Search

CN-121997013-A - Emergency response grade determining method and system for hydrogenation device

CN121997013ACN 121997013 ACN121997013 ACN 121997013ACN-121997013-A

Abstract

The invention discloses an emergency response grade determining method and system for a hydrogenation device, wherein the emergency response grade determining method comprises the steps of collecting results generated when an accident of the hydrogenation device occurs in a historical period, taking emergency measures and working data of the device, determining all characteristics of the accident according to the working data, then obtaining an evaluation result which is made based on expert knowledge and respectively represents the importance of the characteristics in the current period and the historical period, obtaining characteristic comprehensive importance according to the reliability degree of the corresponding evaluation result, generating an accident association index, analyzing the types of injury areas corresponding to the accident types of different hydrogenation devices, the influence of the injury ranges and the emergency measures on the severity of the results, generating potential result indexes, predicting the working data of a target hydrogenation device, further combining a fuzzy comprehensive evaluation method, generating an accident situation development index, and determining the emergency response grade according to each index. The invention can accurately acquire the emergency response grade.

Inventors

  • HOU XIAOJING
  • HOU XIAOBO
  • ZHANG GUANGWEN
  • WU GUANJUN
  • MAO WENFENG
  • WANG WEIQIANG

Assignees

  • 中国石油化工股份有限公司
  • 中石化安全工程研究院有限公司

Dates

Publication Date
20260508
Application Date
20241101

Claims (15)

  1. 1. A method for determining an emergency response level for a hydrogenation unit, comprising: Collecting results generated when a hydrogenation device accident occurs in a historical period, taking emergency measures and working data of devices, determining all characteristics causing the accident according to the working data, then obtaining a plurality of first evaluation results representing the characteristic importance of the current period and a plurality of second evaluation results representing the characteristic importance of the historical period, which are made based on expert knowledge, for each characteristic, and evaluating the reliability degree of each evaluation result according to the source of each evaluation result to obtain the characteristic comprehensive importance so as to generate an accident association index representing the comprehensive correlation of each characteristic and the target hydrogenation device accident; Analyzing the types of injury areas and injury ranges corresponding to the different hydrogenation device accident types and the influence of the emergency measures on the severity of the results to generate potential result indexes representing the severity of the target hydrogenation device accident results; Acquiring the change characteristics of the working data to predict the working data of the target hydrogenation device, and further generating an accident situation development index representing the accident development trend of the target hydrogenation device by combining a fuzzy comprehensive evaluation method; and obtaining the emergency response grade of the current target hydrogenation device according to each index.
  2. 2. The emergency response level determination method according to claim 1, wherein the first evaluation result and the second evaluation result are important, non-important, or not, and wherein the step of evaluating the reliability degree of each evaluation result according to the source of each evaluation result to obtain the feature integrated importance includes: configuring a grading value for each evaluation result according to the importance degree; For each feature, marking the grading value of each first evaluation result as a first grading value; And extracting second evaluation results made by expertise with accident influence factors from the plurality of second evaluation results aiming at each feature, marking the grading value of each extracted second evaluation result as a second grading value, further determining the reliability degree of each extracted second evaluation result according to the professional field of the expert making each extracted second evaluation result, carrying out weight assignment on the corresponding second evaluation result according to the reliability degree, and calculating the total grading value to represent the comprehensive importance of each feature to the accident of the target hydrogenation device based on the combination of the first grading value and the second grading value.
  3. 3. The emergency response level determination method according to claim 2, wherein in the step of generating an accident correlation index indicating the comprehensive correlation of each feature with the target hydrogenation unit accident, comprising: And analyzing the correlation degree between each feature and the hydrogenation device accidents by using the working data, further calculating the ratio between the number of correlated accidents and the number of uncorrelated accidents according to each feature, taking the ratio as an accident correlation correction factor for correcting the accident correlation index, and combining the total grading value based on the ratio to obtain the accident correlation index.
  4. 4. The emergency response level determination method according to claim 3, wherein the total score value is calculated using the following expression: Where ZS i denotes a total score value, N denotes a total number of first evaluation results, x denotes a number of first evaluation results, f d denotes a first score value, b 1 and b 2 denote coefficients, respectively, m denotes a total number of first evaluation results and second evaluation results, N denotes the same number as an actual evaluation result among all evaluation results, f j denotes a second score value, w denotes a weight, and i denotes a number of features.
  5. 5. The emergency response level determination method of claim 4, wherein the incident association index is obtained using the following expression: Where S 1 denotes an accident association index, MS i denotes a degree of correlation, C i denotes an accident association correction factor, and M denotes the total number of all features causing an accident.
  6. 6. The method for determining the emergency response level according to any one of claims 1 to 5, wherein the different types of hydrogenation unit accidents include, but are not limited to, fire, explosion and poisoning, and the types of injury areas include, but are not limited to, dead areas, severe injury areas and light injury areas, and the step of analyzing the types of injury areas and the injury ranges corresponding to the different types of hydrogenation unit accidents includes: aiming at each hydrogenation device accident type, the environmental information of the position of the hydrogenation device when the hydrogenation device accident occurs in the historical period is utilized to obtain the injury range corresponding to different injury area types.
  7. 7. The emergency response level determination method of claim 6, wherein in the step of analyzing the impact of the emergency measure on the severity of the outcome, comprising: Based on an AHP algorithm, constructing a hierarchical structure model, evaluating the influence of each emergency measure on the severity of the consequences by analyzing the first relative importance degree of each first evaluation index compared with the severity of the consequences and the second relative importance degree of each second evaluation index compared with each first evaluation index to obtain a first weight for evaluating the first relative importance degree corresponding to each first evaluation index and a second weight for evaluating the second relative importance degree corresponding to each second evaluation index, further obtaining a weight vector for evaluating the relative importance degree of each second evaluation index compared with the severity of the consequences, thereby obtaining a weight coefficient for representing the influence of each evaluation index on the severity of the consequences of the target hydrogenation device, The result severity is used as a target layer element; Taking process control, material isolation, emergency fire protection, regional planning and fire and explosion prevention in the emergency measures as criterion layer elements, and recording as the first evaluation index; sub-emergency measures respectively belonging to the process control, the material isolation, the emergency fire protection, the regional planning and the fire protection and explosion prevention are taken as measure layer elements and are marked as second evaluation indexes.
  8. 8. The emergency response grade determination method of claim 7, wherein in the step of generating a potential outcome index indicative of a severity of a target hydrogenation unit incident outcome, comprising: judging the effectiveness of corresponding emergency measures according to the results, and respectively assigning 1 and 0 to the effective emergency measures and the ineffective emergency measures; Calculating the product of emergency measure assignment and the weight coefficient of the second evaluation index aiming at each second evaluation index, and further calculating the sum of the corresponding product results of all the second evaluation indexes subordinate to the first evaluation index aiming at each first evaluation index, and marking the sum as a first result; And calculating the product of the sum of the first results and the weight coefficient of the first evaluation index aiming at each first evaluation index, marking the product as a second result, further obtaining the sum of all the second results, configuring a corresponding injury degree grading value for each injury region type according to the injury degree based on the sum, and further combining the corresponding injury range to obtain the potential result index.
  9. 9. The emergency response grade determination method according to any one of claims 1 to 8, characterized in that in the step of generating an accident situation development index indicating the accident development trend of the target hydrogenation apparatus, it includes: Corresponding working data ranges are configured according to different possible degrees of accidents of the target hydrogenation device, a fuzzy comprehensive evaluation method is adopted, a correlation between predicted working data and predicted membership states representing the possibility of accidents of the target hydrogenation device is established, membership functions for predicting the possibility of accidents of the target hydrogenation device are obtained, based on the membership functions, the numerical value of the predicted membership states is obtained by utilizing the numerical value of the predicted working data, and then the accident situation development index is obtained.
  10. 10. The emergency response grade determination method of claim 9, wherein the membership function is represented by the following expression: μ(x)=0,x∈[l 1 ,μ 1 ] Wherein μ (x) represents a general state membership function, x represents prediction work data, μ 1l represents a class I low-limit state membership function, μ 1h represents a class I high-limit state membership function, μ 2l represents a class II low-limit state membership function, and μ 2h represents a class II high-limit state membership function.
  11. 11. The emergency response level determination method according to any one of claims 1 to 10, wherein the step of obtaining the change characteristics of the operation data to predict the operation data of the target hydrogenation apparatus includes: Based on the working data, working data of a previous period is used as input information of a preset model, and working data of a next period is used as output information of the preset model, so that a working data prediction model is built through training of the preset model; and predicting the working data of the target hydrogenation device by taking the working data of the target hydrogenation device in the current period as the input information of the working data prediction model to obtain corresponding predicted working data, thereby obtaining the predicted working data.
  12. 12. The emergency response level determining method according to any one of claims 2 to 5, wherein the determining of the reliability degree of each extracted second evaluation result in accordance with the professional field to which the expert who made each extracted second evaluation result belongs includes: If the professional field is a device, judging that the reliability of the extracted second evaluation result is highest; If the professional field is emergency, judging that the reliability of the extracted second evaluation result is moderate; If the professional field is neither device nor emergency, the extracted second evaluation result is judged to have the lowest reliability.
  13. 13. The emergency response level determination method of claim 12, wherein in the process of assigning weights to the respective second evaluation results, comprising: The weight of the second evaluation result with the highest reliability is assigned to be 2; assigning the weight of the second evaluation result with moderate reliability to 1.5; and (5) assigning the weight of the second evaluation result with the lowest reliability to 1.
  14. 14. The emergency response level determining method according to claim 13, wherein in configuring the scoring value for each evaluation result in accordance with the degree of importance, comprising: For the evaluation results, important, non-important and indeterminate whether important, the score values were respectively set to 1 point, 0.5 point and 0 point.
  15. 15. An emergency response level determination system for a hydrogenation unit, the emergency response level determination system comprising: The accident association index acquisition module is used for collecting results generated when the hydrogenation device accident occurs in the historical period, taking emergency measures and working data of the device, determining all characteristics causing the accident according to the working data, then acquiring a plurality of first evaluation results representing the characteristic importance of the current period and a plurality of second evaluation results representing the characteristic importance of the historical period, which are made based on expert knowledge, for each characteristic, evaluating the reliability degree of each evaluation result according to the source of each evaluation result, and obtaining the characteristic comprehensive importance so as to generate an accident association index representing the comprehensive correlation of each characteristic and the target hydrogenation device accident; A potential outcome index acquisition module for analyzing the injury zone types and injury ranges corresponding to the different hydrogenation unit accident types, and the impact of the emergency measure on the severity of the outcome to generate a potential outcome index representing the severity of the target hydrogenation unit accident outcome; The accident situation development index acquisition module is used for acquiring the change characteristics of the working data so as to predict the working data of the target hydrogenation device and further generating an accident situation development index representing the accident development trend of the target hydrogenation device by combining with a fuzzy comprehensive evaluation method; And the emergency response grade determining module is used for obtaining the emergency response grade of the current target hydrogenation device according to each index.

Description

Emergency response grade determining method and system for hydrogenation device Technical Field The invention belongs to the technical field of chemical engineering safety, and particularly relates to an emergency response grade determining method and system for a hydrogenation device. Background The chemical production process is complex, and flammable, explosive or toxic medium is often involved in the reaction process. Once the reaction is out of control, the safety production accident can be caused, and the safety of personnel, property and environment is endangered. In order to solve the problem, early emergency information support in multiple links of chemical production is urgently needed. The chemical accident has the characteristics of sudden occurrence, more uncertain factors, serious accident consequences, large influence range and the like, and the abnormal working condition which appears in the safety operation management of the chemical device is intervened in advance, so that the three-level evolution trend of the abnormality-initial-accident is rapidly and accurately predicted, and the three-level evolution trend is always a difficulty and a hot spot of research. With the rapid development of computer technology, research and application of artificial intelligence deep learning algorithms have also been rapidly developed. In recent years, the deep learning technology is widely applied to the fields of big data analysis, image recognition, language recognition, video analysis and text analysis, and has been very successful. Deep learning is essentially a process that performs feature descriptions. Therefore, the method is based on the deep learning principle to analyze big data, the deep learning technology is adopted to predict the trend of the key response parameters, and the technology can be developed into a novel prediction method. The prior art discloses an emergency response early warning method based on an electric power emergency, which comprises the following steps of selecting a designated area needing to be subjected to electric network data analysis on a GIS electric network data layer, setting a threshold value of a response level, collecting electric network data information, meteorological data information and regional geological disaster information, establishing an emergency response judgment standard for data analysis, judging event types and grades when the judgment standard meets at least one, classifying the event types according to the nature and content of the event, classifying the event types according to the severity of the event, classifying the specific grades, analyzing and judging the influence range of the emergency and equipment facilities of the electric network by combining the topological structure and the spatial geographic information of the electric network, evaluating an optimal scheme and carrying out an emergency plan. The method respectively gives early warning according to the emergency level, the intelligent material allocation improves the disposal efficiency of emergency disposal personnel, and provides powerful support for emergency disposal of emergency, but the emergency response discrimination standard mainly adopts qualitative and semi-quantitative methods, is only applicable to the electrical field, and has extremely strong specialization and limitation. The prior art also discloses a multi-time-sequence-based deep learning dangerous rock deformation prediction method and device, which are mainly characterized in that dangerous rock images are acquired according to a dangerous rock monitoring device, the characteristics of the dangerous rock images are extracted by using a Caffe visualization tool, a AlexNet model established by the dangerous rock images and characteristic labels is trained, the distributed characteristics of the dangerous rock are identified, a multi-time-sequence of the dangerous rock deformation is established by using collected dangerous rock image characteristic data, a plurality of data samples are established, the learning samples are subjected to fitting learning by using a deep learning technology, finally, the prediction data of the plurality of time sequences are subjected to optimization comparison by using a screening program compiled by Matlab software, and a prediction result carried out by the time sequence with the minimum error is output. In addition, the corresponding apparatus is also described in detail. According to the method, deformation images of all time phases of a dangerous rock body are analyzed and processed to obtain sample data, a prediction model is built, so that dangerous rock deformation prediction is automatically and rapidly carried out, accuracy and flexibility in dangerous rock prediction can be embodied, basis can be provided for dangerous rock instability prediction and dangerous rock collapse prediction and prevention and control, and the method is mainly applied to the field of im