IoT-based mission reliability evaluation and maintenance optimization of intelligent manufacturing systems integrating human errors and heterogeneous feedstocks

The rapid advancement of the Internet of Things (IoT) has driven significant interest in mission reliability evaluation and maintenance optimization for intelligent manufacturing systems (IMS) in intelligent manufacturing. However, existing studies have largely overlooked the impacts of human errors and heterogeneous feedstocks (qualified feedstocks and unqualified feedstocks) on machine degradation and buffer reliability. Additionally, the influence of maintenance priority constraints on the effectiveness of multi-objective optimization has received limited attention. Therefore, an IoT-based IMS mission reliability evaluation method is proposed, which incorporates the impacts of human errors and feedstocks. In addition, a multi-objective maintenance optimization algorithm that takes maintenance priority constraints into account is proposed. First, a new mission reliability modeling method considering heterogeneous feedstocks and human errors is proposed to characterize the impacts of interactions between processing machines, inspection machines, buffers, heterogeneous feedstocks, and humans on the degradation of manufacturing systems. Second, an IoT-based mission reliability evaluation method for manufacturing systems is proposed. Third, a multi-objective genetic algorithm (MOGA) with maintenance priority constraints is proposed to optimize reliability and cost. Finally, a case of an engine cylinder head manufacturing system is given to illustrate the effectiveness of the proposed method.