论文部分内容阅读
生产装置能否安全有效地运行,已经成为衡量工业生产发展水平的主要标志之一。面临日益复杂的化工过程生产装置,提高化工过程报警系统的性能有着重要的指导意义。传统的报警阈值参数设置方法局限性大,为了提升化工过程报警系统性能,需要对某些过程参数的报警阈值进行优化设置。本文针对传统粒子群算法的不足,采用了参数自适应的粒子群算法,该自适应粒子群算法通过实时调节自身的参数,使得能够较快地寻找到最优个体,且不容易陷入局部最优解。通过对一标准函数的研究,结果表明该自适应粒子群算法比传统的粒子群算法能够较快的达到最优解。随后,用该算法优化TE过程某一参数的报警阈值,降低了报警过程中误报和漏报的总次数,提高了报警系统的性能。本文所提方法为指导生产装置的安全运行提供了有效策略。
Whether the production plant can operate safely and effectively has become one of the major indicators of the level of industrial production. In the face of increasingly complex chemical process plant, improving the performance of chemical process alarm system has an important guiding significance. Traditional alarm threshold parameter setting method is limited, in order to enhance the performance of chemical process alarm system, the alarm threshold of some process parameters needs to be optimized. In order to overcome the shortcomings of traditional particle swarm optimization algorithm, a particle swarm optimization algorithm based on adaptive parameters is adopted. This adaptive particle swarm algorithm adjusts its own parameters in real time so that the optimal individual can be quickly found and can not easily fall into the local optimum solution. The results of a standard function show that the adaptive particle swarm optimization algorithm can reach the optimal solution faster than the traditional particle swarm optimization algorithm. Subsequently, the algorithm is used to optimize the alarm threshold of certain parameters of the TE process, which reduces the total number of false positives and false negatives in the alarm process, and improves the performance of the alarm system. The method proposed in this paper provides an effective strategy to guide the safe operation of production plant.