International Conference on Mechatronics Technology and Intelligent Manufacturing (ICMTIM)

DisassemblyResearch on Disassembly Scheduling Optimization Based on Quantum Annealing in Intelligent Manufacturing Environment

Y S Zhang, Cong Liang

Published Apr 17, 2026• 0 citations

Abstract

Addressing the challenges of multi-device collaboration, significant dynamic disturbances, and poor optimization performance of traditional algorithms in disassembly scheduling within intelligent manufacturing environments, this paper constructs a multi-objective optimization model integrating total project duration, equipment energy consumption, and load balancing. A weighted approach is employed to handle the coupling of objectives. Constraints are set based on the actual scenario, and the quantum annealing algorithm is simplified and adapted. A dynamic adaptive quantum annealing algorithm (DAQA) is designed based on the traditional quantum annealing algorithm, incorporating three mechanisms: dynamic neighborhood generation, adaptive cooling schedule, and dynamic disturbance compensation. This addresses the bottlenecks of slow convergence, susceptibility to local optima, and weak antidisturbance capability of traditional algorithms. Comparative experiments are conducted using three datasets of different sizes, comparing DAQA with traditional quantum annealing, genetic algorithms, and particle swarm optimization. The results show that DAQA outperforms the compared algorithms in terms of solution accuracy, convergence speed, runtime, robustness, and energy consumption optimization. It can effectively adapt to the dynamic disassembly scenario in intelligent manufacturing, improving scheduling efficiency and resource utilization. Note that the algorithm is currently validated on a classical hardware-based D-Wave simulation platform, and its performance on actual quantum annealers with inherent noise and limited connectivity will be verified in subsequent hardware experiments.

DOI: 10.1109/icmtim69588.2026.11526662

Related papers

Quantum annealing for CAD-based disassembly sequence optimization

José Azucena, Joao Paulo Jacomini Prioli

Abstract Disassembly is the core of sustainable recovery processes, enabling the reuse, remanufacturing, and recycling of end-of-life products. Disassembly Sequence Optimization (DSO) is the key to achieving practical and efficient disassembly applications in industrial scenarios. This study presents a novel approach to DSO by leveraging Quantum Annealing (QA) through Quadratic Unconstrained Binary Optimization (QUBO) and Constrained Quadratic Model (CQM) formulations integrated with CAD-based assembly designs. The proposed methods aim to address computational challenges in industrial disassembly applications. We evaluated these methods against classical heuristics using two distinct product designs. For a smaller, denser assembly, the hybrid CQM model demonstrated superior performance in terms of solution quality and computational time. Conversely, for a larger, sparser assembly, a classical heuristic achieved better results in solution quality when constraining computational time compared to the hybrid quantum approaches. The QUBO model, although did not overcome classical, showed promise in exploring solution spaces, obtaining better solution quality than CQM for the larger problem. These findings indicate that the current practical utility of quantum annealing for DSO is influenced by problem size, structure, and hybrid workflow efficiency. Future research should focus on optimizing the balance between classical and quantum resources to further enhance efficiency. As quantum hardware continues to advance, these formulations have the potential to revolutionize sustainable manufacturing by optimizing disassembly planning with greater efficiency and adaptability to large assemblies.

The International Journal of Advanced Manufacturing TechnologyDec 18, 20252 citations

Quantum Optimization of Energy Consumption in Flexible Manufacturing Systems Integrating Renewable Power Sources

Baran Bilgin

As modern manufacturing transitions toward flexible and energy-adaptive production environments, optimizing energy consumption has become essential for achieving operational sustainability and aligning with global decarbonization goals. Traditional optimization techniques often struggle with the nonlinear, multi-objective, and stochastic nature of energy flows in flexible manufacturing systems, especially when integrating intermittent renewable energy sources such as solar and wind. This study proposes a quantum-enhanced optimization framework leveraging quantum annealing, variational quantum algorithms, and hybrid quantum–classical solvers to minimize energy usage while maintaining production throughput and scheduling feasibility. The approach formulates energy allocation, load balancing, and production scheduling as combinatorial optimization problems that benefit from quantum parallelism and high-dimensional state exploration. Simulations conducted on benchmark manufacturing models demonstrate that the quantum-enabled framework improves peak-load reduction, enhances renewable utilization rates, and reduces overall energy consumption by up to 22% compared to classical baselines. These results indicate the transformative potential of quantum optimization in enabling cleaner, more resilient, and sustainably powered manufacturing ecosystems.

Next generation.Nov 24, 20250 citations

Multi-objective Quantum Annealing approach for solving flexible job shop scheduling in manufacturing

Philipp Schworm, Xiangqian Wu, Matthias Klar +2 more

Flexible Job Shop Scheduling (FJSSP) is a challenging optimization problem with multiple conflicting objectives used to model and compute real-world process scheduling tasks. In order for a manufacturing system to remain competitive, it is necessary to compute such optimization problems quickly and efficiently. The limitations of conventional optimization methods frequently stem from a delicate balance between solution quality and computation time. Consequently, a pressing need for solution algorithms arises that can effectively transcend these limitations. This paper presents a novel Quantum Annealing-based solving algorithm (QASA) for computing FJSSP, leveraging the power of Quantum Annealing combined with classical techniques. The proposed approach aims to optimize a multi-criterial FJSSP considering makespan, total workload, and job priority simultaneously. QASA employs a Hamiltonian formulation with Lagrange parameters to integrate the problem's constraints and objectives. By assigning appropriate weights to the objectives, the method allows the prioritization of certain objectives over others. To handle the computational complexity of large FJSSP instances, the problem is decomposed into smaller subproblems, and a decision logic based on bottleneck factors is employed to select critical jobs for computation combined with variable pruning techniques. To evaluate the effectiveness of the proposed approach, experiments are conducted on benchmark problems, considering makespan, total workload, and priority objectives. Therefore, QASA combining tabu search, simulated annealing, and Quantum Annealing is used for efficient computation and is compared with a classical solving algorithm (CSA) combining tabu search and simulated annealing. The results demonstrate that QASA outperforms CSA in terms of solution quality, as measured by set coverage and hypervolume ratio metrics. Furthermore, computational efficiency analysis reveals that QASA achieves superior Pareto solutions compared to the classical approach, with a reasonable increase in computation time.

arXiv:2311.09637Journal of Manufacturing SystemsDec 2, 202350 citations

A Quantum Annealing-Based Approach for Multi-Objective Optimization in Flexible Job Shop Scheduling using Quantum- Adaptive Flex Scheduler

T.R. Chinnusamy, Velur Loganathan Raja, Gopalakrishnan T +1 more

Abstract The advent of quantum computing has introduced transformative potential for solving complex optimization problems, particularly in the field of manufacturing. This paper presents the Quantum-Adaptive Flex Scheduler (QAFS), a hybrid algorithm that leverages Quantum Annealing (QA) to address the Flexible Job Shop Scheduling Problem (FJSSP) with multiple objectives. QAFS integrates quantum mechanics with traditional heuristic methods to efficiently navigate the vast solution space of FJSSP, overcoming the computational limitations faced by classical algorithms. Our computational study demonstrates that QAFS significantly improves key performance metrics: it reduces makespan by 10–15%, enhances workload distribution by 5–10%, and achieves priority adherence 10–20% more effectively than Classical Scheduling Algorithms (CSA). Moreover, QAFS achieves superior solution quality, attaining an 85% C-metric coverage and a HyperVolume Ratio (HVR) of 0.92, underscoring its capability to generate Pareto-efficient solutions in multi-objective scenarios. These findings highlight the practical potential of QAFS to revolutionize production planning and control in manufacturing, offering a scalable and adaptive solution that responds effectively to real-time constraints and fluctuating market demands.

Dec 12, 20240 citations

Quantum-classical hybrid algorithm using quantum annealing for multi-objective job shop scheduling

Kenta Sawamura, Kensuke Araki, Naoki Maruyama +2 more

Efficient production planning is essential in modern manufacturing to improve performance indicators such as lead time and to reduce reliance on human intuition. While mathematical optimization approaches, formulated as job shop scheduling problems, have been applied to automate this process, solving large-scale production planning problems remains computationally demanding. Moreover, many practical scenarios involve conflicting objectives, making traditional scalarization techniques ineffective in finding diverse and useful Pareto-optimal solutions. To address these challenges, we developed a quantum-classical hybrid algorithm that decomposes the problem into two subproblems: resource allocation and task scheduling. Resource allocation is formulated as a quadratic unconstrained binary optimization problem and solved using annealing-based methods that efficiently explore complex solutions. Task scheduling is modeled as a mixed-integer linear programming problem and solved using conventional solvers to satisfy detailed scheduling constraints. We validated the proposed method using benchmark instances based on foundry production scenarios. Experimental results demonstrate that our hybrid approach achieves superior solution quality and computational efficiency compared to traditional monolithic methods. This work offers a promising direction for high-speed, multi-objective scheduling in industrial applications.

quant-pharXiv:2511.03257Nov 6, 20250 citations

Quantum annealing algorithm-driven industrial robot dynamic path planning and collision avoidance system

Yan Wang

Industrial robots play a pivotal role in modern manufacturing, yet achieving real-time path planning and reliable collision avoidance in dynamic environments remains a major challenge. Traditional algorithms often fail to balance efficiency, adaptability, and safety. This paper presents a quantum annealing (QA)-based approach to optimize robot navigation by minimizing travel time, energy consumption, and collision risk under operational constraints. By integrating QA with real-time sensor data and robot kinematics, the system dynamically replans trajectories in response to environmental changes. Comparative simulations demonstrate that the QA method outperforms classical algorithms such as Particle Swarm Optimization (PSO) and A-Star (A*) in both computational speed and path quality. These results highlight the potential of quantum annealing as a powerful tool for intelligent robotic navigation in complex industrial settings.

IET conference proceedings.Jan 1, 20260 citations