基于免疫克隆约束多目标优化方法的电网故障诊断

发布时间：2018-10-29 10:56

【摘要】：针对基于优化技术的电网故障诊断的现有数学模型存在权值分配受人为主观因素影响的问题,提出了基于免疫克隆约束多目标优化方法的电网故障诊断。首先,在剖析原有诊断模型的目标函数的基础上,提出采用多目标优化的方式,将电网故障诊断问题转变为多目标优化问题,并采用Pareto最优解的方法进行求解,降低了故障诊断过程中人为主观因素造成的误差。其次,考虑现有数学模型采用罚函数法处理约束问题的不足之处,将约束条件转化为一个目标函数,使约束多目标优化问题转化为无约束多目标优化问题,进而提出采用免疫克隆约束多目标优化算法进行求解,制定了适用于电网故障诊断问题的多目标Pareto优化算法流程。最后,采用模糊集理论对Pareto最优解集中的解进行评价。故障实例和复杂电网故障案例的诊断结果验证了所提方法的有效性与可行性。
[Abstract]:In order to solve the problem that the weight distribution is affected by human subjective factors in the existing mathematical model of power network fault diagnosis based on optimization technology, a multi-objective optimization method based on immune clone constraints is proposed. Firstly, on the basis of analyzing the objective function of the original diagnosis model, a multi-objective optimization method is proposed to transform the power network fault diagnosis problem into a multi-objective optimization problem, and the method of Pareto optimal solution is used to solve the problem. The error caused by subjective factors in fault diagnosis is reduced. Secondly, considering the disadvantages of penalty function method in the existing mathematical model, the constraint condition is transformed into an objective function, and the constrained multi-objective optimization problem is transformed into an unconstrained multi-objective optimization problem. Then an immune clone constrained multi-objective optimization algorithm is proposed to solve the problem, and a multi-objective Pareto optimization algorithm flow chart is developed for power network fault diagnosis problem. Finally, the fuzzy set theory is used to evaluate the solution of Pareto optimal solution set. The effectiveness and feasibility of the proposed method are verified by fault diagnosis examples and complex power network fault cases.
【作者单位】：华北电力大学电气与电子工程学院;
【基金】：国家自然科学基金项目(51377054) 中央高校基本科研业务费专项资金资助项目(2017XS019)~~
【分类号】：TM732

【相似文献】