning model for the unsafe state of trackless rubber-wheeled vehicle drivers was constructed and its efficacy was evaluated. Using the XGBoost algorithm, the indicators with significant changes after body-brain fatigue were selected as the input values of the model, and the three fatigue grades classified were used as the output values to construct the early warning model, and the model was trained and tested, and the correctness rate of the model's training set was 100%, and that of the test set was 90.48%. Introducing the model test confusion matrix to evaluate the unsafe state warning model of this study, the results show that the overall performance of this warning model for grade warning is better. The results show that the overall performance of this warning model is good for the level warning. And the verification of the example application shows that this warning model can be good for the warning of the unsafe state of the driver of the trackless rubber-wheeled vehicle.

In summary, this study quantifies and extracts the EEG data features of body-brain fatigue by designing fatigue-induced experiments, constructs an early warning model of unsafe state, realizes accurate and reliable early warning of unsafe state of trackless rubber-wheeled vehicle drivers, and provides theoretical basis and technological support for the coal mine supervisory department, coal mine enterprises, etc. to curb the formation of unsafe behaviors.

[1]袁亮,吴劲松,杨科.煤炭安全智能精准开采关键技术与应用[J].采矿与安全工程学报,2023,40(05):861-868.

[2]王双明,师庆民,王生全,申艳军,孙强,蔡玥.富油煤的油气资源属性与绿色低碳开发[J].煤炭学报,2021,46(05):1365-1377.

[3]袁亮.煤炭精准开采科学构想[J].煤炭学报,2017,42(01):1-7.

[4]康红普,王国法,王双明,等.煤炭行业高质量发展研究[J].中国工程科学,2021,23(05):130-138.

[5]金智新,曹孟涛,王宏伟.“中等收入”与新“双控”背景下煤炭行业转型发展新机遇[J].煤炭科学技术,2023,51(01):45-58.

[6]袁亮,张通,张庆贺,江丙友,吕鑫,李姗姗,付强.双碳目标下废弃矿井绿色低碳多能互补体系建设思考[J].煤炭学报,2022,47(06):2131-2139.

[7]刘见中,孙海涛,雷毅,曹偈.煤矿区煤层气开发利用新技术现状及发展趋势[J].煤炭学报,2020,45(01):258-267.

[8]张洪杰. 煤矿安全风险综合评价体系及应用研究[D].中国矿业大学,2011.

[9]Niu S. Coal mine safety production situation and management strategy[J]. Management & Engineering, 2014(14):78-82.

[10]犹梦洁. 基于文本挖掘的煤矿安全风险识别与评价研究[D].中国矿业大学,2023.

[11]王兆丰,王龙,董家昕,王俏.冷冻取芯过程含瓦斯煤样温度场演化规律模拟研究[J].煤炭学报,2021,46(01):199-210.

[12]蔺亚兵,秦勇,王兴,段中会,马东民. 彬长低阶煤高瓦斯矿区瓦斯地质及其涌出特征[J].煤炭学报,2019,44(07):2151-2158.

[13]程远平. 煤矿瓦斯防治理论与工程应用[M]. 徐州:中国矿业大学出版社，2010.

[14]袁亮. 我国深部煤与瓦斯共采战略思考[J]. 煤炭学报, 2016, 41(1):1-6.

[15]Tong, Q. China’s coal mine accident statistics analysis and one million tons mortality prediction. IETI Trans, 2016, 2(1), 61-72.

[16]郭民,郁钟铭.人员不安全行为对构建本质安全型矿井的影响分析[J].煤矿安全,41(10):115-118.

[17]张培森,李复兴,朱慧聪,等.2008—2020年煤矿事故统计分析及防范对策[J].矿业安全与环保,2022,49(01):128-134

[18]房耀洲,刘明举,魏建平,刘秋菊.我国煤矿事故特征及对策研究[J].煤炭技术,2007(12):3-5.

[19]中国煤炭工业协会.2022煤炭行业发展年度报告[R].北京:煤炭工业网,2022.

[20]de Lange FP, Faber LG, Maurits NM, Lorist MM. Mental fatigue affects visual selective attention.PloS ONE(2012) 7:e48073.

[21]van der Linden D, Frese M, Meijman TF. Mental fatigue and the control of cognitive processes: effects on perseveration and planning.Acta Psychol.(2003) 113:45–65.

[22]Ranjana K. Mehta and Michael J. Agnew. Effects of concurrent physical and mental demands for a short duration static task[J]. International Journal

[23]韩启东.对煤矿胶轮车运输安全的思考[J].河北农机,2019,(07):67.

[24]唐淑芳,邱上进.煤矿胶轮车运输安全的思考[J].煤矿机械,2015,(08):11-12.

[25]潘文超,周升举.特大型矿井防爆无轨胶轮车运输安全管理[J].中国科技信息,2011,(07):202.

[26]张宁.基于贝叶斯网络的煤矿瓦斯爆炸风险判识与预警研究[D].安徽理工大学,2020.

[27]扈志成,李双忠.浅析济三煤矿无轨胶轮车运输安全管理的特点[J].山东煤炭科技,2009,(03):55-56.

[28]Fiona Barwick and Peter Arnett and Semyon Slobounov. EEG correlates of fatigue during administration of a neuropsychological test battery[J]. Clinical Neurophysiology, 2011, 123(2) : 278-284.

[29]Mehta RK, Parasuraman R. Effects of mental fatigue on the development of physical fatigue: a neuroergonomic approach.Hum Fact.(2013) 56:645–56.

[30]Ranjana K. Mehta and Michael J. Agnew. Effects of concurrent physical and mental demands for a short duration static task[J]. International Journal

[31]Lorist Monicque M et al. Motor fatigue and cognitive task performance in humans.[J]. The Journal of physiology, 2002, 545(Pt 1) : 313-9.

[32]Mahdi Azarnoosh et al. Investigation of mental fatigue through EEG signal processing based on nonlinear analysis: Symbolic dynamics[J]. Chaos, Solitons and Fractals, 2011, 44(12) : 1054-1062.

[33]Shen KQ, Li XP, Ong CJ, Shao SY, Wilder-Smith EP. EEG-based mental fatigue measurement using multi-class support vector machines with confidence estimate.Clin Neurophysiol. (2008)119:1524–33.

[34]Tanaka M, Shigihara Y, Ishii A, Funakura M, Kanai E, Watanabe Y. Effect of mental fatigue on the central nervous system: an electroencephalography study. Behav Brain Funct. (2012) 8:48–55.

[35]Understanding Cognitive Performance During Robot-Assisted Surgery[J]. Khurshid A. Guru;;Somayeh B. Shafiei;;Atif Khan;;Ahmed A. Hussein;;Mohamed Sharif;;Ehsan T. Esfahani.Urology,2015(4).

[36]Virtual surgical planning in endoscopic skull base surgery[J]. Stephan K. Haerle;;MichaelJ.Daly;;HarleyH.L.Chan;;AllanVescan;;WalterKucharczyk;;JonathanC.Irish.TheLaryngoscope,2013(12).

[37]董帆.基于OpencvOpenCV软件部队疲劳驾驶预警系统的设计[J].电子技术与软件工程,2016(02):61.

[38]He J, Zhang Y, Zhang C, et al. A Noninvasive R eal-Time Solution for Driving Fatigue Detection Based on Left Prefrontal EEG and Eye B link[C]// InternationalConference on Brain and Health Informatics. Springer International Publishing, 2016:325-335.

[39]Zeng S, Li J, Jiang L, et al. A driving assistant safety method based on human eye fatigue detection[C]// Control and Decision Conference. IEEE, 2017: 6370-6377.

[40]杨渝书,姚振强,李增勇,等.心电图时频域指标在驾驶疲劳评价中的有效性研究[J].机械设计与制造,2002(05):94-95.

[41]黄鹏.便携式肌疲劳分析系统研制[D].中国科学技术大学,2015.

[42]Rodney Petrus Balandong, Rana Fayyaz Ahmad,Mohamad Naufal Mohamad Saad, Aamir Saeed Malik. A Review on EEG-Based Automatic Sleepiness Detection Systems for Driver.[J]. IEEE Access,2018(6): 22908-22919.

[43]程如中,赵勇,戴勇,等.基于Adaboost方法的车载嵌入式疲劳驾驶预警系统[J].北京大学学报(自然科学版),2012,48(05):719-726.

[44]Patel M,Lal SK, Kavanagh D,et al. Applying Neural Network Analysis on Heart Rate Variability Data to Assess Driver Fatigue [J ]. Expert Systems with Applications ,2011 ,38( 6) :7235-7242.

[45]徐礼胜,张闻勖,庞宇轩,等.基于短时心电信号的疲劳驾驶检测算法[J].东北大学学报(自然科学版),2019,40(07):937-941.

[46]吴雪,王娆芬.基于迁移学习的深层卷积神经网络心电信号疲劳分类[J].中国医学物理学杂志,2021,38(10):1258-1263.

[47]宋海燕，张建国，王珺,等.基于表面肌电的人体背部负重行走肌肉疲劳特性研究[J]生物医学工程学杂志, 2016, 33 (3) :426-430

[48]Rongrong F, Hong W. Detection of driving fatigue by using noncontact emg and ecg signals measurement system[J]. International journal of neural systems, 2014, 24(3).

[49]王越,张驎.矿工肌肉疲劳状况及事故预防研究[J].中国安全科学学报,2021,31(03):191-196.）

[50]Kikuchi M, Fukushima K. Pattern recognition with eye movement: a neural network model[C]/jcnn. IEEE, 2000: 2037.

[51]Lyapunov S. I.,Shoshina I. I.,Lyapunov I. S.. Tremor Eye Movements as an Objective Marker of Driver’s Fatigue[J]. Human Physiology,2022,48(1):71-77.

[52]王磊宇,武淑红,李海芳.基于眼部行为的驾驶疲劳评价指标研究[J].太原理工大学学报,2015,46(04):440-443.

[53]Zhang C, Yu X. Estimating Mental Fatigue Based on Electroencephalogram and Heart Rate V ariability [J]. Polish Journal of Medical Physics And Engineering, 2010, 16(2): 67 - 84.

[54]Borghini G, Vecchiato G, Toppi J, et al. Assessment of mental fatigue during car driving by using high resolution EEG activity and neurophysiologic indices[C]//2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 2012: 6442-6445.

[55]叶柠,孙宇舸.基于EEG小波包子带能量比的疲劳驾驶检测方法[J].东北大学学报(自然科学版),2012,33(08):1088-1092.

[56]金纯,曾伟.基于脑电的实时疲劳监测算法的研究[J].科学技术与工程,2015,15(34):231-234+241.

[57]R. Chai et al. Driver fatigue classification with independent component by entropy rate bound minimization analysis in an EEG-based system [J]. IEEE J. Biomed. Health Inform, 2016, 21(3): 715-724

[58]Hongtao W, Andrei D, ItratA N, et al. A novel real-time driving fatigue detection system based on wirelessdry EEG[J]. Cognitive neurodynamics, 2018, 12(4).

[59]徐军莉,王平,穆振东.融合眼动和脑电特征的疲劳驾驶检测研究[J].重庆交通大学学报(自然科学版),2021,40(12):7-11.周继红,杨傲,袁丹凤,等.疲劳驾驶及其评估方法进展[J].伤害医学(电子版),2021,10(03):45-50.

[60]唐美霞,何勇.基于双眼定位与状态判决疲劳检测算法[J].计算机工程与设计,2018,39(06):1750-1754+1787.

[61]洪子梦,周秀,邬小鲁.一种基于眼睛长宽比的船舵手疲劳检测方法[J].电子测试,2021(07):71-73.

[62]冯晓锋.基于融合眼嘴头部特征的疲劳驾驶检测方法[J].安全与环境学报,2022,22(01):263-270.

[63]Chu J W,Jin L S,Tong B L,et al.A monitoring method of driver mouth behavior based on machine vision[A]. In: IEEE Intelligent V ehicles Symposium[C]. Parma, Italy: IEEE Inc, 2004: 351-356.

[64]Choi IH , Kim Y G. Head pose and gaze direction tracking for detecting a drowsy driver[C].2014 International Conference on Big Data and Smart Computing (BIGCOMP). Bangkok, Thailand, 2014:241-244.

[65]Shulei, Wu, Zihang, Suo,Huandong, Chen,et al. Road rage detection algorithm based on fatigue driving and facial feature point location[J]. Neural Computing and Applications, 2022(prepublish).

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

[67]田水承,孙璐瑶,唐艺璇,胥静,陈小绳.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.

[68]田水承,丁洋.基于ANP和SD的矿工不安全行为干预策略研究[J].煤矿安全,2023,54(08):252-257.

[69]丁宝成.煤矿安全预警模型及应用研究[D].辽宁工程技术大学,2010.

[70]牛强，周勇，王志晓，等.基于自组织神经网络的煤矿安全预警系统[J].计算机工程与设计，2006 (10)1752-1756.

[71]李文,武玉梁.煤矿危险源风险预警与控制的研究[J].中国安全生产科学技术,2009,5(04):154-157.

[72]谭章禄,任超,王泽.煤矿安全预警与检查闭环管理系统研究与设计[J].中国煤炭,2015,41(10):75-78.

[73]王学琛.煤矿安全生产风险评价与预警系统研究[D].武汉理工大学,2017.

[74]陈佳林.煤矿安全生产大数据预警预测平台研究[J].电脑知识与技术,2018,14(01):26-27+34.

[75]袁亮,姜耀东,何学秋,等.煤矿典型动力灾害风险精准判识及监控预警关键技术研究进展[J].煤炭学报,2018,43(02):306-318.

[76]张宁.基于贝叶斯网络的煤矿瓦斯爆炸风险判识与预警研究[D].安徽理工大学,2020.

[77]陈佳林,付恩三.基于柔性神经元的煤矿安全风险预警模型研究[J].煤炭工程,2021,53(07):187-191.

[78]Wasilewski S. Modern Systems of Gas Hazard Monitoring in Polish Coal Mines[3J].Archives of Mining Sciences,2008,53(4):511-524.

[79]Chen P, Xie Y H, Jin Petal. A Wireless Sensor Data-Based Coal Minc Gas Monitoring Algorithm with Least Squares Support Vector Machines Optimized by Swarm Intclligence Techniques[J]. International Journal of Distributed Sensor Networks,2018,14(5):1477-1550.

[80]刘年平.煤矿安全生产风险预警研究[D].重庆大学,2012.

[81]李超,石向荣,黄剑华.基于脑电信号处理的疲劳驾驶预警系统的设计与实现[J].科学技术创新,2018(02):75-76.

[82]胡纯严,胡良平.合理进行多元分析——主成分分析[J].四川精神卫生,2023,36(S1):48-54.

[83]王秀芬.阿尔特曼预测模型的局限性与交互式多准则判别分析法的运用[J].现代财经-天津财经学院学报,1998,(07):29-31.

[84]钟守铭，刘碧森，王晓梅等.神经网络稳定性理论[M].北京:科学出版社，2008

[85]钟永光.系统动力学[M]. 北京:科学出版社,2009:25-35.

[86]曹庆贵,张广宇,张建.基于神经网络和证据理论的煤矿风险预警模型[J].矿业安全与环保,2011,38(01):81-83.

[87]贺京同,潘凝,张建勋,卢桂章. 基于模糊神经网络的宏观经济预警研究[J]. 预测, 2000, (04): 42-45

[88]Ruigen Yao, Shamim N. Pakzad. Autogressive statistical pattern recognition algorithms for damage detection in civil structures[J]. Mechanical Systems and Signal Processing, 2012, (31): 355-368.

[89]廖红强,邱勇,杨侠,等.对应用层次分析法确定权重系数的探讨[J].机械工程师,2012(06):22-25.

[90]罗美菊,刘红玲.随机非线性互补问题的条件风险价值模型及其求解方法[J].系统科学与数学,2015,35(09):1081-1091.

[91]孙望书,孙旭.利用分类树辅助Logistic回归建模[J].统计与管理,2023,38(05):4-12.

[92]沈根祥,周泽峰.拟得分驱动条件异方差自回归极差模型及其实证研究[J/OL].中国管理科学,1-14[2024-03-10].

[93]丁圆苹,党耀国,王俊杰.欧勒多项式驱动的自适应多变量灰色预测模型及应用[J/OL].中国管理科学,1-20[2024-03-10].

[94]匡乐红,陈德奇.基于粗糙集理论对层次分析法的改进[J].山西建筑,2009,35(33):90-93.

[95]唐皇,魏立桥,尹勇等.基于概率有向图模型的船舶进出港航路规划[J].华中科技大学学报(自然科学版),2020,48(05):105-109.

[96]杨永杰,孙震,陈芝琦等.基于熵权-物元可拓模型的施工安全评价研究[J/OL].工程管理学报,1-6[2024-03-10].

[97]彭语冰,俞桂杰.基于多元统计分析和横截面回归的航线需求预测模型[J].工业技术经济,2007,(04):81-84.

[98]王耀中,侯俊军,刘志忠.经济预警模型述评[J].湖南大学学报(社会科学版),2004(02):27-31.

[99]Kaminsky,Lizondo,Reinhart.LeadingIndicatorsofCurrencyCrises[R].lMFWorkingPaper,1997,97/79

[100]韦善阳,杨涛.基于人-机-环境耦合效应的掘进工作面安全高效生产[J].华北科技学院学报,2014,11(07):10-13.

[101]徐明伟,金龙哲,田兴华,等.受限空间不同照度环境下VDT作业视觉疲劳[J].工程科学学报,2020,42(12):1605-1612.

[102]周克元.综合评价温度高度及湿度对人体舒适度的影响分析—以徐州市为例[J].保山学院学报,2019,38(02):19-22

[103]刘厚金,俞佩镐,林嘉壁.矿山粉尘浓度标准和测尘技术发展动向[J].煤矿安全技术,1982(03):46-52.

[104]景国勋,王远声,周霏,等.短期噪声暴露对作业人员心率的影响[J].工业安全与环保,2019,45(08):70-73.

[105]卓小宇,张东.基于深度学习的质子热声信号走时提取方法[J].信息技术,2020,44(09):79-84+89.

[106]李梦蝶,熊艳,李彦等.基于EEG探索刺激条件下设计中的顿悟现象[J].机械,2019,46(01):1-6.

[107]Bear M F. Neuroscience: exploring the brain[M]. Baltimore: Lippincott Williams& Wilkins, 2014.

[108]Cummings L, Dane A, Rhodes J, et al. Diurnal variation in the quantitative EEG inhealthy adult volunteers[J]. British Journal of ClinicalPharmacology, 2000,50(1):21-26.

[109]AkerstedtT,GillbergM.Subjective and Objective Sleepiness in the Active Individual[J].International Journal of Neuroscience,1990,52(1-2):29-37.

[110]Riethmeister V, Matthews R W, Dawson D, et al. Time-of-Day and Days-on-Shift Predict Increased Fatigue over Two-Week Offshore Day-Shifts[J].Applied Ergonomics, 2019,78:157-163.

[111]Ahsberg E, Kecklund G,Akerstedt T, et al. Shiftwork and Different Dimensions ofFatigue[J]. International Journal of Industrial Ergonomics, 2000,26(4):457-465.

[112]杨圣韬,尹晓峰,高炳宏.应用主观疲劳量表量化运动负荷的研究进展[J].体育科研2019,40(05):85-94.

[113]景国勋,吕鹏飞,周霏,等.基于E-Prime的煤矿噪声对矿工反应时与出错数的影响效应研究[J].安全与环境学报,2018,18(06):2285-2289.

[114]Tanaka M, Mizuno K, Tajima S, et al. Central nervous system fatigue altersautonomic nerve activity. Life Sci ,2009,84(7-8):235~239

[115]Eston R G, Faulkner J A, Mason E A, et al. The Validity of Predicting Maximal OxygenUptake from Perceptually Regulated Graded Exercise Tests of Different Durations[J].European Journal of Applied Physiology, 2006, 97(5): 535-541.

[116]杨竹青,李勇,胡德文.独立成分分析方法综述[J].自动化学报,2002,(05):762-772.

[117]孙盛燕,杨兵.递增负荷运动时 RPB、心率和血乳酸的关系[J].湖州师范学院学报,2015,37(02):63-68.

[118]Belyavin A, Wright N A. Changes in Electrical Activity of the Brain with Vigilance[J]. Electroencephalography and Clinical Neurophysiology, 1987, 66(2): 137-144.

[119]王福旺,王宏.长途客车驾驶员疲劳状态脑电特征分析[J].仪器仪表学报,2013,34(5):1146-1152.

[120]Roelands B, Meeusen R. The Relation between Brain Neurotransmitter Concentrations and Supraspinal Fatigue[J]. Plos One, 2013, 8(10): 53631.

[121]董建梁,李鹏,马晨光.基于脑电检测的煤矿矿工井下疲劳作业监测研究[J].中国科技信息,2014(16):82-83.

[122]He J,Liu D,Wan Z, et al. A noninvasive real-time dtiving fatigue detectiontechnology based on left prefrontal Attention and Meditation EEG[CV/ IntemationalConference on Multisensor Fusion and Information Integration for IntelligentSystems. IEEE,2014:1-6.

[123]廖红强,邱勇,杨侠,等.对应用层次分析法确定权重系数的探讨[J].机械工程师,2012(06):22-25.

[124]佘丛国,席酉民.我国企业预警研究理论综述[J].预测,2003(02):23-29+2.

[125]刘剑利.聚类分析和主成分回归在工业统计数据中的应用[D].吉林大学,2014.

[126]Cheng Y.Research on Credit Strategy Based on XGBoost Algorithm and OptimizationProblem[C]/Joumal of Physics: Conference Series.IOP Publishing, 2021,1865(4): 042-137.

[127]Al-kababchee S G M, Algamal Z Y, Qasim O S. Enhancement of K-meansClustering in Big Data based on Equilibrium Optimizer Algorithm[J]. Journal of Intelligent Systems,2023, 32(1): 20220230.