Modern industrial development is accompanied by the increasingly frequent occurrence of accidental release atmospheric dispersion events,causing extremely serious human and property losses and environmental pollution,...Modern industrial development is accompanied by the increasingly frequent occurrence of accidental release atmospheric dispersion events,causing extremely serious human and property losses and environmental pollution,in which rapid and accurate prediction of atmospheric dispersion is an important task to mitigate the unexpected consequences.In this paper,we take the case of previous years as the starting point,firstly,the occurred hazardous chemical atmospheric dispersion accidents in the past five years are shown,and the related concepts of hazardous chemical atmospheric dispersion are given.Then,the current state of atmospheric dispersion research is reviewed,well-known experiments on atmospheric dispersion of hazardous chemicals are summarized,and correspondingly the existing atmospheric dispersion prediction models are classified into simplified-experience models,mechanism-and rule-driven models and data-driven models.In particular,for the purpose of rapid atmospheric dispersion prediction,some research on atmospheric detection and identification are analyzed in detail.Moreover,the relevant professional software for atmospheric dispersion prediction are introduced,and also their calculation adaptabilities regarding time-consumption and output accuracy are discussed.Thereinafter,according to the shortcomings of existing atmospheric dispersion prediction models in research and application fields,the development trend of atmospheric dispersion prediction research and technology is foreseen,and some feasible future research directions are proposed as follows:(1)the fusion of image processing techniques,the establishment of a database of historical accident scene information and meteorological information,(2)new correction algorithms,and(3)an emergency response system for full-scene atmospheric dispersion prediction.展开更多
Refined risk prediction must be achieved to guarantee the safe and steady operation of chemical production processes.However,there is high nonlinearity and association coupling among massive,complicated multisource pr...Refined risk prediction must be achieved to guarantee the safe and steady operation of chemical production processes.However,there is high nonlinearity and association coupling among massive,complicated multisource process data,resulting in a low accuracy of existing prediction technology.For that reason,a real-time risk prediction method for chemical processes based on the attention-based bidirectional long short-term memory(Attention-based Bi-LSTM)is proposed in this study.First,multisource process data,such as temperature,pressure,flow rate,and liquid level,are preprocessed for denoising.Data correlation is analyzed in time windows by setting time windows and moving step lengths to explore correlations,thus establishing a complex network model oriented to the chemical production process.Second,network structure entropy is introduced to reduce the dimensions of the multisource process data.Moreover,a 1D relative risk sequence is acquired by maxemin deviation standardization to judge whether the chemical process is in a steady state.Finally,an Attention-based Bi-LSTM algorithm is established by integrating the attention mechanism and the Bi-LSTM network to fit and train 1D relative risk sequences.In that way,the proposed algorithm achieves real-time prediction and intelligent perception of risk states during chemical production.A case study based on the Tennessee Eastman process(TEP)is conducted.The validity and reasonability of the proposed method are verified by analyzing distribution laws of relative risks under normal and fault conditions.Also,the proposed algorithm importantly improves the prediction accuracy of chemical process risks relative to that of existing prediction technologies.展开更多
基金the financial support provided by the Fundamental Research Funds for Central Universities(BUCTRC202014).
文摘Modern industrial development is accompanied by the increasingly frequent occurrence of accidental release atmospheric dispersion events,causing extremely serious human and property losses and environmental pollution,in which rapid and accurate prediction of atmospheric dispersion is an important task to mitigate the unexpected consequences.In this paper,we take the case of previous years as the starting point,firstly,the occurred hazardous chemical atmospheric dispersion accidents in the past five years are shown,and the related concepts of hazardous chemical atmospheric dispersion are given.Then,the current state of atmospheric dispersion research is reviewed,well-known experiments on atmospheric dispersion of hazardous chemicals are summarized,and correspondingly the existing atmospheric dispersion prediction models are classified into simplified-experience models,mechanism-and rule-driven models and data-driven models.In particular,for the purpose of rapid atmospheric dispersion prediction,some research on atmospheric detection and identification are analyzed in detail.Moreover,the relevant professional software for atmospheric dispersion prediction are introduced,and also their calculation adaptabilities regarding time-consumption and output accuracy are discussed.Thereinafter,according to the shortcomings of existing atmospheric dispersion prediction models in research and application fields,the development trend of atmospheric dispersion prediction research and technology is foreseen,and some feasible future research directions are proposed as follows:(1)the fusion of image processing techniques,the establishment of a database of historical accident scene information and meteorological information,(2)new correction algorithms,and(3)an emergency response system for full-scene atmospheric dispersion prediction.
基金supported by the National Natural Science Foundation of China(52004014)the Fundamental Research Funds for the Central Universities(ZY2406)the National Key Research&Development Program of China(2021YFB3301100).
文摘Refined risk prediction must be achieved to guarantee the safe and steady operation of chemical production processes.However,there is high nonlinearity and association coupling among massive,complicated multisource process data,resulting in a low accuracy of existing prediction technology.For that reason,a real-time risk prediction method for chemical processes based on the attention-based bidirectional long short-term memory(Attention-based Bi-LSTM)is proposed in this study.First,multisource process data,such as temperature,pressure,flow rate,and liquid level,are preprocessed for denoising.Data correlation is analyzed in time windows by setting time windows and moving step lengths to explore correlations,thus establishing a complex network model oriented to the chemical production process.Second,network structure entropy is introduced to reduce the dimensions of the multisource process data.Moreover,a 1D relative risk sequence is acquired by maxemin deviation standardization to judge whether the chemical process is in a steady state.Finally,an Attention-based Bi-LSTM algorithm is established by integrating the attention mechanism and the Bi-LSTM network to fit and train 1D relative risk sequences.In that way,the proposed algorithm achieves real-time prediction and intelligent perception of risk states during chemical production.A case study based on the Tennessee Eastman process(TEP)is conducted.The validity and reasonability of the proposed method are verified by analyzing distribution laws of relative risks under normal and fault conditions.Also,the proposed algorithm importantly improves the prediction accuracy of chemical process risks relative to that of existing prediction technologies.
