基于BP神经网络的农机安全评价敏感性分析

doi:10.13733/j.jcam.issn.2095⁃5553.2022.03.016

摘要/Abstract

摘要： 为减少农业机械运行过程中安全事故发生的概率，提出基于BP神经网络的农机安全评价敏感分析方法，降低农机的安全风险。通过对农机的人—机—环境系统分析，确定各项安全评价指标体系；对农机进行安全等级界定；将指标参数进行样本归一化处理，建立基于BP神经网络的安全评价敏感性映射模型；对BP神经网络数学模型和Tchaban算法进行计算分析，得到农机的安全测试预测值、敏感性系数。研究表明：构建10项二级指标信息的农机安全评价体系；确定BP神经网络结构为“9-10-1”型；农机安全风险值的分布在0.70≤Y<0.85，预测结果与实际情况较符合；Tchaban算法敏感性分析出较大的安全指标的敏感系数依次为维修人员2.42%、电气系统2.28%、作业空间2.05%。为农机产品进行模块化、系统化的方案设计优以及之后产品迭代设计提出设计指导方向。

关键词: 安全评价, 人机环境系统, 农机产品, BP神经网络, 敏感性分析

Abstract: In order to reduce the occurrence of safety accidents in agricultural machinery, a sensitivity analysis method of agricultural machinery safety evaluation based on BP neural network was proposed. Through analysis of the man⁃machine⁃environment system of agricultural machinery, various safety evaluation index systems were determined whereby the safety level of agricultural machinery was defined, the index parameters were sampled and normalized, and the safety evaluation sensitivity mapping model based on BP neural network was established. BP neural network mathematical model and Tchaban algorithm were calculated and analyzed, and the predicted value and sensitivity coefficient of agricultural machinery safety test were obtained. The results showed that an agricultural machinery safety evaluation system with 10 secondary indexes had been constructed. The structure of BP neural network was “9-10-1”. The distribution of the safety risk value of agricultural machinery was 0.70≤Y<0.85, and the prediction results were in good agreement with the actual situation. According to the sensitivity analysis of Tchaban algorithm, the sensitivity coefficients of large safety indicators were 2.42% for maintenance personnel, 2.28% for electrical system, and 2.05% for work space. The presented sensitivity analysis method provides design guidance for modular and systematic scheme design optimization of agricultural machinery products and subsequent product iterative design.

Key words: safety assessment, man?machine environment system, agricultural machinery, BP neural network, sensitivity analysis

中图分类号:

S225.92: S23

罗兵, 张建敏. 基于BP神经网络的农机安全评价敏感性分析[J]. 中国农机化学报, 2022, 43(3): 120-126.

Luo Bing, Zhang Jianmin.. Sensitivity analysis of agricultural machinery safety evaluation based on BP neural network[J]. Journal of Chinese Agricultural Mechanization, 2022, 43(3): 120-126.

参考文献

[1] 张健, 刘小英, 张敬东. 基于集对理论的农业机械安全风险评价研究[J]. 中国农机化学报, 2018, 39(11): 90-93.
Zhnag Jian, Liu Xiaoying, Zhang Jingdong. Research on safety risk evaluation for agricultural machinery based on set pair theory [J]. Journal of Chinese Agricultural Mechanization, 2018, 39(11): 90-93.
[2] 张健, 刘小英, 张敬东, 等. 基于可拓理论的农业机械安全风险评价研究[J]. 中国农机化学报, 2014, 35(2): 57-60, 66.
Zhang Jian, Liu Xiaoying, Zhang Jingdong, et al. Agricultural machinery safety and risk evaluation based on extension method [J]. Journal of Chinese Agricultural Mechanization, 2014, 35(2): 57-60, 66.
[3] 杨欣, 孙萍, 魏津瑜. 农业机械产品安全风险评价方法研究[J]. 中国农机化学报, 2015, 36(4): 320-324.
Yang Xin, Sun Ping, Wei Jinyu. Research on safety risk evaluation method of agricultural machinery products [J]. Journal of Chinese Agricultural Mechanization, 2015, 36(4): 320-324.
[4] 刘宏, 肖建华. 我国农机安全事故分析及预防对策研究[J]. 中国农机化学报, 2012, 32(1): 27-30.
Liu Hong, Xiao Jianhua. Research on analysis and prevention measures of agricultural machinery safety accidents [J]. Chinese Agricultural Mechanization, 2012, 32(1): 27-30.
[5] A S X, B X Z. Application of man⁃machine⁃environment system engineering in coal mines safety management⁃sciencedirect [J]. Procedia Engineering, 2014, 84(2): 87-92.
[6] 张兵, 张建生, 黄文生. 神经网络在柱塞泵故障诊断中的应用[J]. 中国农机化学报, 2015, 36(2): 274-276.
Zhang Bing, Zhang Jiansheng, Huang Wensheng. Study on the neural network application in pump fault diagnosis [J]. Journal of Chinese Agricultural Mechanization, 2015, 36(2): 274-276.
[7] 郝志勇, 刘伟, 夏玮, 等. 基于BP神经网络的吸运风机故障诊断[J]. 工程设计学报, 2012, 19(1): 57-60, 66.
Hao Zhiyong, Liu Wei, Xia Wei, et al. Fault diagnosis of the fan with air suction based on BP neural network [J]. Journal of Engineering Design, 2012, 19(1): 57-60, 66.
[8] 邓铮强. 基于GA-BP神经网络的施工升降机安全评价研究[D]. 西安: 长安大学, 2016.
Deng Zhengqiang. The evaluation for builders hoist safety based on GA-BP neural network [D]. Xi’an: Chang’an University, 2016.
[9] 张芳兰, 杨明朗, 刘卫东. 基于模糊TOPSIS方法的汽车形态设计方案评价[J]. 计算机集成制造系统, 2014, 20(2): 276-283.
Zhang Fanglan, Yang Minglang, Liu Weidong. Evaluation of automobile form design based on fuzzy TOPSIS [J]. Computer Integrated Manufacturing Systems, 2014, 20(2): 276-283.
[10] 李静, 李方义, 周丽蓉, 等. 基于BP神经网络的产品生命周期评价敏感性分析[J]. 计算机集成制造系统, 2016, 22(3): 666-671.
Li Jing, Li Fangyi, Zhou Lirong, et al. Sensitivity analysis for life cycle assessment of product based on back propagation neural network [J]. Computer Integrated Manufacturing Systems, 2016, 22(3): 666-671.
[11] Ryan, S, Hutcheson, et al. Sensitivity measures for use during conceptual design [J]. International journal of design engineering: IJDE, 2012, 5(1): 1-20.
[12] 唐林, 许志沛, 贺田龙, 等. 基于BP神经网络的转动架稳定性灵敏度分析[J]. 工程设计学报, 2018, 25(5): 576-582.
Tang Lin, Xu Zhipei, He Tianlong, et al. Sensitivity analysis of rotation frame stability based on BP neural network [J]. Chinese Journal of Engineering Design, 2018, 25(5): 576-582.
[13] Sivakumar K, Balamurugan C, Ramabalan S. Evolutionary sensitivity⁃based conceptual design and tolerance allocation for mechanical assemblies [J]. International Journal of Advanced Manufacturing Technology, 2010, 48(1-4): 307-324.
[14] 翟国栋. 综采工作面人机环境系统安全研究[D]. 北京: 中国矿业大学, 2011.
Zhai Guodong. Study on safety of the man⁃machine⁃environment system of the fully mechanized coal face [D]. Beijing: China University of Mining and Technology, 2011.
[15] 张健, 徐召珊, 王丽萍. 基于偏联系数的农用车辆安全风险态势评估[J]. 中国农机化学报, 2020, 41(5): 94-99.
Zhang Jian, Xu Zhaoshan, Wang Liping. Agricultural vehicle safety risk situation assessment based on partial connection number [J]. Journal of Chinese Agricultural Mechanization, 2020, 41(5): 94-99.
[16] 秦代成, 马天政, 张义民, 等. 装载机两柱翻车保护装置的可靠性灵敏度分析[J]. 工程设计学报, 2011, 18(5): 337-340.
Qin Daicheng, Ma Tianzheng, Zhang Yimin, et al. Reliability sensitivity analysis of two column ROPS of loader [J]. Journal of Engineering Design, 2011, 18(5): 337-340.
[17] 李少波, 全华风, 胡建军, 等. 基于在线评测数据驱动的产品感性评价方法[J]. 计算机集成制造系统, 2018, 24(3): 752-761.
Li Shaobo, Quan Huafeng, Hu Jianjun, et al. Perceptual evaluation method of products based on online reviews data driven [J]. Computer Integrated Manufacturing Systems, 2018, 24(3): 752-761.
[18] 何涛, 胡洁, 夏鹏, 等. 基于ReliefF算法与遗传算法的肌电信号特征选择[J]. 上海交通大学学报, 2016, 50(2): 204-208.
He Tao, Hu Jie, Xia Peng, et al. Feature selection of Emg signal based on ReliefF algorithm and genetic algorithm [J]. Journal of Shanghai Jiaotong University, 2016, 50(2): 204-208.
[19] 汤宝平, 习建民, 李锋. 基于Elman神经网络的旋转机械故障诊断[J]. 计算机集成制造系统, 2010, 16(10): 2148-2152.
Tang Baoping, Xi Jianmin, Li Feng. Fault diagnosis for rotating machinery based on Elman neural network [J]. Computer Integrated Manufacturing Systems, 2010, 16(10): 2148-2152.
[20] 迟军, 陈廉清, 杨超珍. 基于小波包分析和Elman网络的切削表面粗糙度预测方法[J]. 中国机械工程, 2010, 21(7): 822-826.
Chi Jun, Chen Lianqing, Yang Chaozhen. Research on prediction of cutting surface roughness based on wavelet packet analysis and Elman network [J]. China Mechanical Engineering, 2010, 21(7): 822-826.
[21] 李辉, 郑海起, 杨绍普. 基于EMD和Teager能量算子的轴承故障诊断研究[J]. 振动与冲击, 2008, 27(10): 15-17, 22.
Li Hui, Zheng Haiqi, Yang Shaopu. Bearing fault diagnosis based on EMD and Teager kaiser energy operator [J]. Journal of Vibration and Shock, 2008, 27(10): 15-17, 22.
[22] 陈小明, 洪军, 阎海红, 等. 基于Elman神经网络的振镜扫描系统误差校正技术研究[J]. 西安交通大学学报, 2006, 40(5): 587-590.
Chen Xiaoming, Hong Jun, Yan Haihong, et al. Study on error correction in dual galvanometer scanning system based on Elman recurrent neural network [J]. Journal of Xi'an Jiaotong University, 2006, 40(5): 587-590.
[23] 刘贵立, 张国英. 基于小波包的遗传神经网络故障诊断系统研究[J]. 机械工程学报, 2000, 36(9): 110-112.
Liu Guili, Zhang Guoying. Study on genetic neural network of the fault diagnosis based on wavelet packet [J]. Chinese Journal of Mechanical Engineering, 2000, 36(9): 110-112.
[24] 张琦, 邵立福. 基于Elman神经网络的液压泵故障诊断模型研究[J]. 机床与液压, 2004(10): 274-275, 193.
Zhang Qi, Shao Lifu. Research on hydraulic pump fault diagnosis model based on Elman neural net [J]. Machine Tool & Hydraulics, 2004(10): 274-275, 193.