A tunnel ventilation scheme optimization method and system

Abstract

The present invention discloses a method and system for optimizing a tunnel ventilation scheme, the method comprising: acquiring real-time environmental data and fan operating parameter data in a tunnel, classifying them, and obtaining discrimination data and initial data; comparing the discrimination data with preset tunnel specifications and standards; if the limit is exceeded, obtaining the calculated values ​​of environmental indicators at preset monitoring points in the tunnel through computer simulation tests based on the initial data, and performing error analysis; if the error analysis result meets the preset threshold requirements, formulating several initial fan parameter schemes, continuing to perform computer simulation tests, and obtaining N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points; obtaining a relationship matrix between N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points, solving it, and obtaining the optimization result of the tunnel ventilation scheme; the present invention avoids the subjective influence of human factors on the ventilation scheme, so as to adapt to different emergencies and ensure a safe tunnel operation environment.

Description

Technical Field

[0001] The present invention belongs to the technical field of tunnel operation ventilation, and in particular relates to a tunnel ventilation scheme optimization method and system. Background Art

[0002] In recent years, with the advancement of highway tunnel operation ventilation theory and technology, highway tunnel ventilation operation safety is an important topic; due to the special internal structure of the tunnel, the long-term retention of harmful gases in the tunnel will have an adverse effect on the health of personnel; at the same time, the tunnel emergency plan has a slow response speed and a long time to emergency situations, which seriously threatens the life safety of personnel; therefore, how to quickly and effectively deal with emergencies in the tunnel operation ventilation process has always attracted the attention of researchers; at present, the tunnel operation ventilation plan often adopts a graded classification method, and different fan operating parameters are selected for different tunnel ventilation levels; although this method is relatively simple and easy to operate, it lacks a systematic, accurate and reasonable ventilation plan, which can be summarized as follows:

[0003] First, the air quality inside the tunnel is affected by many factors, including traffic volume, vehicle type, tunnel length, temperature and humidity inside the tunnel, etc. Therefore, the air quality inside the tunnel is different for different tunnel types and in different time periods of the same tunnel. It is difficult to adapt to different tunnel internal environments and lack of systematicity and specificity to formulate ventilation plans only by using the graded method.

[0004] Secondly, the ventilation plan formulated using the graded classification method does not formulate a reasonable optimal plan for different tunnel emergencies. It is greatly affected by subjective factors and lacks theoretical verification. The accuracy and rationality of the ventilation plan need to be discussed, so a more reasonable ventilation optimization plan needs to be proposed.

[0005] Third, the existing method of grading ventilation schemes cannot make timely adjustments to sudden situations inside the tunnel, has a long response time, and lacks real-time performance. In the face of sudden situations, the fan power may be too high or insufficient. If the fan power is excessive, it will cause energy waste. If the fan power is insufficient, it cannot meet the ventilation needs of the tunnel under sudden situations. Therefore, the optimization problem of ventilation schemes for different sudden situations needs to be solved urgently. Summary of the invention

[0006] In view of the technical problems existing in the prior art, the present invention provides a tunnel ventilation scheme optimization system and method to solve the shortcomings of the existing tunnels using grade classification to select operational ventilation schemes, which has poor ventilation effect and long response time when encountering emergencies; and the use of grade classification to select operational ventilation schemes is too simple for classifying emergencies, and the fan operation scheme is single, which cannot effectively provide different ventilation optimization schemes for different emergencies.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is:

[0008] The present invention provides a method for optimizing a tunnel ventilation scheme, which is characterized by comprising:

[0009] Obtain real-time environmental data and fan operating parameter data in the tunnel;

[0010] Classifying the real-time environmental data and wind turbine operating parameter data in the tunnel to obtain discrimination data and initial data;

[0011] Comparing the identified data with preset tunnel specifications and standards;

[0012] If the value of a certain environmental indicator in the discrimination data exceeds the limit value of the preset tunnel specification standard, then according to the initial data, through a first computer simulation test, a calculated value of the environmental indicator at a preset monitoring point in the tunnel is obtained;

[0013] Performing error analysis on the calculated value of the environmental index at the preset monitoring point in the tunnel and the real-time monitoring value of the environmental index to obtain an error analysis result;

[0014] If the error analysis result meets the preset threshold requirement, N groups of initial proposed fan parameter schemes are formulated within the value space of the fan parameters; for each group of initial proposed fan parameter schemes, a second computer simulation test is performed to obtain N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points;

[0015] Obtaining a relationship matrix between the N groups of initial fan parameters and the calculated values ​​of environmental indicators at the N groups of preset monitoring points by a polynomial fitting method;

[0016] The relationship matrix is ​​solved by using a multi-objective genetic algorithm to obtain the optimal fan parameters, that is, the optimization result of the tunnel ventilation scheme is obtained.

[0017] Furthermore, the real-time environmental data in the tunnel include wind speed and direction data at the tunnel entrance, temperature data in the tunnel, harmful gas concentration data in the tunnel, smoke concentration data in the tunnel, dust concentration data in the tunnel, size information of vehicles to be passed through the tunnel, and position information of vehicles passing through the tunnel; the fan operation parameter data include real-time operation parameters of the fan in the tunnel;

[0018] Among them, the discrimination data includes temperature data in the tunnel, harmful gas concentration data in the tunnel, smoke concentration data in the tunnel and dust concentration data in the tunnel; the initial data includes wind speed and direction data at the tunnel entrance, size information of vehicles to pass through the tunnel, position information of vehicles passing through the tunnel and real-time operating parameters of the fan in the tunnel.

[0019] Furthermore, according to the initial data, the process of obtaining the calculated value of the environmental index at the preset monitoring point in the tunnel through a first computer simulation test is as follows:

[0020] Construct a tunnel fluid space model;

[0021] According to the tunnel fluid space model, empirical parameters in the fluid control equation and the turbulence model equation are corrected by historical tunnel data to obtain the fluid control equation and the turbulence model equation of the tunnel fluid space model;

[0022] According to the initial data, the fluid control equation and the turbulence model equation of the tunnel fluid space model are solved to obtain the calculated value of the environmental index at the preset monitoring point in the tunnel.

[0023] Furthermore, the fluid control equation of the tunnel fluid space model is:

[0024]

[0025] Where ρ is the fluid density; is the calculated value of the environmental index at the preset monitoring point in the tunnel, that is, the physical quantity to be solved; is the transport coefficient of the physical quantity to be solved; is the source term of the physical quantity to be solved;

[0026] The turbulence model equation of the tunnel fluid space model is the Standard k-ε equation:

[0027] Among them, the k equation is:

[0028]

[0029] The ε equation is:

[0030]

[0031]

[0032] Where ρ is the fluid density; k is the turbulence coefficient; t is the time; u i is the velocity component of the fluid; x i 、x j is the distance component; t is the time; G k is the turbulent kinetic energy generated by the average velocity gradient of the fluid; G b is the turbulent kinetic energy generated by the buoyancy of the fluid; ε is the kinetic energy dissipation rate of the turbulent flow; Y M is the effect of wave expansion in compressible turbulence on the overall dissipation rate; C 1ε , C 2ε , C 3ε , σ k , σ ε are all constants; S k , S ε A user-defined source item.

[0033] Furthermore, the error analysis result is:

[0034]

[0035] Among them, J is the error analysis result; A1 is the real-time monitoring value of the environmental index; A2 is the calculated value of the environmental index at the preset monitoring point in the tunnel.

[0036] Further, if the error analysis result meets the preset threshold requirement, N groups of initial proposed fan parameter schemes are formulated within the value space of the fan parameters; for each group of initial proposed fan parameter schemes, a second computer simulation test is performed to obtain N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points, as follows:

[0037] By using the random vector method, N groups of fan operating parameter combination schemes are formulated in the parameter value space of fans at different positions in the tunnel; the fan operating parameter combination scheme is the initial proposed fan parameter scheme;

[0038] Construct a tunnel fluid space model;

[0039] According to the tunnel fluid space model, empirical parameters in the fluid control equation and the turbulence model equation are corrected by historical tunnel data to obtain the fluid control equation and the turbulence model equation for determining the tunnel fluid space model;

[0040] According to each combination of the fan operating parameters, the fluid control equations and the turbulence model equations of the tunnel fluid space model are solved respectively to obtain N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points.

[0041] Furthermore, the relationship matrix between the N groups of initial fan parameters and the calculated values ​​of environmental indicators at the N groups of preset monitoring points is:

[0042]

[0043] Among them, y i is the calculated value of the environmental index at the i-th preset monitoring point; a i , b i 、c i d i 、f i are the coefficients of the i-th higher-order terms respectively; is the nth order term of the mth initial fan parameter.

[0044] Furthermore, the objective function of the multi-objective genetic algorithm is:

[0045]

[0046] Where fitness(I) is the objective function of the multi-objective genetic algorithm; w k is the weight of the kth optimization objective, that is, the weight of the kth wind turbine parameter to be optimized; f k (I) is the optimal value of the kth optimization objective.

[0047] The present invention also provides a tunnel ventilation scheme optimization system, comprising:

[0048] Real-time data acquisition unit, used to obtain real-time environmental data and fan operating parameter data in the tunnel;

[0049] A data processing unit, used for classifying the real-time environmental data and wind turbine operating parameter data in the tunnel to obtain discrimination data and initial data;

[0050] A computer test unit is used to compare the discrimination data with a preset tunnel specification standard; if the value of a certain environmental indicator in the discrimination data exceeds the limit value of the preset tunnel specification standard, then according to the initial data, through a simulation test, a calculated value of the environmental indicator at a preset monitoring point in the tunnel is obtained; an error analysis is performed on the calculated value of the environmental indicator at the preset monitoring point in the tunnel and the real-time monitoring value of the environmental indicator to obtain an error analysis result; if the error analysis result meets the preset threshold requirement, then within the value space of the fan parameter, N groups of initial proposed fan parameter schemes are formulated; for each group of initial proposed fan parameter schemes, a second computer simulation test is performed to obtain N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points; a relationship matrix between the N groups of initial fan parameters and the calculated values ​​of environmental indicators at preset monitoring points is obtained through a polynomial fitting method; a multi-objective genetic algorithm is used to solve the relationship matrix to obtain the optimal fan parameters, that is, to obtain the optimization result of the tunnel ventilation scheme;

[0051] An intelligent operation unit, used for transmitting the optimization result of the tunnel ventilation scheme to a fan control system;

[0052] The fan control system is used to respond to the optimization result of the tunnel ventilation plan and correct the operating parameters of the fan in the tunnel.

[0053] Furthermore, the real-time data acquisition unit includes a tunnel operation environment monitoring instrument, a vehicle-mounted GPS positioning system, a tunnel video monitoring system, and a fan parameter acquisition module;

[0054] The tunnel operation environment detection instrument comprises an anemometer (1), a temperature sensor (6) and a gas concentration sensor (7); the anemometer (1) is arranged at the tunnel entrance and is used to obtain wind speed and direction data at the tunnel entrance; the temperature sensor (6) is arranged at intervals along the tunnel axis and is located on the tunnel side wall and is used to obtain temperature data in the tunnel; the gas concentration sensor (7) is arranged at intervals along the tunnel axis and is located on the tunnel side wall and is used to obtain harmful gas concentration data, smoke concentration data and dust concentration data in the tunnel;

[0055] The vehicle-mounted GPS positioning system is used to obtain the position information of vehicles passing through the tunnel;

[0056] The tunnel video monitoring system is arranged at the entrance of the tunnel; it is used to obtain the license plate information of the vehicle to be passed through the tunnel, and obtain the size information of the vehicle to be passed through the tunnel through the license plate information;

[0057] The fan parameter acquisition module is used to obtain fan operating parameter data from the tunnel fan control system.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The present invention provides a tunnel ventilation scheme optimization direction and system. According to the real-time environmental data in the tunnel and the fan operating parameter data, the ventilation scheme is randomly simulated through computer simulation test results, and the optimal scheme is obtained through a multi-objective genetic algorithm. The subjective influence of human factors on the ventilation scheme is avoided to the greatest extent, so as to adapt to different emergency situations and effectively shorten the execution response time of the optimal ventilation scheme after the emergency occurs.

[0060] Furthermore, computer simulation tests were performed to solve the calculated values ​​of environmental indicators at preset monitoring points in the tunnel, and the accuracy of the test results was verified by the environmental indicator data obtained through monitoring, thereby establishing a computer simulation test that is consistent with the actual tunnel operation ventilation process, and obtaining an accurate relationship matrix to optimize the ventilation plan.

[0061] Furthermore, the random vector method is used to globally select ventilation schemes within the value space of fan parameters, that is, to formulate initial fan parameters, which effectively avoids the situation where artificial scheme formulation is prone to local data loss and insufficient global parameter accuracy. The scheme formulated using the random vector method is more random and comprehensive than that formulated manually.

[0062] Furthermore, by using a multi-objective genetic algorithm for rapid optimization, the optimal plan can be quickly formulated for the monitoring point data in multiple areas, and the plan can be transmitted to the wind turbine control system via optical cable to perform wind turbine parameter correction, achieving rapid response time and automatic data transmission, thereby saving human resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A flow chart of the tunnel ventilation scheme optimization method according to the present invention;

[0064] Figure 2 It is a structural block diagram of the tunnel ventilation scheme optimization system of the present invention;

[0065] Figure 3 This is a structural diagram of the tunnel ventilation scheme optimization system layout described in the present invention.

[0066] Among them, A real-time data acquisition unit, B data processing unit, C computer test unit, D intelligent operation unit; 1 wind speed and direction meter, 2 vehicle-mounted GPS positioning system, 3 infrared identification monitoring instrument, 4 fan control system, 5 tunnel optical cable, 6 temperature sensor, 7 gas concentration sensor, 8 supercomputer. DETAILED DESCRIPTION

[0067] In order to make the technical problems, technical solutions and beneficial effects solved by the present invention more clearly understood, the present invention is further described in detail in the following specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0068] As attached Figure 1 As shown, the present invention provides a method for optimizing a tunnel ventilation scheme, comprising the following steps:

[0069] Step 1, obtaining real-time environmental data and fan operating parameter data in the tunnel; wherein the real-time environmental data includes wind speed and direction data at the tunnel entrance, temperature data in the tunnel, harmful gas concentration data in the tunnel, smoke concentration data in the tunnel, dust concentration data in the tunnel, size information of vehicles to pass through the tunnel, and position information of vehicles passing through the tunnel; the fan operating parameter data includes real-time operating parameters of the fan in the tunnel.

[0070] Step 2: classify the real-time environmental data and the fan operating parameter data in the tunnel to obtain discrimination data and initial data; wherein the discrimination data includes temperature data in the tunnel, harmful gas concentration data in the tunnel, smoke concentration data in the tunnel, and dust concentration data in the tunnel; the initial data includes wind speed and direction data at the tunnel entrance, size information of vehicles to pass through the tunnel, location information of vehicles passing through the tunnel, and real-time operating parameters of the fan in the tunnel.

[0071] Step 3: Compare the judgment data with the preset tunnel specification standard to check whether the data is abnormal; if normal, that is, if the values ​​of all environmental standards of the judgment data are within the limit range of the preset tunnel specification standard, return to step 1 and continue to collect data; otherwise, execute step 4.

[0072] Step 4: If the value of a certain environmental indicator in the judgment data exceeds the limit value of the preset tunnel specification standard, then based on the initial data, a calculated value of the environmental indicator at a preset monitoring point in the tunnel is obtained through a first computer simulation test; wherein the environmental indicator at the preset monitoring point in the tunnel is of the same type as the environmental indicator whose value exceeds the limit in the judgment data.

[0073] In the present invention, the harmful gas concentration data at a preset monitoring point B in a tunnel and the abnormal temperature data at a preset monitoring point C in the tunnel are taken as an example; wherein, according to the initial data, the process of obtaining the calculated value of the environmental index at the preset monitoring point in the tunnel through a first computer simulation test is as follows:

[0074] Step 41: construct a tunnel fluid space model using a preset programming language; and divide the tunnel fluid space model into a plurality of grids using a finite element method.

[0075] Step 42: According to the tunnel fluid space model, the empirical parameters in the fluid control equation and the turbulence model equation are corrected by using historical tunnel data to obtain the fluid control equation and the turbulence model equation of the tunnel fluid space model; wherein the fluid control equation of the tunnel fluid space model is:

[0076]

[0077] Where ρ is the fluid density; is the calculated value of the environmental index at the preset monitoring point in the tunnel, that is, the physical quantity to be solved; is the transport coefficient of the physical quantity to be solved; is the source term of the physical quantity to be solved;

[0078] The turbulence model equation of the tunnel fluid space model is the Standard k-ε equation:

[0079] Among them, the k equation is:

[0080]

[0081] The ε equation is:

[0082]

[0083]

[0084] Where ρ is the fluid density; k is the turbulence coefficient; t is the time; u i is the velocity component of the fluid; x i 、x j is the distance component; t is the time; G k is the turbulent kinetic energy generated by the average velocity gradient of the fluid; G b is the turbulent kinetic energy generated by the buoyancy of the fluid; ε is the kinetic energy dissipation rate of the turbulent flow; Y M is the effect of wave expansion in compressible turbulence on the overall dissipation rate; C 1ε , C 2ε , C 3ε , σ k , σ ε are all constants; S k , S ε User-defined source terms, such as heat source terms and mass source terms.

[0085] Step 43: Solve the fluid control equation and the turbulence model equation of the tunnel fluid space model according to the initial data to obtain the calculated values ​​of the environmental indicators at the preset monitoring points in the tunnel; specifically, use the initial data as the initial conditions of the tunnel fluid space model after grid division, solve the fluid control equation and the turbulence model equation, and obtain the harmful gas concentration data of preset monitoring points A, B, C and D in the tunnel and the temperature data in the tunnel.

[0086] Step 5: Perform error analysis on the calculated value of the environmental indicator at the preset monitoring point in the tunnel and the real-time monitoring value of the environmental indicator to obtain an error analysis result; specifically, the error analysis result is calculated by dividing the absolute value of the difference between the calculated value of the environmental indicator at the preset monitoring point in the tunnel and the real-time monitoring value of the environmental indicator by the real-time monitoring value of the environmental indicator; wherein the error analysis result is:

[0087]

[0088] Among them, J is the error analysis result; A1 is the real-time monitoring value of the environmental index; A2 is the calculated value of the environmental index at the preset monitoring point in the tunnel.

[0089] Step 6. If the error analysis result meets the preset threshold requirement, a random vector method is used to formulate N groups of fan operating parameter combination schemes within the fan parameter value space; the fan operating parameter combination scheme is the initial proposed fan parameter scheme; for each group of fan operating parameter combination schemes, a second computer simulation test is performed to obtain N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points; if the error analysis result does not meet the preset threshold requirement, return to step 4, and re-obtain the calculated values ​​of environmental indicators at preset monitoring points in the tunnel by adjusting the fluid control equations and the empirical parameters in the turbulence model equations of the tunnel fluid space model.

[0090] The process of the second computer simulation test is similar to that of the first computer simulation test, except that the initial proposed fan parameter scheme of each group is used to replace the real-time operating parameters of the fans in the tunnel in the first computer simulation test, as follows:

[0091] Construct a tunnel fluid space model;

[0092] Determining the fluid control equation and turbulence model equation of the tunnel fluid space model according to the tunnel fluid space model;

[0093] According to each set of the initially proposed fan parameter schemes, the fluid control equations and the turbulence model equations of the tunnel fluid space model are solved respectively to obtain N sets of initial fan parameters and N sets of calculated values ​​of environmental indicators at preset monitoring points.

[0094] Step 7: Obtain a relationship matrix between the N groups of initial fan parameters and the N groups of calculated values ​​of environmental indicators at preset monitoring points by a polynomial fitting method; wherein the relationship matrix between the N groups of initial fan parameters and the N groups of calculated values ​​of environmental indicators at preset monitoring points is:

[0095] [Z]=[k][P]

[0096] Among them, Z is the environmental index to be optimized, k is the high-order term coefficient, and P is the high-order term of fan pressure.

[0097] Specifically:

[0098]

[0099] Among them, y i is the calculated value of the environmental index at the i-th preset monitoring point; a i , b i 、c i d i 、f i are the coefficients of the i-th higher-order terms respectively; is the nth order term of the mth initial fan parameter.

[0100] Step 8: Using a multi-objective genetic algorithm, the relationship matrix is ​​solved to obtain the optimal fan parameters, that is, the optimization result of the tunnel ventilation scheme is obtained.

[0101] Before solving the relationship matrix using the multi-objective genetic algorithm, the relationship matrix is ​​converted to obtain the relationship equation of gas concentration-fan pressure and the relationship equation of temperature-fan pressure, that is, the solution of the relationship matrix is ​​converted into the solution of the above mathematical equations; the conversion process is as follows:

[0102] In the present invention, the random vector method is used to formulate N groups of initial fan parameter combination schemes within the fan parameter value space, and the harmful gas concentration at the preset monitoring point B and the temperature at the preset monitoring point C are obtained by performing a computer simulation test again, thereby obtaining schemes A, B, C, D, E, ...; the details are as shown in Table 1:

[0103] Table 1 Proposed N groups of initial fan parameter combination schemes

[0104]

[0105] Establishing a first polynomial and a second polynomial according to a relationship matrix between the N groups of initial fan parameters and the calculated values ​​of environmental indicators at the N groups of preset monitoring points;

[0106] The first polynomial is:

[0107]

[0108] The second polynomial is:

[0109]

[0110] According to the polynomial fitting method, the parameters are determined, that is, the relationship equation f1(x) between gas concentration and fan pressure and the relationship equation f2(x) between temperature and fan pressure are obtained.

[0111] In the process of solving the gas concentration-fan pressure relationship equation f1(x) and the temperature-fan pressure relationship equation f2(x) by using the multi-objective genetic algorithm, the constraints of the multi-objective genetic algorithm are:

[0112]

[0113] Among them, X is the maximum pressure that the local fan can provide, X i,max The maximum pressure that each fan can reach.

[0114] The objective function of the multi-objective genetic algorithm is:

[0115]

[0116] Where fitness(I) is the objective function of the multi-objective genetic algorithm; w k is the weight of the kth optimization objective, that is, the weight of the kth wind turbine parameter to be optimized; f k (I) is the optimal value of the kth optimization objective.

[0117] In the present invention, with the goal of reducing the temperature and the concentration of harmful gases, the relationship equation f1(x) between the gas concentration and the fan pressure and the relationship equation f2(x) between the temperature and the fan pressure are solved to obtain the values ​​of the first polynomial and the second polynomial when the temperature data in the tunnel and the concentration of harmful gases in the tunnel are optimal; finally, according to the weights of the temperature data in the tunnel and the concentration of harmful gases in the tunnel in the optimization level, the optimal solution for the optimal values ​​of the two is determined, that is, the optimization result of the tunnel ventilation solution is obtained.

[0118] Step 9, transmitting the optimization result of the tunnel ventilation scheme to the fan control system through the tunnel optical cable; the fan control system responds to the optimization result of the tunnel ventilation scheme and corrects the operating parameters of the fan in the tunnel; at the same time, continues to determine whether the real-time monitoring values ​​in the tunnel are normal; after the fan runs for a preset operating time, if the data monitoring value is normal, then continue to the next stage of monitoring; if it is abnormal, activate the emergency plan; wherein, the emergency plan includes restricting traffic volume, evacuating personnel or emergency rescue.

[0119] The tunnel ventilation scheme optimization method described in the present invention randomly simulates the ventilation scheme based on the real-time environmental data in the tunnel through simulation test results, and obtains the optimal scheme through a multi-objective genetic algorithm, thereby avoiding the subjective influence of human factors on the ventilation scheme to the greatest extent, so as to adapt to different emergency situations and effectively shorten the execution response time of the optimal ventilation scheme after the emergency occurs.

[0120] As attached Figure 2-3 As shown, the present invention also provides a tunnel ventilation scheme optimization system, including a real-time data acquisition unit A, a data processing unit B, a computer test unit C, an intelligent operation unit D, a fan control system 4, a tunnel optical cable 5 and a supercomputer 8; wherein the data processing unit B and the computer test unit C are encapsulated in the supercomputer 8 through programming; the supercomputer 8 is connected to the intelligent operation unit through the tunnel optical cable 5, and the intelligent operation unit is connected to the fan control system 4.

[0121] In the present invention, the real-time data acquisition unit is used to obtain real-time environmental data and fan operating parameter data in the tunnel; the data processing unit is used to classify the real-time environmental data and fan operating parameter data in the tunnel to obtain discrimination data and initial data; the computer test unit is used to compare the discrimination data with the preset tunnel specification standard; if the value of a certain environmental indicator in the discrimination data exceeds the limit value of the preset tunnel specification standard, then according to the initial data, through simulation test, the calculated value of the environmental indicator at the preset monitoring point in the tunnel is obtained; the calculated value of the environmental indicator at the preset monitoring point in the tunnel and the real-time monitoring value of the environmental indicator are analyzed to obtain the error analysis result; if the error analysis result meets the preset threshold If the value requirement is met, N groups of initial proposed fan parameter schemes are formulated within the value space of the fan parameters; for each group of initial proposed fan parameter schemes, a second computer simulation test is carried out to obtain N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points; a relationship matrix between the N groups of initial fan parameters and the N groups of calculated values ​​of environmental indicators at preset monitoring points is obtained by a polynomial fitting method; a multi-objective genetic algorithm is used to solve the relationship matrix to obtain the optimal fan parameters, that is, to obtain the optimization result of the tunnel ventilation scheme; the intelligent operation unit is used to transmit the optimization result of the tunnel ventilation scheme to the fan control system; the fan control system is used to respond to the optimization result of the tunnel ventilation scheme and correct the operating parameters of the fan in the tunnel.

[0122] In the present invention, the real-time data acquisition unit includes a tunnel operation environment monitoring instrument, a vehicle-mounted GPS positioning system 2, a tunnel video monitoring system, an infrared recognition monitor 3 and a fan parameter acquisition module; the tunnel operation environment detection instrument includes an anemometer 1, a temperature sensor 6 and a gas concentration sensor 7; the anemometer 1 is arranged at the tunnel entrance to obtain the wind speed and direction data at the tunnel entrance; the temperature sensor 6 is arranged at intervals along the tunnel axis and is located on the tunnel side wall to obtain the temperature data in the tunnel; the gas concentration sensor 7 is arranged at intervals along the tunnel axis and is located on the tunnel side wall , used to obtain the harmful gas concentration data, smoke concentration data and dust concentration data in the tunnel; the vehicle-mounted GPS positioning system 2 is used to obtain the position information of vehicles passing through the tunnel; the tunnel video monitoring system is set at the entrance of the tunnel; it is used to obtain the license plate information of the vehicles to be passed through the tunnel, and obtain the size information of the vehicles to be passed through the tunnel through the license plate information; the infrared recognition monitor 3 is arranged at intervals along the axis of the tunnel and is located on the side wall of the tunnel, and is used to identify the position information of personnel; the fan parameter acquisition module is used to obtain the fan operation parameter data from the tunnel fan control system.

[0123] The tunnel ventilation scheme optimization method and system described in the present invention are as follows: by installing a wind speed and direction meter 1 at the tunnel entrance, and installing an infrared recognition monitor 3, a fan control system 4, a tunnel optical cable 5, a temperature sensor 6 and a gas concentration sensor 7 in the tunnel; the real-time environmental data and other data information in the tunnel are transmitted to a supercomputer 8 by means of the tunnel optical cable 5; a real-time data acquisition unit is used to obtain the real-time environmental data in the tunnel; a data processing unit is used to classify the real-time environmental data in the tunnel to obtain discrimination data and initial data; by classifying the real-time environmental data in the tunnel, the initial data is used as the initial parameters of the calculation test unit.

[0124] In the present invention, the computer test unit is used to compare the discrimination data with the limit value of the preset tunnel standard; if the value of a certain environmental indicator does not exceed the standard value, it returns to the real-time data acquisition unit to continue the data acquisition work; if the value of a certain environmental indicator exceeds the standard value, the initial data is assigned as the initial parameter to the grid in the tunnel fluid space model in the computer test unit; the tunnel ventilation operation process at that moment is simulated by computer, and the result data is returned for comparison with the monitoring data; if they are inconsistent, the empirical parameters are changed and recalculated; if they are consistent, random variables are used to formulate several initial fan parameter schemes within the value space of the ventilation machinery operation capacity, and the computer test unit is continued. Replace the initial fan parameters with the fitted fan scheme, solve the control equation and turbulence equation, and get the corresponding relationship between the fan pressure and some abnormal parameters; analyze the corresponding relationship through polynomial fitting, get the coefficients of high-order terms and thus determine the functional relationship; finally, combine the fan constraints and use the multi-objective genetic algorithm to quickly solve and get the optimal operating fan scheme; control the operating status of the ventilation mechanical device through the intelligent operation unit, and continue to collect data; when the mechanical device has been working for a period of time under the optimal scheme, the monitoring value has a downward trend, which means that the emergency state is effectively controlled; otherwise, activate the emergency plan to carry out related work, such as limiting traffic volume, evacuating personnel or emergency rescue.

[0125] In the present invention, a preset programming language is used to simulate the finite element method, a fluid space model consistent with that in the physical tunnel is built in the supercomputer, and the fluid flow state in the tunnel is solved by the control equation and the turbulence equation, thereby realizing a joint optimization response mode between the physical tunnel and the computer test unit; the real-time data in the tunnel is input into the supercomputer through the tunnel optical cable; at the same time, the solved optimal operating fan scheme parameters also control the fan control system; the turbulence equation has a variety of solution equations, which can be reasonably selected through the monitored data; at the same time, when building a computer test, a data survey of the application tunnel should be conducted in advance, a tunnel fluid space model should be built, and the empirical parameters in the equation should be debugged, so as to achieve the requirement that the error is easily met during the solution process.

[0126] The optimization method and system described in the present invention can accurately analyze tunnel optimization plans under different emergency situations and control fan operation for problems such as excessive pollutants, sudden fires and traffic congestion that are common in tunnel operation, thereby solving the problem of rapid organization of optimization plans for emergencies in different locations and situations. At the same time, it also avoids the problem of large subjective factors in artificially formulating plans on a global scale, which leads to local data loss, and achieves the goal of more accurate control of fan parameters and more significant results in handling emergencies.

[0127] The present invention can be used in tunnels that use fans as ventilation methods; first, temperature sensors, gas sensors and infrared identification monitors are installed at certain intervals in the tunnel, and wind speed and direction meters are installed at the tunnel entrance, and the fan operation parameters are obtained in real time through the fan control system, and are connected to a supercomputer through a line to realize the data transmission function; at the same time, the vehicle-mounted GPS positioning system can be connected to the supercomputer through a network system to realize real-time position monitoring; secondly, a 1:1 tunnel fluid space model is established, and a programming language is used to implement fluid control equations and turbulence equations to build a computer experimental platform; initial data is introduced into the tunnel flow field as the initial value of the computer simulation test, and a random variable method scheme formulation module, a polynomial fitting module and a multi-objective genetic algorithm module are established; finally, an intelligent operation module is built so that the optimal solution obtained can control the working state of the fan and can contact relevant departments at the same time.

[0128] In the present invention, the information such as personnel, vehicles, flow field, temperature field, gas concentration, etc. in the tunnel is monitored in real time, the analysis of the tunnel flow field is realized through code programming, and the feasibility is verified through the monitoring information, and further a number of schemes are defined globally by using random vectors, the relationship matrix is ​​solved by polynomial fitting, and the optimal scheme is obtained by using a multi-objective genetic algorithm, and finally the operation status of the fan at that moment and the implementation of the plan in an emergency are guided; in the whole process, the data is mainly transmitted through the existing optical cables in the tunnel, and the vehicle and personnel information can be carried out by using GPS positioning systems, infrared recognition and other instruments, so that the fan control center can still quickly respond to the optimal operation ventilation plan under different emergency situations.

[0129] The tunnel ventilation scheme optimization method and system described in the present invention can effectively shorten the time for executing the optimal scheme response after an emergency occurs, and extend the time from the occurrence of the accident to the start of rescue; formulate a scheme through a random vector method, and solve the optimal scheme through a multi-objective genetic algorithm, thereby avoiding the subjective influence of human factors on the ventilation scheme to the greatest extent, and thus adapting to various different emergency situations; transmit data through tunnel optical cables, and control the fan system through a supercomputer, so as to achieve rapid response time and automatic data transmission, thereby saving human resources.

[0130] In the present invention, a computer test platform is used to perform global rapid optimization of the scheme, and the parameter change values ​​of the ventilation mechanical device can be accurately obtained, which is significantly different from the traditional graded ventilation scheme; the present invention can cope with various abnormal emergencies during tunnel operation by randomly formulating schemes, and has the characteristic of one situation corresponding to one solution, which can better adapt to sudden abnormal conditions; a number of initial fan parameter schemes are globally selected in the value space by the random vector method, which effectively avoids the situation that the artificial formulation of the scheme is prone to local data loss and insufficient global parameter accuracy, and the scheme formulated by the random vector method is more random and comprehensive than the artificial formulation; a computer test platform is used to simulate the tunnel operation stage, and then the test results are verified by the data obtained by monitoring, so as to establish a computer test consistent with the actual process, so as to obtain an accurate relationship matrix to optimize the ventilation scheme; a multi-objective genetic algorithm is used for rapid optimization, and the optimal scheme can be quickly formulated for the monitoring point data in multiple areas, and the scheme is transmitted to the fan control system through an optical cable to perform fan parameter correction.

[0131] The above embodiment is only one of the implementation methods that can realize the technical solution of the present invention. The scope of protection claimed by the present invention is not limited only to this embodiment, but also includes changes, replacements and other implementation methods that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed by the present invention.

Claims

1. A method for optimizing tunnel ventilation scheme, characterized in that: include: Obtain real-time environmental data and fan operating parameter data in the tunnel; Classifying the real-time environmental data and wind turbine operating parameter data in the tunnel to obtain discrimination data and initial data; Comparing the identified data with preset tunnel specifications and standards; If the value of a certain environmental indicator in the discrimination data exceeds the limit value of the preset tunnel specification standard, then according to the initial data, through a first computer simulation test, a calculated value of the environmental indicator at a preset monitoring point in the tunnel is obtained; Performing error analysis on the calculated value of the environmental index at the preset monitoring point in the tunnel and the real-time monitoring value of the environmental index to obtain an error analysis result; If the error analysis result meets the preset threshold requirement, N groups of initial proposed fan parameter schemes are formulated within the value space of the fan parameters; for each group of initial proposed fan parameter schemes, a second computer simulation test is performed to obtain N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points; Obtaining a relationship matrix between the N groups of initial fan parameters and the calculated values ​​of environmental indicators at the N groups of preset monitoring points by a polynomial fitting method; The relationship matrix is ​​solved by using a multi-objective genetic algorithm to obtain the optimal fan parameters, that is, the optimization result of the tunnel ventilation scheme is obtained.

2. A tunnel ventilation scheme optimization method according to claim 1, characterized in that: The real-time environmental data in the tunnel include wind speed and direction data at the tunnel entrance, temperature data in the tunnel, harmful gas concentration data in the tunnel, smoke concentration data in the tunnel, dust concentration data in the tunnel, size information of vehicles to be passed through the tunnel, and position information of vehicles passing through the tunnel; the fan operation parameter data include real-time operation parameters of the fan in the tunnel; Among them, the discrimination data includes temperature data in the tunnel, harmful gas concentration data in the tunnel, smoke concentration data in the tunnel and dust concentration data in the tunnel; the initial data includes wind speed and direction data at the tunnel entrance, size information of vehicles to pass through the tunnel, position information of vehicles passing through the tunnel and real-time operating parameters of the fan in the tunnel.

3. A tunnel ventilation scheme optimization method according to claim 1, characterized in that: The process of obtaining the calculated values ​​of the environmental indicators at the preset monitoring points in the tunnel through the first computer simulation test according to the initial data is as follows: Construct a tunnel fluid space model; According to the tunnel fluid space model, empirical parameters in the fluid control equation and the turbulence model equation are corrected by historical tunnel data to obtain the fluid control equation and the turbulence model equation of the tunnel fluid space model; According to the initial data, the fluid control equation and the turbulence model equation of the tunnel fluid space model are solved to obtain the calculated value of the environmental index at the preset monitoring point in the tunnel.

4. A tunnel ventilation scheme optimization method according to claim 3, characterized in that: The fluid control equation of the tunnel fluid space model is: Where ρ is the fluid density; is the calculated value of the environmental index at the preset monitoring point in the tunnel, that is, the physical quantity to be solved; is the transport coefficient of the physical quantity to be solved; is the source term of the physical quantity to be solved; The turbulence model equation of the tunnel fluid space model is the Standard k-ε equation: Among them, the k equation is: The ε equation is: Where ρ is the fluid density; k is the turbulence coefficient; t is the time; u i is the velocity component of the fluid; x i 、x j is the distance component; t is the time; G k is the turbulent kinetic energy generated by the average velocity gradient of the fluid; G b is the turbulent kinetic energy generated by the buoyancy of the fluid; ε is the kinetic energy dissipation rate of the turbulent flow; Y M is the effect of wave expansion in compressible turbulence on the overall dissipation rate; C 1ε , C 2ε , C 3ε , σ k , σ ε are all constants; S k , S ε A user-defined source item.

5. The method for optimizing tunnel ventilation scheme according to claim 1, characterized in that: The error analysis results are: Among them, J is the error analysis result; A1 is the real-time monitoring value of the environmental index; A2 is the calculated value of the environmental index at the preset monitoring point in the tunnel.

6. A tunnel ventilation scheme optimization method according to claim 1, characterized in that: If the error analysis result meets the preset threshold requirement, N groups of initial proposed fan parameter schemes are formulated within the value space of the fan parameters; for each group of initial proposed fan parameter schemes, a second computer simulation test is performed to obtain N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points, as follows: By using the random vector method, N groups of fan operating parameter combination schemes are formulated in the parameter value space of fans at different positions in the tunnel; the fan operating parameter combination scheme is the initial proposed fan parameter scheme; Construct a tunnel fluid space model; According to the tunnel fluid space model, empirical parameters in the fluid control equation and the turbulence model equation are corrected by historical tunnel data to obtain the fluid control equation and the turbulence model equation for determining the tunnel fluid space model; According to each combination of the fan operating parameters, the fluid control equations and the turbulence model equations of the tunnel fluid space model are solved respectively to obtain N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points.

7. A tunnel ventilation scheme optimization method according to claim 1, characterized in that: The relationship matrix between the N groups of initial fan parameters and the calculated values ​​of environmental indicators at the N groups of preset monitoring points is: Among them, y i is the calculated value of the environmental index at the i-th preset monitoring point; a i , b i 、c i d i 、f i are the coefficients of the i-th higher-order terms respectively; is the nth order term of the mth initial fan parameter.

8. The method for optimizing tunnel ventilation scheme according to claim 1, characterized in that: The objective function of the multi-objective genetic algorithm is: Where fitness(I) is the objective function of the multi-objective genetic algorithm; w k is the weight of the kth optimization objective, that is, the weight of the kth wind turbine parameter to be optimized; f k (I) is the optimal value of the kth optimization objective.

9. A tunnel ventilation scheme optimization system, characterized in that: include: Real-time data acquisition unit, used to obtain real-time environmental data and fan operating parameter data in the tunnel; A data processing unit, used for classifying the real-time environmental data and wind turbine operating parameter data in the tunnel to obtain discrimination data and initial data; A computer test unit, used for comparing the identification data with preset tunnel specification standards; If the value of a certain environmental indicator in the discrimination data exceeds the limit value of the preset tunnel specification standard, then according to the initial data, through simulation test, a calculated value of the environmental indicator at a preset monitoring point in the tunnel is obtained; an error analysis is performed between the calculated value of the environmental indicator at the preset monitoring point in the tunnel and the real-time monitoring value of the environmental indicator to obtain an error analysis result; If the error analysis result meets the preset threshold requirement, then N groups of initial proposed fan parameter schemes are formulated within the value space of the fan parameters; for each group of initial proposed fan parameter schemes, a second computer simulation test is performed to obtain N groups of initial fan parameters and N groups of calculated values ​​of environmental indicators at preset monitoring points; a relationship matrix between the N groups of initial fan parameters and the calculated values ​​of environmental indicators at the N groups of preset monitoring points is obtained by a polynomial fitting method; a multi-objective genetic algorithm is used to solve the relationship matrix to obtain the optimal fan parameters, that is, to obtain the optimization result of the tunnel ventilation scheme; An intelligent operation unit, used for transmitting the optimization result of the tunnel ventilation scheme to a fan control system; The fan control system is used to respond to the optimization result of the tunnel ventilation plan and correct the operating parameters of the fan in the tunnel.

10. A tunnel ventilation scheme optimization system according to claim 9, characterized in that: The real-time data acquisition unit includes tunnel operation environment monitoring instruments, vehicle-mounted GPS positioning system, tunnel video monitoring system and fan parameter acquisition module; The tunnel operation environment monitoring instrument comprises an anemometer (1), a temperature sensor (6) and a gas concentration sensor (7); the anemometer (1) is arranged at the tunnel entrance and is used to obtain wind speed and direction data at the tunnel entrance; the temperature sensor (6) is arranged at intervals along the tunnel axis and is located on the tunnel side wall and is used to obtain temperature data in the tunnel; the gas concentration sensor (7) is arranged at intervals along the tunnel axis and is located on the tunnel side wall and is used to obtain harmful gas concentration data, smoke concentration data and dust concentration data in the tunnel; The vehicle-mounted GPS positioning system is used to obtain the position information of vehicles passing through the tunnel; The tunnel video monitoring system is arranged at the entrance of the tunnel; Used to obtain the license plate information of the vehicle to be passed through the tunnel, and obtain the size information of the vehicle to be passed through the tunnel through the license plate information; The fan parameter acquisition module is used to obtain fan operating parameter data from the tunnel fan control system.

Images