Evaluation method for hidden safety dangers of hydropower construction based on fuzzy neural network
-
摘要: 水电工程施工过程中存在的安全隐患多且动态变化,是造成水电工程事故多发的主要原因。为评价水电工程施工的安全隐患程度,基于模糊综合评价和BP神经网络建立了水电工程施工安全隐患评价模型,构建了一个具有多层次和多指标特性的水电工程施工安全隐患诊断指标体系,提出了重大、较大、一般、较小以及轻微的5个等级划分。结合实例,对某水电工程施工进行评价,确定其安全隐患等级,并对评价结果进行分析。结果表明:该水电站施工安全隐患等级为3级,符合其实际隐患排查情况。评价提出的模糊神经网络模型可操作性强,能有效分析水电工程施工安全隐患,对于水电工程施工过程的安全隐患排查具有一定参考意义。Abstract: There are many hidden safety dangers and dynamic changes in the construction process of hydropower projects, which is the main reason for the frequent accidents during the construction of hydropower projects. In order to evaluate the degree of the potential safety dangers in the period of construction, an evaluation model for the hidden safety dangers of the hydropower construction is established based on fuzzy comprehensive evaluation and BP neural network. A multi-level with multi-index system for the diagnosis of the hidden dangers during the construction is developed, and five levels, namely major, large, general, small and slight levels, are proposed. Using the example, the hydropower construction is evaluated, the safety hazard level is determined, and the evaluation results are analyzed. The evaluation results of the potential safety dangers show that the hidden safety danger level of the example station is the third level, which conforms to the actual situation of hidden danger investigation. The fuzzy neural network model proposed in this paper has strong operability and can effectively analyze the potential hidden safety dangers during the construction. It has a certain reference value for the investigation of the potential hidden safety dangers in the construction process of hydropower projects.
-
表 1 水电工程施工安全评价指标体系
Table 1. Safety evaluation index system for hydropower construction
目标层 指标层 二级指标层 水电工程施工
安全评价人的因素B1 施工人员的安全文化素质(B11) 职业危害预防(B12) 个人安全防护用品(B13) 施工操作规程(B14) 安全教育及培训(B15) 设备设施B2 脚手架工程(B21) 施工机械设备及特种设备(B22) 施工供电及安全标志(B23) 安全防护设备设施(B24) 设备的状态及养护(B25) 管理因素B3 现场专业安全指导(B31) 安全检查(B32) 安全管理机构及岗位设置(B33) 现场应急救援及安全措施(B34) 安全法规及行业标准执行(B35) 环境因素B4 施工作业环境(B41) 气候条件(B42) 施工通道(B43) 施工现场扬尘及噪声(B44) 高空落物(B45) 地质条件B46) 表 2 1~9标度含义
Table 2. 1~9 Scaling meanings
标度 含义 1 两个因素同等重要 3 两个因素相比,前者更重要 5 两个因素相比,前者明显重要 7 两个因素相比,前者强烈重要 9 两个因素相比,前者极端重要 2,4,6,8 表示上述相邻判断的中间值 倒数 若元素i与元素j的重要性之比为a,那么元素j与元素i重要性之比为1/a 表 3 样本数据
Table 3. Sample data of neural network intput
序号 各组数据 1 2 3 4 5 6 7 8 9 10 B11 0.76 0.76 0.72 0.68 0.64 0.72 0.64 0.72 0.84 0.72 B12 0.64 0.80 0.80 0.84 0.80 0.60 0.68 0.72 0.52 0.56 B13 0.68 0.80 0.84 0.80 0.76 0.60 0.64 0.68 0.72 0.76 B14 0.72 0.68 0.72 0.88 0.72 0.68 0.60 0.60 0.68 0.60 B15 0.88 0.88 0.76 0.72 0.80 0.52 0.80 0.48 0.52 0.64 B21 0.88 0.88 0.88 0.80 0.76 0.68 0.52 0.48 0.76 0.76 B22 0.72 0.72 0.80 0.64 0.88 0.72 0.64 0.76 0.76 0.76 B23 0.80 0.92 0.80 0.72 0.68 0.52 0.56 0.64 0.64 0.68 B24 0.88 0.84 0.76 0.68 0.72 0.68 0.56 0.64 0.56 0.84 B25 0.84 0.72 0.80 0.76 0.68 0.72 0.76 0.80 0.80 0.68 B31 0.60 0.80 0.88 0.72 0.60 0.48 0.44 0.60 0.48 0.56 B32 0.80 0.88 0.76 0.84 0.80 0.68 0.64 0.68 0.68 0.76 B33 0.80 0.84 0.72 0.88 0.72 0.64 0.56 0.72 0.80 0.64 B34 0.72 0.80 0.84 0.76 0.76 0.60 0.64 0.72 0.64 0.76 B35 0.88 0.76 0.80 0.68 0.52 0.60 0.56 0.52 0.56 0.60 B41 0.84 0.88 0.76 0.76 0.84 0.80 0.76 0.72 0.76 0.88 B42 0.72 0.88 0.80 0.88 0.76 0.72 0.64 0.80 0.76 0.80 B43 0.80 0.72 0.76 0.68 0.76 0.88 0.72 0.64 0.80 0.76 B44 0.76 0.76 0.72 0.76 0.60 0.60 0.76 0.60 0.60 0.64 B45 0.88 0.88 0.80 0.76 0.72 0.72 0.80 0.68 0.76 0.68 B46 0.80 0.84 0.76 0.88 0.84 0.80 0.64 0.88 0.72 0.84 表 4 样本期望值
Table 4. Expectation values for sample data
序号 期望值 类型 序号 期望值 类型 训练样本1 (0 1 0 0 0) 较大 训练样本6 (0 0 0 1 0) 较小 训练样本2 (1 0 0 0 0) 重大 训练样本7 (0 0 1 0 0) 一般 训练样本3 (0 0 1 0 0) 一般 训练样本8 (1 0 0 0 0) 重大 训练样本4 (1 0 0 0 0) 重大 检测样本1 (0 0 1 0 0) 一般 训练样本5 (0 1 0 0 0) 较大 检测样本2 (0 0 1 0 0) 一般 表 5 检测数据对比
Table 5. Comparison of testing data
序号 重大 较大 一般 较小 轻微 期望值 类型 1 0.008 8 0.001 2 0.760 0 0.193 2 0 (0 0 1 0 0) 一般 2 0 0.000 4 0.980 6 0.080 2 0 (0 0 1 0 0) 一般 表 6 安全生产隐患统计
Table 6. Statistics of hidden dangers in safety production
次 年(季度) 人的因素 环境因素 管理因素 设备设施因素 2013(1) 4 1 4 6 2013(2) 6 2 7 4 2013(3) 9 4 10 5 2013(4) 7 3 8 5 合计 26 10 29 20 表 7 模糊评判标准
Table 7. Fuzzy evaluation criteria
指标体系 评分标准值 重大 较大 一般 较小 轻微 施工人员安全文化素质B11 2 0 6 4 4 职业危害预防B12 0 1 8 5 2 个人安全防护用品B13 0 4 7 3 2 施工操作规程B14 0 0 6 6 4 安全教育及培训B15 0 0 8 4 4 脚手架工程B21 1 0 10 3 2 施工机械设备及特种设备B22 1 3 7 5 0 施工供电及安全标志B23 0 4 7 5 0 安全防护设备设施B24 2 4 8 2 0 设备的状态及养护B25 1 3 7 5 0 现场的专业安全指导B31 1 3 6 4 2 安全检查B32 0 2 9 5 0 安全管理机构及岗位设置B33 0 0 4 10 2 现场应急救援及安全措施B34 0 0 3 8 5 安全法规及行业标准执行B35 0 0 8 6 2 施工作业环境B41 1 1 7 4 3 气候条件B42 0 0 4 8 4 施工通道B43 0 2 5 5 4 施工现场扬尘及噪声B44 0 3 6 5 2 物体打击B45 2 2 6 6 0 地质条件B46 1 2 7 4 2 表 8 预测数据
Table 8. Forecast data
因素 归一化后 因素 归一化后 因素 归一化后 B11 0.500 0 B23 0.587 5 B35 0.475 0 B12 0.500 0 B24 0.675 0 B41 0.512 5 B13 0.562 5 B25 0.600 0 B42 0.400 0 B14 0.375 0 B31 0.562 5 B43 0.462 5 B15 0.450 0 B32 0.562 5 B44 0.525 0 B21 0.537 5 B33 0.425 0 B45 0.600 0 B22 0.600 0 B34 0.375 0 B46 0.550 0 表 9 模型预测输出
Table 9. Model predictive output
序号 重大 较大 一般 较小 轻微 期望值 类型 1 0.001 8 0.005 0 0.999 4 0.000 6 0 (0 0 1 0 0) 一般 -
[1] 郑丽娟. 水利水电工程施工安全评价与管理系统研究[D]. 保定: 河北农业大学, 2015. ZHENG Lijuan.Water resources and hydropower engineering construction safety evaluation and management system[D]. Baoding: Agricultural University of Hebei Province, 2015. (in Chinese) [2] 邓淑珍. 中国水利发展回顾过去成绩斐然 展望未来任重道远—访国务院研究室农村司司长黄守宏[J]. 中国水利,2005(24):1-3. (DENG Shuzhen. Review of great achievements made in the past and foresee heavy tasks in the future-Huang Shouhong, director-general of Rural Department of Research Office of the State Council[J]. China Water Resources, 2005(24): 1-3. (in Chinese) doi: 10.3969/j.issn.1000-1123.2005.24.001 [3] 王东青, 王立军. 水利水电工程施工安全分析与对策[J]. 中国科技纵横,2014(4):161. (WANG Dongqing, WANG Lijun. Safety analysis and countermeasures for construction of water conservancy and hydropower projects[J]. China Science & Technology Overview, 2014(4): 161. (in Chinese) doi: 10.3969/j.issn.1671-2064.2014.04.108 [4] 谷庆红. 冶金行业安全管理模式探讨[J]. 工业安全与环保,2003,29(7):35-39. (GU Qinghong. A discussion on safety management model of metallurgical trade[J]. Industrial Safety and Environmental Protection, 2003, 29(7): 35-39. (in Chinese) doi: 10.3969/j.issn.1001-425X.2003.07.015 [5] 卢岚, 杨静, 秦嵩. 建筑施工现场安全综合评价研究[J]. 土木工程学报,2003,36(9):46-50, 82. (LU Lan, YANG Jing, QIN Song. A study on the safety assessment on building sites[J]. China Civil Engineering Journal, 2003, 36(9): 46-50, 82. (in Chinese) doi: 10.3321/j.issn:1000-131X.2003.09.008 [6] KEELEY A R, MATSUMOTO K. Relative significance of determinants of foreign direct investment in wind and solar energy in developing countries-AHP analysis[J]. Energy Policy, 2018, 123: 337-348. doi: 10.1016/j.enpol.2018.08.055 [7] 李岱远, 高而坤, 吴永祥, 等. 基于网络层次分析法的节水型社会综合评价[J]. 水利水运工程学报,2017(2):29-37. (LI Daiyuan, GAO Erkun, WU Yongxiang, et al. Comprehensive evaluation of water-saving society based on analytic network process[J]. Hydro-Science and Engineering, 2017(2): 29-37. (in Chinese) [8] 宋占智, 蒋尚明, 金菊良, 等. 蚌埠市农业旱灾脆弱性综合评价[J]. 水利水运工程学报,2017(3):56-63. (SONG Zhanzhi, JIANG Shangming, JIN Juliang, et al. Comprehensive assessment of agricultural drought vulnerability based on improved cloud similarity: a case study of Bengbu city[J]. Hydro-Science and Engineering, 2017(3): 56-63. (in Chinese) [9] 徐镇凯, 温勇兵, 魏博文, 等. 基于组合赋权模糊云理论的高边坡稳定性评价[J]. 水利水运工程学报,2017(1):10-17. (XU Zhenkai, WEN Yongbing, WEI Bowen, et al. Stability evaluation method for high slope based on fuzzy cloud theory combined with weights[J]. Hydro-Science and Engineering, 2017(1): 10-17. (in Chinese) [10] 岳强, 刘福胜, 刘仲秋. 基于模糊层次分析法的平原水库健康综合评价[J]. 水利水运工程学报,2016(2):62-68. (YUE Qiang, LIU Fusheng, LIU Zhongqiu. Comprehensive assessment of plain reservoir health based on fuzzy and hierarchy analyses[J]. Hydro-Science and Engineering, 2016(2): 62-68. (in Chinese) [11] 林琳. 基于BP神经网络的水利工程风险管理研究[D]. 赣州: 江西理工大学, 2015. LIN Lin. Research on risk management of water conservancy project based on BP neural network[D]. Ganzhou: Jiangxi University of Science and Technology, 2015. (in Chinese) [12] 苗姜龙, 陈曦, 吕彦楠, 等. 基于BP神经网络的冻土路基变形预测与可靠度分析[J]. 自然灾害学报,2018,27(4):81-87. (MIAO Jianglong, CHEN Xi, LV Yannan, et al. Prediction on deformation and reliability of subgrade of Qinghai-Tibet Railway based on BP neural network method[J]. Journal of Natural Disasters, 2018, 27(4): 81-87. (in Chinese) [13] KORDANULI B, BARJAKTAROVIĆ L, JEREMIĆ L, et al. Appraisal of artificial neural network for forecasting of economic parameters[J]. Physica A: Statistical Mechanics and its Applications, 2017, 465: 515-519. doi: 10.1016/j.physa.2016.08.062 [14] HAFIZ F, ABDENNOUR A. An adaptive neuro-fuzzy inertia controller for variable-speed wind turbines[J]. Renewable Energy, 2016, 92: 136-146. doi: 10.1016/j.renene.2016.01.100 -