Operational optimization is essential in modern industry and unsuitable operations will deteriorate the performance of industrial processes. Since measuring error and multiple working conditions are inevitable in practice, it is necessary to reduce their negative impacts on operational optimization under the case-based reasoning (CBR) framework. In this paper, a local density-based abnormal case removal method is proposed to remove the abnormal cases in a case retrieval step, so as to prevent performance deterioration in industrial operational optimization. More specifically, the reasons as to why classic CBR would retrieve abnormal cases are analyzed from the perspective of case retrieval in industry. Then, a local density-based abnormal case removal algorithm is designed based on the Local Outlier Factor (LOF), and properly integrated into the traditional case retrieval step. Finally, the effectiveness and the superiority of the local density-based abnormal case removal method was tested by a numerical simulation and an industrial case study of the cut-made process of cigarette production. The results show that the proposed method improved the operational optimization performance of an industrial cut-made process by 23.5% compared with classic CBR, and by 13.3% compared with case-based fuzzy reasoning.

中文翻译：

---

CBR框架下基于局部密度的工业运营优化异常案例去除方法

运营优化在现代工业中至关重要，不合适的运营会降低工业流程的性能。由于测量误差和多个工作条件在实践中是不可避免的，因此有必要在基于案例的推理（CBR）框架下减少它们对操作优化的负面影响。在本文中，提出了一种基于局部密度的异常案例去除方法，用于在案例检索步骤中去除异常案例，以防止工业运营优化中的性能恶化。更具体地说，从行业案例检索的角度分析了经典CBR为什么会检索异常案例的原因。然后，基于局部异常因子（LOF）设计了一种基于局部密度的异常案例去除算法，并适当地整合到传统的案例检索步骤中。最后，通过数值模拟和卷烟生产切制过程的工业案例研究，验证了基于局部密度的异常情况去除方法的有效性和优越性。结果表明，与经典CBR相比，所提出的方法将工业切割过程的操作优化性能提高了23.5%，与基于案例的模糊推理相比提高了13.3%。