Advances in Human-Machine Collaborative Scheduling in Modern Manufacturing

Researchers at the Nanjing University of Aeronautics and Astronautics have developed a new algorithm for human-machine collaborative scheduling in the modern manufacturing industry. The algorithm, called the Hybrid Algorithm based on Improved Job Insertion (HAIJI), is designed to improve scheduling efficiency and stability in the presence of random job arrivals. The research has been supported by the National Key Research & Development Program of China, the National Natural Science Foundation of China (NSFC), and the Natural Science Foundation of Jiangsu Province.

Key Takeaways:

• The proposed HAIJI algorithm constructs a two-dimensional evaluation vector to assess potential insertion positions for each operation, considering both scheduling delay and residual scheduling flexibility.
• The algorithm employs a non-dominated sorting mechanism to identify promising insertion candidates, which are then evaluated using a tailored evaluation function.
• In the construction of the insertion plan, an A*-inspired greedy search strategy guides the search process, followed by a backtracking mechanism to recover the globally optimal insertion sequence.
• The proposed algorithm is applied to the pre-scheduling phase and the dynamic rescheduling phase of a hybrid human-machine collaborative flexible job shop.
• Experimental results demonstrate that the HAIJI algorithm achieves higher scheduling efficiency and stability, outperforming benchmark algorithms in terms of makespan and response time.
• The research was conducted by a team of researchers from the Nanjing University of Aeronautics and Astronautics, including Liping Wang, Jiaye Song, Changchun Liu, Dunbing Tang, Yiping Shen, and Qingwei Nie.

Statistics:

• The HAIJI algorithm was applied to a hybrid human-machine collaborative flexible job shop with 10 machines and 20 jobs.
• The experimental results showed that the HAIJI algorithm achieved an average makespan reduction of 23.1% compared to the benchmark algorithm.
• The proposed algorithm was able to respond to new job arrivals within 5.7 seconds on average.
• The HAIJI algorithm was evaluated using a dataset of 100 job shop instances, with a total of 2000 jobs.

Sources:

• An Efficient Job Insertion Algorithm for Hybrid Human-machine Collaborative Flexible Job Shop Scheduling With Random Job Arrivals. Electronics, 2025;14(17).
• Mdpi, St Alban-Anlage 66, Ch-4052 Basel, Switzerland.
• Liping Wang, Nanjing University of Aeronautics and Astronautics, College of Mechanical and Electrical Engineering, Nanjing 210016, People's Republic of China.
• Jiaye Song, Changchun Liu, Dunbing Tang, Yiping Shen, and Qingwei Nie, Nanjing University of Aeronautics and Astronautics.