Optimization and Simulation of Adaptive Production Scheduling Based on Hybrid Decision-making Mechanism

doi:10.16182/j.issn1004731x.joss.25-0452

Abstract

Abstract:

To optimize flexible production scheduling with the objectives of the longest makespan, mean tardiness, and bottleneck machine processing load rate, a hybrid decision-making mechanism scheduling algorithm was proposed based on the decision complexity and constraint characteristics of machine assignment and task sequencing. The algorithm adopted a two-dimensional chromosome to encode machine assignment and a heuristic rule to evaluate task sequencing priority, enhancing the adaptability of the method to decision-making optimization. In order to further improve the performance of the proposed scheduling method, an adaptive rule strategy was designed based on the distribution of processing time required for waiting scheduling tasks to achieve dynamic adaptability of the decision-making to scheduling scenarios, thereby improving the comprehensive advantage level of global optimization. Experimental tests show that the proposed method helps to improve the optimization efficiency of scheduling and provides non-dominated solution sets occupying higher dominant positions.

Key words: flexible production scheduling, hybrid decision-making mechanism, adaptive rule strategy, evolutionary algorithm, genetic programming hyper-heuristics

CLC Number:

TP18

Ji Zhicheng, Quan Zhen, Wang Yan. Optimization and Simulation of Adaptive Production Scheduling Based on Hybrid Decision-making Mechanism[J]. Journal of System Simulation, 2025, 37(7): 1791-1803.

Figures/Tables 12

Table 1

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Table 2

HV metric results of scheduling solution sets

实例	规模	$μ i$ 值区间	HDMSA-AR	HDMSA-DR1	HDMSA-DR2	NSGA-II	MOEA/D
MK01	$10 × 6$	$[1.0,2.5]$	0.67(0.01)	0.50(0.01)( $-$ )	0.56(0.05)( $-$ )	0.68(0.01)( $+$ )	0.69(0.01)( $+$ )
MK02	$10 × 6$	$[1.0,2.5]$	0.66(0.02)	0.48(0.02)( $-$ )	0.56(0.05)( $-$ )	0.64(0.01)( $≈$ )	0.65(0.02)( $≈$ )
MK03	$15 × 8$	$[1.0,2.5]$	0.67(0.01)	0.43(0.01)( $-$ )	0.26(0.04)( $-$ )	0.56(0.01)( $-$ )	0.60(0.01)( $-$ )
MK04	$15 × 8$	$[1.0,2.5]$	0.66(0.01)	0.50(0.01)( $-$ )	0.36(0.07)( $-$ )	0.61(0.01)( $-$ )	0.65(0.02)( $≈$ )
MK05	$15 × 4$	$[1.0,5.0]$	0.58(0.01)	0.27(0.01)( $-$ )	0.24(0.02)( $-$ )	0.45(0.02)( $-$ )	0.51(0.01)( $-$ )
MK06	$10 × 10$	$[1.0,3.0]$	0.68(0.02)	0.50(0.04)( $-$ )	0.53(0.06)( $-$ )	0.63(0.02)( $-$ )	0.63(0.02)( $-$ )
MK07	$20 × 5$	$[1.5,3.0]$	0.56(0.02)	0.35(0.01)( $-$ )	0.34(0.02)( $-$ )	0.52(0.01)( $-$ )	0.54(0.01)( $-$ )
MK08	$20 × 10$	$[1.5,3.0]$	0.50(0.01)	0.26(0.01)( $-$ )	0.14(0.01)( $-$ )	0.46(0.01)( $-$ )	0.52(0.01)( $≈$ )
MK09	$20 × 10$	$[1.0,4.0]$	0.65(0.01)	0.34(0.04)( $-$ )	0.17(0.02)( $-$ )	0.52(0.01)( $-$ )	0.55(0.02)( $-$ )
MK10	$20 × 15$	$[1.0,3.0]$	0.61(0.01)	0.38(0.03)( $-$ )	0.10(0.01)( $-$ )	0.53(0.01)( $-$ )	0.56(0.02)( $-$ )
MK11	$30 × 5$	$[1.0,8.0]$	0.47(0.01)	0.20(0.02)( $-$ )	0.13(0.02)( $-$ )	0.43(0.01)( $-$ )	0.47(0.01)( $≈$ )
MK12	$30 × 10$	$[1.5,4.0]$	0.55(0.01)	0.26(0.01)( $-$ )	0.20(0.02)( $-$ )	0.51(0.01)( $-$ )	0.56(0.01)( $≈$ )
MK13	$30 × 10$	$[1.0,5.0]$	0.62(0.01)	0.33(0.02)( $-$ )	0.18(0.02)( $-$ )	0.53(0.01)( $-$ )	0.57(0.01)( $-$ )
MK14	$30 × 15$	$[1.0,5.0]$	0.56(0.01)	0.21(0.03)( $-$ )	0.18(0.03)( $-$ )	0.46(0.01)( $-$ )	0.52(0.02)( $-$ )
MK15	$30 × 15$	$[1.0,4.0]$	0.66(0.01)	0.34(0.03)( $-$ )	0.14(0.02)( $-$ )	0.57(0.02)( $-$ )	0.61(0.01)( $-$ )

Table 2

Table 3

MID metric results of scheduling solution sets

实例	规模	$μ i$ 值区间	HDMSA-AR	HDMSA-DR1	HDMSA-DR2	NSGA-II	MOEA/D
MK01	$10 × 6$	$[1.0,2.5]$	0.50(0.01)	0.69(0.01)( $+$ )	0.81(0.03)( $+$ )	0.57(0.02)( $+$ )	0.64(0.02)( $+$ )
MK02	$10 × 6$	$[1.0,2.5]$	0.52(0.02)	0.73(0.02)( $+$ )	0.81(0.07)( $+$ )	0.58(0.02)( $+$ )	0.65(0.04)( $+$ )
MK03	$15 × 8$	$[1.0,2.5]$	0.49(0.01)	0.75(0.01)( $+$ )	1.04(0.01)( $+$ )	0.60(0.01)( $+$ )	0.58(0.01)( $+$ )
MK04	$15 × 8$	$[1.0,2.5]$	0.50(0.03)	0.69(0.03)( $+$ )	0.93(0.05)( $+$ )	0.57(0.03)( $+$ )	0.60(0.03)( $+$ )
MK05	$15 × 4$	$[1.0,5.0]$	0.57(0.01)	0.86(0.01)( $+$ )	1.03(0.02)( $+$ )	0.74(0.01)( $+$ )	0.75(0.01)( $+$ )
MK06	$10 × 10$	$[1.0,3.0]$	0.49(0.02)	0.69(0.05)( $+$ )	0.83(0.03)( $+$ )	0.52(0.02)( $+$ )	0.60(0.01)( $+$ )
MK07	$20 × 5$	$[1.5,3.0]$	0.61(0.01)	0.81(0.01)( $+$ )	1.00(0.05)( $+$ )	0.67(0.01)( $+$ )	0.77(0.04)( $+$ )
MK08	$20 × 10$	$[1.5,3.0]$	0.64(0.01)	0.86(0.01)( $+$ )	1.14(0.01)( $+$ )	0.69(0.01)( $+$ )	0.67(0.01)( $+$ )
MK09	$20 × 10$	$[1.0,4.0]$	0.45(0.01)	0.80(0.03)( $+$ )	1.13(0.01)( $+$ )	0.57(0.02)( $+$ )	0.61(0.02)( $+$ )
MK10	$20 × 15$	$[1.0,3.0]$	0.44(0.01)	0.79(0.02)( $+$ )	1.15(0.03)( $+$ )	0.56(0.02)( $+$ )	0.58(0.03)( $+$ )
MK11	$30 × 5$	$[1.0,8.0]$	0.66(0.01)	0.90(0.01)( $+$ )	1.13(0.04)( $+$ )	0.72(0.01)( $+$ )	0.73(0.01)( $+$ )
MK12	$30 × 10$	$[1.5,4.0]$	0.56(0.01)	0.85(0.01)( $+$ )	1.07(0.02)( $+$ )	0.65(0.01)( $+$ )	0.64(0.01)( $+$ )
MK13	$30 × 10$	$[1.0,5.0]$	0.48(0.01)	0.82(0.01)( $+$ )	1.07(0.02)( $+$ )	0.58(0.01)( $+$ )	0.61(0.01)( $+$ )
MK14	$30 × 15$	$[1.0,5.0]$	0.54(0.01)	0.90(0.01)( $+$ )	1.11(0.02)( $+$ )	0.68(0.02)( $+$ )	0.67(0.01)( $+$ )
MK15	$30 × 15$	$[1.0,4.0]$	0.42(0.02)	0.81(0.02)( $+$ )	1.10(0.04)( $+$ )	0.53(0.02)( $+$ )	0.54(0.02)( $+$ )

Table 3

Fig. 6

Fig. 7

Table 4

Completion deadline information for jobs in MK01

工件	$d i$	工件	$d i$	工件	$d i$	工件	$d i$	工件	$d i$
$J 1$	44.0	$J 3$	23.0	$J 5$	30.0	$J 7$	22.0	$J 9$	54.0
$J 2$	37.0	$J 4$	32.0	$J 6$	44.0	$J 8$	55.0	$J 10$	28.0

Table 4

Fig. 8

References 22

[1]	Dauzère-Pérès Stéphane, Ding Junwen, Shen Liji, et al. The Flexible Job Shop Scheduling Problem: A Review[J]. European Journal of Operational Research, 2024, 314(2): 409-432.
[2]	Zhang Fangfang, Mei Yi, Su Nguyen, et al. Instance-rotation-based Surrogate in Genetic Programming with Brood Recombination for Dynamic Job-shop Scheduling[J]. IEEE Transactions on Evolutionary Computation, 2023, 27(5): 1192-1206.
[3]	Quan Zhen, Wang Yan, Liu Xiang, et al. Virtual Workflows and Adaptive Optimization Scheduling of Production Process with Feedback Constraints[J]. Engineering Applications of Artificial Intelligence, 2025, 152: 110728.
[4]	Xu Yuanxing, Zhang Mengjian, Wang Deguang, et al. Hybrid Gaussian Quantum Particle Swarm Optimization and Adaptive Genetic Algorithm for Flexible Job-shop Scheduling Problem[J]. Engineering Applications of Artificial Intelligence, 2025, 154: 110882.
[5]	Wang Wentao, Zhao Jing. An Enhanced Memetic Algorithm for Energy-efficient and Low-carbon Flexible Job Shop Scheduling Problem Considering Machine Restart[J]. Journal of Manufacturing Systems, 2025, 80: 457-478.
[6]	Hou Yingjie, Liao Xiaojuan, Chen Guangzhu, et al. Co-evolutionary NSGA-III with Deep Reinforcement Learning for Multi-objective Distributed Flexible Job Shop Scheduling[J]. Computers & Industrial Engineering, 2025, 203: 110990.
[7]	Samsuria Erlianasha, Mohd Saiful Azimi Mahmud, Norhaliza Abdul Wahab, et al. An Improved Adaptive Fuzzy-genetic Algorithm Based on Local Search for Integrated Production and Mobile Robot Scheduling in Job-shop Flexible Manufacturing System[J]. Computers & Industrial Engineering, 2025, 204: 111093.
[8]	田梦蝶, 贾世会, 迟晓妮, 等. 基于混沌映射的改进GA求解柔性作业车间调度[J]. 组合机床与自动化加工技术, 2025(3): 226-231.
	Tian Mengdie, Jia Shihui, Chi Xiaoni, et al. Improved GA Based on Chaotic Mapping for Flexible Job Shop Scheduling[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2025(3): 226-231.
[9]	闫炳龙, 叶春明. 考虑工人约束的分布式柔性作业车间调度问题研究[J]. 组合机床与自动化加工技术, 2025(4): 188-194.
	Yan Binglong, Ye Chunming. Research on Distributed Flexible Job Shop Scheduling Problem Considering Worker Constraints[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2025(4): 188-194.
[10]	周伟, 孙瑜, 李西兴, 等. 混合遗传变邻域搜索算法求解柔性车间调度问题[J]. 计算机工程与设计, 2024, 45(7): 2041-2049.
	Zhou Wei, Sun Yu, Li Xixing, et al. Hybrid Genetic Variant Neighborhood Search Algorithm for Flexible Job-shop Scheduling Problem[J]. Computer Engineering and Design, 2024, 45(7): 2041-2049.
[11]	靳思远, 彭程, 王薇, 等. 基于向量映射代理模型的分布式柔性作业车间调度算法[J]. 控制与决策, 2025, 40(5): 1561-1570.
	Jin Siyuan, Peng Cheng, Wang Wei, et al. Distributed Flexible Job Shop Scheduling Algorithm Based on Avector Mapping Surrogate Model[J]. Control and Decision, 2025, 40(5): 1561-1570.
[12]	裴琦斐. 作业车间瓶颈识别与生产调度研究[D]. 徐州: 中国矿业大学, 2017.
	Pei Qifei. Study on Bottleneck Identification and Scheduling in Job Shop[D]. Xuzhou: China University of Mining and Technology, 2017.
[13]	Ju Zeliang, Wang Yan, Quan Zhen, et al. Bottleneck Alleviation and Scheduling Optimization of Flexible Manufacturing System Based on Information-energy Flow Model[J]. Swarm and Evolutionary Computation, 2024, 89: 101600.
[14]	Lu Hong, Qiao Fei. An Efficient Adaptive Genetic Algorithm for Energy Saving in the Hybrid Flow Shop Scheduling with Batch Production at Last Stage[J]. Expert Systems, 2022, 39(2): e12678.
[15]	Quan Zhen, Wang Yan, Liu Xiang, et al. Multi-objective Evolutionary Scheduling Based on Collaborative Virtual Workflow Model and Adaptive Rules for Flexible Production Process with Operation Reworking[J]. Computers & Industrial Engineering, 2024, 187: 109848.
[16]	Zhang Fangfang, Mei Yi, Nguyen S, et al. Task Relatedness-based Multitask Genetic Programming for Dynamic Flexible Job Shop Scheduling[J]. IEEE Transactions on Evolutionary Computation, 2023, 27(6): 1705-1719.
[17]	Koza J R. Genetic Programming as a Means for Programming Computers by Natural Selection[J]. Statistics and Computing, 1994, 4(2): 87-112.
[18]	Brandimarte Paolo. Routing and Scheduling in a Flexible Job Shop by tabu Search[J]. Annals of Operations Research, 1993, 41(3): 157-183.
[19]	Deb K, Pratap A, Agarwal S, et al. A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.
[20]	Zhang Qingfu, Li Hui. MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition[J]. IEEE Transactions on Evolutionary Computation, 2007, 11(6): 712-731.
[21]	While L, Hingston P, Barone L, et al. A Faster Algorithm for Calculating Hypervolume[J]. IEEE Transactions on Evolutionary Computation, 2006, 10(1): 29-38.
[22]	Piroozfard Hamed, Kuan Yew Wong, Wai Peng Wong. Minimizing Total Carbon Footprint and Total Late Work Criterion in Flexible Job Shop Scheduling by Using an Improved Multi-objective Genetic Algorithm[J]. Resources Conservation and Recycling, 2018, 128: 267-283.

属性	特征	描述
任务特征	OPT	某工序所需加工时长
	APT	某工件所有工序所需加工时长总和
	LPT	某工序所属工件的上一工序完工时间
	EST	某工序的最早可开始加工时间
	NPT	某工序所属工件的下一工序所需加工时长
	RON	某工件剩余任务数量
	ROT	某工件剩余任务所需加工时长总和
	DRT	某工件的完工期限之前剩余时间
机器特征	MIT	某机器成为空闲机器的时刻
	WPT	等待在某机器上排序的任务所需加工时长总和
	NIT	在某机器上调度下一工序将产生的机器新增空载运行时长