室内多消防水炮协同灭火任务规划研究

Research on indoor multi⁃fire water cannons cooperative fire fighting task planning

室内大空间消防系统通常采用多个固定式智能消防水炮组成水炮群进行灭火。为改善室内多消防水炮对多火源灭火效率,提出一种基于火灾损失代价和灭火时间代价的粒子群任务规划算法。首先,采用整数编码方式对粒子进行编码,一组编码对应一组任务分配解;然后,应用非线性自适应权重更新方法动态调整算法关键参数,提升算法性能。为避免陷入局部最优解,采用基于模拟退火的自适应粒子群算法,以一定概率接受差解,提高粒子多样性,帮助算法跳出局部最优。针对火源动态变化和灭火过程中新发火源,设计了一种分阶段任务规划策略,与所提算法结合可有效解决动态规划问题。实例仿真结果表明,该算法在寻优效率和结果稳定性方面优于标准粒子群算法和自适应粒子群算法,具有良好的应用价值。

Usually,fire fighting system in large indoor space is a fire fighting water cannon group formed of multiple fixed intelligent fire cannons.In order to improve the efficiency of indoor fire fighting with multi⁃fire water cannons to multi⁃fire sources,a particle swarm task planning algorithm based on fire loss cost and fire fighting time cost is proposed.The particle is encoded by integer coding.A set of task assignment solutions is obtained by decoding a set of encodings.And then,the key parameters are dynamically adjusted by a nonlinear adaptive weight updating method,so as to enhance the performance of the algorithm.An adaptive particle swarm optimization(APSO)algorithm based on simulated annealing(SA)algorithm is used to make the inferior solutions accepted with a certain probability,improve the particle diversity,and help the algorithm to escape from the local optimal.For the dynamic change of fire source and new fire source in the fire fighting process,a phased task planning strategy is designed,which can effectively solve the dynamic task planning problem by combining with the proposed algorithm.The simulation results show that the proposed algorithm is superior to the standard PSO algorithm and APSO algorithm in terms of optimization efficiency and stability.Therefore,it has good application value.