Predicting the optimum availability of the physical processing unit of sewage treatment plant is defined as a Nondeterministic Polynomial time-hard problem. Recently many researchers have utilized soft computing techniques to handle this issue. However, the existing techniques are far from the optimal solutions as soft computing techniques suffer from various issues such as, poor computational speed, getting stuck in local optima, pre-mature convergence, etc. Therefore, in this work a novel mathematical model is designed and implemented using Markov process and Chapman-Kolmogorov equations derived by assuming arbitrary repair rates and exponentially distributed failure rates. Thereafter, Genetic Algorithm and Particle Swarm Optimization techniques are utilized to optimize the availability and performance of physical processing unit. The needed data has been collected with the help of plant personnel and results are also shared with them. Experimental results reveal that the Particle Swarm Optimization based proposed model outperforms the competitive techniques.

预测污水处理厂物理处理单元的最佳可用性被定义为非确定性多项式时间困难问题。最近，许多研究人员利用软计算技术来处理这个问题。然而，现有技术远非最优解，因为软计算技术存在计算速度差、陷入局部最优、过早收敛等各种问题。因此，在这项工作中，设计了一个新的数学模型并使用马尔可夫过程和通过假设任意修复率和指数分布故障率导出的 Chapman-Kolmogorov 方程实现。此后，利用遗传算法和粒子群优化技术来优化物理处理单元的可用性和性能。在工厂人员的帮助下收集了所需的数据，结果也与他们共享。实验结果表明，基于粒子群优化提出的模型优于竞争技术。