基于t-SSA-BP的煤矿噪声职业健康损害预测

doi:10.16265/j.cnki.issn1003-3033.2023.12.2068

摘要/Abstract

摘要：

为精准预测煤矿接噪人员职业健康损害情况,基于分位图法选取健康损害数据影响因素,依据噪声职业健康损害评估方法,以自适应t分布变异因子和麻雀搜索算法(SSA)作为参数优化算法,建立t-SSA-BP煤矿噪声职业健康损害预测模型,利用基准函数测试算法寻优性能,并以陕北地区10个煤矿为研究对象,采用现场调查、理论分析和Matlab仿真模拟方法验证煤矿噪声职业健康损害预测模型。结果表明:噪声暴露强度、个体年龄、接噪工龄和接噪岗位4个指标是煤矿噪声健康损害的影响因素;t-SSA较SSA在4种基准函数上整体精度提升66.0%,5种噪声健康损害神经网络预测模型预测精度从高到低依次为:t-SSA-BP > SSA-BP > PSO-BP > CFA-PSO-RBF > PSO-GRNN,t-SSA-BP预测模型的平均绝对误差(MAE)、平均绝对百分误差(MAPE)相比SSA-BP分别降低68.1%、66.7%,决定系数(R²)达0.999,预测精度明显提升,且收敛速度更快。

关键词: 自适应t分布变异因子, 麻雀搜索算法(SSA), 煤矿噪声, 健康损害预测, BP神经网络

Abstract:

In order to accurately predict the occupational health damage of workers exposed to noise in coal mines, the influencing factors were selected based on the quantile plot method. According to the noise occupational health damage assessment method, the adaptive t distribution variation operator and SSA were used as parameter optimization algorithms to establish the t-SSA-BP coal mine noise occupational health damage prediction model, and the benchmark function was used to test the optimization performance of the algorithm. 10 coal mines in northern Shaanxi were taken as the research objects, and the prediction model was verified by field investigation, theoretical analysis and Matlab simulation. The results show that the noise exposure intensity, individual age, length of service and noise exposure post are the influencing factors of noise health damage in coal mines. The overall accuracy of t-SSA is 66.0%, which is higher than that of SSA in four benchmark functions. The order of accuracy of the five prediction models is: t-SSA-BP>SSA-BP>PSO-BP>CFA-PSO-RBF>PSO-GRNN. Compared with SSA-BP, the MAE and MAPE of t-SSA-BP prediction model decreases by 68.1% and 66.7% respectively, and the R² reaches 0.999. The prediction accuracy and convergence rate are significantly improved.

Key words: adaptive t distribution mutation operator, sparrow search algorithm (SSA), coal mine noise, prediction of health damage, BP neural network

高晓旭, 高璐, 潘相旭, 高翔, 麻昊. 基于t-SSA-BP的煤矿噪声职业健康损害预测[J]. 中国安全科学学报, 2023, 33(12): 214-222.

GAO Xiaoxu, GAO Lu, PAN Xiangxu, GAO Xiang, MA Hao. Prediction of occupational health damage caused by coal mine noise based on t-SSA-BP[J]. China Safety Science Journal, 2023, 33(12): 214-222.

图/表 12

图1

图2

图3

图4

表1

基准函数

函数	变量特征	函数表达式	取值范围	维数
F1	单峰可分离	$f 1 (x) = ∑ i = 1 30 i x i 4 + r n d$	[-1.28,1.28]	30
F2	单峰不可分离	$f 2 (x) = ∑ i = 1 30 - 1 [100 (x i + 1 - x i 2) 2 + (x i - 1) 2]$	[-30,30]	30
F3	多峰可分离	$f 3 (x) = ∑ i = 1 30 [x i 2 - 10 c o s (2 π x i) + 10]$	[-5.12,5.12]	30
F4	多峰不可分离	$f 4 (x) = 14000 ∑ i = 1 30 x i 2 - ∏ i = 1 30 c o s x i i + 1$	[-600,600]	30

表1

图5

表2

表3

图6

图7

图8

表4

参考文献 19

[1]	关品品, 周玉竹, 宋宛亭, 等. 四川省煤矿井下噪声调查分析[J]. 中华劳动卫生职业病杂志, 2022, 40(2):149-151.
	GUAN Pinpin, ZHOU Yuzhu, SONG Wanting, et al. Investigation and analysis of underground noise in Sichuan coal mines[J]. Chinese Journal of Industrial Hygiene and Occupational Diseases, 2022, 40(2):149-151.
[2]	王浩, 蒋承林, 史莉莉. 煤矿井下噪声危害分析及对策[J]. 中国安全生产科学技术, 2011, 7(12):183-187.
	WANG Hao, JIANG Chenglin, SHI Lili. Analysis and countermeasures on underground noise hazards of coal mine[J]. Journal of Safety Science and Technology, 2011, 7(12):183-187.
[3]	郑夏雯, 聂臻, 丰峰, 等. 衢州市2016—2019年造纸行业噪声作业工人听力损失及其影响因素分析[J]. 实用预防医学, 2022, 29(1):59-62.
	ZHENG Xiawen, NIE Zhen, FENG Feng, et al. Hearing lose and its influencing factors among noise-exposed workers in paper industry in Quzhou city, 2016-2019 [J]. Practical Preventive Medicine, 2022, 29(1):59-62.
[4]	罗燕, 尹颀, 王小明, 等. 2015—2019年重庆市涪陵区职业性噪声危害及影响因素分析[J]. 职业与健康, 2021, 37(8):1127-1129,1 133.
	LUO Yan, YIN Qi, WANG Xiaoming, et al. Analysis on hazard and influencing factors of occupational noise in Fuling district of Chongqing from 2015-2019[J]. Occupation and Health, 2021, 37(8):1127-1129,1 133.
[5]	郑宇. 建筑施工噪声监测及职业健康损害评价研究[D]. 北京: 清华大学, 2014. ZHENG Yu. The monitoring and analysis of building construction noise and its health impacts on construction workers
	[ D. Beijing: Tsinghua University, 2014. [6 ]
[7]	张渤苓, 王一然, 王露露, 等. 燃煤发电职业危害暴露健康负担评价方法[J]. 中国安全生产科学技术, 2021, 17(11):179-185.
	ZHANG Boling, WANG Yiran, WANG Lulu, et al. Method of health burden assessment on occupational hazard exposure in coal-fired power generation[J]. Journal of Safety Science and Technology, 2021, 17(11):179-185.
[8]	SUN Kan, AZMAN A S. Evaluating hearing loss risks in the mining industry through MSHA citations[J]. Journal of Occupational and Environmental Hygiene, 2018, 15(3):246-262. doi: 10.1080/15459624.2017.1412584 pmid: 29200378
[9]	娄高中, 谭毅. 基于PSO-BP神经网络的导水裂隙带高度预测[J]. 煤田地质与勘探, 2021, 49(4):198-204.
	LOU Gaozhong, TAN Yi. Prediction of the height of water flowing fractured zone based on PSO-BP neural network[J]. Coal Geology & Exploration, 2021, 49(4):198-204.
[10]	尹会永, 周鑫龙, 郎宁, 等. 基于SSA优化的GA-BP神经网络煤层底板突水预测模型与应用[J]. 煤田地质与勘探, 2021, 49(6):175-185.
	YIN Huiyong, ZHOU Xinlong, LANG Ning, et al. Prediction model of water inrush from coal floor based on GA-BP neural network optimized by SSA and its application[J]. Coal Geology & Exploration, 2021, 49(6):175-185.
[11]	吴静娴, 缪汉韬, 刘佳佳. 汽车产业工人听力状况调查及噪声性聋影响因素相关性研究[J]. 中国临床研究, 2017, 30(5):713-716.
[12]	岑永庄, 邓燕君, 刘新霞. 噪声作业所致工人职业性听力损失风险回顾性队列研究[J]. 中国公共卫生, 2016, 32(5):642-645.
	CEN Yongzhuang, DENG Yanjun, LIU Xinxia. Risk of hearing loss in noise-exposed workers: a retrospective cohort study[J]. Chinese Journal of Public Health, 2016, 32(5):642-645.
[13]	肖华. 某烟厂 2013-2015年接触噪声作业人员职业健康状况研究[D]. 长春: 吉林大学, 2017.
	XIAO Hua. The study of conditions for occupational workers who exposed to noise in a tobacco factory in 2013-2015[D]. Changchun: Jilin University, 2017.
[14]	贾丙宏, 祝文硕, 王瑞富, 等. 基于SSA-BP神经网络模型的风暴潮灾害损失评估[J]. 海洋预报, 2022, 39(2):50-58.
	JIA Binghong, ZHU Wenshuo, WANG Ruifu, et al. The assessment of storm surge disaster loss based on SSA-BP neural network model[J]. Marine Forecasts, 2022, 39(2):50-58.
[15]	XUE Jiankai, SHEN Bo. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1):22-34.
[16]	杨洁, 程晓健, 穆彦斌. 基于PSO-RBF神经网络的海战场电磁态势预测[J]. 现代电子技术, 2019, 42(3):1-5.
	YANG Jie, CHENG Xiaojian, MU Yanbin. Sea battlefield electromagnetic state prediction based on PSO-RBF neural network[J]. Modern Electronics Technique, 2019, 42(3):1-5.
[17]	韩斐斐, 刘升. 基于自适应t分布变异的缎蓝园丁鸟优化算法[J]. 微电子学与计算机, 2018, 35(8):117-121.
	HAN Feifei, LIU Sheng. Adaptivesatin bower birdoptimization algorithm based on tdistribution mutation[J]. Microelectronics & Computer, 2018, 35(8):117-121.
[18]	郑度奎, 程远鹏, 李昊燃, 等. IAFSA-GRNN在油田集输管道CO₂腐蚀速率预测中的应用[J]. 中国安全科学学报, 2022, 32(1):110-117. doi: 10.16265/j.cnki.issn1003-3033.2022.01.015
	ZHENG Dukui, CHENG Yuanpeng, LI Haoran, et al. Application of IAFSA-GRNN in CO₂ corrosion rate prediction of oil gathering pipelines[J]. China Safety Science Journal, 2022, 32(1):110-117. doi: 10.16265/j.cnki.issn1003-3033.2022.01.015
[19]	张坤鳌, 赵凯. 基于改进CFA PSO-RBF神经网络的温室温度预测研究[J]. 计算机应用与软件, 2020, 37(6):95-99,107.
	ZHANG Kun'ao, ZHAO Kai. Greenhouse temperature prediction based on improved CFA PSO-RBF neural network[J]. Computer Applications and Software, 2020, 37(6):95-99,107.

函数	算法	最优值	最劣值	平均值	标准差
F1	SSA	3.701×10^-4	3.083×10^-3	2.577×10^-3	1.676×10^-3
F1	t-SSA	2.229×10^-4	2.962×10^-3	9.817×10^-4	7.569×10^-4
F2	SSA	4.219×10^-7	2.447×10^-2	2.994×10^-3	5.507×10^-3
F2	t-SSA	2.106×10^-7	1.795×10^-2	2.774×10^-3	4.857×10^-3
F3	SSA	5.684×10^-14	7.425×10^-2	3.721×10^-3	1.618×10^-2
F3	t-SSA	5.680×10^-14	6.629×10^-4	3.334×10^-5	1.444×10^-4
F4	SSA	1.110×10^-16	1.827×10^-3	9.136×10^-5	3.982×10^-4
F4	t-SSA	1.110×10^-16	7.756×10^-5	3.907×10^-6	1.689×10^-5

样本编号	接噪岗位(标签)	检测地点	L_EX,8h/dB(A)	年龄	工龄/a	DALY/10^-6a
1	采煤机司机(1)	采煤机司机操作位	98.2	46	10	7.09
2	刮板机司机(2)	刮板输送机机头	87.1	50	15	5.63
3	破碎机司机(3)	破碎机旁	88.3	44	13	6.94
4	马蒂尔司机(4)	带式输送机自移机尾	93.1	48	11	6.34
︙	︙	︙	︙	︙	︙	︙
608	拣矸工(17)	拣矸胶带放矸口	83.7	42	10	6.93
609	选煤工(18)	选煤厂一层	79.5	43	6	6.27
610	主通风机司机(19)	主通风机操作处	79.1	44	5	6.01
611	空压机司机(20)	空压机房	81.2	29	1	8.26
612	水处理工(21)	值班室	74.6	34	3	7.23

算法	MSE/10^-15		MAE/10^-8		MAPE		R²
算法	训练集	测试集	训练集	测试集	训练集	测试集	训练集	测试集
SSA-BP	0.542	1.397	1.622	2.356	0.002	0.003	0.999	0.997
t-SSA-BP	0.087	0.116	0.663	0.751	0.001	0.001	0.999	0.999
PSO-BP	28.654	20.600	12.731	10.721	0.018	0.014	0.967	0.960
PSO-GRNN	0.306	35.945	1.053	14.234	0.001	0.018	0.999	0.930
CFA-PSO-RBF	22.112	22.479	10.524	10.130	0.014	0.013	0.974	0.956

[1]	汪伟, 崔欣超, 祁云, 梁然, 贾宝山, 薛凯隆. 基于SSA-RF的采空区煤自燃温度回归分析模型[J]. 中国安全科学学报, 2023, 33(9): 136-141.
[2]	古莹奎, 汪源金, 石昌武. 基于EWM和SVR的滚动轴承剩余使用寿命预测方法[J]. 中国安全科学学报, 2023, 33(9): 49-55.
[3]	杨明, 贾改妮, 刘毛毛, 全星苑. 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(5): 177-184.
[4]	岳仁田, 韩蒙. 基于四诊法的管制席安全运行状态诊断^*[J]. 中国安全科学学报, 2021, 31(9): 52-59.
[5]	王海飙, 陈海超, 李蕊, 于贺, 赵天怡. 城市应急避难场所管理体系构建与应用^*[J]. 中国安全科学学报, 2021, 31(12): 153-159.
[6]	肖鹏, 谢行俊, 双海清, 刘朝阳, 王海宁, 徐经苍. 基于KPCA-CMGANN算法的瓦斯涌出量预测研究[J]. 中国安全科学学报, 2020, 30(5): 39-47.
[7]	江新, 杜海文, 袁轩, 胡文佳, 郑霞忠, 孙正熙. 神经网络范式下硐室群施工安全风险预警研究[J]. 中国安全科学学报, 2018, 28(2): 181-186.
[8]	张智, 何雨, 黄茜, 何汉平, 鲍洪志. 含硫气井完整性风险等级预测研究^*[J]. 中国安全科学学报, 2017, 27(10): 155-161.
[9]	付华，许凡，徐耀松，孙朋. 基于变权重RBF组合模型的煤与瓦斯突出强度预测[J]. 中国安全科学学报, 2013, 23(8): 65-.
[10]	王云飞，梁伟，张来斌. 多层融合的管道泄漏诊断技术研究[J]. 中国安全科学学报, 2013, 23(8): 171-.
[11]	刘志强，於以辰，汪澎. 驾驶员注视行为模式识别技术研究[J]. 中国安全科学学报, 2013, 23(6): 80-.
[12]	钱枫林，崔健. BP神经网络模型在应急需求预测中的应用——以地震伤亡人数预测为例[J]. 中国安全科学学报, 2013, 23(4): 20-.
[13]	张锦伟，姚安林，杨璐，李荣翰. 基于风险的输气站场设施检测周期确定方法研究[J]. 中国安全科学学报, 2013, 23(4): 167-.
[14]	汪伟，罗周全，王益伟，贾楠. 金属矿山采空区危险性辨识的遗传BP模型研究[J]. 中国安全科学学报, 2013, 23(2): 39-.
[15]	葛继科，李太福，苏盈盈，刘兴华. 基于Relief F和BP神经网络的安全评价指标体系精简化建模[J]. 中国安全科学学报, 2013, 23(10): 15-.