Because the fault data of rail transit switch machine are difficult to obtain and the site fault is difficult to reproduce, it is difficult to diagnose or predict the switch machine. In this paper, the power fault data of S700K switch machine is divided into creeping fault and mutation fault, and a simulation data generator for generating massive fault data is developed. The generators involve the synthesis of minority over-sampling techniques and generative confrontation networks. Finally, the long-term memory neural network is used to predict the generated gradual fault data to verify the authenticity and reliability of the simulation data generator. The experimental results show that the generated data can predict the future power trend of the switch machine, which proves the authenticity and feasibility of the simulation data generator.

Interruptible load management plays an important role in maintaining the reliability and security of power systems and reducing price spike of power markets, thus has been widely used in power systems. Interruptible loads dispatch problem with multi-period and multi-interruptible-load is usually a multi-objective, combinatorial optimization problem, and its solution method needs to be carefully investigated. Application of intelligent optimization algorithms to the multi-period interruptible load dispatch problem is discussed in this paper. Multi objectives, such as minimizing the interruption payments and interruption frequency, can be included in the proposed interruptible load dispatch model. The characteristics of different interruptible loads are also considered. Numerical simulations using discrete binary particle swarm optimization (BPSO) and the genetic algorithm (GA) show that the BPSO can obtain better solutions than that of the GA. Thus the BPSO presents better potentials in solving the interruptible load dispatch problem.