Method for optimizing suburban tunnel blasting parameters

Abstract

The invention provides a method for optimizing suburban tunnel blasting parameters. The method comprises the following steps: S1, acquiring historical data of suburban tunnel blasting construction; s2, determining environment indexes during blasting based on the environment parameters during blasting; S3, constructing a BP neural network prediction model, and inputting the historical construction parameters and the corrected environment indexes into the BP neural network prediction model for training; s4, setting construction parameters of a plurality of groups of to-be-blasted working faces, and respectively inputting the construction parameters of the to-be-blasted working faces into the trained BP neural network prediction model to predict blasting parameters of the to-be-blasted working faces; and S5, constructing an optimization objective function, substituting the construction parameters of the to-be-blasted working face into the optimization objective function for calculation, and taking the construction parameter corresponding to the minimum value of the optimization objective function as the optimal construction parameter of the to-be-blasted working face.

Description

Technical Field

[0001] This invention relates to a method for optimizing construction parameters, and more particularly to a method for optimizing blasting parameters for suburban tunnels. Background Technology

[0002] The drilling and blasting method for tunnel construction in suburban areas faces a dual contradiction between "engineering needs" and "environmental constraints": on the one hand, it is necessary to ensure the progress and quality of excavation, and on the other hand, the noise, dust and harmful gases generated by blasting can easily disturb the lives of surrounding residents.

[0003] In current technologies, the design of blasting parameters for suburban areas relies heavily on experience. This approach fails to meet environmental requirements because environmental monitoring during blasting lags behind construction; monitoring and analysis are conducted post-blast. Furthermore, during blasting, environmental parameters such as noise, dust, and harmful gases are affected by vibration rates, and blasting vibration is closely related to blasting parameters (also known as blasting construction parameters). Current technologies do not consider the impact of blasting vibration on these parameters, leading to lower accuracy in post-blast assessments. Consequently, the blasting parameters determined by current experience-based design methods still have a significant impact on surrounding residents and the environment during blasting.

[0004] Therefore, in order to solve the above-mentioned technical problems, it is urgent to propose a new technical approach. Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide a method for optimizing blasting parameters in suburban tunnels. By taking into account the environmental information from historical blasting operations, the method determines the corresponding parameter indices and trains a parameter prediction model using these indices. This effectively ensures the accuracy of the prediction model parameters, resulting in more accurate environmental indices predicted by the model. Furthermore, it accurately determines the optimal blasting parameters, minimizing the environmental impact of blasting performed with these parameters, ensuring the environmental quality of residents around the tunnel site, and facilitating coordinated safety control.

[0006] This invention provides a method for optimizing blasting parameters in suburban tunnels, comprising the following steps:

[0007] S1. Obtain historical data on blasting construction of suburban tunnels, including construction parameters and environmental parameters during blasting;

[0008] S2. Determine the environmental parameters during blasting based on the environmental parameters during blasting;

[0009] S3. Construct a BP neural network prediction model and input historical construction parameters and corrected environmental indicators into the BP neural network prediction model for training.

[0010] S4. Set multiple sets of construction parameters for the working face to be blasted, and input the construction parameters of the multiple sets of working faces to be blasted into the trained BP neural network prediction model to predict the blasting parameters of the working face to be blasted.

[0011] S5. Construct an optimization objective function, substitute the construction parameters of the working face to be blasted into the optimization objective function for calculation, and take the construction parameters corresponding to the minimum value of the optimization objective function as the optimal construction parameters of the working face to be blasted.

[0012] Furthermore, the construction parameters include the amount of explosives, the detonation time interval, the borehole spacing, and the filling length;

[0013] The environmental indicators during the blasting include noise levels, dust concentration, and harmful gas levels.

[0014] The environmental parameters during blasting are determined by environmental parameters, among which:

[0015] Environmental parameters include baseline inherent noise, vibration radiated noise, ambient wind speed, blasting-induced wind speed, blasting vibration rate of surrounding rock, ambient wind speed, and tunnel ventilation wind speed after blasting.

[0016] Furthermore, the noise index is corrected using the following method:

[0017]

[0018] in: Indicates noise level; Indicates the inherent noise of the reference. This refers to the vibration and radiation noise during blasting; This represents the environmental correction factor. This represents the time correction factor.

[0019] Furthermore, the dust concentration index correction formula is as follows:

[0020]

[0021] in: Indicates the target location Dust concentration at the location, Indicates the intensity of the dust source under blasting action; Indicates the total effective wind speed. This represents the dust diffusion coefficient in the y-direction. The z-axis represents the dust diffusion coefficient, where z and y represent the z-axis and y-axis coordinates of the target location; N represents the suburban obstacle correction coefficient.

[0022] Furthermore, the dust source intensity under the blasting action Determined using the following method:

[0023] ;

[0024] in: This represents a coefficient related to the lithology of the surrounding rock, where M represents the amount of rock blasted. This indicates the vibration rate during blasting of the surrounding rock.

[0025] Furthermore, the total effective wind speed is determined using the following method. :

[0026] ;

[0027] in: Indicates ambient wind speed. Indicates the blast-induced wind speed. This indicates the angle between the ambient wind and the blast-induced wind.

[0028] Furthermore, the hazardous gas index is determined using the following method:

[0029] ;

[0030] in: Indicates the level of harmful gases. Q represents the empirical proportionality coefficient, and Q represents the bankruptcy and pollution coefficient. Indicates the space closure correction factor. This represents the green belt obstruction correction coefficient, and A represents the area of ​​the tunnel cross-section. This indicates the ventilation coefficient inside the tunnel after the blasting. This represents the turbulence correction function.

[0031] Furthermore, the turbulence correction function Specifically:

[0032] ;

[0033] in: Represents the turbulence Reynolds number, and I represents the turbulence intensity. , This represents the correction factor.

[0034] Furthermore, the optimization objective function is:

[0035] ;

[0036] in, This indicates the weight of the corresponding item, and ; This indicates the maximum permissible noise level during blasting. This indicates the maximum permissible amount of hazardous gases during blasting. This indicates the maximum allowable dust concentration during blasting.

[0037] The beneficial effects of this invention are as follows: By taking into account the environmental information from historical blasting operations, the blasting vibration rate factor is determined, and the corresponding parameter indicators are used to train the parameter prediction model. This effectively ensures the accuracy of the prediction model parameters, and the environmental indicators predicted by the model are more accurate. Furthermore, the optimal blasting parameters can be accurately determined, resulting in a smaller environmental impact from blasting implemented with these parameters. This ensures the environmental quality of residents around the tunnel site and facilitates coordinated control in terms of safety. Attached Figure Description

[0038] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0039] Figure 1 This is a schematic diagram of the process of the present invention.

[0040] Figure 2 This is a schematic diagram of the coordinate system of the present invention. Detailed Implementation

[0041] The present invention will be further described in detail below:

[0042] This invention provides a method for optimizing blasting parameters in suburban tunnels, comprising the following steps:

[0043] S1. Obtain historical data on blasting construction of suburban tunnels, including construction parameters and environmental parameters during blasting;

[0044] S2. Determine the environmental parameters during blasting based on the environmental parameters during blasting;

[0045] S3. Construct a BP neural network prediction model and input historical construction parameters and corrected environmental indicators into the BP neural network prediction model for training.

[0046] S4. Set multiple sets of construction parameters for the working face to be blasted, and input the construction parameters of the multiple sets of working faces to be blasted into the trained BP neural network prediction model to predict the blasting parameters of the working face to be blasted; wherein, the BP neural network prediction model adopts the existing BP neural network and the corresponding loss function, which will not be described in detail here. The BP neural network has the characteristics of multiple inputs and multiple outputs, thereby enabling it to meet the prediction requirements of multiple environmental indicators of this invention.

[0047] S5. Construct an optimization objective function, substitute the construction parameters of the working face to be blasted into the optimization objective function for calculation, and take the construction parameters corresponding to the minimum value of the optimization objective function as the optimal construction parameters for the working face to be blasted. That is, the trained neural network predicts the corresponding environmental indicators through multiple construction parameters, and then substitutes the environmental indicators into the optimization objective function to obtain multiple function values. The combination of construction parameters corresponding to the minimum function value is the optimal construction parameter, which can be implemented according to the parameters in actual construction. Through this invention, by taking into account the blasting vibration rate factor and environmental factors (such as building obstruction and reflection, green belt obstruction, etc.) in the environmental information of historical blasting construction, the corresponding parameter indicators are determined, and the parameter prediction model is trained with these parameter indicators, thereby effectively ensuring the accuracy of the prediction model parameters. The environmental indicators predicted by this model are more accurate, and the optimal blasting parameters can be accurately determined, so that the environmental impact of blasting implemented with these parameters is smaller, ensuring the environmental quality of residents around the tunnel site area, and facilitating safety coordination and control. Moreover, the whole process is simple, easy to implement, and highly adaptable, and can be adapted to various relatively complex suburban scenarios.

[0048] In this embodiment, the construction parameters include the amount of explosives, the detonation time interval, the spacing between blast holes, and the filling length;

[0049] The environmental indicators during the blasting include noise levels, dust concentration, and harmful gas levels.

[0050] The environmental parameters during blasting are determined by environmental parameters, among which:

[0051] Environmental parameters include baseline inherent noise, vibration radiated noise, ambient wind speed, blasting-induced wind speed, blasting vibration rate of surrounding rock, ambient wind speed, and tunnel ventilation wind speed after blasting.

[0052] In this embodiment, the noise index is corrected using the following method:

[0053]

[0054] in: Indicates noise level; Indicates the inherent noise of the reference. This refers to the vibration and radiation noise during blasting; This represents the environmental correction factor. This represents the time correction factor; the relationship between vibration radiation noise and blasting vibration rate is as follows:

[0055] Where e1 and e2 are empirical constants obtained through regression analysis of measured data. Essentially, it's a quantitative compensation for the "energy enhancement / attenuation" during noise propagation. Buildings and green belts around the blasting area alter the noise propagation path. Buildings reflect noise, and the superposition of reflected waves and direct waves enhances the noise; in this case, K1 is taken as a positive correction. Green belts absorb and attenuate noise, and vegetation consumes sound energy; in this case, K1 is taken as a negative correction. The time correction coefficient M1 reduces the calculated sound pressure level, indirectly increasing the control requirements for nighttime blasting noise. By introducing time and environmental correction coefficients, the accuracy of noise index determination can be effectively ensured, providing accurate data support for subsequent processing.

[0056] The correction formula for the dust concentration index is:

[0057]

[0058] in: Indicates the target location Dust concentration at the location, Indicates the intensity of the dust source under blasting action; Indicates the total effective wind speed. This represents the dust diffusion coefficient in the y-direction. The z-axis represents the dust diffusion coefficient, where z and y represent the z-axis and y-axis coordinates of the target location; N represents the suburban obstacle correction coefficient. In suburban scenes, obstacles such as buildings and vegetation can hinder dust diffusion, resulting in increased local dust concentration at the expense of reducing the dust diffusion range. This needs to be adjusted using the correction coefficient N. The coordinate system mentioned above is as follows: Figure 2 As shown, the x-axis represents the direction of borehole extension, i.e., the direction of dust diffusion.

[0059] The dust source intensity under the blasting action Determined using the following method:

[0060] ;

[0061] in: This represents a coefficient related to the lithology of the surrounding rock. It indicates the time taken for the surrounding rock to change from its original state to a dusty state during blasting, with a unit path change, and the unit is s / m. M represents the amount of rock blasted. Indicates the vibration rate during blasting;

[0062] The total effective wind speed is determined using the following method. :

[0063] ;

[0064] in: Indicates ambient wind speed. This indicates the blast-induced wind speed (this wind is generated by the shock wave effect and thermal buoyancy effect of the blast). This represents the angle between the ambient wind and the blast-induced wind. By considering not only the blast vibration rate but also the influence of ambient wind, rain, and blast-induced wind, the dust concentration at the target location can be accurately determined, providing accurate data support for subsequent processing.

[0065] In this example, the harmful gas index was determined using the following method:

[0066] ;

[0067] in: Indicates the level of harmful gases. Q represents the empirical proportionality coefficient, and Q represents the bankruptcy and pollution coefficient. Indicates the space closure correction factor. This represents the green belt obstruction correction coefficient, and A represents the area of ​​the tunnel cross-section. This indicates the ventilation coefficient inside the tunnel after the blasting. This represents the turbulence correction function.

[0068] The turbulence correction function Specifically:

[0069] ;

[0070] in: Represents the turbulence Reynolds number, and I represents the turbulence intensity. , This represents the correction factor.

[0071] The optimization objective function is:

[0072] ;

[0073] in, This indicates the weight of the corresponding item, and ; This indicates the maximum permissible noise level during blasting. This indicates the maximum permissible amount of hazardous gases during blasting. This indicates the maximum allowable dust concentration during blasting.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for optimizing parameters of a near-field tunnel blast, the method comprising: The method comprises the following steps: ​ S1. Obtain suburban tunnel blasting construction history data, which includes construction parameters and environmental parameters at the time of blasting; S2. Determine the environmental index at the time of blasting based on the environmental parameters at the time of blasting; S3. Construct a BP neural network prediction model, input the historical construction parameters and the corrected environmental index into the BP neural network prediction model for training; S4. Set multiple groups of construction parameters of the working face to be blasted, and input the multiple groups of construction parameters of the working face to be blasted into the trained BP neural network prediction model to predict the blasting parameters of the working face to be blasted; S5. Construct an optimization objective function, substitute the construction parameters of the working face to be blasted into the optimization objective function for calculation, and take the construction parameters corresponding to the minimum value of the optimization objective function as the optimal construction parameters of the working face to be blasted.

2. The method according to claim 1, wherein: The construction parameters include explosive quantity, initiation time interval, blast hole spacing, and stemming length; The environmental index at the time of blasting includes noise index, dust concentration index, and harmful gas index; The environmental index at the time of blasting is determined by the environmental parameters, wherein: The environmental parameters include reference inherent noise, vibration radiation noise, environmental wind speed, blasting-induced wind speed, surrounding rock blasting vibration rate, environmental wind speed, and post-blasting tunnel ventilation wind speed.

3. The method according to claim 2, wherein: The noise index is corrected by the following method: wherein: represents a noise index; represents a reference intrinsic noise, represents a blast-induced vibration radiation noise; represents an environmental correction coefficient, represents a time correction coefficient.

4. The method of optimizing parameters of a near-tunnel blast according to claim 2, wherein: The dust concentration index correction formula is: wherein: represents the dust concentration at the target position, represents the dust source intensity under the blasting action; represents the total effective wind speed, represents the dust diffusion coefficient in the y direction, represents the dust diffusion coefficient in the z direction, z and y represent the z-axis coordinate value and the y-axis coordinate value of the target position; N represents the near suburban obstacle correction coefficient.​ 5. The method of optimizing parameters of a suburban tunnel blast according to claim 4, wherein: The dust source intensity under the blasting effect Determined by the following method: ； wherein: represents a coefficient related to the lithology of the surrounding rock, M represents the amount of blasted rock, represents the vibration velocity of the surrounding rock blasting.

6. The method of optimizing parameters of a near-tunnel blast according to claim 4, wherein: The total effective wind speed is determined by the method : ； wherein: represents the ambient wind speed, represents the blast-induced wind speed, represents the angle between the ambient wind and the blast-induced wind.

7. The method of optimizing parameters of a near-tunnel blast according to claim 2, wherein: The harmful gas index is determined by the following method: ； wherein: represents a harmful gas index, represents an empirical proportional coefficient, Q represents a blasting pollution coefficient, represents a space sealing correction coefficient, represents a green belt retardation correction coefficient, A represents an area of a tunnel section, represents a ventilation coefficient in a tunnel after blasting, represents a turbulent flow correction function.

8. The method of optimizing parameters of a near-tunnel blast according to claim 7, wherein: The turbulence correction function Specifically: ； wherein: represents the turbulent Reynolds number, I represents the turbulent intensity, , represents the correction factor.

9. The method of optimizing parameters of a near-tunnel blast according to claim 2, wherein: The optimization objective function is: ； wherein, represents the weight of the corresponding item, and ; represents the maximum noise allowed at the time of blasting, represents the maximum value of the harmful gas allowed at the time of blasting, represents the maximum value of the dust concentration allowed at the time of blasting.

Images