电梯设备安全事故率的广义代数差分预测模型

doi:10.16265/j.cnki.issn1003-3033.2023.01.0088

中国安全科学学报 ›› 2023, Vol. 33 ›› Issue (1): 64-69.doi: 10.16265/j.cnki.issn1003-3033.2023.01.0088

电梯设备安全事故率的广义代数差分预测模型

晋良海¹^,²^,³(), 陈颖¹^,^**(), 杨应柳¹, 邵波¹^,²

¹ 三峡大学水利与环境学院,湖北宜昌 443002
² 三峡大学安全生产标准化评审中心,湖北宜昌 443002
³ 湖北安环科技有限公司,湖北宜昌 443002

收稿日期:2022-08-28 修回日期:2022-11-19 出版日期:2023-01-28 发布日期:2023-07-28
通讯作者: ** 陈颖(1998—),女,湖北宜昌人,硕士研究生,主要研究方向为安全工效学、安全科学与工程。E-mail: cying2306@163.com。
作者简介:
晋良海 (1973—),男,四川简阳人,博士,教授,主要从事安全工效学、建设项目运筹管理等方面的研究。E-mail:jinlianghai@ctgu.edu.cn。
基金资助:
国家自然科学基金资助(52179136); 国家自然科学基金资助(72204141)

Generalized algebraic difference approach prediction model for elevator equipment safety accidents rate

JIN Lianghai¹^,²^,³(), CHEN Ying¹^,^**(), YANG Yingliu¹, SHAO Bo¹^,²

¹ College of Hydraulic & Environmental Engineering, China Three Gorges University, Yichang Hubei 443002, China
² Safety Production Standardization Review Center of China Three Gorges University, Yichang Hubei 443002, China
³ Hubei Anhuan Technology Co., Ltd., Yichang Hubei 443002, China

Received:2022-08-28 Revised:2022-11-19 Online:2023-01-28 Published:2023-07-28

摘要/Abstract

摘要：

为预测电梯设备安全事故发生率,采用广义代数差分法(GADA)建立动态差分预测模型。首先,采用GADA设置多自由参数,构建系列动态差分方程;其次,采用代数差分法(ADA)设置单自由变量,构建对照方程;然后,耦合分析统计指标和图形形态,厘定电梯设备安全事故率的最优GADA预测模型;最后,利用近16年我国电梯设备安全事故数据验证分析最优预测理论模型的有效性。结果表明:我国电梯设备的安全事故发生率呈整体降低的趋势,但万台事故率的下降趋势有所减缓;采用GADA由指数方程推导的模型偏差为0.002 2,均方根误差(RMSE)为 0.045 352, 拟合度为0.886 8,是最佳预测模型,预测值相对误差为5.9%。该模型可根据电梯设备登记数、万台事故数等实时数据进行更新,预测我国电梯设备的安全事故发生率。

关键词: 电梯设备, 安全事故, 广义代数差分法(GADA), 代数差分法(ADA), 预测模型, 万台事故率

Abstract:

To predict the occurrence rate of elevator equipment accidents, the generalized algebraic difference approach was used to establish a dynamic difference prediction model. Firstly, the generalized algebraic difference approach was used to set multi-free-parameters and constructed a series of dynamic difference equations. Secondly, the algebraic difference approach was used to set single-free-parameter and constructed a control equation. Then, coupled with the analysis of statistical indicators and graphical patterns, the optimal generalized algebraic difference prediction model for the safety accident rate of elevator equipment was determined. Finally, the data of elevator equipment accidents in China over the past 16 years were used to verify the effectiveness of the optimal prediction theoretical model. The results show that the accident rate of elevator equipment in China presents an overall decreasing trend, but the decreasing trend of the accident rate per 10 000 units slows down. Using the generalized algebraic difference approach, the model derives from the exponential equation with the deviation of 0.002 2, the root mean square error (RMSE) of 0.0453 52 and the fitting degree of 0.886 8 is the best prediction model, and the relative error of its prediction value is 5.9%. The prediction model can be updated according to the real-time data such as the amount of registered elevator equipment and the number of accidents rate per 10 000 units, and can effectively predict the accident rate of elevator equipment in China.

Key words: elevator equipment, difference model, generalized algebraic difference approach (GADA), algebraic difference approach (ADA), prediction model, accidents rate per 10 000 units

晋良海, 陈颖, 杨应柳, 邵波. 电梯设备安全事故率的广义代数差分预测模型[J]. 中国安全科学学报, 2023, 33(1): 64-69.

JIN Lianghai, CHEN Ying, YANG Yingliu, SHAO Bo. Generalized algebraic difference approach prediction model for elevator equipment safety accidents rate[J]. China Safety Science Journal, 2023, 33(1): 64-69.

图/表 6

图1

表1

基础方程与差分方程

基础方程	自由参数	x的解	差分方程
S = aexp(bq)	a = x	x = S₀/exp(bq₀)	S = [S₀/exp(bq₀)]exp(bq)(模型E0)
S = aq^b	a = exp(x) b = c₁+c₂x	x = [ln(S₀)-c₁ln(q₀)]/[1+c₂ln(q₀)]	$S = e x p (x) q c 1 + c 2 x$ (模型E1)
S = aq^b	a = exp(x) b = c₁+c₂/x	$x = 12 [F + F 2 - 4 c 2 l n (q 0)] F = l n (S 0) - c 1 l n (q 0)$	$S = e x p (x) q c 1 + c 2 / x$ (模型E2)
S = aexp(bq)	a = exp(x) b = cx	x = ln(S₀)/(1+cq₀)	S = exp[(1+cq)ln(S₀)/(1+cq₀)](模型E3)
S = aexp(bq)	a = exp(x) b = c/x	$x = 12 {l n (S 0) + [l n (S 0)] 2 - 4 c q 0}$	S = exp(x+cq/x) (模型E4)

表1

表2

图2

图3

图4

参考文献 18

[1]	曾珠, 罗云, 杨燕鹏, 等. 特种设备社会风险水平定量分析[J]. 中国安全科学学报, 2014, 24(8):119-124.
	ZENG Zhu, LUO Yun, YANG Yanpeng, et al. Quantitative analysis of social risk level of special equipment[J]. China Safety Science Journal, 2014, 24(8):119-124.
[2]	杜娅, 谢科范, 梁本部, 等. 电梯安全风险因素分析及预警研究[J]. 安全与环境工程, 2021, 28(4):71-79.
	DU Ya, XIE Kefan, LIANG Benbu, et al. Factors analysis and early warning of elevator safety risk[J]. Safety and Environmental Engineering, 2021, 28(4):71-79.
[3]	国家市场监管总局. 市场监管总局关于2020年全国特种设备安全状况的通告[EB/OL]. [2022-06-12]. https://gkml.samr.gov.cn/nsjg/tzsbj/202103/t20210315_326902.html.
[4]	田水承, 景国勋. 安全管理学[M]. 北京: 机械工业出版社, 2016:213.
[5]	李中兴, 陈国华, 李刚, 等. 基于PHA-FMEA的电梯安全评估方法及应用[J]. 中国安全科学学报, 2014, 24(10):60-64.
	LI Zhongxing, CHEN Guohua, LI Gang, et al. PHA-FMEA-based elevator safety assessment method and its application[J]. China Safety Science Journal, 2014, 24(10):60-64.
[6]	WANG Feng, ZHANG Jinguang, LIANG Xuedong, et al. Elevator safety risk and countermeasures based on FTA-TFN[J]. Applied Mathematics & Information Sciences, 2014, 8(4):1741-1748.
[7]	朱明, 王志荣, 梁华, 等. 基于GM(1,1)的残差修正模型的电梯故障率预测[J]. 安全与环境学报, 2017, 17(5):1701-1704.
	ZHU Ming, WANG Zhirong, LIANG Hua, et al. Prediction of the elevator failure rate based on the residual error correcting model of GM(1,1)[J]. Journal of Safety and Environment, 2017, 17(5):1701-1704.
[8]	YU Jie, HU Bo. Influence of the combination of big data technology on the spark platform with deep learning on elevator safety monitoring efficiency[J]. Plos One, 2020, 15(6):DOI: 10.1371/journal.pone.0234824. doi: 10.1371/journal.pone.0234824
[9]	许素睿. 基于HFACS的电梯事故人因分析[J]. 中国安全科学学报, 2019, 29(7):70-75. doi: 10.16265/j.cnki.issn1003-3033.2019.07.012
	XU Surui. Analyiss of human factors of elevator accidents based on HFACS[J]. China Safety Science Journal, 2019, 29(7):70-75. doi: 10.16265/j.cnki.issn1003-3033.2019.07.012
[10]	RAU P P, LIAO Pinchao, GUO Zhi, et al. Personality factors and safety attitudes predict safety behaviour and accidents in elevator workers[J]. International Journal of Occupational Safety and Ergonomics, 2020, 26(4):719-727. doi: 10.1080/10803548.2018.1493259
[11]	CIESZEWSKI C J, BAILEY R L. Generalized algebraic difference approach: theory based derivation of dynamic site equations with polymorphism and variable asymptotes[J]. Forest Science, 2000, 46(1) :116-126.
[12]	崔庆玲, 罗云, 崔刚, 等. 基于灰色理论的特种设备安全事故预测研究[J]. 中国安全生产科学技术, 2013, 9(5):141-144.
	CUI Qingling, LUO Yun, CUI Gang, et al. Study on prediction of special equipment accident based on grey theory[J]. Journal of Safety Science and Technology, 2013, 9(5):141-144.
[13]	CIESZEWSKI C J, STRB M, ZASADA M. New dynamic site equation that fits best the Schwappach data for Scots pine (Pinus sylvestris L.) in Central Europe[J]. Forest Ecology and Management, 2007, 43(1) : 83-93.
[14]	赵磊, 倪成才, GORDON N. 加拿大哥伦比亚省美国黄松广义代数差分型地位指数模型[J]. 林业科学, 2012, 48(3):74-81.
	ZHAO Lei, NI Chengcai, GORDON N. Generalized algebraic difference site index model for Pnderosa pine in British Columbia, Canada[J]. Scientia Silvae Sinicae, 2012, 48(3):74-81.
[15]	MEVIK B H, WEHRENS R. The pls package: principal component and partial least squares regression in R[J]. Journal of Statistical Software, 2007, 18(2):1-23.
[16]	AVEN T. The risk concept:historical and recent development trends[J]. Reliability Engineering and System Safety, 2012, 99:33-44. doi: 10.1016/j.ress.2011.11.006
[17]	谷梦瑶, 李光海, 戴之希. 融合事故表征和CBR的特种设备事故预测研究[J]. 计算机工程与应用, 2022, 58(1):255-267. doi: 10.3778/j.issn.1002-8331.2007-0361
	GU Mengyao, LI Guanghai, DAI Zhixi. Research on accident prediction method of special equipment based on accident characterization and CBR[J]. Computer Engineering and Applications, 2022, 58(1):255-267. doi: 10.3778/j.issn.1002-8331.2007-0361
[18]	曾珠, 罗云, 杨燕鹏, 等. 适于监管的特种设备使用过程关键风险因素辨识分析[J]. 中国安全科学学报, 2014, 24(2):157-163.
	ZENG Zhu, LUO Yun, YANG Yanpeng, et al. Identification and analysis of special equipment's use-related key risk factors suitable for supervision[J]. China Safety Science Journal, 2014, 24(2):157-163.

编号	参数	估计值	标准误	R²	Bias	RMSE
E1	c₁	-57.377 6	1.90×10⁶	0.862 31	0.000 22	0.050 020
E1	c₂	22.418 5	7.52×10⁶	0.862 31	0.000 22	0.050 020
E2	c₁	57.707 0	1.99×10⁵	0.862 31	0.000 22	0.050 020
E2	c₂	-147.659 0	5.02×10⁵	0.862 31	0.000 22	0.050 020
E3	c	0.005 1	9.08×10^-4	0.886 80	0.000 20	0.045 352
E4	c	0.002 0	1.38×10^-4	0.886 63	-0.000 82	0.045 384
E0	b	0.003 2	1.69×10^-4	0.886 79	0.000 55	0.045 354

电梯设备安全事故率的广义代数差分预测模型

Generalized algebraic difference approach prediction model for elevator equipment safety accidents rate

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 18

相关文章 15

编辑推荐

Metrics

本文评价

[1]	孟祥海, 由冰玉, 邱志雄, 李之啸, 张明扬. 基于事故修正系数的山区高速公路事故预测模型[J]. 中国安全科学学报, 2023, 33(1): 10-17.
[2]	杨佩佩, 熊坚, 何扬帆. 公路小半径曲线路段驾驶人焦虑水平模型[J]. 中国安全科学学报, 2023, 33(1): 227-232.
[3]	朱方艳, 周献锋, 高健, 王帅. 基于SAS分析的夏季生产安全事故特征和防范[J]. 中国安全科学学报, 2022, 32(S1): 23-28.
[4]	唐涛, 甘婧. 基于国内外铁路运营数据的列车运行时间预测模型[J]. 中国安全科学学报, 2022, 32(6): 123-130.
[5]	方雪, 谢朝武, 黄锐. 扎根理论下国内漂流旅游安全事故成因机制[J]. 中国安全科学学报, 2022, 32(4): 23-29.
[6]	曹杨. 我国海洋石油安全事故分类与分级研究[J]. 中国安全科学学报, 2022, 32(3): 18-24.
[7]	高云骥, 罗越扬, 李智胜, 张玉春, 喻洋阳, 李涛. 分岔隧道火灾烟气回流长度及温度分布试验研究[J]. 中国安全科学学报, 2022, 32(3): 109-115.
[8]	张利冬, 宋泽阳, 罗振敏, 赵珊珊. 基于机器学习的煤自然发火期预测[J]. 中国安全科学学报, 2022, 32(12): 118-124.
[9]	柯丽华, 陈魁香, 胡南燕, 谭铭, 张光权, 孟欢欢. 基于SNA的露天矿爆破安全风险评估[J]. 中国安全科学学报, 2022, 32(10): 48-56.
[10]	郑文博. 国内外建筑工程安全管理主要成就:基于安全事故、安全管理制度及相关文献的研究[J]. 中国安全科学学报, 2022, 32(10): 8-17.
[11]	曹勇, 卢云峰, 贺一博, 李明, 刘小杰. 外委承包商安全管理策略研究[J]. 中国安全科学学报, 2021, 31(S1): 8-13.
[12]	杨小朋, 闫瑞兵, 彭莉莉. 大型煤炭企业事故致因模型及对策分析[J]. 中国安全科学学报, 2021, 31(S1): 73-79.
[13]	巫诚诚, 陈大伟. 交叉口非机动车冲突易发点空间预测模型^*[J]. 中国安全科学学报, 2021, 31(8): 165-171.
[14]	隆能增, 袁梅, 王关亮, 王清辉, 许石青, 李鑫灵. 煤与瓦斯突出微震-瓦斯互动响应预警研究[J]. 中国安全科学学报, 2021, 31(4): 125-132.
[15]	刘雨晴, 张培红. 大坡度倾斜巷道火灾烟气温度分布特征研究[J]. 中国安全科学学报, 2021, 31(4): 156-162.