Structural damage detection using deep learning and FE model updating techniques.

The structural condition can be estimated by various methods. Damage detection, as one of those methods, deals with identifying changes in specific features within structural behavior based on numerical models. Since the method is based on simulation for various damage conditions, there are limitations in applicability due to inevitable discrepancies between the analytical model and the actual structure. Finite element model updating is a technique for establishing a finite element model that can reflect the current state of a target structure based on the measured responses. It is performed based on optimization for various structural parameters, but the final output can converge differently depending on the initial model and the characteristics of the algorithm. Although the updated model may not faithfully replicate the target structure as it is, it can be considered equivalent in terms of the relationship between the structural properties and behavioral characteristics of the target. This allows for the analysis of changes in the mechanical relationships established for the target structure. The change can be related to structural damage, and artificial intelligence technology can provide an alternative solution in such complex problems where analytical approaches are challenging. Taking practical aspects from the aforementioned methods, a novel structural damage detection methodology is presented in this study for identifying the location and extent of the damage. Model updating is used to establish a reference model that reflects the structural characteristics of the target. Training data for various damage conditions based on the reference model allows the artificial intelligence networks to identify damage to the target structure.

Types and Characteristics of Fatal Accidents Caused by Multiple Processes in a Workplace: Based on Actual Cases in South Korea.

As the social cost of disasters increases and safety is being emphasized, policy regulations at the national level have been implemented. However, various fatal accidents are continually occurring as continued economic development and enhanced technologies have increased demand and complicated the industrial structure. Workers in different industries, performing similar jobs, often experience different workplace hazards, which can result in similar types of accidents. Therefore, new policy regulations have been established to separate multiple processes and work in workplaces and are being implemented in several countries to minimize damage caused by new types of industrial accidents. Supervision and management appropriate for contractors or safety and health officials with legal obligations are required to play a regulatory role when these types of industrial accidents are likely to occur. This study classified accidental types and their characteristics based on actual cases, in which potential risks exist at multiple processes in a workplace. First, raw data of work-related fatalities that occurred in South Korea were reviewed and classified as fatal accidents caused by multiple processes in workplaces using the proposed method. Next, the classified actual cases were prepared as statistical data and analyzed based on the various categories. Finally, the accident type based on multiple processes, including risks and characteristics, in workplaces was proposed. As a result, this study improved the safety awareness and understanding of regulatory subjects regarding industrial accidents caused by multiple processes in workplaces and is expected to improve the effectiveness of the existing policy to prevent workplace accidents.

Suggestion of an Improved Evaluation Method of Construction Companies' Industrial Accident Prevention Activities in South Korea.

Workers in the construction industry are constantly exposed to dangers during work that can lead to death or disability. Despite recent advances in construction technology, the presence of these risks for workers has become an unresolved social problem. In particular, most companies often recognize that it is necessary to mitigate against risks posed to worker only after an accident has occurred. Recently, there has been an increasing demand for the development of new safety technologies and policy proposals to ensure the safety of workers during construction or work. However, the right solution is not coping after an accident but preventing it, and this must be accompanied by voluntary efforts by the company. To work toward such solutions, Korea is implementing an evaluation of construction companies' industrial accident prevention activities without legal regulations or coercion to encourage voluntary accident prevention activities by companies. The purpose of this study is to propose an effective improvement direction for the system implemented by the Korea Occupational Safety and Health Agency. First, by analyzing the details of the system and the data of the evaluation results, the system's effectiveness and rationality are reviewed, and steps for improvement are determined. Next, an evaluation model is proposed considering the size of the company to be evaluated and the level of safety and health, and its validity is verified through a survey of construction workers. Finally, a plan to induce the voluntary participation of construction companies in this system and the role of the supervisory authority are presented. This study is expected to serve as an important example of an effective safety policy model by encouraging companies' voluntary efforts to prevent accidents in the construction industry and raise the level of potential safety and health awareness.