With the continuous expansion of the global market size of electronic products, manufacturing enterprises are confronted with the dual challenges of quality control and cost optimization. In view of the limitations of the traditional single-stage model that neglects the dynamic correlation of processes and the multi-objective synergy, this paper proposes a hybrid optimization model (MDPGA) that integrates Markov Decision Process (MDP) and Genetic Algorithm (GA). By constructing a four-layer 0-1 planning framework, it quantifies the cost-benefit relationship of detection, disassembly and interchange losses, and uses the Markov model to depict the quality state transition of multiple processes to solve the problem of error accumulation. Combined with the global optimization ability of GA, it adaptively adjusts the detection strategy and disassembly recovery plan to achieve dynamic decision optimization. Experiments show that in the scenario of 8-piece assembly, the profit of this model increases by 23.7%, the resource waste is reduced by 32%, and it demonstrates strong robustness in scenarios with a 20% defective rate and high interchange loss. The research provides an intelligent decision-making tool that balances quality compliance and profit maximization for multi-stage production systems, promoting the coordinated development of intelligent manufacturing and circular economy.

Tengxi Li, Yu Gao, Juan Xu. Cascading Quality Control with Evolutionary Intelligence—A Markov-Embedded Genetic Algorithm Approach for Profit-Optimized Electronics Production Systems. Academic Journal of Mathematical Sciences (2025), Vol.6, Issue 2: 48-55. https://doi.org/10.25236/AJMS.2025.060207.

[1] Montgomery D C. Introduction to statistical quality control[M]. John wiley & sons, 2020.

[2] Gupta R, Aggarwal M, Swaran Ahuja. Hamiltonian graph analysis–mixed integer linear programming (HGA-MILP) based link failure detection system in optical data center networks[J]. Journal of Optical Communications, 2023, 44(3): 351-358.

[3] Zhang Y, Tzeng E, Du Y, et al. Large-scale reinforcement learning for diffusion models[C]//European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2024: 1-17.

[4] Wu M, Wang X, Chen X, et al. The threshold effect of R&D investment on regional economic performance in China considering environmental regulation[J]. Technology Analysis & Strategic Management, 2020, 32(7): 851-868.

[5] Zhang X, Fan M, Wang D, et al. Top-k feature selection framework using robust 0–1 integer programming[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(7): 3005-3019.