Rail transit tunnel gas leakage risk assessment method

Abstract

The application discloses a kind of tunnel gas leakage risks of rail transit, it is related to risk assessment technical field, including the following steps: obtaining the historical failure frequency of each substation sensor in gas monitoring system, and the historical failure frequency is risk calculation processing, obtain the failure risk of each substation in gas monitoring system;Obtain the distance of each substation from target station, and determine the position risk of each substation according to distance;Obtain the historical gas concentration data of each substation sensor, and based on grey prediction model, historical gas concentration data is predicted processing, obtain the predicted gas concentration data of each substation;Based on failure risk, position risk and predicted gas concentration data, using fuzzy comprehensive evaluation method, the gas leakage risk of rail transit tunnel is evaluated and processed, and target risk comprehensive evaluation value is obtained.The method is more accurately evaluated by quantitative analysis gas leakage risk, significantly improve the accuracy of gas accident prediction.

Description

Technical Field

[0001] This invention relates to the field of risk assessment technology, and specifically to a method for assessing the risk of gas leakage in rail transit tunnels. Background Technology

[0002] With the rapid development of urban rail transit systems, safety issues within tunnels have received increasing attention. Gas leakage, as a potentially significant safety risk, especially in underground tunnels, can lead not only to major accidents such as explosions and fires but also pose a significant threat to rail transit operations and the safety of people's lives and property. Therefore, effective risk assessment is crucial for timely prevention and response to gas leakage accidents. The challenges of gas leakage risk assessment lie primarily in two aspects: first, the risk of gas leakage is highly uncertain, influenced by various factors such as tunnel location, gas concentration, and equipment malfunction; second, most existing assessment methods lack dynamism and cannot monitor and assess risks in real time. Therefore, determining an effective quantitative risk assessment method for highly complex and dynamically changing environments is key to improving the safety management level of urban rail transit tunnels.

[0003] Currently, the assessment methods for gas leakage risks in urban rail transit tunnels mainly focus on qualitative analysis, while quantitative risk assessment methods are relatively lacking.

[0004] However, the existing qualitative methods often rely on expert experience for assessment, lacking scientific quantitative standards and making it difficult to accurately predict the probability of gas leaks and the potential consequences of accidents. Furthermore, existing methods generally neglect the influence of complex factors such as environmental factors, changes in gas concentration, and the reliability of monitoring systems. Therefore, determining a method that can consider multiple complex factors and conduct scientific and accurate risk quantification assessments is a pressing problem that needs to be solved. Summary of the Invention

[0005] In view of the above-mentioned shortcomings in the existing technology, the present invention provides a method for assessing the risk of gas leakage in rail transit tunnels. This method solves the problems of the lack of scientific quantitative standards, the difficulty in accurately predicting the probability of gas leakage and the possible consequences of accidents, and the neglect of the influence of complex factors such as environmental factors, gas concentration changes, and the reliability of monitoring systems.

[0006] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows:

[0007] A method for assessing the risk of gas leakage in rail transit tunnels, comprising:

[0008] The historical fault frequency of sensors at each substation in the gas monitoring system is obtained, and the risk calculation is performed on the historical fault frequency to obtain the fault risk of each substation in the gas monitoring system.

[0009] Obtain the distance of each substation from the target station, and determine the location risk of each substation based on the distance;

[0010] Historical gas concentration data of each substation sensor is obtained, and the historical gas concentration data is predicted based on the grey prediction model to obtain the predicted gas concentration data of each substation.

[0011] Based on the aforementioned fault risk, location risk, and predicted gas concentration data, a fuzzy comprehensive evaluation method is used to assess the gas leakage risk in rail transit tunnels, resulting in a comprehensive target risk assessment value.

[0012] Furthermore, the risk calculation processing of the historical fault frequencies to obtain the fault risk of each substation in the gas monitoring system includes:

[0013] The failure risk is calculated using the following formula:

[0014]

[0015] in, For the aforementioned failure risk, For the first i Historical fault frequency of sensors connected to each substation This represents the total number of failures that occurred across all sensors.

[0016] Furthermore, determining the location risk of each substation based on the distance includes:

[0017] When the distance is no greater than a first preset value, the location risk is the first risk;

[0018] When the distance is greater than a first preset value and less than a second preset value, the location risk is the second risk.

[0019] When the distance is greater than the second preset value, the location risk is the third risk.

[0020] Furthermore, before performing prediction processing on the historical gas concentration data based on the grey prediction model to obtain the predicted gas concentration data for each substation, the method further includes:

[0021] The sample dataset corresponding to the historical gas concentration data is determined, and the sample dataset is accumulated once to obtain the accumulated sequence.

[0022] Further, the prediction processing of the historical gas concentration data based on the grey prediction model to obtain the predicted gas concentration data for each substation includes:

[0023] Based on the gray prediction model, a differential equation is established for the sample dataset, and the cumulative sequence is used to replace the differential equation to obtain a difference equation. The coefficients of the differential equation and the difference equation include: development coefficient and gray action quantity.

[0024] The development coefficient and the gray action quantity are solved in matrix form to obtain the target development coefficient and the target gray action quantity. The target development coefficient and the target gray action quantity are then input into the time response function to obtain the prediction function.

[0025] Based on the prediction function, the historical gas concentration data is processed to obtain the predicted gas concentration data for each substation.

[0026] Further, the step of performing prediction processing on the historical gas concentration data based on the prediction function to obtain the predicted gas concentration data for each substation includes:

[0027] The prediction function is solved to obtain the cumulative prediction value;

[0028] The predicted cumulative values ​​are subtracted to obtain the predicted gas concentration data for each substation.

[0029] Furthermore, based on the fault risk, the location risk, and the predicted gas concentration data, a fuzzy comprehensive evaluation method is used to assess the gas leakage risk in the rail transit tunnel, resulting in a comprehensive target risk assessment value, including:

[0030] Membership functions for the fault risk, the location risk, and the predicted gas concentration data are constructed respectively to obtain the fault risk membership function, the location risk membership function, and the predicted gas concentration data membership function.

[0031] The values ​​of the fault risk membership function, the location risk membership function, and the predicted gas concentration data membership function are determined based on historical data. An evaluation matrix is ​​then constructed based on these values, where rows represent evaluation objects and columns represent evaluation criteria.

[0032] The risk of gas leakage in the rail transit tunnel is assessed based on the evaluation matrix to obtain the comprehensive risk assessment value of the target.

[0033] Furthermore, the assessment of the gas leakage risk in the rail transit tunnel based on the evaluation matrix to obtain the comprehensive risk assessment value includes:

[0034] The weights of the fault risk, the location risk, and the predicted gas concentration data are determined based on the historical data, and a weight vector is formed by combining the weights of the fault risk, the location risk, and the predicted gas concentration data.

[0035] The evaluation matrix is ​​multiplied by the weight vector to obtain the comprehensive risk assessment value of the target.

[0036] The beneficial effects of this invention are as follows: This method calculates fault risk, location risk, and predicted gas concentration by acquiring historical fault frequency, distance from the target station, and historical gas concentration data of sensors at each substation in the gas monitoring system. Then, a fuzzy comprehensive evaluation method is used to comprehensively assess the fault risk, location risk, and predicted gas concentration to obtain a comprehensive target risk assessment value, thus completing the assessment of gas leakage risk in rail transit tunnels. It comprehensively considers multiple risk factors, including fault risk, location risk, and predicted gas concentration, providing urban rail transit operators with an effective method and approach for gas tunnel risk assessment. By quantitatively calculating three different risks in gas sections—equipment fault risk, location risk, and concentration risk—and then qualitatively deriving risk values ​​at different locations within the tunnel using fuzzy comprehensive evaluation, it effectively fills a gap in the current field. This not only helps relevant departments accurately assess gas leakage risk but also provides a scientific basis for tunnel construction and operation management, improving the safety and emergency response capabilities of urban rail transit systems, significantly enhancing the accuracy of gas accident prediction and prevention, reducing potential safety hazards, ensuring the smooth operation of urban rail transit, and providing strong protection for public travel safety. Attached Figure Description

[0037] Figure 1 This is a flowchart illustrating the method. Detailed Implementation

[0038] The specific embodiments of the present invention are described below to enable those skilled in the art to understand the present invention. However, it should be understood that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, various changes are obvious as long as they are within the spirit and scope of the present invention as defined and determined by the appended claims. All inventions utilizing the concept of the present invention are protected.

[0039] like Figure 1 As shown, the method for assessing the risk of gas leakage in this rail transit tunnel includes the following steps:

[0040] S1. Obtain the historical fault frequency of the sensor at each substation in the gas monitoring system, and perform risk calculation processing on the historical fault frequency to obtain the fault risk of each substation in the gas monitoring system.

[0041] Among them, the sensor can be a gas concentration monitoring sensor, and the substation can be formed by dividing the gas tunnel into sections according to the sensor access location. The number of sensors in each substation can be, for example, 5-15, without specific restrictions, and can be flexibly selected according to the actual situation.

[0042] S2. Obtain the distance of each substation from the target station, and determine the location risk of each substation based on the distance;

[0043] The target station can be, for example, the actual station around the tunnel corresponding to the substation formed by the sensor. The location risk is determined according to the distance of the substation from the target station. When some substations are located between two target stations, the distance of the nearest station is selected for calculation.

[0044] S3. Obtain historical gas concentration data from the sensors at each substation, and perform prediction processing on the historical gas concentration data based on the grey prediction model to obtain predicted gas concentration data for each substation.

[0045] Among them, the predicted gas concentration data can be, for example, the predicted average gas concentration of all sensors in the substation. This predicted average gas concentration can be used as the gas concentration risk data of the substation. The grey prediction model can be, for example, the GM(1,1) model in the generalized grey prediction model.

[0046] S4. Based on the fault risk, the location risk, and the predicted gas concentration data, the fuzzy comprehensive evaluation method is used to assess the gas leakage risk of the rail transit tunnel and obtain the target risk comprehensive evaluation value.

[0047] This embodiment provides a method for assessing the risk of gas leakage in rail transit tunnels. This method calculates fault risk, location risk, and predicted gas concentration by acquiring historical fault frequencies, distances from the target station, and historical gas concentration data from sensors at each substation in the gas monitoring system. A fuzzy comprehensive evaluation method is then used to comprehensively assess these factors, yielding a target risk comprehensive assessment value to complete the assessment of gas leakage risk in the rail transit tunnel. This method comprehensively considers multiple risk factors, including fault risk, location risk, and predicted gas concentration, providing urban rail transit operators with an effective method and approach for assessing gas tunnel risks. By quantitatively calculating three different risks in gas sections—equipment fault risk, location risk, and concentration risk—and then qualitatively deriving risk values ​​at different locations within the tunnel using fuzzy comprehensive evaluation, it effectively fills a gap in the current field. This not only helps relevant departments accurately assess gas leakage risks but also provides a scientific basis for tunnel construction and operation management, improving the safety and emergency response capabilities of urban rail transit systems, significantly enhancing the accuracy of gas accident prediction and prevention, reducing potential safety hazards, ensuring the smooth operation of urban rail transit, and providing strong protection for public travel safety.

[0048] In one possible implementation, risk calculation is performed on the historical failure frequency to obtain the failure risk of each substation in the gas monitoring system, including:

[0049] The failure risk is calculated using the following formula:

[0050]

[0051] in, For the risk of failure, For the first i Historical fault frequency of sensors connected to each substation This represents the total number of failures that occurred across all sensors.

[0052] In one possible implementation, the location risk of each substation is determined based on distance, including:

[0053] When the distance is no greater than the first preset value, the location risk is the first risk;

[0054] When the distance is greater than the first preset value and less than the second preset value, the location risk is the second risk.

[0055] When the distance is greater than the second preset value, the location risk is classified as the third risk.

[0056] The first preset value can be, for example, 500 meters, the second preset value can be, for example, 1500 meters, the risk value of the first risk can be, for example, 0.8, the risk value of the second risk can be, for example, 0.5, and the risk value of the third risk can be, for example, 0.2.

[0057] Understandably, the closer the substation is to the target station, the higher the risk; the farther the substation is from the target station, the lower the risk.

[0058] In one possible implementation, before obtaining the predicted gas concentration data for each substation by performing prediction processing on historical gas concentration data based on a grey prediction model, the method further includes:

[0059] Determine the sample dataset corresponding to the historical gas concentration data, and perform an accumulation generation process on the sample dataset to obtain the accumulation sequence.

[0060] Predictive processing of historical gas concentration data can be exemplified by daily prediction, where gas concentration data from a sensor over the past week or days is used to predict the gas concentration for the next week or days. Alternatively, it can involve determining the prediction time granularity based on a data sample or as needed, thus establishing an original sample dataset. This sample dataset could, for example, be: , where n is the number of sample points, and , For the sample dataset, the first n Individual gas concentration data.

[0061] The sample dataset can be accumulated and generated using, for example, the following formula:

[0062]

[0063] in, For the sample dataset, the first k The accumulated values ​​of gas concentration data can be summed to obtain an accumulated sequence, for example:

[0064]

[0065] in, This is the accumulated value of the first gas concentration data in the sample dataset. This is the cumulative value of the second gas concentration data in the sample dataset. For the sample dataset, the first k The cumulative value of gas concentration data.

[0066] In one possible implementation, historical gas concentration data is processed based on a grey prediction model to obtain predicted gas concentration data for each substation, including:

[0067] A differential equation for the sample dataset is established based on the grey prediction model, and the cumulative sequence is used to replace the differential equation to obtain the difference equation. The coefficients of the differential equation and the difference equation include the development coefficient and the grey action quantity.

[0068] The differential equation can be, for example, as follows:

[0069]

[0070] in, a It is the development coefficient. b It is the gray action quantity. This represents the cumulative sequence of the gas concentration data sample dataset.

[0071] The difference equation can be, for example:

[0072]

[0073] in, yes background value, Represents the sequence of the original sample dataset. n It is the number of sample points. k This means greater than or equal to 1 and less than or equal to 1. n- A positive integer equal to 1.

[0074] For example, it can be represented as:

[0075]

[0076] The development coefficient and gray action are solved in matrix form to obtain the target development coefficient and target gray action. The target development coefficient and target gray action are then input into the time response function to obtain the prediction function.

[0077] The development coefficient and gray action quantity can be solved in matrix form, for example, as follows:

[0078]

[0079] in, Y This is a matrix of gas concentration data. B The background value matrix, Given the development coefficient and grey action matrix, the linear equations derived from this matrix regarding the development coefficient and grey action are as follows: The solution to this linear equation is the development coefficient and the gray action quantity.

[0080] The time response function can be, for example:

[0081]

[0082] in, e is the base of the natural logarithm. e The value is 2.718.

[0083] Based on the prediction function, the historical gas concentration data is processed to obtain the predicted gas concentration data for each substation.

[0084] In one possible implementation, historical gas concentration data is processed based on a prediction function to obtain predicted gas concentration data for each substation, including:

[0085] The prediction function is solved to obtain the cumulative prediction value;

[0086] The predicted cumulative values ​​are subtracted to obtain the predicted gas concentration data for each substation.

[0087] For example, the predicted gas concentration data could be:

[0088]

[0089] In one possible implementation, based on fault risk, location risk, and predicted gas concentration data, a fuzzy comprehensive evaluation method is used to assess the gas leakage risk in rail transit tunnels, obtaining a comprehensive target risk assessment value, including:

[0090] Membership functions for fault risk, location risk, and predicted gas concentration data are constructed respectively, resulting in the fault risk membership function, location risk membership function, and predicted gas concentration data membership function.

[0091] The membership function can be a value from 0 to 1, representing the degree to which an object meets a certain standard. For example, the membership functions of the location risk membership function based on the above location risk have membership values ​​of 0.8, 0.5, and 0.2 for different standards.

[0092] Based on historical data, the values ​​of the membership functions for fault risk, location risk, and predicted gas concentration are determined respectively. An evaluation matrix is ​​then constructed based on these values, with rows representing evaluation objects and columns representing evaluation criteria.

[0093] Historical data can be, for example, historical data rules or historical data experience values.

[0094] The risk of gas leakage in rail transit tunnels is assessed based on the evaluation matrix, and the comprehensive risk assessment value is obtained.

[0095] In one possible implementation, the risk of gas leakage in rail transit tunnels is assessed based on an evaluation matrix to obtain a comprehensive target risk assessment value, including:

[0096] The weights of fault risk, location risk, and predicted gas concentration data are determined based on historical data, and a weight vector is formed by combining these weights.

[0097] The weights reflect the contribution of each evaluation criterion to the overall evaluation.

[0098] The evaluation matrix and the weight vector are multiplied to obtain the comprehensive risk assessment value of the target.

[0099] The comprehensive risk assessment value can be obtained, for example, using the following formula:

[0100]

[0101] in, C To make a comprehensive evaluation, R For the evaluation matrix, W This is the weight vector.

[0102] This method quantitatively assesses the reliability of gas detection systems in each section using historical sensor failure frequency data. Based on grey system theory, a grey prediction model is constructed, using historical gas concentration data as a key indicator to predict the risk level of gas leakage. Considering the differences in distance between different gas sections and station locations, the impact of leakage varies. Therefore, the model conducts location risk assessments for different inter-station sections to provide more accurate safety assurance. Finally, a fuzzy comprehensive evaluation method is used to assess the overall risk of gas leakage, obtaining a specific target risk comprehensive assessment value. This method combines qualitative and quantitative analysis, comprehensively considering multiple risk factors. It provides urban rail transit operators with an effective method and approach for gas tunnel risk assessment, overcoming the problems of lacking scientific quantitative standards for gas leakage risk, difficulty in accurately predicting the probability of gas leakage and the potential consequences of accidents, and the general neglect of the impact of complex factors such as environmental factors, gas concentration changes, and monitoring system reliability on gas leakage risk. It provides a method that can consider multiple complex factors and conduct scientific and accurate risk quantification assessment.

[0103] To better support the accuracy of the comprehensive risk assessment value of this application, the following is a practical case verification process provided by this application:

[0104] Based on the sensor fault log and gas concentration data monitored by the sensors during a six-month operation period of a subway tunnel, the fault risks of the three substations are 0.3, 0.2, and 0.5, respectively; the location risks are 0.8, 0.5, and 0.2, respectively; and the predicted gas concentration values ​​are 0.2, 0.6, and 0.4, respectively. Based on the actual situation and historical data, the weights of the three evaluation indicators—fault risk, location risk, and gas concentration data risk—are 1, 2, and 7, respectively. Therefore, the evaluation matrix is ​​as follows:

[0105]

[0106] The weight vector is:

[0107]

[0108] The overall risk assessment value is:

[0109]

[0110] The comprehensive risk assessment values ​​for these three substations are 3.3, 5.4, and 3.7, respectively. Based on the actual situation, these risk assessment values ​​are relatively accurate.

Claims

1. A method for evaluating the risk of gas leakage in a rail transit tunnel, characterized in that, The method comprises the following steps: obtaining historical failure frequency of each substation sensor in a gas monitoring system, and performing risk calculation processing on the historical failure frequency to obtain failure risk of each substation in the gas monitoring system; obtaining distance of each substation from a target station, and determining position risk of each substation according to the distance; obtaining historical gas concentration data of each substation sensor, and performing prediction processing on the historical gas concentration data based on a grey prediction model to obtain predicted gas concentration data of each substation; based on the failure risk, the position risk and the predicted gas concentration data, performing evaluation processing on the gas leakage risk of the rail transit tunnel by using a fuzzy comprehensive evaluation method to obtain a target risk comprehensive evaluation value; before the step of performing prediction processing on the historical gas concentration data based on the grey prediction model to obtain the predicted gas concentration data of each substation, the method further comprises the following steps: determining a sample data set corresponding to the historical gas concentration data, and performing one-time accumulation generation processing on the sample data set to obtain an accumulated sequence; the step of performing prediction processing on the historical gas concentration data based on the grey prediction model to obtain the predicted gas concentration data of each substation comprises the following steps: establishing a differential equation of the sample data set based on the grey prediction model, and replacing the differential equation with the accumulated sequence to obtain a difference equation, wherein coefficients of the differential equation and the difference equation comprise a development coefficient and a grey action amount; solving the development coefficient and the grey action amount in a matrix form to obtain a target development coefficient and a target grey action amount, and inputting the target development coefficient and the target grey action amount into a time response function to obtain a prediction function; performing prediction processing on the historical gas concentration data based on the prediction function to obtain predicted gas concentration data of each substation.

2. The method of claim 1, wherein, the step of performing risk calculation processing on the historical failure frequency to obtain the failure risk of each substation in the gas monitoring system comprises the following steps: the failure risk is calculated by using the following formula: wherein, is the failure risk, is the failure risk, i is the historical failure frequency of the access sensor of the i-th substation, represents the total number of failures occurred by all sensors.

3. The method of claim 1, wherein, the step of determining the position risk of each substation according to the distance comprises the following steps: when the distance is not greater than a first preset value, the position risk is a first risk; when the distance is greater than the first preset value and less than a second preset value, the position risk is a second risk; when the distance is greater than the second preset value, the position risk is a third risk.

4. The method of claim 1, wherein, the step of performing prediction processing on the historical gas concentration data based on the prediction function to obtain predicted gas concentration data of each substation comprises the following steps: solving the prediction function to obtain a predicted accumulated value; performing accumulation reduction processing on the predicted accumulated value to obtain the predicted gas concentration data of each substation.

5. The method of claim 1, wherein, the step of performing evaluation processing on the gas leakage risk of the rail transit tunnel by using the fuzzy comprehensive evaluation method based on the failure risk, the position risk and the predicted gas concentration data to obtain a target risk comprehensive evaluation value comprises the following steps: Membership functions of the failure risk, the position risk and the predicted gas concentration data are constructed respectively to obtain a failure risk membership function, a position risk membership function and a predicted gas concentration data membership function; Values of the failure risk membership function, values of the position risk membership function and values of the predicted gas concentration data membership function are determined according to historical data, and a judgment matrix is constructed based on the values of the failure risk membership function, the values of the position risk membership function and the values of the predicted gas concentration data membership function, wherein rows in the judgment matrix represent judgment objects and columns represent judgment standards; The rail transit tunnel gas leakage risk is evaluated based on the judgment matrix to obtain the target risk comprehensive evaluation value.

6. The method of claim 5, wherein, The evaluation of the rail transit tunnel gas leakage risk based on the judgment matrix to obtain the target risk comprehensive evaluation value comprises: Weights of the failure risk, weights of the position risk and weights of the predicted gas concentration data are determined according to the historical data, and the weights of the failure risk, the weights of the position risk and the weights of the predicted gas concentration data are combined into a weight vector; The judgment matrix is multiplied by the weight vector to obtain the target risk comprehensive evaluation value.

Images