scholarly journals Determining the Optimal Method for Analyzing Specific Accidents (Case study: Falling accidents in the construction project of a combined cycle power plant)

2021 ◽  
Author(s):  
Reza RADMANFAR ◽  
Alireza HAJI HOSSEINI ◽  
Reza JAFARI NODOUSHAN
Keyword(s):  
Power Plant ◽  
Combined Cycle ◽  
Accident Analysis ◽  
Analysis Method ◽  
Decision Matrix ◽  
Accident Investigation ◽  
Optimal Method ◽  
Expert Opinions ◽  
Sequence Of Events ◽  
Special Power

Introduction: Today, accident investigation and analysis is an important component of safety programs in preventive measures. Incident investigation involves collecting all the information and actual interpretations of an incident, analyzing information to find out the causes of the incident, and writing an incident report. Methods: This descriptive-analytical article was conducted to determine the most important criteria for investigating and selecting the techniques of accident investigation as well as analyzing and selecting the best method of accident analysis in the events of the power plant industry. In this research, previous research studies were studied and expert opinions were collected with regard to the most important criteria for choosing a specific accident analysis method. Later, the 4 accident analysis methods was applied in a special power plant accident and the decision matrix was designed based on the strengths and weaknesses of the model formation. Finally, these four methods were prioritized using the Topsis decision-making method. Results: The key factors in investigating the main criteria for selecting an incident analysis method included the ability to understand the sequence of events in the model, identifying the root causes, descriptiveness and ability to provide reasons for managers and specialists, the need for technical experts, and the time criterion. The TRIPOD BETA method was selected as the best method for analyzing the power accidents. Conclusion: The TRIPOD BETA method was introduced as the most effective method for investigating power plant accidents.

scholarly journals Comparison of error tree analysis and TRIPOD BETA in accident analysis of a power plant industry using hierarchical analysis

2020 ◽  
Author(s):  
A Akhavan ◽  
H Karimi ◽  
GH Halvani
Keyword(s):  
Power Plant ◽  
Accident Analysis ◽  
Hierarchical Analysis ◽  
Analysis Method ◽  
Industrial Accidents ◽  
Optimal Method ◽  
Expert Opinions ◽  
Training Courses ◽  
Model Realism ◽  
Time Required

Introduction: Due to the importance and necessity of accident analysis, it is necessary to use the proper technique for precise accident analysis and provide corrective and preventive measures to prevent an accident's recurrence. Materials and Methods: In this descriptive-analytical paper, the most important criteria for investigating and selecting accident investigation and analysis techniques and selecting the best accident analysis method were identified in critical industrial accidents in the construction phase, were identified and analyzed. In this study, the most important criteria for selecting an accident analysis method were identified using previous research and gathering expert opinions. Then, two critical power plant accidents were analyzed using TRIPOD BETA and FTA accident analysis methods. Then the pairwise comparisons matrix was formed based on the strengths and weaknesses of the models. Finally, the prioritization of these two methods was done using the hierarchical analysis decision-making method.  Results: In this paper, seven key factors, model realism, model descriptive, systematic modeling, run time, required training courses, ability to quantify, and visibility of events, were identified as the most important criteria for selecting an incident analysis method. Conclusion: The TRIPOD BETA method has been introduced as an optimal method for investigating specific events due to its capabilities.

scholarly journals Air pollution forecasting application based on deep learning model and optimization algorithm

2021 ◽  
Author(s):  
Azim Heydari ◽  
Meysam Majidi Nezhad ◽  
Davide Astiaso Garcia ◽  
Farshid Keynia ◽  
Livio De Santoli
Keyword(s):  
Air Pollution ◽  
Wind Speed ◽  
Power Plant ◽  
Air Temperature ◽  
Short Term Memory ◽  
Combined Cycle ◽  
Short Term ◽  
Term Memory ◽  
Proposed Model ◽  
Long Short Term Memory

AbstractAir pollution monitoring is constantly increasing, giving more and more attention to its consequences on human health. Since Nitrogen dioxide (NO2) and sulfur dioxide (SO2) are the major pollutants, various models have been developed on predicting their potential damages. Nevertheless, providing precise predictions is almost impossible. In this study, a new hybrid intelligent model based on long short-term memory (LSTM) and multi-verse optimization algorithm (MVO) has been developed to predict and analysis the air pollution obtained from Combined Cycle Power Plants. In the proposed model, long short-term memory model is a forecaster engine to predict the amount of produced NO2 and SO2 by the Combined Cycle Power Plant, where the MVO algorithm is used to optimize the LSTM parameters in order to achieve a lower forecasting error. In addition, in order to evaluate the proposed model performance, the model has been applied using real data from a Combined Cycle Power Plant in Kerman, Iran. The datasets include wind speed, air temperature, NO2, and SO2 for five months (May–September 2019) with a time step of 3-h. In addition, the model has been tested based on two different types of input parameters: type (1) includes wind speed, air temperature, and different lagged values of the output variables (NO2 and SO2); type (2) includes just lagged values of the output variables (NO2 and SO2). The obtained results show that the proposed model has higher accuracy than other combined forecasting benchmark models (ENN-PSO, ENN-MVO, and LSTM-PSO) considering different network input variables. Graphic abstract

Sign in / Sign up

Export Citation Format

Share Document