• Journal of the Korean Institute of Gas
• /
• v.22 no.2
• /
• pp.1-20
• /
• 2018

Despite many measures, still from time to time catastrophic events occur, even after reviewing potential scenarios with HAZID tools. Therefore, it is evident that in order to prevent such events, answering the question: "What can go wrong?" requires more enhanced HAZID tools. Recently, new system based approaches have been proposed, such as STPA (system-theoretic process analysis) and Blended Hazid, but for the time being for several reasons their availability for general use is very limited. However, by making use of available advanced software and technology, traditional HAZID tools can still be improved in degree of completeness of identifying possible hazards and in work time efficiency. The new HAZID methodology proposed here, the Data-based semi-Automatic HAZard IDentification (DAHAZID), seeks to identify possible scenarios with a semi-automated system approach. Based on the two traditional HAZID tools, Hazard Operability (HAZOP) Study and Failure Modes, Effects, and Criticality Analysis (FMECA), the new method will minimize the limitations of each method. This will occur by means of a thorough systematic preparation before the tools are applied. Rather than depending on reading drawings to obtain connectivity information of process system equipment elements, this research is generating and presenting in prepopulated work sheets linked components together with all required information and space to note HAZID results. Next, this method can be integrated with proper guidelines regarding process safer design and hazard analysis. To examine its usefulness, the method will be applied to a case study.

• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.485-500
• /
• 2023

Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.