Journal of Safety and Sustainability最新文献

The frequency and intensity of wildfires have significantly increased in the United States over recent decades, posing profound threats to community safety and ecological sustainability. The escalating losses of human life, property, and biodiversity demand a proactive approach to wildfire prediction and management. This study proposes a highly efficient deep learning framework, utilizing a geospatial database of wildfire incidents in the United States from 1992 to 2018, aimed at bolstering our collective resilience against such disasters. The framework comprises two components: firstly, leveraging deep neural networks (DNN), the cause and size of potential wildfires are predicted, achieving accuracy rates of 76.9% and 76.4% for 5-class classification respectively. Secondly, a forecast model using long short term memory networks (LSTM) and an autoencoder is used to anticipate the likelihood of imminent wildfires, focusing on highly at-risk regions such as California. A specific model created to perform one-week forecasts for California achieved a coefficient of determination (R²) and root-mean-square error (RMSE) of 0.90 and 49.5076, respectively. These predictive models offer a significant step towards advancing community safety and environmental sustainability by facilitating timely and effective responses, thereby mitigating the catastrophic effects of wildfires on human life, properties, and delicate ecosystems.

Nuclear power plants (NPPs) are required to operate on a flexible profitable production plan while guaranteeing high safety standards. Deep reinforcement learning (DRL) is an effective method to find the most profitable operation & maintenance (O&M) strategy to adopt in a complex system. However, profit-driven only DRL neglects safety-related issues. In this paper, we propose a DRL approach to solve single-objective sequential decision problems (SOSDPs) and multi-objective sequential decision problems (MOSDPs) to find O&M strategies that trade off reliability and profit. The combinatorial problem related with the training of the RL agent to search for the optimal solution is addressed by Monte Carlo tree search (MCTS), whose performance is compared with the traditionally adopted proximal policy optimization (PPO) & imitation learning (IL). A case study is considered for demonstration.

With the continuous emergence of complex safety & security (SS) problems, SS complexity studies have become an inevitable tendency of SS science development. First, evolutions of research paths and objects of SS science in the past 100 years and some typical new viewpoints on SS science research in recent years are briefly summarized in order to prove the necessity of SS complexity studies. Also, multi-dimensional analysis of SS problems is made to show the essential reason why SS complexity studies are required. Then, historical analysis method, reasoning method, induction method, theoretical modeling method and prediction method are used to carry out the following research on the basic theory of the SS complexity: typical methods and principles of SS complexity studies are summarized; core concepts and basic definitions of SS complexity are built; some criteria on judging SS complex issues are put forward; models which can be used to express the SS complexity system are constructed and some controlling strategies for the SS complex system are proposed; and finally, the conclusions and outlooks of SS complexity studies are given. These results are of great significance for enrichment of SS science.