考虑工人无聊感知的作业车间安全生产调度研究

doi:10.16265/j.cnki.issn1003-3033.2025.12.1724

摘要/Abstract

摘要：

为实现作业车间的安全高效生产,提出一种考虑工人无聊感知的双资源柔性作业车间调度问题(BP-DRFJSP)模型。首先,分析工人重复性作业中所产生的无聊感对工作效率与生产安全事故风险的影响,构建量化该影响的数学模型,并以最大完工时间和生产安全事故风险为优化目标建立调度模型;然后,通过设计多目标足球队训练算法(MO-FTTA)求解该模型;最后,通过MO-FTTA与其他3种常见算法进行对比试验与实例分析,验证该算法的性能与可行性。结果表明:使用MO-FTTA求解BP-DRFJSP模型时,在95%的算例中均能获得更优的超体积(HV)与反转世代距离(IGD),且C值均接近于1,同时,90%算例的目标函数值优于其他对比算法;实例验证中,MO-FTTA将最大完工时间缩短为79.635 min,并使安全生产事故风险降低1.25%,能够在有效提升生产效率的同时降低生产安全事故风险,实现车间的安全高效生产。

关键词: 工人无聊感知(BP), 安全生产调度, 加工效率, 生产安全事故, 双资源柔性作业车间调度(DRFJSP), 多目标足球队训练算法(MO-FTTA)

Abstract:

To achieve safe and efficient work in job shops, this paper proposed a BP-DRFJSP model that considers workers' boredom perception. First, the impact of boredom arising from repetitive tasks on work efficiency and work safety accident risks was analyzed. A mathematical model was developed to quantify this impact, and a scheduling model was established with the optimization objectives of minimizing makespan and production safety risks. Then, a MO-FTTA was designed to solve the model. Finally, comparative experiments and a case study involving MO-FTTA and three other common algorithms were conducted to verify the performance and feasibility of the proposed approach. The results show that when solving BP-DRFJSP model, MO-FTTA achieves better hypervolume (HV) and inverted generational distance (IGD) in 95% of the test instances, with C-metric values close to 1. Moreover, it yields superior objective function values in 90% of the instances compared to other algorithms. In the case study, MO-FTTA reduces the makespan to 79.635 minutes and lowers work safety risk by 1.25%, demonstrating its effectiveness in enhancing production efficiency while mitigating safety risks, thereby supporting safe and efficient workshop operations.

Key words: workers' boredom perception(BP), work safety scheduling, processing efficiency, work safety accidents, dual-resource flexible job shop scheduling (DRFJSP), multi-objective football team training algorithm (MO-FTTA)

中图分类号:

X910安全人体学

郭晨, 吴成森, 李仙乐. 考虑工人无聊感知的作业车间安全生产调度研究[J]. 中国安全科学学报, 2025, 35(12): 8-17.

GUO Chen, WU Chengsen, LI Xianyue. Study on work safety job shop scheduling considering worker boredom perception[J]. China Safety Science Journal, 2025, 35(12): 8-17.

图/表 16

图1

图2

图3

图4

图5

表1

表2

表3

表4

表5

表6

表7

表8

图6

图7

图8

参考文献 20

[1]	钟茂华, 魏玉东, 范维澄, 等. 事故致因理论综述[J]. 火灾科学, 1999, 8(3):36-42.
	ZHONG Maohua, WEI Yudong, FAN Weicheng, et al. Overview on accident-causing theories[J]. Fire Safety Science, 1999, 8(3): 36-42.
[2]	刘全龙, 彭雨蒙, 赵盼, 等. 基于HFACS模型的制造企业机械伤害事故致因分析[J]. 中国安全科学学报, 2023, 33(3):51-59. doi: 10.16265/j.cnki.issn1003-3033.2023.03.1128
	LIU Quanlong, PENG Yumeng, ZHAO Pan, et al. Causal analysis of mechanical injury accidents in manufacturing enterprises based on the HFACS model[J]. China Safety Science Journal, 2023, 33(3): 51-59. doi: 10.16265/j.cnki.issn1003-3033.2023.03.1128
[3]	GAME A M. Workplace boredom coping: health, safety, and HR implications[J]. Personnel Review, 2007, 36(5): 701-721. doi: 10.1108/00483480710774007
[4]	AZIZI N, ZOLFAGHARI S, LIANG Ming. Modeling job rotation in manufacturing systems: the study of employee's boredom and skill variations[J]. International Journal of Production Economics, 2010, 123(1): 69-85. doi: 10.1016/j.ijpe.2009.07.010
[5]	FISHERL C D. Boredom at work: a neglected concept[J]. Human Relations, 1993, 46(3): 395-417. doi: 10.1177/001872679304600305
[6]	CLEARY M, SAYERS J, LOPEZ V, et al. Boredom in the workplace: reasons, impact, and solutions[J]. Issues in Mental Health Nursing, 2016, 37(2): 83-89. doi: 10.3109/01612840.2015.1084554 pmid: 26864838
[7]	AZIZI N. Manufacturing productivity improvement: a study of human boredom, job rotation and scheduling[D]. Ottawa: University of Ottawa, 2009.
[8]	TAN Weihua, YUAN Xiaofang, WANG Jinlei, et al. A fatigue-conscious dual resource constrained flexible job shop scheduling problem by enhanced NSGA-II: an application from casting workshop[J]. Computers & Industrial Engineering, 2021, 160: DOI:10.1016/j.cie.2021.107557.
[9]	SHI Jiaxuan, CHEN Mingzhou, MA Yumin, et al. A new boredom-aware dual-resource constrained flexible job shop scheduling problem using a two-stage multi-objective particle swarm optimization algorithm[J]. Information Sciences, 2023, 643: DOI:10.1016/j.ins.2023.119141.
[10]	YEOW J A, NG P K, TAN K S, et al. Effects of stress, repetition, fatigue and work environment on human error in manufacturing industries[J]. Journal of Applied Sciences, 2014, 14(24): 3464-3471. doi: 10.3923/jas.2014.3464.3471
[11]	张冰鉴, 苏秦, 刘海龙. 基于FTA-BN的云ERP不安全事件的人因失误分析[J]. 中国安全科学学报, 2023, 33(2):38-47. doi: 10.16265/j.cnki.issn1003-3033.2023.02.0412
	ZHANG Bingjian, SU Qin, LIU Hailong. Human error analysis of unsafe events in cloud ERP based on FTA-BN[J]. China Safety Science Journal, 2023, 33(2): 38-47. doi: 10.16265/j.cnki.issn1003-3033.2023.02.0412
[12]	LEVESON N. A new accident model for engineering safer systems[J]. Safety Science, 2004, 42(4): 237-270. doi: 10.1016/S0925-7535(03)00047-X
[13]	TIAN Zhirui, GAI Mei. Football team training algorithm: a novel sport-inspired meta-heuristic optimization algorithm for global optimization[J]. Expert Systems with Applications, 2024,245: DOI:10.1016/j.eswa.2023.123088.
[14]	USMAN S, LU Cong. Job-shop scheduling with limited flexible workers considering ergonomic factors using an improved multi-objective discrete Jaya algorithm[J]. Computers & Operations Research, 2024, 162: DOI:10.1016/j.cor.2023.106456.
[15]	ZHU Nan, GONG Guiliang, LU Dian, et al. An effective reformative memetic algorithm for distributed flexible job-shop scheduling problem with order cancellation[J]. Expert Systems with Applications, 2024, 237: DOI:10.1016/j.eswa.2023.121205.
[16]	MENG Leilei, ZHANG Chaoyong, ZHANG Biao, et al. MILP modeling and optimization of multi-objective flexible job shop scheduling problem with controllable processing times[J]. Swarm and Evolutionary Computation, 2023, 82: DOI:10.1016/j.swevo.2023.101374.
[17]	SHI Shuangyuan, XIONG Hegen. Solving the multi-objective job shop scheduling problems with overtime consideration by an enhanced NSGA-Ⅱ[J]. Computers & Industrial Engineering, 2024, 190: DOI:10.1016/j.cie.2024.110001.
[18]	ZHU Kaikai, GONG Guiliang, PENG Ningtao, et al. Dynamic distributed flexible job-shop scheduling problem considering operation inspection[J]. Expert Systems with Applications, 2023, 224: DOI:10.1016/j.eswa.2023.119840.
[19]	BRANDIMARTE P. Routing and scheduling in a flexible job shop by tabu search[J]. Annals of Operations Research, 1993, 41(3): 157-183. doi: 10.1007/BF02023073
[20]	WU Xiuli, YUAN Qi, WANG Ling. Multiobjective differential evolution algorithm for solving robotic cell scheduling problem with batch-processing machines[J]. IEEE Transactions on Automation Science and Engineering, 2021, 18(2): 757-775. doi: 10.1109/TASE.2020.2969469

参数组合	水平			结果
参数组合	p	I	U	结果
1	1	1	1	0.372 1
2	1	2	2	0.556 0
3	1	3	3	0.743 6
4	2	1	2	0.557 6
5	2	2	3	0.817 2
6	2	3	1	0.646 1
7	3	1	3	0.534 6
8	3	2	1	0.763 2
9	3	3	2	0.628 9
u₁	0.557 2	0.488 1	0.593 8	—
u₂	0.673 6	0.712 1	0.580 8	—
u₃	0.642 2	0.672 8	0.698 5	—

算例	HV				IGD
算例	MO-FTTA	ENSGA-II	MMA	TS-MOPSO	MO-FTTA	ENSGA-II	MMA	TS-MOPSO
D₁	0.962 4	0.475 7	0.637 5	0.813 3	0.071 5	0.414 0	0.211 7	0.236 7
D₂	0.913 8	0.697 5	0.799 6	0.750 8	0.096 4	0.332 6	0.359 7	0.148 1
D₃	0.971 2	0.660 1	0.736 4	0.843 7	0.054 6	0.317 3	0.305 3	0.245 8
D₄	1.222 2	0.845 2	0.862 7	0.858 6	0.193 0	0.713 0	0.447 0	0.309 5
D₅	1.097 2	0.310 8	0.630 2	0.753 6	0.166 7	0.594 9	0.555 3	0.318 6
D₆	1.031 8	0.771 2	0.791 0	0.811 6	0.143 6	0.680 5	0.357 0	0.259 6
D₇	1.310 3	0.516 2	0.797 1	1.056 1	0.051 9	0.580 9	0.539 3	0.475 8
D₈	1.534 0	0.449 8	0.734 5	0.824 0	0.204 4	0.851 5	0.771 7	0.565 2
D₉	1.476 0	0.517 6	0.734 7	0.854 9	0.131 7	0.689 9	0.462 6	0.352 4
D₁₀	2.108 1	0.762 8	1.052 1	1.134 8	0.033 9	0.477 1	0.421 0	0.376 6
K₁	1.393 0	0.565 8	0.962 3	0.944 4	0.183 7	0.878 4	0.342 9	0.350 3
K₂	1.561 9	0.697 8	0.994 7	1.233 3	0.123 8	0.448 6	0.326 4	0.203 3
K₃	1.059 6	0.708 1	0.739 0	0.912 3	0.078 0	0.206 9	0.215 6	0.070 7
K₄	1.969 2	0.739 8	0.731 6	0.998 7	0.099 3	0.562 5	0.376 3	0.150 8
K₅	1.802 5	0.574 9	0.734 6	0.753 9	0.119 1	0.386 7	0.214 4	0.284 4
K₆	2.292 0	0.936 9	0.798 9	0.814 6	0.233 9	0.314 2	0.699 9	0.482 6
K₇	1.079 1	0.746 1	0.770 3	0.820 7	0.358 9	0.563 6	0.528 7	0.463 7
K₈	1.077 0	0.517 7	0.636 9	0.996 2	0.475 7	0.690 9	0.490 1	0.485 3
K₉	1.911 3	0.744 1	0.773 5	0.829 0	0.292 1	0.458 1	0.429 4	0.379 8
K₁₀	1.993 0	1.565 8	0.962 3	1.044 4	0.183 7	0.478 4	0.242 9	0.250 3

算例	C(q₁,q₂)	C(q₂,q₁)	C(q₁,q₃)	C(q₃,q₁)	C(q₁,q₄)	C(q₄,q₁)
D₁	1.000 0	0.000 0	1.000 0	0.038 4	1.000 0	0.135 8
D₂	0.935 4	0.025 7	0.875 4	0.000 0	0.864 9	0.000 0
D₃	0.881 2	0.000 0	0.867 9	0.000 0	0.826 9	0.000 0
D₄	1.000 0	0.000 0	1.000 0	0.034 9	1.000 0	0.000 0
D₅	1.000 0	0.070 6	0.845 2	0.142 3	0.762 0	0.247 5
D₆	0.941 5	0.036 4	0.755 8	0.163 4	0.751 5	0.182 6
D₇	1.000 0	0.073 0	1.000 0	0.025 1	0.896 0	0.093 1
D₈	0.995 2	0.016 1	1.000 0	0.081 6	1.000 0	0.000 0
D₉	1.000 0	0.095 8	0.782 8	0.239 9	0.651 9	0.254 9
D₁₀	1.000 0	0.000 0	1.000 0	0.000 0	1.000 0	0.000 0
K₁	0.994 8	0.045 2	0.930 4	0.043 9	0.834 4	0.154 3
K₂	1.000 0	0.019 4	1.000 0	0.078 4	1.000 0	0.019 6
K₃	0.919 6	0.000 0	0.955 3	0.000 0	0.828 6	0.085 2
K₄	1.000 0	0.000 0	1.000 0	0.020 8	1.000 0	0.000 0
K₅	1.000 0	0.049 1	0.950 0	0.061 6	0.908 6	0.027 3
K₆	0.942 3	0.005 6	1.000 0	0.064 2	0.903 1	0.104 3
K₇	0.968 2	0.000 0	0.937 4	0.052 5	0.909 5	0.044 5
K₈	1.000 0	0.022 1	0.925 1	0.000 0	0.855 9	0.138 9
K₉	1.000 0	0.014 1	1.000 0	0.000 0	1.000 0	0.000 0
K₁₀	1.000 0	0.000 0	0.930 4	0.043 9	0.914 4	0.054 3

算例	MO-FTTA		ENSGA-II		MMA		TS-MOPSO
算例	f₁	f₂/%	f₁	f₂/%	f₁	f₂/%	f₁	f₂/%
D₁	12.158 6	1.91	16.815 3	2.74	15.252 2	2.72	14.232 3	2.68
D₂	15.411 3	2.42	18.067 0	4.79	19.884 7	3.82	17.643 5	3.75
D₃	12.128 5	1.81	16.543 6	2.53	15.659 4	3.36	14.993 6	3.93
D₄	12.116 5	1.83	16.125 9	1.75	14.076 8	2.25	14.043 3	4.06
D₅	11.219 3	0.54	13.801 4	0.89	14.849 5	2.52	12.300	1.71
D₆	13.698 9	3.45	17.868 0	3.47	15.639 9	4.62	16.821 2	3.07
D₇	12.485 7	1.28	16.623 1	3.83	14.523 3	3.77	15.172 1	2.81
D₈	13.279 1	1.66	18.561 3	2.23	15.485 2	2.73	14.264 1	4.92
D₉	12.192 9	1.34	13.835 8	2.69	13.132 5	3.29	14.725 9	1.49
D₁₀	19.047 4	3.38	22.963 2	4.47	22.702 5	4.76	23.363 0	3.85
K₁	50.794 8	2.32	62.330 4	3.40	60.814 4	3.66	62.084 8	4.81
K₂	41.153 6	1.85	54.526 5	2.99	52.311 4	3.49	65.099 6	3.60
K₃	326.419 6	2.51	393.855 3	3.61	402.028 6	2.47	341.113 2	4.62
K₄	87.259 5	2.76	94.986 1	3.60	102.614 1	4.25	101.593 7	3.22
K₅	340.931 3	3.05	397.550 0	3.43	383.908 6	4.25	357.127 8	5.74
K₆	71.742 3	3.68	89.819 0	4.49	83.303 1	4.67	91.123 7	4.14
K₇	261.508 2	2.56	332.407 4	3.41	297.909 5	4.24	289.242 2	3.35
K₈	639.121 1	2.25	697.955 1	3.33	691.655 9	3.48	651.961 8	4.52
K₉	596.725 3	2.53	603.646 8	4.41	649.702 9	3.50	671.352 7	4.92
K₁₀	431.794 8	2.17	512.330 4	3.84	493.814 4	2.63	542.084 8	2.26

结构件	工序	可加工设备	对应加工时间/min	工序类型	工序等级
J₁	O₁₁	M₁/M₃/M₅	20/25/18	3	3
	O₁₂	M₁/M₄/M₅	15/17/14	3	1
	O₁₃	M₂/M₃/M₄	12/13/11	1	3
	O₁₄	M₂/M₄/M₅	12/10/19	2	3
J₂	O₂₁	M₁/M₄/M₅	14/16/13	3	3
	O₂₂	M₂/M₃/M₅	10/11/9	1	3
	O₂₃	M₂/M₃/M₄	18/17/19	4	1
J₃	O₃₁	M₁/M₄/M₅	18/20/17	2	2
	O₃₂	M₁/M₂/M₃	35/40/33	2	2
	O₃₃	M₁/M₃/M₅	25/28/23	3	3
	O₃₄	M₂/M₃/M₅	13/15/12	3	1
	O₃₅	M₁/M₂/M₄	14/12/12	1	1
J₄	O₄₁	M₁/M₄/M₅	14/16/13	1	2
	O₄₂	M₁/M₂/M₃	35/38/34	4	2
	O₄₃	M₃/M₃/M₄	28/30/27	2	2
	O₄₄	M₁/M₃/M₄	18/20/17	3	1
J₅	O₅₁	M₁/M₃/M₅	22/25/20	1	2
	O₅₂	M₁/M₂/M₄	28/30/27	3	2
	O₅₃	M₁/M₄/M₅	15/18/14	4	1
	O₅₄	M₂/M₃/M₄	8/10/9	4	2
J₇	O₇₁	M₁/M₂/M₃	11/12/10	4	3
	O₇₂	M₃/M₄/M₅	18/16/15	1	2
	O₇₃	M₁/M₃/M₄	13/12/11	2	3
J₈	O₈₁	M₁/M₃/M₅	16/14/15	2	1
	O₈₂	M₂/M₃/M₄	21/20/19	1	1
	O₈₃	M₁/M₃/M₅	12/15/13	2	3
	O₈₄	M₂/M₃/M₄	10/12/14	4	1