Abstract
Material handling systems, as an important part of different type of manufacturing processes, face the same challenges as manufacturing industries pushed nowadays forward by innovative ideas and technologies to the next level loudly announced as industry 4.0. Development of the next generation of automated manufacturing systems involves advanced approaches to material handling systems design and their close integration with the higher levels of manufacturing and production control and management, e.g. manufacturing execution systems (MES), enterprise resource planning (ERP). In the presence of increasing demands for manufacturing process optimization, the role of supervisory level of material handling systems is much more advanced today, ensuring not only data acquisition, visualization, monitoring, supervisory control, as well as synchronization with the higher control levels (FEM, ERP), but also providing functionality for supporting maintenance and decision-making processes to reduce downtimes, operations and maintenance costs. The article deals with the integration of control and maintenance functions in the hierarchical control system of a crane. The supervisory system for supporting control and proactive maintenance is prototyped at the laboratory overhead travelling crane. The article presents the control-measurement equipment and intelligent software tools implemented in the supervisory control and data acquisition (SCADA) system to aid decision-making process in proactive maintenance. The overview of the main components of the supervisory control and proactive maintenance subsystems is provided, and their respective role in control, supervision, and proactive maintenance is explained. The crane’s supervisory control includes the stereovision-based subsystem applied to identify the crane’s transportation workspace, determine the safety and time-optimal point-to-point trajectory of a payload. The proactive maintenance module consists of the human machine interface (HMI) supporting decision-making process, intelligent tools for upcoming downtime/failure prediction, and the crane's girder inspection using the metal magnetic memory technique.
Machine Learning Based Approach to a Crane Load Estimation