Thumbnail Image

Anomaly Detection Based Framework for Profile Monitoring

Al-Rahim, Nour Al-Huda Z. Al-Abed
A Master of Science thesis in Engineering Systems Management by Nour Al-Huda Z. Al-Abed Al-Rahim entitled, “Anomaly Detection Based Framework for Profile Monitoring”, submitted in May 2023. Thesis advisor is Dr. Hussam Alshraideh and thesis co-advisor is Dr. Mahmoud Awad. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).
Due to significant developments in technology, manufacturing processes are being equipped with sensors that provide continuous monitoring of the input and output process parameters. Signals observed through such sensors provide crucial details about the quality of the manufactured items. While significant amount of work has been found in the literature that aims at monitoring products quality through acquired process signals, these studies assume enough frequency of defective products implying balanced models training data. In the case of data imbalance, such methods provide biased and misleading prediction results. This work presents an anomaly detection-based framework for monitoring profile generating processes in the case of infrequent process defectives. The framework is based on the use of Isolation Forest (IF), Local Outlier Factor (LOF) and Density Based Scan (DBSCAN) algorithms. The proposed framework is illustrated through two case studies, a thread tapping process and a 3D printing process. For the tapping process, the DBSCAN model provided the best performance with AUC=0.83, accuracy=71.34%, and sensitivity=82.31%, compared to the IF and LOF models. For the 3D printing process, the IF algorithm achieved the best performance with AUC=0.85, accuracy=74.83%, and sensitivity=82.22%, outperforming the LOF and DBSCAN models. These findings demonstrate the efficacy of the proposed framework for monitoring profile generating processes and its potential to improve quality control in manufacturing processes.
External URI