基于RS-RBFNN的邮轮建造物资物流集配风险预警

doi:10.16265/j.cnki.issn1003-3033.2023.06.1033

摘要/Abstract

摘要：

为解决邮轮建造物资物流集配层级复杂、耦合因素众多引起的产需脱节问题,提出一种粗糙集(RS)融合径向基神经网络(RBFNN)的集成风险预警模型。首先,基于物资物流集配风险因素分析,构建风险预警指标体系,利用网络分析法(ANP)建立指标间相互依赖和反馈关系评价模型,并据此确定指标重要度;其次,采用功效系数法确定历史数据警情,并以此作为神经网络输出端;最后,利用RS作为RBFNN的前置处理系统,对某邮轮建造过程机电物资物流集配进行风险预警建模,并与RBFNN、反向传播神经网络(BPNN)和RS-BPNN进行性能比较。结果表明:RS-RBFNN模型能有效简化神经网络结构,提高测效率和准确性,克服BP网络训练时间长、稳定性较差且容易陷入局部极小的弊病。

关键词: 粗糙集(RS), 径向基神经网络(RBFNN), 邮轮建造物资, 物流集配, 风险预警, 反向传播神经网络(BPNN)

Abstract:

An ensemble risk early warning model based on RS and RBFNN fusion was proposed. After constructing the risk early warning index system, the ANP was used to analyze the coupling relationship between indicators and determine the weight values. The efficacy coefficient method was used to determine the historical data alarm, which was used as the output of the neural network. The RS-RBFNN model was used to conduct a risk early warning research on the logistics of mechanical and electrical materials during the construction of a cruise ship, and the performance was compared with RBFNN, BPNN and RS-BPNN. The research shows that the RS-RBFNN model effectively simplifies the neural network structure, improves efficiency and accuracy, and overcomes the shortcomings of BPNN of training time long, poor stability and easy to fall into local minima.

Key words: rough set (RS), radial basis function neural network (RBFNN), cruise ship construction material, logistics collection and distribution, risk early warning, back propagation neural network (BPNN)

谢露强, 徐靖, 王海燕. 基于RS-RBFNN的邮轮建造物资物流集配风险预警[J]. 中国安全科学学报, 2023, 33(6): 114-121.

XIE Luqiang, XU Jing, WANG Haiyan. Risk early warning model of cruise ship construction material logistics collection and distribution based on RS-RBFNN[J]. China Safety Science Journal, 2023, 33(6): 114-121.

图/表 11

图1

图2

表1

续表1

表2

表3

表4

表5

表6

预警模型性能比较

预警模型	网络结构	训练时间/s	$α$	$β$	$δ$	$R 2$
BPNN	18×11×1	3.716 1	0.184 2	0.210 6	0.268 1	0.979 7
RS-BPNN	6×10×1	2.913 6	0.108 2	0.124 3	0.093 4	0.993 9
RBFNN	18×12×1	2.380 3	0.138 2	0.157 3	0.194 0	0.985 1
RS-RBFNN	6×10×1	0.989 3	0.071 0	0.081 5	0.036 0	0.997 3

表6

图3

图4

参考文献 17

[1]	ZHENG Yahong, KE Jiangcen, WANG Haiyan. Risk propagation of concentralized distribution logistics plan change in cruise construction[J]. Processes, 2021, 9(8): DOI:10.3390/PR9081398. doi: 10.3390/PR9081398
[2]	CUMPERAYOT P, KOUWENBERG R. Early warning systems for currency crises: a multivariate extreme value approach[J]. Journal of International Money Finance, 2013, 36: 151-171. doi: 10.1016/j.jimonfin.2013.03.008
[3]	LIN Jianxiong. Design of enterprise financial early warning model based on complex embedded system[J]. Microprocessors Microsystems, 2021, 80: DOI:10.1016/j.micpro.2020.103532. doi: 10.1016/j.micpro.2020.103532
[4]	冯巩, 夏元友, 王智德, 等. 基于位移信息融合的露天矿边坡动态预警方法[J]. 中国安全科学学报, 2022, 32(3): 116-122. doi: 10.16265/j.cnki.issn1003-3033.2022.03.016
	FENG Gong, XIA Yuanyou, WANG Zhide, et al. Dynamic early warning method of open-pit mine slopes based on integrated displacement information[J]. China Safety Science Journal, 2022, 32(3): 116-122. doi: 10.16265/j.cnki.issn1003-3033.2022.03.016
[5]	YANG Wendong, TANG Guolin, HAO Yan, et al. A novel framework for forecasting, evaluation and early-warning for the influence of PM10 on public health[J]. Atmosphere, 2021, 12(8): DOI:10.3390/atmos12081020. doi: 10.3390/atmos12081020
[6]	JIA Xiaohui, ZHANG Donghui. Prediction of maritime logistics service risks applying soft set based association rule: an early warning model[J]. Reliability Engineering System Safety, 2021, 207: DOI:10.1016/j.ress.2020.107339. doi: 10.1016/j.ress.2020.107339
[7]	XIANG Ziquan, YANG Jiaqi, NASEEM M H, et al. Risk assessment of cruise construction logistics allocation based on improved intuitionistic fuzzy TOPSIS method[J]. Journal of Intelligent & Fuzzy Systems, 2022, 43(4): 5237-5250.
[8]	KLIESTIK T, VRBKA J, ROWLAND Z. Bankruptcy prediction in Visegrad group countries using multiple discriminant analysis[J]. Equilibrium Quarterly Journal of Economics and Economic Policy, 2018, 13(3): 569-593.
[9]	PANG Fengrui, LUO Qinghong, HONG Xiuqin, et al. The study on the early warning period of varicella outbreaks based on logistic differential equation model[J]. Epidemiology Infection, 2019, 147: DOI: 10.1017/S0950268818002868. doi: 10.1017/S0950268818002868
[10]	DABROWSKI J J, BEYERS C, DE VILLIERS J P. Systemic banking crisis early warning systems using dynamic Bayesian networks[J]. Expert Systems with Applications, 2016, 62: 225-242. doi: 10.1016/j.eswa.2016.06.024
[11]	QU Zhigang, FENG Hao, ZENG Zhoumo, et al. A SVM-based pipeline leakage detection and pre-warning system[J]. Measurement, 2010, 43(4): 513-519. doi: 10.1016/j.measurement.2009.12.022
[12]	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(1): 27-33. doi: 10.16265/j.cnki.issn1003-3033.2022.01.004
	SHI Juan, CHANG Dingyi, ZHENG Peng. An early warning model of unsafe behaviors of construction workers based on BP neural network[J]. China Safety Science Journal, 2022, 32(1): 27-33. doi: 10.16265/j.cnki.issn1003-3033.2022.01.004
[13]	CHEN Yanyu, ZHENG Wenzhe, LI Wenbo, et al. Large group activity security risk assessment and risk early warning based on random forest algorithm[J]. Pattern Recognition Letters, 2021, 144: 1-5. doi: 10.1016/j.patrec.2021.01.008
[14]	JAVAN S L, SEPEHRI M M, JAVAN M L, et al. An intelligent warning model for early prediction of cardiac arrest in sepsis patients[J]. Computer Methods Programs in Biomedicine, 2019, 178: 47-58. doi: 10.1016/j.cmpb.2019.06.010
[15]	WEI Xianfu. A method of enterprise financial risk analysis and early warning based on decision tree model[J]. Security Communication Networks, 2021, 2021: 1-9.
[16]	NIU Bing, ZHANG Hui, ZHOU Guangya, et al. Safety risk assessment and early warning of chemical contamination in vegetable oil[J]. Food Control, 2021, 125: DOI: 10.1016/j.foodcont.2021.107970. doi: 10.1016/j.foodcont.2021.107970
[17]	PAWLAK Z. Rough sets[J]. International Journal of Computer & Information Sciences, 1982, 11: 341-356.

一级指标	权重	二级指标	指标依存关系	局部权重	综合权重
B₁	0.332 8	C₁	C₃,C₄,C₆,C₇, C₈,C₁₀,C₁₁,C₁₂	0.243 9	0.081 2
		C₂	C3,C₄,C₁₀, C₁₁,C₁₂,C₁₃	0.194 6	0.064 8
		C₃	C₄,C₁₀,C₁₁,C₁₂	0.181 1	0.060 3
		C₄	C₁,C₃,C₇, C₁₀,C₁₁,C₁₂	0.380 4	0.126 6
B₂	0.194 3	C₅	C₆,C₇,C₈,C₉	0.282 6	0.054 9
		C₆	C5,C₇,C₈, C₉	0.161 7	0.031 4
		C₇	C₃,C₅, C₆,C₈,C₉	0.190 8	0.037 1
		C₈	C₅, C₆,C₇,C₉	0.082 4	0.01 6
		C₉	C₁₀,C₁₁,C₁₂,C₁₃	0.282 5	0.054 9
B₃	0.127 7	C₁₀	C₁₁,C₁₂	0.191 3	0.024 4
		C₁₁	C₁₂	0.132 3	0.016 9
		C₁₂	C₁₃	0.136 5	0.017 4
		C₁₃	C₇,C₈	0.539 8	0.068 9

一级指标	权重	二级指标	指标依存关系	局部权重	综合权重
B₄	0.345 2	C₁₄	C₁,C₃,C₄,C₅, C₆,C₇,C₈,C₉, C₁₀,C₁₁,C₁₂	0.340 0	0.117 4
		C₁₅	C₉,C₁₄, C₁₆,C₁₈	0.215 9	0.074 5
		C₁₆	C₂, C₉,C₁₀,C₁₁, C₁₂,C₁₅,C₁₈	0.200 8	0.069 3
		C₁₇	C₁,C₂, C₃, C₄,C₅,C₈,C₉, C₁₆,C₁₈	0.173 5	0.059 9
		C₁₈	C₃,C₉,C₁₀, C₁₁,C₁₂,C₁₆	0.069 8	0.024 1

警度	区间	描述
无警	[90,100]	风险可忽略,物流集配整体状况良好
轻警	[85,90)	较小风险,存在个别指标不达标状况,但整体物流集配风险可控可接受
中警	[80,85)	中度风险,部分预警指标出现异常,有必要给予足够重视
重警	[0,80]	重度风险,大部分指标偏离预警线,物流集配整体趋于恶化,有必要立即采取措施管控

时间	综合风险指数	警度	时间	综合风险指数	警度
2020-07	83.1	中警	2021-03	82.4	中警
2020-08	84.2	中警	2021-04	81.7	中警
2020-09	86.1	轻警	2021-05	85.8	轻警
2020-10	84.0	中警	2021-06	86.3	轻警
2020-11	85.0	轻警	2021-07	90.2	无警
2020-12	81.8	中警	2021-08	87.4	轻警
2021-01	77.9	重警	2021-09	88.60	轻警
2021-02	78.8	重警	2021-10	87.4	轻警

U	时期T																		J
U	T₁	T₂	T₃	T₄	T₅	T₆	T₇	T₈	T₉	T₁₀	T₁₁	T₁₂	T₁₃	T₁₄	T₁₅	T₁₆	T₁₇	T₁₈	J
1	3	2	4	2	1	1	2	1	1	1	1	1	2	1	1	1	4	1	3
2	2	3	3	1	1	2	4	2	2	1	2	1	1	1	1	1	4	2	3
3	3	2	4	1	2	2	3	1	2	2	4	3	2	1	2	1	3	2	2
4	4	2	3	2	2	2	3	1	2	2	3	2	3	1	2	1	3	1	3
︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙
16	3	4	3	1	3	2	2	2	1	3	2	2	1	4	4	4	4	4	2