Deep Fuzzy Cognitive Maps for Defect Inspection in Antenna Assembly

Production line calibration is a critical industrial task that requires thoroughly planned actions. Even tiny deviations from the optimal settings can cause dramatic deficiencies. Automated Root Cause Analysis can be employed to suggest the actions that result in faulty states, and therefore, to resolve situations and prevent recurrence. This work presents a methodology for Root Cause Analysis focused on the calibration process of a valve block in an elevator system. The causalities (weighted interconnections) between oil flow control (actions) and system velocity (output) are estimated using Pearson Correlation. The produced weight matrix is evaluated by exploiting expert knowledge. An FCM model for Root Cause Analysis is developed to study the system behavior and explore the root causes of deficiencies. The proposed approach eliminates the need for labeled root causes. Results support the efficiency of the proposed FCM model for correcting the sub-optimal configurations; the proposed approach seems to work even when the calibration actions are unknown.