Risk Assessment Method for Marine Engineering Project Bidding Based on Back Propagation Neural Network

doi:10.16183/j.cnki.jsjtu.2023.S1.26

Abstract

Abstract:

The marine engineering industry is an internationalized sector, whose internationalization determines the intensity of competition. In the bidding process, it is crucial for company decision-makers to conduct accurate risk assessments, as this plays a vital role in the long-term development of the company. A high accuracy project risk assessment model is established after analyzing and identifying relevant risk factors in such projects based on quantifying qualitative problems using the fuzzy analytic hierarchy process (FAHP) and utilizing the high fault-tolerance and generalization capabilities of the back propagation (BP) neural network. Thus, the model provides an effective and efficient risk analysis tool for supporting enterprises in the marine engineering industry in the bidding decision-making process.

Key words: marine engineering bidding, risk assessment, back propagation (BP) neural network, fuzzy analytic hierarchy process (FAHP)

CLC Number:

XIA Yu, WANG Lei. Risk Assessment Method for Marine Engineering Project Bidding Based on Back Propagation Neural Network[J]. Journal of Shanghai Jiao Tong University, 2023, 57(S1): 46-53.

Figures/Tables 7

Fig.1

Fig.2

Fig.3

Tab.1

Tab.2

Tab.3

Tab.4

References 18

[1]	孙贤胜, 单卫国, 高振宇, 等. 重塑全球能源格局的2022[J]. 国际石油经济, 2023, 31(1): 24-30.
	SUN Xiansheng, SHAN Weiguo, GAO Zhenyu, et al. 2022: Reshaping the global energy landscape[J]. International Petroleum Economics, 2023, 31 (1): 24-30.
[2]	中国石油集团经济技术研究院. 2018年国内外油气行业发展报告[M]. 北京: 石油工业出版社, 2019.
	China Petroleum Corporation Economic and Technological Research Institute. 2018 domestic and foreign oil and gas industry development report[M]. Beijing: Petroleum Industry Press, 2019.
[3]	吴林强, 张涛, 徐晶晶, 等. 全球海洋油气勘探开发特征及趋势分析[J]. 国际石油经济, 2019, 27(3): 29-36.
	WU Linqiang, ZHANG Tao, XU Jingjing, et al. Characteristics and trends of global offshore oil and gas exploration and development[J]. International Petroleum Economics, 2019, 27 (3): 29-36.
[4]	黄海龙, 胡志良, 代万宝, 等. 海上风电发展现状及发展趋势[J]. 能源与节能, 2020, 177(6): 51-53.
	HUANG Hailong, HU Zhiliang, DAI Wanbao, et al. Development status and trend of offshore wind power[J]. Energy and Energy Conservation, 2020, 177 (6): 51-53.
[5]	谢周峰, 卫文灿, 孙超, 等. 海外EPC项目的风险管理问题研究[J]. 中国市场, 2013, 717(2): 76-78.
	XIE Zhoufeng, WEI Wenchan, SUN Chao, et al. Research on risk management of overseas EPC projects[J]. China Market, 2013, 717 (2): 76-78.
[6]	URIL B, URIL D, GUAN B B. A time/cost/quality risk model[C]\\Proceedings of IRNOP VII Project Research Conference. Beijing, China: Publishing House of Electronic Industry, 2006: 631-640.
[7]	BOERINGER D W, WERNER D H. A comparison of particle swarm optimization and genetic algorithms for a phased array synthesis problem[C]\\Antennas & Propagation Society International Symposium. Columbus, Ohio, USA: IEEE, 2003: 181-184.
[8]	BELFARES L, KLIBI W, LO N, et al. Multi-objectives Tabu Search based algorithm for progressive resource allocation[J]. European Journal of Operational Research, 2007, 177(3): 1779-1799. doi: 10.1016/j.ejor.2005.10.012 URL
[9]	ZHENG D, NG S T, KUMARASWAMY M M. Applying a genetic algorithm-based multiobjective approach for time-cost optimization[J]. Journal of Construction Engineering & Management, 2004, 130(2): 168-176.
[10]	陶自成, 何彦舫. 模糊综合评判风险管理技术在EPC项目投标决策中的应用[J]. 国际经济合作, 2015, 357(9): 83-86.
	TAO Zicheng, HE Yanfang. The application of fuzzy comprehensive evaluation risk management technology in EPC project bidding decision[J]. Journal of International Economic Cooperation, 2015, 357(9): 83-86.
[11]	ZHOU X P, ZOU B H, PENG J. The causes and countermeasures of implicit cost of international EPC project[C]\\Conference Proceedings of the 7th International Symposium on Project Management (ISPM2019). Chongqing,China: Aussino Academic Publishing House, 2019: 1120-1125.
[12]	LI W F, LING L. Cost control of sub-contracted projects based on EPC petrochemical engineering[J]. Journal of Physics: Conference Series, 2020, 1649(1): 012004. doi: 10.1088/1742-6596/1649/1/012004
[13]	KIM M H, LEE E B. A forecast model for the level of engineering maturity impact on contractor’s procurement and construction costs for offshore EPC megaprojects[J]. Energies, 2019, 12(12): 2295-1-18. doi: 10.3390/en12122295 URL
[14]	LI S, WANG Y J, ZENG Y. The standardization system of water conservancy project cost management under the EPC general contract model[J]. IOP Conference Series: Earth and Environmental Science, 2021, 787(1): 012118. doi: 10.1088/1755-1315/787/1/012118
[15]	LIU H R. Analysis on cost control and management scheme of oil and gas pipeline EPC project under transnational government credit[J]. Journal of Oil and Gas Technology, 2019, 41(4): 76-80.
[16]	王博, 顿新春, 李智勇. 基于BP神经网络的水利工程投标决策模型及应用[J]. 水电能源科学, 2013, 31(3): 131-134.
	WANG Bo, DUN Xinchun, LI Zhiyong. A decision model for water conservancy engineering bidding based on BP neural network and its application[J]. Water Resources and Power, 2013, 31(3): 131-134.
[17]	CRISTIAN C N, SHAN Y W, PHIL L, et al. Bridge maintenance prioritization using analytic hierarchy process and fusion tables[J]. Automation in Construction, 2019, 101: 99-110. doi: 10.1016/j.autcon.2019.01.016 URL
[18]	马志远. 基于序贯概率比检验和小波神经网络的齿轮箱故障诊断方法[D]. 武汉: 武汉工程大学, 2016.
	MA Zhiyuan. Gearbox fault diagnosis based on sequential probability ratio test and wavelet neural network[D]. Wuhan: Wuhan University of Engineering, 2016.

影响投标的因素集			评分
一级指标	二级指标		低	较低	一般	较高	高
	是否符合招标条件	B11	1	5	2	1	1
	融资能力或现金流	B12	6	2	1	1	0
承包企业自身因素	类似项目经验	B13	1	4	2	2	1
B1	当前任务量	B14	2	5	2	1	0
	期望投资回报	B15	2	5	2	1	0
	项目工期	B21	3	3	3	1	0
项目因素	项目规模	B22	2	5	1	1	1
B2	项目技术要求复杂度	B23	0	1	4	3	2
	业主经济实力	B31	7	1	1	1	0
业主因素	业主信誉	B31	6	2	1	1	0
B3	投标规范的严格性	B33	2	6	1	1	0
	竞争对手数量	B41	1	1	4	2	2
竞争对手因素	竞争对手实力	B42	1	4	4	1	0
B4	竞争对手和业主关系	B43	2	5	2	1	0
	经济环境	B51	2	4	3	1	0
环境因素	社会环境	B52	2	4	3	1	0
B5	自然环境	B53	2	3	4	1	0

序号	权重	序号	权重
1	0.168	10	0.096
2	0.096	11	0.128
3	0.184	12	0.224
4	0.136	13	0.16
5	0.136	14	0.136
6	0.136	15	0.144
7	0.152	16	0.144
8	0.248	17	0.152
9	0.088

表类型	判断矩阵						特征向量	权重值/%	最大特征值	CI值
表类型	A	B1	B2	B3	B4	B5	特征向量	权重值/%	最大特征值	CI值
	B1	1					0.871	14.13
	B2	1/3	1				0.334	5.42
二级因素	B3	2	5	1			1.108	17.97	5.423	0.106
	B4	1	2	3	1		1.149	18.64
	B5	3	8	2	3	1	2.702	43.84
	B1	B11	B12	B13	B14	B15
	B11	1					2.297	31.01
	B12	1/4	1				0.608	8.21
	B13	1/4	1	1			0.608	8.21	5.039	0.01
	B14	1/8	1/2	1/2	1		0.33	4.45
	B15	2	6	6	8	1	3.565	48.12
	B2	B21	B22	B23
	B21	1					1.587	45.79
	B22	1/4	1				0.437	12.60	3.009	0.005
	B23	1	3	1			1.442	41.61
三级因素	B3	B31	B32	B33
	B31	1					0.63	17.44
	B32	4	1				2.289	63.37	3.009	0.005
	B33	1	1/3	1			0.693	19.19
	B4	B41	B42	B43
	B41	1					0.405	10.95
	B42	3	1				1.145	30.90	3.004	0.002
	B43	5	2	1			2.154	58.16
	B5	B51	B52	B53
	B51	1					0.737	16.18
	B52	1/2	1				0.397	8.72	3.006	0.003
	B53	5	8	1			3.42	75.10

对应评语集	网络评价结果			实际评价结果
对应评语集	测试项目1	测试项目2	测试项目3	测试项目1	测试项目2	测试项目3
低	0.212 0	0.138 8	0.134 8	0.223 2	0.151 3	0.080 0
较低	0.348 2	0.186 3	0.125 9	0.398 5	0.203 1	0.179 9
一般	0.270 8	0.309 0	0.210 5	0.292 3	0.311 4	0.185 5
较高	0.131 4	0.243 1	0.129 2	0.065 1	0.184 5	0.207 7
高	0.038 6	0.112 2	0.406 2	0.018 4	0.149 7	0.346 9