Safety-civilized measure cost prediction precision study on construction project

doi:10.16265/j.cnki.issn1003-3033.2023.08.0829

Abstract

Abstract:

In order to precisely measure the safety-civilized measure cost of construction projects, the CBR-MIC-RF prediction model method was suggested. 12 influencing parameters of safety and civilization construction cost were chosen as candidate feature variables using the sample data of 61 typical projects collected through a field study. CBR technique was used to retrieve sample similarities in order to build the training sample set for the model. MIC was used to determine the input feature variables of the main model. On this foundation, three Random Forest models (RF, MIC-RF, and CBR-MIC-RF) were merged, and empirical data was used to analyse their prediction precision. The results show that sample similarity search and identification of key feature variables can significantly improve the prediction precision of RF models (mean absolute percentage error(MAPE) is 3.35%). The model prediction precision varies with the similarity thresholds of different levels, and setting the appropriate similarity thresholds is crucial to improving the prediction effectiveness of the models. The CBR-MIC-RF model can achieve a better prediction performance than the support vector machine model.

Key words: construction project, safety-civilized measure cost, prediction precision, case-based reasoning (CBR), maximum information coefficient (MIC), random forest (RF)

WU Fanghao, CHEN Wei, SUN Huizhong, NIU Li, FU Jianhua. Safety-civilized measure cost prediction precision study on construction project[J]. China Safety Science Journal, 2023, 33(8): 51-58.

Figures/Tables 7

Tab.1

Tab.2

Fig.1

Fig.2

Tab.3

Performance of RF with three input variables

代号	实际值/ 万元	RF		MIC-RF		CBR-MIC-RF
代号	实际值/ 万元	预测值/万元	相对误差/%	预测值/万元	相对误差/%	预测值/万元	相对误差/%
P₁	2 532	2 507	0.98	2 488	1.76	2 485	1.85
P₂	687	732	6.58	742	8.08	704	2.53
P₃	2 101	2 533	20.60	2 260	7.61	2 101	0.00
P₄	414	404	2.22	432	4.39	415	0.35
P₅	2 162	2 057	4.86	1 955	9.56	2 011	6.98
P₆	408	428	4.89	405	0.75	377	7.62
P₇	255	337	32.01	286	12.20	258	0.94
P₈	568	655	15.39	560	1.36	603	6.15
P₉	902	820	9.05	898	0.41	896	0.71
P₁₀	1 953	1 718	12.05	1 997	2.26	2 083	6.63
P₁₁	807	835	3.49	915	13.33	829	2.72
P₁₂	794	803	1.16	894	12.54	824	3.71
MAPE/%		9.44		6.19		3.35
P_max/%		20.60		13.33		7.62
$P p < 5 %$		50%		50%		75%

Tab.3

Fig.3

Fig.4

References 18

[1]	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. doi: 10.16265/j.cnki.issn1003-3033.2022.10.1932
	ZHENG Wenbo. Main achievements of construction engineering safety management: review of safety accidents, safety management system, and relevant literature[J]. China Safety Science Journal, 2022, 32(10):8-17. doi: 10.16265/j.cnki.issn1003-3033.2022.10.1932
[2]	李秀云, 杨高升, 李杰. 最优安全文明施工措施费费率计取模型的构建与应用[J]. 中国安全生产科学技术, 2013, 9(10):147-151.
	LI Xiuyun, YANG Gaosheng, LI Jie. Establishment and application of accrual model about optimal safe and civilized construction measures fee rate[J]. Journal of Safety Science and Technology, 2023, 9(10):174-151.
[3]	GURCANLI G E, BILIR S, SEVIM M. Activity based risk assessment and safety cost estimation for residential building construction projects[J]. Safety Science, 2015, 80: 1-12. doi: 10.1016/j.ssci.2015.07.002
[4]	BELAY A M, TORP O, THODESEN C, et al. A framework for organizing a resilient cost benefit analysis for construction projects[J]. Procedia Engineering, 2016, 145: 1169-1176. doi: 10.1016/j.proeng.2016.04.151
[5]	LEE J, JEONG J, SOH J, et al. Quantitative analysis of the accident prevention costs in Korean construction projects[J]. Buildings, 2022, 12(10): DOI:10.3390/BUILDINGS12101536.
[6]	KETABI A B, HERAVI G. Developing a framework for evaluating construction project safety levels and optimal cost allocation to safety influential factors[J]. Engineering, Construction and Architectural Management, 2022, 29(2): 643-668. doi: 10.1108/ECAM-07-2020-0536
[7]	陈伟, 周曼, 叶家军, 等. 建筑工程安全施工费费率测算的PSO-BP模型研究[J]. 中国安全科学学报, 2016, 26(5):146-151.
	CHEN Wei, ZHOU Man, YE Jiajun, et al. PSO-BP modeling research on fee rate measurement of construction project safe construction cost[J]. China Safety Science Journal, 2016, 26(5):146-151.
[8]	陈伟, 杨主张, 容思思, 等. 地铁安全文明施工费费率标准动态测算研究[J]. 中国安全科学学报, 2018, 28(4):145-150. doi: 10.16265/j.cnki.issn1003-3033.2018.04.025
	CHEN Wei, YANG Zhuzhang, RONG Sisi, et al. Dynamic calculation method of safety-civilized measure cost rate of subway project[J]. China Safety Science Journal, 2018, 28(4):145-150. doi: 10.16265/j.cnki.issn1003-3033.2018.04.025
[9]	张舒, 代涵, 史秀志, 等. 基于PSO-RF的建筑安全文明施工费费率预测[J]. 安全与环境学报, 2022, 22(2):844-850.
	ZHANG Shu, DAI Han, SHI Xiuzhi, et al. Prediction of fee rate for safety-civilized construction cost based on PSO-RF model[J]. Journal of Safety and Environment, 2022, 22(2):844-850.
[10]	杨文臣, 周燕宁, 田毕江, 等. 基于聚类分析和SVM的二级公路交通事故严重度预测[J]. 中国安全科学学报, 2022, 32(5):163-169. doi: 10.16265/j.cnki.issn1003-3033.2022.05.1263
	YANG Wenchen, ZHOU Yanning, TIAN Bijiang, et al. Traffic accident severity prediction for secondary highways based on cluster analysis and SVM model[J]. China Safety Science Journal, 2022, 32(5):163-169. doi: 10.16265/j.cnki.issn1003-3033.2022.05.1263
[11]	KARABADJI N E I, KORBA A A, ASSI A, et al. Accuracy and diversity-aware multi-objective approach for random forest construction[J]. Expert Systems with Applications, 2023,225: DOI:10.1016/J.ESWA.2023.120138.
[12]	赖成光, 陈晓宏, 赵仕威, 等. 基于随机森林的洪灾风险评价模型及其应用[J]. 水利学报, 2015, 46(1):58-66.
	LAI Chengguang, CHEN Xiaohong, ZHAO Shiwei, et al. A flood risk assessment model based on random forest and its application[J]. Journal of Hydraulic Engineering, 2015, 46(1):58-66.
[13]	SPEISER J L, MILLER M E, TOOZE J, et al. A comparison of random forest variable selection methods for classification prediction modeling[J]. Expert Systems with Applications, 2019, 134: 93-101. doi: 10.1016/j.eswa.2019.05.028 pmid: 32968335
[14]	XIAO Xue, SKITMORE M, YAO Weixin, et al. Improving robustness of case-based reasoning for early-stage construction cost estimation[J]. Automation in Construction, 2023, 151:DOI:10.1016/j.autcon.2023.104777.
[15]	RESHEF D N, RESHEF Y A, FINUCANE H K, et al. Detecting novel associations in large data sets[J]. Science, 2011, 334(6062): 1518-1524. doi: 10.1126/science.1205438 pmid: 22174245
[16]	罗为检. 应用最大信息系数和支持向量机估测森林蓄积量[J]. 东北林业大学学报, 2022, 50(1):40-45.
	LUO Weijian. Forest volume estimation using maximum information coefficient and support vector machine[J]. Journal of Northeast Forestry University, 2022, 50(1):40-45.
[17]	BREIMAN L. Random forests[J]. Machine Learning, 2001, 45: 5-32. doi: 10.1023/A:1010933404324
[18]	温博文, 董文瀚, 解武杰, 等. 基于改进网格搜索算法的随机森林参数优化[J]. 计算机工程与应用, 2018, 54(10):154-157. doi: 10.3778/j.issn.1002-8331.1612-0328
	WEN Bowen, DONG Wenhan, XIE Wujie, et al. Parameter optimization method for random forest based on improved grid search algorithm[J]. Computer Engineering and Applications, 2018, 54(10):154-157. doi: 10.3778/j.issn.1002-8331.1612-0328

代号	变量名称	量化方式
Y	安全文明施工费/万元	数值型
x₁	建筑类型	1-居住建筑,2-公共建筑,3-工业建筑
x₂	结构类型	1-框架结构,2-框剪结构,3-剪力墙结构
x₃	占地面积/m²	数值型
x₄	建筑面积/m²	数值型
x₅	建筑檐高/m	数值型
x₆	工程地段	1-中心城区临街,2-中心城区非临街,3-远城区
x₇	工期/d	数值型
x₈	合同造价/万元	数值型
x₉	单方造价/(元·m^-2)	数值型
x₁₀	合同人工费/万元	数值型
x₁₁	合同机械费/万元	数值型
x₁₂	安全文明施工评定等级	1-样板,2-优秀, 3-合格,4-不合格

代号	x₁	x₂	x₃	x₄	x₅	x₆	x₇	x₈	x₉	x₁₀	x₁₁	x₁₂	Y
P₁	2	1	144 000	164 000	11	1	330	125 166	3 439	12 133	13 780	1	2 532
P₂	1	3	46 557	119 048	32	2	905	20 172	1 695	4 975	1 227	2	687
P₃	3	2	42 682	177 900	27	3	970	75 763	2 726	26 143	1 711	1	2 101
P₄	3	2	27 680	71 160	30	2	870	13 198	1 877	3 426	424	2	414
P₅	2	2	49 054	155 500	51	1	492	85 390	3 342	11 726	1 620	3	2 162
P₆	3	1	50 301	50 367	24	2	450	12 752	2 532	2 055	582	2	408
P₇	2	3	20 990	22 767	81	1	540	9 510	4 177	1 912	326	3	255
P₈	2	1	100 994	87 560	10	3	580	17 615	2 516	2 317	2 451	1	568
P₉	1	3	72 961	141 300	132	2	1 200	28 734	2 034	6 271	801	2	902
P₁₀	1	3	109 967	326 000	96	2	589	62 384	1 914	13 727	1 471	1	1 953
P₁₁	1	3	62 000	240 200	96	1	545	26 685	1 111	5 871	534	2	807
P₁₂	1	2	53 102	146 500	54	3	1 100	25 291	1 726	6 076	475	2	794