Menghan Li

Traditional electric-drive maize seed-metering systems, when operating at high speeds, are constrained by insufficient control accuracy and sluggish dynamic response, making it difficult to guarantee qualified single-seed placement rates, which directly affects field sowing quality and subsequent maize yield. To address the inherent shortcomings of conventional fuzzy PID control—namely, lagging manual parameter tuning and the susceptibility of standard particle swarm optimization to local optima—this paper proposes an improved particle swarm optimization algorithm. By introducing adaptive inertia weight and chaotic mutation operators to optimize the iterative mechanism of the particle swarm optimization, precise tuning of fuzzy PID control parameters is achieved. Simulink simulations show that the improved algorithm reduces the optimal fitness value by 60.66% compared with the standard algorithm, and increases the convergence speed by 30%. Bench test results confirm that, under operating speeds of 10–14 km/h, the proposed control strategy exhibits superior dynamic and steady-state performance; at the high operating speed of 14 km/h, the seeding quality index and coefficient of variation in plant spacing are 91.2% and 10.8%, respectively, representing significant improvements over PSO-Fuzzy-PID (88.1%, 12.8%) and conventional Fuzzy-PID (83.2%, 16.2%). This study can provide an important theoretical basis for precise control of high-speed maize seeding.