生产过程中人的极限工作时间研究
|
摘要
操作工人在长时间的工作过程中,由于精神和身体的疲劳会产生失误,人的可靠性降低,导致生产残次品,甚至危及人身安全。为了了解在保证可靠性的前提下操作者最长可持续的工作时间(极限工作时间),提出了一种结合统计过程控制图(statistical process control chart,SPCC)和差分自回归移动平均(autoregressive integrated moving average,ARIMA)模型的方法。用连续时间中单位时间间隔内的次品率衡量人的可靠度,并形成次品率时序序列(defective rate time series,DRTS)。一方面使用该数列基于ARIMA构建SPCC,并确定样本的上控制线(up control line,UCL)、下控制线(low control line,LCL)和极限时间范围;另一方面使用ARIMA和支持向量机(support vector machine,SVM)配合实时跟踪算法(realtime tracing algorithm,RTA)对需要确定极限工作时间(limit working time,LWT)的某一操作者的DRTS进行预测。最后将预测曲线置于SPCC中来确定该操作者LWT的范围。通过对10个操作者8 h,每隔10 min采样得到的DRTS分析,表明该类工作参数的范围为UCL=[3. 89,4. 66]、LCL=[-4. 98,-3. 90]、LWT=[393,450] min,确定了一个新操作者的LWT为[435,452] min,即435 min时该操作者就应该停止工作进行休息。
In the process of long work hours,operators can produce errors due to mental and physical exhaustion,human reliability is reduced,and it leads to production of incomplete and even endangers humanal safety. In order to understand operator's longest sustainable working time on the premise of given reliability,this paper put forward a method of combining SPCC and ARIMA. With unit time interval defect rate in the continuous time to measure the reliability of human,and it formed a defective rate time series. On the one hand,it built the SPCC using DRTS based on ARIMA to determine the sample of UCL,LCL and LWT range. On the other hand,it predicted the DRTS of an operator using ARIMA and SVM with RTA. Finally this method put the prediction curve into the SPCC to determine the LWT range. Based on 8 hours,10 operators DRTS analysis of sampling for every 10 minutes,the results indicate that the scope of this kind of working parameters for the UCL =[3. 89,4. 66],LCL =[-4. 98,-3. 90],LWT =[393,450]. It identifies a new operator LWT is[435,452]minutes,435 minutes when the operator sill stop working to have a rest.
In the process of long work hours,operators can produce errors due to mental and physical exhaustion,human reliability is reduced,and it leads to production of incomplete and even endangers humanal safety. In order to understand operator's longest sustainable working time on the premise of given reliability,this paper put forward a method of combining SPCC and ARIMA. With unit time interval defect rate in the continuous time to measure the reliability of human,and it formed a defective rate time series. On the one hand,it built the SPCC using DRTS based on ARIMA to determine the sample of UCL,LCL and LWT range. On the other hand,it predicted the DRTS of an operator using ARIMA and SVM with RTA. Finally this method put the prediction curve into the SPCC to determine the LWT range. Based on 8 hours,10 operators DRTS analysis of sampling for every 10 minutes,the results indicate that the scope of this kind of working parameters for the UCL =[3. 89,4. 66],LCL =[-4. 98,-3. 90],LWT =[393,450]. It identifies a new operator LWT is[435,452]minutes,435 minutes when the operator sill stop working to have a rest.
引文
[1]柴松,余建星,马维林,等.基于CREAM和不确定推理的人因可靠性分析方法[J].天津大学学报:自然与工程技术版,2012,45(11):958-962.(Chai Song,Yu Jianxing,Ma Weilin,et al. A human reliability analysis method based on CREAM and uncertain reasoning[J]. Journal of Tianjin University:Science and Technology,2012,45(11):958-962.)
[2]柴松,余建星,杜尊峰,等.海洋工程人因可靠性定量分析方法与应用[J].天津大学学报:自然与工程技术版,2011,44(10):914-919.(Chai Song,Yu Jianxing,Du Zunfeng,et al. Quantitative human reliability analysis methods and application of offshore engineering[J]. Journal of Tianjin University:Science and Technology,2011,44(10):914-919.)
[3]董学军,陈英武.基于补偿和不可替代因素合成的人因可靠性分析方法[J].系统工程理论与实践,2012,32(9):2087-2096.(Dong Xuejun,Chen Yingwu. Method of human reliability analysis based on CSICF[J]. Systems Engineering—Theory&Practice,2012,32(9):2087-2096.)
[4]蒋建军,张力,王以群,等.基于隐马尔可夫的核电厂半数字化人—机界面事故诊断过程人因可靠性模型[J].核动力工程,2012,33(5):79-82.(Jiang Jianjun,Zhang Li,Wang Yiqun,et al.Human factors reliability model of half-digital human-machine interface during diagnosing process based on hide Markov in nuclear power plants[J]. Nuclear Power Engineering,2012,33(5):79-82.)
[5]蒋建军,张力,王以群,等.考虑人因的核电厂主控室认知可靠性模型研究[J].核动力工程,2012,33(1):66-72.(Jiang Jianjun,Zhang Li,Wang Yiqun,et al. Research on cognitive reliability model for main control room considering human factors in nuclear power plants[J]. Nuclear Power Engineering,2012,33(1):66-72.)
[6]倪蓉.煤矿职工疲劳度相关因素分析与控制研究[J].煤矿安全,2013,44(10):230-233.(Ni Rong. Fatigue related factors analysis and control study for coal mine workers[J]. Safety in Coal Mines,2013,44(10):230-233.)
[7] Hu Xinyao,Qu Xingda. An individual-specific fall detection model based on the statistical process control chart[J]. Safety Science,2014,64(4):13-21.
[8]秦摇鹏,苏怀智,沈跃军.基于ARIMA-RTA组合模型的海堤工程沉降预测[J].水利水运工程学报,2013(5):66-70.(Qin Yaopeng,Su Huaizhi,Shen Yuejun. Prediction of seawall settlement based on ARIMA-RTA model[J]. Hydro-Science and Engineering,2013(5):66-70.)
[9]黄彬彬,谷波,任能.基于ARIMA-SVM模型的翅片管蒸发器结霜性能预测[J].上海交通大学学报,2009,43(10):1622-1631.(Huang Binbin,Gu Bo,Ren Neng. Frosting performance prediction of finned tube evaporator based on ARIMA-SVM model[J]. Journal of Shanghai Jiaotong University,2009,43(10):1622-1631.)
[10]崔铁军,马云东.基于泛函网络的周期来压预测方法研究[J].计算机科学,2013,40(6A):242-246.(Cui Tiejun,Ma Yundong.Prediction of periodic weighting based on optimized functional networks[J]. Computer Science,2013,40(6A):242-246.)
[11]Cui Tiejun,Li Shasha. Study on the relationship between system reliability and influencing factors under big data and multi-factors[EB/OL]. https://doi. org/10. 1007/s10586-017-1278-5.
[12]Li Shasha,Cui Tiejun,Li Xingsen,et al. Construction of cloud space fault tree and its application of fault data uncertainty analysis[C]//Proc of International Conference on Machine Learning and Cybernetics. Piscataway,NJ:IEEE Press,2017:195-201.
[13]Li Shasha,Cui Tiejun,Liu Jian. Study on the construction and application of cloudization space fault tree[EB/OL]. https://doi. org/10.1007/s10586-017-1398-y.
[14]崔铁军,马云东.多维空间故障树构建及应用研究[J].中国安全科学学报,2013,23(4):32-37.(Cui Tiejun,Ma Yundong. Research on construction and application of multidimensional spatial fault tree[J]. China Safety Science Journal,2013,23(4):32-37.)
[15]Alwan L C,Roberts H V. Time-series modeling for statistical process control[J]. Journal of Business and Economic Statistics,1988,6(1):87-95.
[16] Haridy S,Wu Zhang. Univariate and multivariate control charts for monitoring dynamic-behavior processes:a case study[J]. Journal of Industrial Engineering and Management,2009,2(3):464-498.
[17]Mohammed M A,Worthington P,Woodall W H. Plotting basic control charts:tutorial notes for healthcare practitioners[J]. Quality and Safety in Healthcare,2009,17(2):137-145.
[18]Box G E P,Jenkins G M. Time series analysis:forecasting and control[M]. 5th ed. Hoboken:Wiley,2015.
[19]Montgomery D C,Jennings C L,Kulahci M. Introduction to time series analysis and forecasting[M]. 2nd ed. Hoboken:Wiley,2015.
[20]何林,欧进萍.基于ARMAX模型及MA参数修正的框架结构动态参数识别[J].振动工程学报,2002,15(1):47-51.(He Lin,Ou Jinping. Dynamic parameter identification of steel frame structure based on ARMAX model and MA parameter updating[J]. Journal of Vibration Engineering,2002,15(1):47-51.)
[21] Nau R. Introduction to ARIMA:non-seasonal models[EB/OL].(2014-11-29). https://people. duke. edu/~rnau/Slides_on_ARIMA_models-Robert_Nau. pdf.
[22] Shewhart W A. Economic control of quality of manufactured product[M]. New York:D. Van Nostrand Company Inc,1931.
[23]Montgomery D C. Introduction to statistical quality control[M]. 6th ed. Hoboken:Wiley,2009.
[2]柴松,余建星,杜尊峰,等.海洋工程人因可靠性定量分析方法与应用[J].天津大学学报:自然与工程技术版,2011,44(10):914-919.(Chai Song,Yu Jianxing,Du Zunfeng,et al. Quantitative human reliability analysis methods and application of offshore engineering[J]. Journal of Tianjin University:Science and Technology,2011,44(10):914-919.)
[3]董学军,陈英武.基于补偿和不可替代因素合成的人因可靠性分析方法[J].系统工程理论与实践,2012,32(9):2087-2096.(Dong Xuejun,Chen Yingwu. Method of human reliability analysis based on CSICF[J]. Systems Engineering—Theory&Practice,2012,32(9):2087-2096.)
[4]蒋建军,张力,王以群,等.基于隐马尔可夫的核电厂半数字化人—机界面事故诊断过程人因可靠性模型[J].核动力工程,2012,33(5):79-82.(Jiang Jianjun,Zhang Li,Wang Yiqun,et al.Human factors reliability model of half-digital human-machine interface during diagnosing process based on hide Markov in nuclear power plants[J]. Nuclear Power Engineering,2012,33(5):79-82.)
[5]蒋建军,张力,王以群,等.考虑人因的核电厂主控室认知可靠性模型研究[J].核动力工程,2012,33(1):66-72.(Jiang Jianjun,Zhang Li,Wang Yiqun,et al. Research on cognitive reliability model for main control room considering human factors in nuclear power plants[J]. Nuclear Power Engineering,2012,33(1):66-72.)
[6]倪蓉.煤矿职工疲劳度相关因素分析与控制研究[J].煤矿安全,2013,44(10):230-233.(Ni Rong. Fatigue related factors analysis and control study for coal mine workers[J]. Safety in Coal Mines,2013,44(10):230-233.)
[7] Hu Xinyao,Qu Xingda. An individual-specific fall detection model based on the statistical process control chart[J]. Safety Science,2014,64(4):13-21.
[8]秦摇鹏,苏怀智,沈跃军.基于ARIMA-RTA组合模型的海堤工程沉降预测[J].水利水运工程学报,2013(5):66-70.(Qin Yaopeng,Su Huaizhi,Shen Yuejun. Prediction of seawall settlement based on ARIMA-RTA model[J]. Hydro-Science and Engineering,2013(5):66-70.)
[9]黄彬彬,谷波,任能.基于ARIMA-SVM模型的翅片管蒸发器结霜性能预测[J].上海交通大学学报,2009,43(10):1622-1631.(Huang Binbin,Gu Bo,Ren Neng. Frosting performance prediction of finned tube evaporator based on ARIMA-SVM model[J]. Journal of Shanghai Jiaotong University,2009,43(10):1622-1631.)
[10]崔铁军,马云东.基于泛函网络的周期来压预测方法研究[J].计算机科学,2013,40(6A):242-246.(Cui Tiejun,Ma Yundong.Prediction of periodic weighting based on optimized functional networks[J]. Computer Science,2013,40(6A):242-246.)
[11]Cui Tiejun,Li Shasha. Study on the relationship between system reliability and influencing factors under big data and multi-factors[EB/OL]. https://doi. org/10. 1007/s10586-017-1278-5.
[12]Li Shasha,Cui Tiejun,Li Xingsen,et al. Construction of cloud space fault tree and its application of fault data uncertainty analysis[C]//Proc of International Conference on Machine Learning and Cybernetics. Piscataway,NJ:IEEE Press,2017:195-201.
[13]Li Shasha,Cui Tiejun,Liu Jian. Study on the construction and application of cloudization space fault tree[EB/OL]. https://doi. org/10.1007/s10586-017-1398-y.
[14]崔铁军,马云东.多维空间故障树构建及应用研究[J].中国安全科学学报,2013,23(4):32-37.(Cui Tiejun,Ma Yundong. Research on construction and application of multidimensional spatial fault tree[J]. China Safety Science Journal,2013,23(4):32-37.)
[15]Alwan L C,Roberts H V. Time-series modeling for statistical process control[J]. Journal of Business and Economic Statistics,1988,6(1):87-95.
[16] Haridy S,Wu Zhang. Univariate and multivariate control charts for monitoring dynamic-behavior processes:a case study[J]. Journal of Industrial Engineering and Management,2009,2(3):464-498.
[17]Mohammed M A,Worthington P,Woodall W H. Plotting basic control charts:tutorial notes for healthcare practitioners[J]. Quality and Safety in Healthcare,2009,17(2):137-145.
[18]Box G E P,Jenkins G M. Time series analysis:forecasting and control[M]. 5th ed. Hoboken:Wiley,2015.
[19]Montgomery D C,Jennings C L,Kulahci M. Introduction to time series analysis and forecasting[M]. 2nd ed. Hoboken:Wiley,2015.
[20]何林,欧进萍.基于ARMAX模型及MA参数修正的框架结构动态参数识别[J].振动工程学报,2002,15(1):47-51.(He Lin,Ou Jinping. Dynamic parameter identification of steel frame structure based on ARMAX model and MA parameter updating[J]. Journal of Vibration Engineering,2002,15(1):47-51.)
[21] Nau R. Introduction to ARIMA:non-seasonal models[EB/OL].(2014-11-29). https://people. duke. edu/~rnau/Slides_on_ARIMA_models-Robert_Nau. pdf.
[22] Shewhart W A. Economic control of quality of manufactured product[M]. New York:D. Van Nostrand Company Inc,1931.
[23]Montgomery D C. Introduction to statistical quality control[M]. 6th ed. Hoboken:Wiley,2009.