Multi-source information fusion early warning system and method for unfavorable geology of tunnel

Abstract

The invention discloses a multi-source information fusion early warning system and method for unfavorable geology of a tunnel, and belongs to the technical field of tunnel engineering.The multi-source information fusion early warning method for the unfavorable geology of the tunnel comprises the steps that S1, initial data, construction monitoring data and environment data of the tunnel geology are obtained; s2, performing noise reduction and normalization processing on the initial data, the construction monitoring data and the environment data; s3, fusing the preprocessed initial data, the construction monitoring data and the environment data; s4, evaluating each risk factor according to the fusion data, the geological condition and the construction condition; s5, formulating a corresponding early warning level and a decision scheme according to a risk assessment result; and S6, outputting an early warning signal according to the early warning level and the decision scheme. The unfavorable geological risk of the tunnel is comprehensively controlled, risk misjudgment caused by one-sided information is avoided, the strategy is reasonably adjusted by accurately determining the early warning level, geological disasters are effectively prevented, and the overall construction efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel engineering, and in particular to a multi-source information fusion early warning system and method for poor tunnel geology. Background Art

[0002] Tunnel engineering plays an important role in the construction of infrastructure such as transportation and water conservancy. However, tunnel construction often faces complex and adverse geological conditions, such as faults, karst caves, and soft strata. These adverse geological conditions may cause serious disasters such as landslides, water inrush, and rock bursts, posing a huge threat to the safety of construction workers, project progress, and investment benefits.

[0003] In the existing technology, the means of collecting adverse geological data are relatively simple, usually relying on only one or a few monitoring equipment, making it difficult to comprehensively obtain multi-source data such as geological information, construction process information and environmental parameters, resulting in inaccurate determination of warning levels, lack of targetedness and effectiveness of response measures, and inability to prevent the occurrence of geological disasters in a timely and effective manner. Summary of the invention

[0004] The purpose of the present invention is to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a multi-source information fusion early warning system and method for poor tunnel geology, which can accurately determine the early warning level and improve the early warning effect and overall construction efficiency.

[0005] According to the first aspect of the present invention, a multi-source information fusion early warning system for poor tunnel geology includes: a geological information acquisition module, which is used to obtain initial data on tunnel geology; a construction monitoring data acquisition module, which is used to collect construction monitoring data of the tunnel; an environmental data acquisition module, which is used to collect environmental data in the tunnel; a data preprocessing module, which is used to perform noise reduction and normalization on the collected data; a data fusion module, which is used to fuse multi-source data; a risk assessment module, which performs risk assessment based on the fused data; an early warning decision module, which formulates an early warning strategy based on the assessment results; an alarm output module, which is used to output an early warning signal; and a control module, which is respectively connected to the geological information acquisition module, the construction monitoring data acquisition module, the environmental data acquisition module, the data preprocessing module, the risk assessment module, the early warning decision module and the alarm output module.

[0006] The multi-source information fusion early warning system for poor tunnel geology according to the embodiment of the present invention has at least the following beneficial effects: the initial data, construction monitoring data and environmental data of the tunnel geology are obtained respectively through the geological information acquisition module, the construction monitoring data acquisition module and the environmental data acquisition module, and the initial data, construction monitoring data and environmental data are sent to the data preprocessing module for noise reduction and normalization processing, and the preprocessed initial data, construction monitoring data and environmental data are fused by the data fusion module, and the risk assessment module combines the fused data, tunnel geological conditions and construction conditions to perform risk assessment, evaluate each risk factor and derive their weights, and finally formulate the corresponding early warning level and decision plan according to the risk assessment results, and output the corresponding early warning signal through the alarm output module. Therefore, by integrating multi-source data, the all-round and multi-level control of the poor geological risks of the tunnel is achieved, avoiding the risk misjudgment caused by one-sided information. At the same time, based on scientific risk assessment algorithms and flexible preset threshold settings, the warning level can be accurately determined. On the one hand, construction strategies can be reasonably adjusted while ensuring safety; on the other hand, response measures can be more targeted, thereby effectively preventing geological disasters, reducing the huge economic losses caused by accidents, avoiding unnecessary shutdowns and delays, and improving overall construction efficiency.

[0007] According to the second aspect of the present invention, a multi-source information fusion early warning method for poor tunnel geology includes:

[0008] S1: Acquire initial data of tunnel geology through the geological information acquisition module, acquire construction monitoring data through the construction monitoring data acquisition module, and acquire environmental data of the tunnel through the environmental data acquisition module;

[0009] S2: Use the data preprocessing module to perform noise reduction and normalization on the initial data, construction monitoring data and environmental data;

[0010] S3: Obtain the processed initial data, construction monitoring data and environmental data, and fuse the pre-processed initial data, construction monitoring data and environmental data using a data fusion module to obtain fused data;

[0011] S4: Obtain fused data, obtain the geological conditions and construction conditions of the tunnel, and the risk assessment module assesses each risk factor based on the fused data, geological conditions and construction conditions to obtain the weight of each risk factor;

[0012] S5: Obtain risk assessment results, and when the risk assessment results are not within the preset first threshold, formulate corresponding warning levels and decision plans;

[0013] S6: Obtain the warning level and decision plan, and the alarm output module outputs a warning signal according to the warning level and decision plan.

[0014] According to some embodiments of the present invention, in S1, the geological information acquisition module includes geological drilling equipment, geological radar and remote sensing equipment respectively connected to the control system, the geological drilling equipment is used to detect the geological lithology of the tunnel, the geological radar is used to survey the structural changes of the strata, and the rocker device is used to survey the distribution of faults.

[0015] According to some embodiments of the present invention, in S1, the construction monitoring data acquisition module includes a stress sensor, a displacement sensor and a seepage pressure sensor respectively connected to the control system, the stress sensor is used to detect stress changes in the surrounding rock, the displacement sensor is used to sense the displacement trend of the tunnel wall, and the seepage pressure sensor is used to feedback the groundwater seepage pressure.

[0016] According to some embodiments of the present invention, in S1, the environmental data acquisition module includes a temperature sensor, a humidity sensor and a gas sensor respectively connected to the control system, the temperature sensor is used to detect the temperature in the tunnel, the humidity sensor is used to detect the humidity in the tunnel, and the gas sensor is used to detect the concentration of harmful gases in the tunnel.

[0017] According to some embodiments of the present invention, in S2, the data preprocessing module includes an outlier removal unit and a data normalization unit, the outlier removal unit is used to remove abnormal data, and the data normalization unit is used to map the data to the [0,1] interval.

[0018] According to some embodiments of the present invention, in S2, the data preprocessing module performs noise reduction and normalization processing on the initial data, the construction monitoring data and the environmental data by using a noise reduction formula, and the noise reduction formula is:

[0019]

[0020] Where Y n is the output value after filtering, X n is the input value, and N is the filter window size.

[0021] According to some embodiments of the present invention, in S3, the data fusion module deeply fuses the preprocessed geological information, construction monitoring data and environmental data through a fusion formula, wherein the fusion formula is:

[0022]

[0023] Where m1(B) and m2(C) are the basic probability distributions of different data sources, and k is the conflict coefficient.

[0024] According to some embodiments of the present invention, in S4, the risk assessment module assesses each risk factor using a risk assessment formula, and the risk assessment formula is:

[0025]

[0026] Where R is the total risk value, ω i is the weight of the ith risk factor, r i is the evaluation value of the ith risk factor.

[0027] According to some embodiments of the present invention, in S6, the warning signal includes an audible alarm, a light flashing alarm, and a remote communication alarm.

[0028] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The present invention is further described below in conjunction with the accompanying drawings and embodiments:

[0030] Figure 1 is a schematic diagram of a multi-source information fusion early warning system for poor tunnel geology according to an embodiment of the first aspect of the present invention;

[0031] Figure 2 It is a flow chart of a multi-source information fusion early warning method for poor tunnel geology according to an embodiment of the second aspect of the present invention. DETAILED DESCRIPTION

[0032] This section will describe in detail the specific embodiments of the present invention. The preferred embodiments of the present invention are shown in the accompanying drawings. The purpose of the accompanying drawings is to supplement the description of the text part of the specification with graphics, so that people can intuitively and vividly understand each technical feature and the overall technical solution of the present invention, but it cannot be understood as a limitation on the scope of protection of the present invention.

[0033] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0034] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0035] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0036] refer to Figure 1 to Figure 2 A multi-source information fusion early warning system and method for poor tunnel geology according to an embodiment of the present invention are described.

[0037] like Figure 1 and Figure 2 As shown, according to the first aspect of the present invention, the multi-source information fusion early warning system for poor tunnel geology includes: a geological information acquisition module, which is used to obtain initial data on tunnel geology; a construction monitoring data acquisition module, which is used to collect construction monitoring data of the tunnel; an environmental data acquisition module, which is used to collect environmental data in the tunnel; a data preprocessing module, which is used to reduce noise and normalize the collected data; a data fusion module, which is used to fuse multi-source data; a risk assessment module, which performs risk assessment based on the fused data; an early warning decision module, which formulates an early warning strategy based on the assessment results; an alarm output module, which is used to output an early warning signal; and a control module, which is respectively connected to the geological information acquisition module, the construction monitoring data acquisition module, the environmental data acquisition module, the data preprocessing module, the risk assessment module, the early warning decision module and the alarm output module.

[0038] The initial data, construction monitoring data and environmental data of the tunnel geology are acquired through the geological information acquisition module, the construction monitoring data acquisition module and the environmental data acquisition module respectively. The initial data, construction monitoring data and environmental data are sent to the data preprocessing module for noise reduction and normalization. The preprocessed initial data, construction monitoring data and environmental data are fused using the data fusion module. The risk assessment module conducts risk assessment based on the fused data, tunnel geological conditions and construction conditions, evaluates each risk factor and derives their weights. Finally, the corresponding warning level and decision plan are formulated according to the risk assessment results, and the corresponding warning signal is output through the alarm output module.

[0039] Therefore, by integrating multi-source data, we can achieve all-round and multi-level control of the adverse geological risks of tunnels, avoiding risk misjudgment caused by one-sided information. At the same time, based on scientific risk assessment algorithms and flexible preset threshold settings, we can accurately determine the warning level, which allows construction to reasonably adjust strategies while ensuring safety, and on the other hand, it can make the response measures more targeted, thereby effectively preventing geological disasters, reducing the huge economic losses caused by accidents, avoiding unnecessary shutdowns and delays, and improving overall construction efficiency.

[0040] like Figure 2 As shown, the multi-source information fusion early warning method for poor tunnel geology according to the second aspect of the present invention includes:

[0041] S1: Acquire initial data of tunnel geology through the geological information acquisition module, acquire construction monitoring data through the construction monitoring data acquisition module, and acquire environmental data of the tunnel through the environmental data acquisition module;

[0042] S2: Use the data preprocessing module to perform noise reduction and normalization on the initial data, construction monitoring data and environmental data;

[0043] S3: Obtain the processed initial data, construction monitoring data and environmental data, and fuse the pre-processed initial data, construction monitoring data and environmental data using a data fusion module to obtain fused data;

[0044] S4: Obtain fused data, obtain the geological conditions and construction conditions of the tunnel, and the risk assessment module assesses each risk factor based on the fused data, geological conditions and construction conditions to obtain the weight of each risk factor;

[0045] S5: Obtain risk assessment results, and when the risk assessment results are not within the preset first threshold, formulate corresponding warning levels and decision plans;

[0046] S6: Obtain the warning level and decision plan, and the alarm output module outputs a warning signal according to the warning level and decision plan.

[0047] In S1, the geological information acquisition module includes geological drilling equipment, geological radar and remote sensing equipment respectively connected to the control system. The geological drilling equipment is used to detect the geological lithology of the tunnel, the geological radar is used to survey the structural changes of the strata, and the rocker equipment is used to survey the distribution of faults.

[0048] In S1, the construction monitoring data acquisition module includes a stress sensor, a displacement sensor and a seepage pressure sensor which are respectively connected to the control system. The stress sensor is used to detect the stress change of the surrounding rock, the displacement sensor is used to sense the displacement trend of the tunnel wall, and the seepage pressure sensor is used to feedback the groundwater seepage pressure.

[0049] In S1, the environmental data acquisition module includes a temperature sensor, a humidity sensor and a gas sensor respectively connected to the control system. The temperature sensor is used to detect the temperature in the tunnel, the humidity sensor is used to detect the humidity in the tunnel, and the gas sensor is used to detect the concentration of harmful gases in the tunnel.

[0050] In S2, the data preprocessing module includes an outlier removal unit and a data normalization unit. The outlier removal unit is used to remove abnormal data, and the data normalization unit is used to map the data to the [0,1] interval.

[0051] In S2, the data preprocessing module performs noise reduction and normalization processing on the initial data, construction monitoring data and environmental data through the noise reduction formula. The noise reduction formula is:

[0052]

[0053] Where Y n is the output value after filtering, X n is the input value, and N is the filter window size.

[0054] In S3, the data fusion module uses a fusion algorithm based on evidence theory to fuse multi-source data. Specifically, the data fusion module deeply fuses the initial data, construction monitoring data and environmental data through a fusion formula. The fusion formula is:

[0055]

[0056] Where m1(B) and m2(C) are the basic probability distributions of different data sources, and k is the conflict coefficient.

[0057] In S4, the risk assessment module evaluates each risk factor through a risk assessment formula, and the risk assessment formula is:

[0058]

[0059] Where R is the total risk value, ω i is the weight of the ith risk factor, r i is the evaluation value of the ith risk factor.

[0060] It should be noted that in the risk assessment module, the analytic hierarchy process is used to determine the weight of each risk factor in combination with the specific geological conditions and construction conditions of the tunnel. The specific geological conditions include the stability of shale, the influence of folds and cracks, and the construction conditions include changes in surrounding rock stress and displacement.

[0061] In S5, the preset threshold is determined according to the tunnel design standard, geological complexity and construction experience, and can be dynamically adjusted according to actual conditions.

[0062] In S6, the warning signals include sound alarm, light flashing alarm and remote communication alarm.

[0063] The following is a specific example to illustrate the multi-source information fusion early warning method for poor tunnel geology.

[0064] S1: Geological drilling equipment was used to detect the geological lithology of the tunnel. The rock hardness values ​​obtained by drilling at three locations were: X1=40MPa, X2=50MPa, and X3=35MPa; geological radar was used to survey the structural changes of the strata. In the two monitorings, the depths of the structural changes of the strata were Y1=12m and Y2=10m respectively; the distribution of faults was surveyed using a rocker device, and one fault was detected with a fault drop of: Z=1.2m.

[0065] Stress sensors are used to detect stress changes in the surrounding rock, and the stress changes measured at three locations are: A1=8MPa, A2=10MPa, A3=6MPa; displacement sensors are used to sense the displacement trend of the tunnel wall, and the displacements measured at two locations are: B1=4mm, B2=3mm; seepage pressure sensors are used to feedback groundwater seepage pressure, and the groundwater pressures measured at two locations are: C1=0.25MPa, C2=0.3MPa.

[0066] A temperature sensor is used to detect the temperature in the tunnel, and the temperatures measured at two times are: T1=25°C, T2=28°C; a humidity sensor is used to detect the humidity in the tunnel, and the humidity measured at two times are: H1=70%, H2=75%; a gas sensor is used to detect the concentration of harmful gases in the tunnel, and the carbon monoxide concentrations measured at two locations are: G1=20ppm, G2=22ppm.

[0067] S2: Use outliers to remove abnormal data, use data normalization units to map data to the [0,1] interval, and use the noise reduction formula to reduce noise and normalize the initial data, construction monitoring data, and environmental data. The noise reduction formula is:

[0068]

[0069] Where Y n is the output value after filtering, X n is the input value, and N is the filter window size.

[0070] Taking rock hardness data as an example, let the filter window size N = 3, for X2 = 50, Y n =50.

[0071] S3: Obtain the processed initial data, construction monitoring data and environmental data, and fuse the pre-processed initial data, construction monitoring data and environmental data using the data fusion module according to the fusion algorithm based on evidence theory. The fusion formula is:

[0072]

[0073] Where m1(B) and m2(C) are the basic probability distributions of different data sources, and k is the conflict coefficient.

[0074] Assume k = 0.1, m1(B1) = 0.3, m1(B2) = 0.4, m2(C1) = 0.5, m2(C2) = 0.6, when A corresponds to B1C1, m(A) = 0.167; when A corresponds to B1C2, m(A) = 0.2; when A corresponds to B2C1, m(A) = 0.222; when A corresponds to B2C2, m(A) = 0.267.

[0075] It should be noted that the preprocessing refers to the noise reduction and normalization processing in S2, and the different data sources refer to the preprocessed initial data, construction monitoring data and environmental data in S2.

[0076] S4: Obtain fusion data, obtain the geological conditions and construction conditions of the tunnel, and the risk assessment module evaluates each risk factor based on the fusion data, geological conditions and construction conditions to obtain the weight of each risk factor. The risk assessment formula is:

[0077]

[0078] Where R is the total risk value, ω i is the weight of the ith risk factor, r i is the evaluation value of the ith risk factor.

[0079] Assume that there are three risk factors with weights ω0=0.3, ω1=0.4, ω2=0.3, corresponding to r0=0.6, r1=0.8, r2=0.7, and calculate R=0.3×0.6+0.4×0.8+0.3×0.7=0.71.

[0080] It should be noted that in the risk assessment module, the analytic hierarchy process is used to determine the weight of each risk factor in combination with the specific geological conditions and construction conditions of the tunnel. The specific geological conditions include the stability of shale, the influence of folds and cracks, and the construction conditions include changes in surrounding rock stress and displacement.

[0081] S5: Obtain risk assessment results, and preset the first threshold value to 0.6. Since 0.71>0.6, a corresponding medium-level warning and a specific decision-making plan are formulated, that is, the installation of the support structure is strengthened while slowing down the construction progress.

[0082] S6: The alarm output module responds quickly to the warning signals output by the warning level and decision plan, outputting strong sound alarms, eye-catching flashing lights and timely remote communication alarms, thereby ensuring that construction site personnel and remote monitoring centers can receive warning information in the first time and take corresponding emergency measures.

[0083] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the technical field without departing from the purpose of the present invention.

Claims

1. A multi-source information fusion early warning system for poor tunnel geology, characterized in that: include: A geological information acquisition module, which is used to obtain initial data of tunnel geology; A construction monitoring data collection module, wherein the construction monitoring data collection module is used to collect the construction monitoring data of the tunnel; An environmental data collection module, wherein the environmental data collection module is used to collect environmental data in the tunnel; A data preprocessing module, which is used to perform noise reduction and normalization processing on the collected data; A data fusion module, wherein the data fusion module is used to fuse multi-source data; A risk assessment module, wherein the risk assessment module performs risk assessment based on the fused data; An early warning decision module, wherein the early warning decision module formulates an early warning strategy according to the evaluation results; An alarm output module, wherein the alarm output module is used to output a warning signal; A control module, wherein the control module is respectively connected to the geological information acquisition module, the construction monitoring data acquisition module, the environmental data acquisition module, the data preprocessing module, the risk assessment module, the early warning decision module and the alarm output module.

2. A multi-source information fusion early warning method for poor tunnel geology, using the multi-source information fusion early warning system for poor tunnel geology according to claim 1, characterized in that: include: S1: acquiring initial data of tunnel geology through the geological information acquisition module, acquiring construction monitoring data through the construction monitoring data acquisition module, and acquiring environmental data of the tunnel through the environmental data acquisition module; S2: Using the data preprocessing module to perform noise reduction and normalization processing on the initial data, the construction monitoring data and the environmental data; S3: Acquire the processed initial data, the construction monitoring data and the environmental data, and fuse the pre-processed initial data, the construction monitoring data and the environmental data using the data fusion module to obtain fused data; S4: acquiring the fused data, the geological conditions of the tunnel and the tunnel construction conditions, and the risk assessment module assessing each risk factor according to the fused data, the geological conditions and the construction conditions to obtain the weight of each risk factor; S5: Obtaining a risk assessment result, and when the risk assessment result is not within a preset first threshold, formulating a corresponding warning level and decision plan; S6: Acquire the warning level and the decision plan, and the alarm output module outputs a warning signal according to the warning level and the decision plan.

3. The multi-source information fusion early warning method for poor tunnel geology according to claim 2 is characterized in that: In S1, the geological information acquisition module includes geological drilling equipment, geological radar and remote sensing equipment respectively connected to the control system, the geological drilling equipment is used to detect the geological lithology of the tunnel, the geological radar is used to survey the structural changes of the strata, and the rocker equipment is used to survey the distribution of faults.

4. The multi-source information fusion early warning method for poor tunnel geology according to claim 2 is characterized in that: In S1, the construction monitoring data acquisition module includes a stress sensor, a displacement sensor and a seepage pressure sensor respectively connected to the control system, the stress sensor is used to detect the stress change of the surrounding rock, the displacement sensor is used to sense the displacement trend of the tunnel wall, and the seepage pressure sensor is used to feedback the groundwater seepage pressure.

5. The multi-source information fusion early warning method for poor tunnel geology according to claim 2 is characterized in that: In S1, the environmental data acquisition module includes a temperature sensor, a humidity sensor and a gas sensor respectively connected to the control system, the temperature sensor is used to detect the temperature in the tunnel, the humidity sensor is used to detect the humidity in the tunnel, and the gas sensor is used to detect the concentration of harmful gases in the tunnel.

6. The multi-source information fusion early warning method for poor tunnel geology according to claim 2 is characterized in that: In S2, the data preprocessing module includes an outlier elimination unit and a data normalization unit, wherein the outlier elimination unit is used to eliminate abnormal data, and the data normalization unit is used to map the data to the interval [0, 1].

7. The multi-source information fusion early warning method for poor tunnel geology according to claim 2 is characterized in that: In S2, the data preprocessing module performs noise reduction and normalization processing on the initial data, the construction monitoring data and the environmental data by using a noise reduction formula, and the noise reduction formula is: Among them, Y n is the output value after filtering, X n is the input value, and N is the filter window size.

8. The multi-source information fusion early warning method for poor tunnel geology according to claim 2 is characterized in that: In S3, the data fusion module deeply fuses the pre-processed initial data, the construction monitoring data and the environmental data through a fusion formula, and the fusion formula is: Among them, m1(B) and m2(C) are the basic probability distributions of different data sources, and k is the conflict coefficient.

9. The multi-source information fusion early warning method for poor tunnel geology according to claim 6 is characterized in that: In S4, the risk assessment module evaluates each risk factor using a risk assessment formula, and the risk assessment formula is: Among them, R is the total risk value, ω i is the weight of the ith risk factor, r i is the evaluation value of the ith risk factor.

10. The multi-source information fusion early warning method for poor tunnel geology according to claim 7 is characterized in that: In S6, the warning signal includes an audible alarm, a light flashing alarm, and a remote communication alarm.

Images