Railway tunnel lining back defect quantitative evaluation method and device

Abstract

The invention discloses a railway tunnel lining back defect quantitative evaluation method and device which can be used in the field of tunnel engineering detection.The method comprises the steps that a tunnel lining deformation joint is determined, and a railway tunnel lining corresponding to geological radar detection data is divided into a plurality of lining segments; for each lining section, determining the defect type and defect parameters of the defect behind the railway tunnel lining; determining a defect risk index of each lining section by using the hierarchical model; wherein the hierarchical model is specifically used for determining the weight of each parameter of the scheme layer and the weight of each parameter of the criterion layer; determining a membership value of each parameter of the scheme layer; determining a membership degree vector of each parameter of the criterion layer; and carrying out unification on the membership degree vector of each parameter of the criterion layer, and calculating a defect risk index of each lining section according to a unification result and the weight of each parameter of the criterion layer. According to the method, the tunnel lining back defect can be quantitatively evaluated, and the tunnel maintenance level is improved.

Description

Technical Field

[0001] This invention relates to the field of tunnel engineering inspection, and in particular to a method and apparatus for quantitative evaluation of defects behind railway tunnel lining. Background Technology

[0002] This section is intended to provide background or context for embodiments of the present invention. The description herein is not intended to imply that it is prior art simply because it is included in this section.

[0003] Existing railway tunnels are widely distributed and operate in complex environments. As a crucial component of infrastructure, the safety of their lining structures directly impacts railway operational safety. Due to construction and environmental factors, defects such as voids, insufficient density, and inadequate thickness may exist behind the tunnel lining. Timely and accurate assessment of these defects is essential for ensuring railway operational safety.

[0004] Currently, the detection of defects in the tunnel lining mainly relies on ground-penetrating radar, with varying numbers of longitudinal survey lines deployed based on the size of the tunnel cross-section. The evaluation of the detection data primarily depends on single indices, such as the length and area of ​​defects, lacking multi-dimensional quantitative analysis. This makes it difficult to comprehensively and accurately grasp the true quality of the tunnel lining when assessing its condition, thus affecting the effectiveness of tunnel maintenance and repair. Summary of the Invention

[0005] This invention provides a method for quantitatively evaluating defects behind railway tunnel linings, used to quantitatively evaluate defects behind tunnel linings and improve tunnel maintenance and repair levels. The method includes:

[0006] Based on the pre-processed ground-penetrating radar detection data, the tunnel lining deformation joints are determined, and the railway tunnel lining corresponding to the ground-penetrating radar detection data is divided into multiple lining segments according to the tunnel lining deformation joints.

[0007] For each lining segment, based on the pre-processed ground-penetrating radar detection data and the tunnel lining deformation joint, the defect type and defect parameters of the defects behind the railway tunnel lining are determined.

[0008] A scheme layer is constructed based on defect parameters, a criterion layer is constructed based on defect types, and a hierarchical model is constructed based on the scheme layer and the criterion layer. The hierarchical model is used to determine the defect risk index of each lining segment. The defect risk index is used to quantitatively represent the defect risk.

[0009] Specifically, the hierarchical model is used for:

[0010] The product scaling method is used to determine the weights of each parameter in the scheme layer and the weights of each parameter in the criterion layer. Based on the variable fuzzy set, the membership values ​​of each parameter in the scheme layer are determined.

[0011] Based on the membership values ​​and weights of each parameter in the scheme layer, determine the membership vector of each parameter in the criterion layer.

[0012] The membership vectors of each parameter in the criterion layer are single-valued. Based on the single-valued results of the membership vectors of each parameter in the criterion layer and the weights of each parameter in the criterion layer, the defect risk index of each lining segment is calculated.

[0013] This invention also provides a device for quantitatively evaluating defects behind railway tunnel linings, used to quantitatively evaluate defects behind tunnel linings and improve tunnel maintenance. The device includes:

[0014] The segmentation module is used to determine the tunnel lining deformation joints based on the preprocessed ground-penetrating radar detection data, and to divide the railway tunnel lining corresponding to the ground-penetrating radar detection data into multiple lining segments based on the tunnel lining deformation joints.

[0015] The defect identification module is used to determine the defect type and defect parameters of the defects behind the railway tunnel lining for each lining segment based on the pre-processed ground radar detection data and the tunnel lining deformation joints.

[0016] The defect evaluation module is used to construct a scheme layer based on defect parameters, a criterion layer based on defect type, and a hierarchical model based on the scheme layer and criterion layer. The hierarchical model is used to determine the defect risk index of each lining segment. The defect risk index is used to quantitatively represent the defect risk.

[0017] It also includes a model processing module, specifically used for:

[0018] The product scaling method is used to determine the weights of each parameter in the scheme layer and the weights of each parameter in the criterion layer. Based on variable fuzzy sets, the membership degree values ​​of each parameter in the scheme layer are determined. Based on the membership degree values ​​and weights of each parameter in the scheme layer, the membership degree vectors of each parameter in the criterion layer are determined. The membership degree vectors of each parameter in the criterion layer are then single-valued. Based on the single-valued results of the membership degree vectors of each parameter in the criterion layer and the weights of each parameter in the criterion layer, the defect risk index of each lining segment is calculated.

[0019] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned method for quantitative evaluation of defects behind railway tunnel lining.

[0020] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for quantitative evaluation of defects behind railway tunnel lining.

[0021] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method for quantitative evaluation of defects behind railway tunnel lining.

[0022] In this embodiment of the invention, based on preprocessed ground-penetrating radar (GPR) detection data, tunnel lining deformation joints are determined. Based on these deformation joints, the railway tunnel lining corresponding to the GPR detection data is divided into multiple lining segments. For each lining segment, based on the preprocessed GPR detection data and the tunnel lining deformation joints, the defect type and defect parameters of the defects behind the railway tunnel lining are determined. A scheme layer is constructed based on the defect parameters, a criterion layer is constructed based on the defect types, and a hierarchical model is constructed based on the scheme layer and the criterion layer. The hierarchical model is then used to determine the defect risk index of each lining segment. The defect risk index is used to quantify defect risk. Specifically, the hierarchical model is used to: determine the weights of each parameter in the scheme layer and the criterion layer using the product scaling method; determine the membership values ​​of each parameter in the scheme layer based on variable fuzzy sets; determine the membership vectors of each parameter in the criterion layer based on the membership values ​​and weights of each parameter in the scheme layer; single-value the membership vectors of each parameter in the criterion layer; and calculate the defect risk index for each lining segment based on the single-valued results and weights of each parameter in the criterion layer. Thus, based on the defect types and parameters behind the tunnel lining, a hierarchical model is established, the weights of each parameter in the scheme layer and the criterion layer are calculated using the product scaling method, the membership values ​​of each parameter in the scheme layer are determined based on variable fuzzy sets, and the defect risk index is constructed. By quantitatively evaluating defects behind the tunnel lining, the level of tunnel maintenance and repair can be improved. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0024] Figure 1 This is a flowchart of a method for quantitatively evaluating defects behind railway tunnel lining provided in an embodiment of the present invention;

[0025] Figure 2 This is a schematic diagram of the quantitative parameter interval division provided in an embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of the tunnel lining area division provided in an embodiment of the present invention;

[0027] Figure 4This is a schematic diagram of the distribution of tunnel lining defects provided in an embodiment of the present invention;

[0028] Figure 5 This is a schematic diagram of a railway tunnel lining defect quantification evaluation device provided in an embodiment of the present invention;

[0029] Figure 6 This is a structural block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0031] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0032] In the description of this specification, the terms "comprising," "including," "having," and "containing" are open-ended terms, meaning that they include but are not limited to. The terms "an embodiment," "a specific embodiment," "some embodiments," and "for example," etc., refer to specific features, structures, or characteristics described in connection with that embodiment or example that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. The order of steps involved in the various embodiments is used to illustrate the implementation of this application, and the order of steps is not limited and can be adjusted appropriately as needed.

[0033] This invention provides a method for quantitatively evaluating defects behind railway tunnel lining. Figure 1 A flowchart for a method to quantitatively evaluate defects behind railway tunnel lining, such as... Figure 1 As shown, it includes:

[0034] Step 101: Based on the preprocessed ground-penetrating radar detection data, determine the tunnel lining deformation joints, and divide the railway tunnel lining corresponding to the ground-penetrating radar detection data into multiple lining segments according to the tunnel lining deformation joints.

[0035] Step 102: For each lining segment, based on the pre-processed ground-penetrating radar detection data and the tunnel lining deformation joint, determine the defect type and defect parameters of the defects behind the railway tunnel lining;

[0036] Step 103: Construct a scheme layer based on defect parameters, a criterion layer based on defect types, and a hierarchical model based on the scheme and criterion layers. Use the hierarchical model to determine the defect risk index for each lining segment. The defect risk index is used to quantify defect risk. Specifically, the hierarchical model is used for:

[0037] Step 1031: Using the product scaling method, determine the weights of each parameter in the scheme layer and the weights of each parameter in the criterion layer respectively. Based on the variable fuzzy set, determine the membership values ​​of each parameter in the scheme layer.

[0038] Step 1032: Determine the membership vector of each parameter in the criterion layer based on the membership values ​​and weights of each parameter in the scheme layer;

[0039] Step 1033: Single-value the membership vectors of each parameter in the criterion layer. Based on the single-valued results of the membership vectors of each parameter in the criterion layer and the weights of each parameter in the criterion layer, calculate the defect risk index of each lining segment.

[0040] The quantitative evaluation method for defects behind railway tunnel lining proposed in this invention integrates multiple key factors such as defect length, lining thickness ratio, and defect location. Compared with traditional single-factor or few-factor evaluation methods, it can more comprehensively reflect the defect status of tunnel lining. The tunnel is divided into segments according to deformation joints, and a lining defect evaluation index is constructed for each segment. This facilitates the rapid location of high-risk areas and provides targeted guidance for maintenance, avoiding the dominance of a single indicator in the evaluation results.

[0041] In one embodiment, it further includes:

[0042] Preprocess the ground-penetrating radar detection data according to the following steps:

[0043] Denoising of ground-penetrating radar detection data is achieved by using wavelet transform based on adaptive threshold.

[0044] Time-depth conversion is performed on the noise-reduced ground-penetrating radar detection data;

[0045] Defect signal features are extracted from the ground-penetrating radar detection data after time-depth conversion according to the set dynamic threshold.

[0046] In one embodiment, defect types include voids, incomplete compaction, and insufficient thickness in the lining;

[0047] Defect parameters include the length of the defect, the lining thickness ratio, the location, and the deterioration level.

[0048] In practical implementation, four key factors were considered: defect length, lining thickness ratio, location, and deterioration level. The weight values ​​of each factor were calculated using the product scaling method, and a lining defect evaluation index was constructed based on a variable fuzzy mathematical set. By quantitatively evaluating defects behind the tunnel lining, the maintenance and repair level of the tunnel can be improved.

[0049] Multiple survey lines (generally 5-7) are laid longitudinally along the tunnel lining cross-section using ground-penetrating radar to acquire radar detection data. Based on the collected data, the defect type (void, non-compactness, insufficient thickness) and the defect length, lining thickness ratio, location, and deterioration level are determined. The tunnel lining is divided into segments according to the tunnel lining deformation joints. For each segment, the defect index of different types of defects within the segment is determined according to the weight of each parameter. Based on the defect index of each segment, the severity of the defects in that segment is determined.

[0050] Defect length refers to the length of the defect extending longitudinally along the tunnel.

[0051] The lining thickness ratio refers to the ratio of the tested lining thickness to the designed lining thickness.

[0052] The locations are determined based on the tunnel arching line, track centerline, and tunnel centerline, including the ascending sidewall, ascending arch waist, arch crown, descending arch waist, and descending sidewall.

[0053] The deterioration level is a relevant regulation established in accordance with the deterioration assessment standards for railway bridge and tunnel structures.

[0054] The lining segment is the lining part between each two adjacent expansion joints. If the expansion joint is not obvious, the segment length is 10m.

[0055] The ground-penetrating radar detection data is preprocessed using the following method:

[0056] Data denoising: The original signal is denoised using wavelet transform based on adaptive threshold. The wavelet basis function is db4, the decomposition level is 5, and the threshold is adjusted according to the signal-to-noise ratio.

[0057] Time-depth conversion: The relative permittivity ε of the lining material was measured using a dielectric constant measuring instrument. r Establish the time-depth conversion formula:

[0058]

[0059] In the formula, d is the defect depth (m); c is the speed of light; and t is the two-way travel time of the electromagnetic wave (s).

[0060] The calculated depth should be corrected based on the depth determined on-site.

[0061] Defect signal feature extraction: Set the dynamic threshold to 3 times the standard deviation of the background noise. When the signal envelope amplitude exceeds the threshold, it is recorded as an abnormal region.

[0062] In one embodiment, a hierarchical model is constructed based on a scheme layer and a criterion layer, including:

[0063] A target layer is constructed with the goal of calculating the defect risk index based on the parameters of the scheme layer and the criterion layer.

[0064] A hierarchical model is constructed based on the scheme layer, criterion layer, and target layer.

[0065] In one embodiment, the product scaling method is used to determine the weights of each parameter in the scheme layer and the weights of each parameter in the criterion layer, including:

[0066] Each parameter in the scheme layer is compared pairwise, and the weight of each parameter in the scheme layer is determined based on the comparison results.

[0067] Each parameter in the criterion layer is compared pairwise, and the weight of each parameter in the criterion layer is determined based on the comparison results.

[0068] In practice, a three-tiered model is established, comprising a target layer (defect risk index), a criterion layer (voids, non-compactness, insufficient thickness), and a scheme layer (defect length, lining thickness ratio, defect location, and deterioration level). Based on the characteristics of the weights of railway tunnel evaluation parameters, the parameters in the criterion layer and the scheme layer are ranked according to their importance.

[0069] The evaluation parameters (such as A and B) are compared pairwise to determine the importance between the two parameters. When the two parameters are equally important, the weight is ω. A :ω B =1:1 =0.5:0.5; When parameter A is slightly heavier than parameter B, the weight is ω. A : And so on.

[0070] In one embodiment, the membership values ​​of each parameter in the scheme layer are determined based on a variable fuzzy set, including:

[0071] Using the defect location as a qualitative parameter, the membership vector corresponding to the defect location is determined according to the preset evaluation criteria.

[0072] Using the length of the defect, the lining thickness ratio, and the deterioration level as quantitative parameters, the membership degree of the defect length, lining thickness ratio, and deterioration level is calculated respectively.

[0073] In one embodiment, the membership vector of each parameter in the criterion layer is determined based on the membership values ​​and weights of each parameter in the scheme layer, including:

[0074] Based on the membership degree of the defect length, lining thickness ratio, and deterioration level, and the membership degree vector corresponding to the defect location, the membership degree matrix of each parameter in the scheme layer is determined.

[0075] Based on the membership degree matrix of each parameter in the scheme layer and the weight of each parameter in the scheme layer, the membership degree vector of each parameter in the criterion layer is determined.

[0076] In practice, the membership degrees of qualitative and quantitative parameters of the scheme layer are determined based on the theory of variable fuzzy sets.

[0077] The location of defects in the scheme layer is used as a qualitative parameter. According to the railway bridge and tunnel structure deterioration assessment standard, when the lining condition value is 1, 2, 3, or 4, the corresponding criterion layer vector is:

[0078] When there are no defects, the lining condition value is 1, and the membership vector is (1, 0, 0, 0);

[0079] When the defect is located in the sidewall, the lining condition value is 2, and the membership vector is (0, 1, 0, 0);

[0080] When the defect is located in the arch waist, the lining condition value is 3 and the membership vector is (0, 0, 1, 0);

[0081] When the defect is located at the crown, the lining condition value is 4 and the membership vector is (0, 0, 0, 1).

[0082] Figure 2 This is a schematic diagram of the quantitative parameter interval division provided in the embodiments of the present invention. The defect length and the lining thickness ratio are quantitative parameters, such as... Figure 2 As shown,

[0083] Determine the membership degree using the following formula:

[0084] X0∈[a,b];X∈[c,d];x is any point in the interval X.

[0085] When x is to the left of point M:

[0086]

[0087] When x is to the right of point M

[0088]

[0089] μ A (x)=[1+D A (x)] / 2 (Equation 4)

[0090] In the above formula, D A (x) is the relative difference function, μ A (x) represents the relative membership degree.

[0091] In the above formula, M is the midpoint value of the interval [a,b], and x is the value of any point within the interval X.

[0092] In the above formula, the membership degree is linearly distributed over the range of values, and β is 1.

[0093] Integrating qualitative and quantitative membership vectors, a membership matrix R' is formed for the scheme layer.

[0094]

[0095] u n1 u n2 u n3 u n4 denoted as the membership degree value of the interval corresponding to x.

[0096] Using the weights and relative membership degrees, and based on the qualitative and quantitative judgment criteria of the evaluation parameters, the defects behind the lining are evaluated in the order of first the scheme layer and then the criterion layer.

[0097] For example, Figure 3 This is a schematic diagram of the tunnel lining area division provided in an embodiment of the present invention. Taking the defects behind the lining of a double-track high-speed railway tunnel as an example for evaluation, the tunnel lining area division is as follows: Figure 3 The section between the arch foot and the arching line of the tunnel cross section is defined as the sidewall area, the section between the arching line and the centerline of the adjacent side track is defined as the arch waist area, and the section between the centerlines of the two tracks is defined as the arch crown area.

[0098] One survey line is placed on each of the left and right side walls, the left and right arch waists, and two survey lines are placed on the arch top area, for a total of 6 survey lines.

[0099] Ground-penetrating radar is used to collect data along the prescribed survey lines to obtain radar detection data. The tunnel dielectric constant is corrected based on on-site calibration. Software is used to process the radar data, extract defect signal characteristics, and determine the defect type.

[0100] Figure 4 This is a schematic diagram of tunnel lining defect distribution provided in an embodiment of the present invention. The tunnel cross-section is unfolded according to a horizontal projection, and the above-mentioned detection results are output in the form of a planar unfolded diagram, as shown below. Figure 4 As shown.

[0101] In the above unfolded diagram, the lining portion between each pair of adjacent expansion joints is defined as a segment. In this embodiment, it is divided into 5 segments.

[0102] Based on their impact on structural safety and stability, the importance of the criterion layers is ranked using the product scaling method. Insufficient thickness is slightly more important than voids, and voids are slightly more important than insufficient density. Therefore, the calculated weight ratio of the criterion layers is:

[0103] ω t :ω c :ω d =1.354 2 :1.354:1=0.438:0.323:0.239 (Equation 1)

[0104] In the above formula, ω t For insufficient thickness, ω c For the pore weight, ω d For non-dense weights

[0105] Similarly, the lining thickness ratio is slightly more important than the defect location, and the defect location is slightly more important than the longitudinal length. Therefore, the weight ratio of the scheme layer is calculated as follows:

[0106] ω y1 :ω y2 :ω y3 = 0.438:0.323:0.239 (Equation 2)

[0107] In the above formula, ω y1 As the weighting factor for the lining thickness ratio, ω y2 ω represents the defect location weight. d Weights are based on vertical length.

[0108] In this embodiment, the deterioration level of railway tunnels is used as the basis for classification, and the lining condition of each level is assigned a value, as shown in Table 1.

[0109] Table 1 Correspondence between Tunnel Lining Deterioration Grades and Lining Condition Values

[0110] Deterioration level Class C Grade B A1 level AA grade Lining condition value 1 2 3 4

[0111] The evaluation criteria for the solution layer are shown in Table 2.

[0112] Table 2. Assessment of Tunnel Lining Defects

[0113]

[0114] The table above divides the parameter values ​​into four standard intervals, with each interval corresponding to a specific lining condition value.

[0115] Based on the criteria for assessing the deterioration of lining defects, the standard range and variable range for each evaluation parameter are determined, as shown in Tables 3-5.

[0116] Table 3 Range of Lining Thickness Ratio

[0117] Lining condition value Standard range Variable range Midpoint M 1 [0.9,1.0) [0.81,1.0) 0.95 2 [0.75,0.9) [0.675,0.99) 0.825 3 [0.6,0.75) [0.54,0.825) 0.675 4 (0,0.6) (0,0.66) 0.3

[0118] Table 4. Range of Cavity Defect Length

[0119]

[0120]

[0121] Table 5. Range of Length for Non-compact Defects

[0122] Lining condition value Standard range Variable range Midpoint M 1 (0,3] (0,3.3] 1.5 2 (3,9] (2.4,9.6] 6.0 3 (9,10] (8.9,10) 9.5 4 - - -

[0123] x of the scheme layer data for each segment n By performing the calculations separately, we can obtain x. n The membership value u in the corresponding interval n1 u n2 u n3 u n4 And by integrating the membership vectors of the defect locations, we obtain the membership matrix of each parameter in the scheme layer for each segment.

[0124] Segment 1:

[0125]

[0126] Segment 2:

[0127]

[0128] Segment 3:

[0129]

[0130] Segment 4:

[0131]

[0132] Segment 5:

[0133]

[0134] According to the formula:

[0135] R = ω yi R'=[r1 r2 r3 r4] (Equation 3)

[0136] Determine the membership vector of the criterion layer parameters.

[0137] In the formula: R is the membership vector, ω yi R' represents the weights of the scheme layer, and R' is the membership matrix.

[0138] r1, r2, r3, and r4 are the products of the scheme layer weights and membership values.

[0139] Based on Equation 4, the membership vector of the criterion layer is single-valued to obtain the technical status value vector of each stage of the scheme layer:

[0140]

[0141] Z1 = [2.56 3.35 3.56 2.21]

[0142] Z2 = [2.21 2.88 4]

[0143] Z3 = [3.77]

[0144] Z4 = [2.54 3.03]

[0145] Z5 = [3.66]

[0146] According to the formula LDI i =ω i ×Z T This allows us to obtain the technical condition index for each segment.

[0147] Where: LDI i ω represents the technical condition index for each segment. i Z represents the criterion layer weights, and Z represents the single-valued membership degree.

[0148] LDI1=1.55 LDI2=2.95 LDI3=1.65 LDI4=1.93 LDI5=1.18;

[0149] Based on the LDI values, the severity of defects in these five lining segments is as follows:

[0150] Segment 2 > Segment 4 > Segment 3 > Segment 1 > Segment 5.

[0151] This invention also provides a device for quantitatively evaluating defects behind railway tunnel linings, as described in the following embodiments. Since the principle behind this device is similar to the method for quantitatively evaluating defects behind railway tunnel linings, its implementation can refer to the implementation of the method for quantitatively evaluating defects behind railway tunnel linings; repeated details will not be elaborated further.

[0152] Figure 5 This is a schematic diagram of the defect quantification evaluation device behind railway tunnel lining provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the device includes:

[0153] The segmentation module 501 is used to determine the tunnel lining deformation joints based on the preprocessed ground-penetrating radar detection data, and to divide the railway tunnel lining corresponding to the ground-penetrating radar detection data into multiple lining segments based on the tunnel lining deformation joints.

[0154] The defect identification module 502 is used to determine the defect type and defect parameters of the defects behind the railway tunnel lining based on the pre-processed ground radar detection data and the tunnel lining deformation joint for each lining segment.

[0155] The defect evaluation module 503 is used to construct a scheme layer based on defect parameters, a criterion layer based on defect type, and a hierarchical model based on the scheme layer and criterion layer. The hierarchical model is used to determine the defect risk index of each lining segment. The defect risk index is used to quantitatively represent the defect risk.

[0156] This also includes a model processing module 5031, which is specifically used for:

[0157] The product scaling method is used to determine the weights of each parameter in the scheme layer and the weights of each parameter in the criterion layer. Based on variable fuzzy sets, the membership degree values ​​of each parameter in the scheme layer are determined. Based on the membership degree values ​​and weights of each parameter in the scheme layer, the membership degree vectors of each parameter in the criterion layer are determined. The membership degree vectors of each parameter in the criterion layer are then single-valued. Based on the single-valued results of the membership degree vectors of each parameter in the criterion layer and the weights of each parameter in the criterion layer, the defect risk index of each lining segment is calculated.

[0158] In one embodiment, a preprocessing module is further included, specifically for:

[0159] Preprocess the ground-penetrating radar detection data according to the following steps:

[0160] Denoising of ground-penetrating radar detection data is achieved by using wavelet transform based on adaptive threshold.

[0161] Time-depth conversion is performed on the noise-reduced ground-penetrating radar detection data;

[0162] Defect signal features are extracted from the ground-penetrating radar detection data after time-depth conversion according to the set dynamic threshold.

[0163] In one embodiment, defect types include voids, incomplete compaction, and insufficient thickness in the lining;

[0164] Defect parameters include the length of the defect, the lining thickness ratio, the location, and the deterioration level.

[0165] In one embodiment, the defect evaluation module 503 is specifically used for:

[0166] A target layer is constructed with the goal of calculating the defect risk index based on the parameters of the scheme layer and the criterion layer.

[0167] A hierarchical model is constructed based on the scheme layer, criterion layer, and target layer.

[0168] In one embodiment, the model processing module 5031 is specifically used for:

[0169] Each parameter in the scheme layer is compared pairwise, and the weight of each parameter in the scheme layer is determined based on the comparison results.

[0170] Each parameter in the criterion layer is compared pairwise, and the weight of each parameter in the criterion layer is determined based on the comparison results.

[0171] In one embodiment, the model processing module 5031 is specifically used for:

[0172] Using the defect location as a qualitative parameter, the membership vector corresponding to the defect location is determined according to the preset evaluation criteria.

[0173] Using the length of the defect, the lining thickness ratio, and the deterioration level as quantitative parameters, the membership degree of the defect length, lining thickness ratio, and deterioration level is calculated respectively.

[0174] In one embodiment, the model processing module 5031 is specifically used for:

[0175] Based on the membership degree of the defect length, lining thickness ratio, and deterioration level, and the membership degree vector corresponding to the defect location, the membership degree matrix of each parameter in the scheme layer is determined.

[0176] Based on the membership degree matrix of each parameter in the scheme layer and the weight of each parameter in the scheme layer, the membership degree vector of each parameter in the criterion layer is determined.

[0177] Based on the aforementioned inventive concept, such as Figure 6 As shown, the present invention also proposes a computer device 600, including a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and executable on the processor 620. When the processor 620 executes the computer program 630, it implements the aforementioned method for quantitative evaluation of defects behind railway tunnel lining.

[0178] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for quantitative evaluation of defects behind railway tunnel lining.

[0179] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method for quantitative evaluation of defects behind railway tunnel lining.

[0180] In summary, in this embodiment of the invention, based on preprocessed ground-penetrating radar (GPR) detection data, tunnel lining deformation joints are determined. Based on these deformation joints, the railway tunnel lining corresponding to the GPR detection data is divided into multiple lining segments. For each lining segment, based on the preprocessed GPR detection data and the tunnel lining deformation joints, the defect type and defect parameters of the defects behind the railway tunnel lining are determined. A scheme layer is constructed based on the defect parameters, a criterion layer is constructed based on the defect types, and a hierarchical model is constructed based on the scheme layer and the criterion layer. The hierarchical model is then used to determine the defect risk of each lining segment. The defect risk index is used to quantify defect risk. Specifically, the hierarchical model is used to: determine the weights of each parameter in the scheme layer and the criterion layer using the product scaling method; determine the membership values ​​of each parameter in the scheme layer based on variable fuzzy sets; determine the membership vectors of each parameter in the criterion layer based on the membership values ​​and weights of each parameter in the scheme layer; single-value the membership vectors of each parameter in the criterion layer; and calculate the defect risk index for each lining segment based on the single-valued results and weights of each parameter in the criterion layer. Thus, based on the defect types and parameters behind the tunnel lining, a hierarchical model is established, the weights of each parameter in the scheme layer and the criterion layer are calculated using the product scaling method, and the membership values ​​of each parameter in the scheme layer are determined based on variable fuzzy sets, constructing the defect risk index. By quantitatively evaluating defects behind the tunnel lining, the level of tunnel maintenance and repair can be improved.

[0181] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0182] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0183] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0184] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0185] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for quantitatively evaluating defects behind railway tunnel lining, characterized in that, include: Based on the pre-processed ground-penetrating radar detection data, the tunnel lining deformation joints are determined, and the railway tunnel lining corresponding to the ground-penetrating radar detection data is divided into multiple lining segments according to the tunnel lining deformation joints. For each lining segment, based on the pre-processed ground-penetrating radar detection data and the tunnel lining deformation joint, the defect type and defect parameters of the defects behind the railway tunnel lining are determined. A scheme layer is constructed based on defect parameters, a criterion layer is constructed based on defect types, and a hierarchical model is constructed based on the scheme layer and the criterion layer. The hierarchical model is used to determine the defect risk index of each lining segment. The defect risk index is used to quantitatively represent the defect risk. Specifically, the hierarchical model is used for: The product scaling method is used to determine the weights of each parameter in the scheme layer and the weights of each parameter in the criterion layer. Based on the variable fuzzy set, the membership values ​​of each parameter in the scheme layer are determined. Based on the membership values ​​and weights of each parameter in the scheme layer, determine the membership vector of each parameter in the criterion layer. The membership vectors of each parameter in the criterion layer are single-valued. Based on the single-valued results of the membership vectors of each parameter in the criterion layer and the weights of each parameter in the criterion layer, the defect risk index of each lining segment is calculated.

2. The method as described in claim 1, characterized in that, Also includes: Preprocess the ground-penetrating radar detection data according to the following steps: Denoising of ground-penetrating radar detection data is achieved by using wavelet transform based on adaptive threshold. Time-depth conversion is performed on the noise-reduced ground-penetrating radar detection data; Defect signal features are extracted from the ground-penetrating radar detection data after time-depth conversion according to the set dynamic threshold.

3. The method as described in claim 1, characterized in that, Defect types include voids, looseness, and insufficient thickness in the lining; Defect parameters include the length of the defect, the lining thickness ratio, the location, and the deterioration level.

4. The method as described in claim 1, characterized in that, A hierarchical model is constructed based on the scheme layer and the criterion layer, including: A target layer is constructed with the goal of calculating the defect risk index based on the parameters of the scheme layer and the criterion layer. A hierarchical model is constructed based on the scheme layer, criterion layer, and target layer.

5. The method as described in claim 1, characterized in that, The product scaling method is used to determine the weights of each parameter at the scheme layer and the weights of each parameter at the criterion layer, including: Each parameter in the scheme layer is compared pairwise, and the weight of each parameter in the scheme layer is determined based on the comparison results. Each parameter in the criterion layer is compared pairwise, and the weight of each parameter in the criterion layer is determined based on the comparison results.

6. The method as described in claim 1, characterized in that, Based on variable fuzzy sets, the membership values ​​of each parameter in the scheme layer are determined, including: Using the defect location as a qualitative parameter, the membership vector corresponding to the defect location is determined according to the preset evaluation criteria. Using the length of the defect, the lining thickness ratio, and the deterioration level as quantitative parameters, the membership degree of the defect length, lining thickness ratio, and deterioration level is calculated respectively.

7. The method as described in claim 6, characterized in that, Based on the membership values ​​and weights of each parameter in the scheme layer, the membership vectors of each parameter in the criterion layer are determined, including: Based on the membership degree of the defect length, lining thickness ratio, and deterioration level, and the membership degree vector corresponding to the defect location, the membership degree matrix of each parameter in the scheme layer is determined. Based on the membership degree matrix of each parameter in the scheme layer and the weight of each parameter in the scheme layer, the membership degree vector of each parameter in the criterion layer is determined.

8. A device for quantitatively evaluating defects behind railway tunnel lining, characterized in that, include: The segmentation module is used to determine the tunnel lining deformation joints based on the preprocessed ground-penetrating radar detection data, and to divide the railway tunnel lining corresponding to the ground-penetrating radar detection data into multiple lining segments based on the tunnel lining deformation joints. The defect identification module is used to determine the defect type and defect parameters of the defects behind the railway tunnel lining for each lining segment based on the pre-processed ground radar detection data and the tunnel lining deformation joints. The defect evaluation module is used to construct a scheme layer based on defect parameters, a criterion layer based on defect type, and a hierarchical model based on the scheme layer and criterion layer. The hierarchical model is used to determine the defect risk index of each lining segment. The defect risk index is used to quantitatively represent the defect risk. It also includes a model processing module, specifically used for: The product scaling method is used to determine the weights of each parameter in the scheme layer and the weights of each parameter in the criterion layer. Based on the variable fuzzy set, the membership values ​​of each parameter in the scheme layer are determined. Based on the membership values ​​and weights of each parameter in the scheme layer, the membership vectors of each parameter in the criterion layer are determined. The membership vectors of each parameter in the criterion layer are then single-valued. Based on the single-valued results of the membership vectors of each parameter in the criterion layer and the weights of each parameter in the criterion layer, the defect risk index of each lining segment is calculated.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

Images