摘要：This paper presents several novel approaches of particle swarm
optimization (PSO) algorithm with new particle velocity equations
and three variants of inertia weight to solve the optimal control
problem of a class of hybrid systems, which are motivated by the
structure of manufacturing environments that integrate process and
optimal control. In the proposed PSO algorithm, the particle
velocities are conceptualized with the local best (or
pbest) and global best (or gbest) of the swarm,
which makes a quick decision to direct the search towards the
optimal (fitness) solution. The inertia weight of the proposed
methods is also described as a function of pbest and gbest, which
allows the PSO to converge faster with accuracy. A typical
numerical example of the optimal control problem is included to
analyse the efficacy and validity of the proposed algorithms.
Several statistical analyses including hypothesis test are done to
compare the validity of the proposed algorithms with the existing
PSO technique, which adopts linearly decreasing inertia weight.
The results clearly demonstrate that the proposed PSO approaches
not only improve the quality but also are more efficient in
converging to the optimal value faster.
