Evaluation method, device, equipment and medium for freeze-thaw damage of concrete in tunnel with large temperature difference
Through deep convolutional neural network, the concrete freeze-thaw damage index is converted into images, and the intelligent evaluation of the risk of freeze-thaw damage in tunnel concrete is solved, which solves the problem of difficulty in accurately judging the risk of freeze-thaw damage in the existing technology and improves the objectivity of the evaluation and efficiency.
Patent Information
- Application Number
- CN202411088207.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-08-09
AI Technical Summary
The existing technology is difficult to accurately judge the risk of freeze-thaw damage of tunnel concrete. The freeze-thaw test method cannot reflect the actual working conditions. The appearance observation method cannot detect internal damage. Ultrasonic detection and infrared detection are of limited applicability in sections with greater risks.
The deep convolutional neural network is used to convert the freeze-thaw damage evaluation index into RGB values to generate images. The trained neural network is used to evaluate the risk of concrete freeze-thaw damage, and the image processing technology is used to achieve intelligent evaluation.
It improves the objectivity and evaluation efficiency of freeze-thaw damage risks, can more accurately judge the risk of freeze-thaw damage of concrete, helps optimize the proportions, and extends the service life of transportation infrastructure.
Smart Images

Figure CN118626973B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of freeze-thaw damage evaluation of concrete in a tunnel with a large temperature difference, and in particular to a freeze-thaw damage evaluation method, device, equipment and medium for concrete in a tunnel with a large temperature difference. Background Art
[0002] The groundwater level in northern my country has risen significantly. Under cold climatic conditions, tunnel concrete is often affected by freeze-thaw cycles, which poses a serious threat to its durability and safety. Therefore, it is necessary to evaluate the severity of freeze-thaw damage to tunnel concrete.
[0003] The methods for evaluating freeze-thaw damage of concrete mainly include freeze-thaw test method, appearance observation method, ultrasonic detection, infrared detection, etc. Among these methods, freeze-thaw test method is suitable for optimizing the mix ratio in the concrete mix ratio design stage. Since it is difficult for the laboratory to accurately reflect the actual working conditions, the excellent antifreeze performance ratio determined by the laboratory may not have good actual antifreeze performance; the appearance observation method is an on-site method, but it cannot detect internal damage; ultrasonic detection and infrared detection are typical non-destructive detection methods, which are suitable for detecting sections with higher risk of freeze-thaw damage. At present, there is a lack of suitable concrete freeze-thaw damage risk evaluation methods, and it is difficult to accurately judge the risk of concrete freeze-thaw damage. Summary of the invention
[0004] The embodiments of the present invention provide a method, device, equipment and medium for evaluating freeze-thaw damage of concrete in a tunnel with a large temperature difference, so as to solve the problem of accurately judging the risk of freeze-thaw damage of concrete.
[0005] In a first aspect, an embodiment of the present invention provides a method for evaluating freeze-thaw damage of concrete in a tunnel with a large temperature difference, comprising:
[0006] Obtain the freeze-thaw damage evaluation index value of the concrete to be evaluated;
[0007] Convert each freeze-thaw damage evaluation index value into an RGB value, generate a graph corresponding to each freeze-thaw damage evaluation index value based on each RGB value, and combine the graphs corresponding to each freeze-thaw damage evaluation index value to obtain a freeze-thaw damage evaluation image of the concrete to be evaluated;
[0008] The freeze-thaw damage evaluation image is input into the trained deep convolutional neural network to obtain the freeze-thaw damage evaluation result of the concrete to be evaluated.
[0009] In a possible implementation, the freeze-thaw damage evaluation index includes one or more of bubble spacing, 28d compressive strength, permeability coefficient, daily cooling rate, saturation degree and annual freeze-thaw times.
[0010] In a possible implementation, each freeze-thaw damage evaluation index value is converted into an RGB value, including:
[0011] For each freeze-thaw damage evaluation index value, the proportion of the freeze-thaw damage evaluation index value in the corresponding index value range is calculated, and the RGB value corresponding to the freeze-thaw damage evaluation index is determined based on the index value proportion and the RGB value range corresponding to the freeze-thaw damage evaluation index value; wherein, the RGB value ranges corresponding to the freeze-thaw damage evaluation index values do not overlap with each other.
[0012] In a possible implementation, before inputting the freeze-thaw damage assessment image into the trained deep convolutional neural network, the method further includes:
[0013] Acquire a freeze-thaw damage image sample set;
[0014] The initial deep convolutional neural network is trained based on the freeze-thaw damage image sample set to obtain a trained deep convolutional neural network.
[0015] In a possible implementation, obtaining a freeze-thaw damage image sample set includes:
[0016] Acquire multiple groups of freeze-thaw damage data; wherein each group of freeze-thaw damage data corresponds to a concrete freeze-thaw damage evaluation instance, including a concrete freeze-thaw damage evaluation index value and a freeze-thaw damage evaluation result;
[0017] For each group of freeze-thaw damage data, each freeze-thaw damage evaluation index value of the group of freeze-thaw damage data is converted into an RGB value, and a graph corresponding to each freeze-thaw damage evaluation index value is generated based on each RGB value, and the graphs corresponding to each freeze-thaw damage evaluation index value are combined to obtain a freeze-thaw damage evaluation image of the group of freeze-thaw damage data as a freeze-thaw damage image sample, and the freeze-thaw damage evaluation result of the group of freeze-thaw damage data is used as a sample label;
[0018] The freeze-thaw damage image samples are combined to obtain a freeze-thaw damage image sample set.
[0019] In a possible implementation, obtaining a freeze-thaw damage image sample set also includes:
[0020] Each freeze-thaw damage image sample is randomly turned upside down to obtain an expanded freeze-thaw damage image sample;
[0021] Each freeze-thaw damage image sample and each expanded freeze-thaw damage image sample are combined to obtain a freeze-thaw damage image sample set.
[0022] In one possible implementation, the deep convolutional neural network includes a first convolutional layer, a first maximum pooling layer, a second convolutional layer, a second maximum pooling layer, a third convolutional layer, a fourth convolutional layer, a fifth convolutional layer, a third maximum pooling layer and three fully connected layers, which are connected in sequence.
[0023] In a second aspect, an embodiment of the present invention provides a freeze-thaw damage assessment device for concrete in a tunnel with a large temperature difference, comprising:
[0024] An acquisition module is used to obtain the freeze-thaw damage evaluation index value of the concrete to be evaluated;
[0025] A conversion module, used to convert each freeze-thaw damage evaluation index value into an RGB value, and generate a graph corresponding to each freeze-thaw damage evaluation index value based on each RGB value, and combine the graphs corresponding to each freeze-thaw damage evaluation index value to obtain a freeze-thaw damage evaluation image of the concrete to be evaluated;
[0026] The evaluation module is used to input the freeze-thaw damage evaluation image into the trained deep convolutional neural network to obtain the freeze-thaw damage evaluation result of the concrete to be evaluated.
[0027] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the first aspect or any possible implementation method of the first aspect are implemented.
[0028] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.
[0029] The embodiment of the present invention provides a method, device, equipment and medium for evaluating freeze-thaw damage of concrete in a large temperature difference section of a tunnel. The freeze-thaw damage risk of concrete is used as the functional relationship between the freeze-thaw damage risk and the relevant indicators, and the freeze-thaw damage evaluation index value of the concrete to be evaluated is used as the input value. The advantage of the neural network system that can approximate any function with arbitrary precision is used to accurately determine the freeze-thaw damage evaluation result of the concrete to be evaluated, and obtain a more objective evaluation result. At the same time, the present invention aims at the problem that the input parameters of the deep convolutional neural network are usually images, and converts each freeze-thaw damage evaluation index value into an RGB value and then into an image, so that the freeze-thaw damage evaluation of concrete can be completed using the deep convolutional neural network, and the effective and intelligent evaluation of the freeze-thaw damage risk of concrete can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0031] Figure 1It is a flow chart for implementing a freeze-thaw damage evaluation method for concrete in a tunnel with a large temperature difference provided by an embodiment of the present invention;
[0032] Figure 2 It is a schematic diagram of the implementation process of a method for evaluating freeze-thaw damage of concrete in a tunnel with a large temperature difference provided by another embodiment of the present invention;
[0033] Figure 3 is a schematic diagram of a freeze-thaw damage assessment image provided by an embodiment of the present invention;
[0034] Figure 4 is a schematic diagram of the structure of a deep convolutional neural network provided by an embodiment of the present invention;
[0035] Figure 5 It is a structural schematic diagram of a device for evaluating freeze-thaw damage of concrete in a tunnel with a large temperature difference provided by an embodiment of the present invention;
[0036] Figure 6 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0037] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.
[0038] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.
[0039] See also Figure 1 , which shows a flow chart of the implementation of the freeze-thaw damage evaluation method for concrete in a tunnel with a large temperature difference provided by an embodiment of the present invention, and is described in detail as follows:
[0040] Step 101, obtaining the freeze-thaw damage evaluation index value of the concrete to be evaluated.
[0041] In this embodiment, indicators representing the microscopic and macroscopic properties of concrete and indicators of environmental effects can be selected to construct an evaluation index system, and specific index values can be used to evaluate the freeze-thaw damage risk of concrete.
[0042] In a possible implementation, the freeze-thaw damage evaluation index includes one or more of bubble spacing, 28d compressive strength, permeability coefficient, daily cooling rate, saturation degree and annual freeze-thaw times.
[0043] In this embodiment, the selected indicators representing the microscopic and macroscopic properties of concrete may specifically include bubble spacing (in micrometers), 28d compressive strength (in megapascals), permeability (in centimeters per second), daily cooling rate (in degrees Celsius per hour), degree of saturation (in %), and annual freeze-thaw cycles (in times).
[0044] At present, the academic and engineering circles have formed the following theories to explain the freeze-thaw damage of concrete: hydrostatic pressure theory, osmotic pressure theory, microporous ice crystal theory, low temperature adsorption theory, saturation-freezing pressure coupling theory, and bonding-stripping theory. Among these six theories, the hydrostatic pressure and osmotic pressure theories emphasize the decisive role of bubble spacing and permeability coefficient on freeze-thaw damage, the microporous ice crystal theory and the saturation-freezing pressure coupling theory have a great relationship with the degree of saturation, and the bonding-stripping theory is related to the strength of concrete. The above theories are also closely related to temperature, and the accumulation of freeze-thaw damage increases with the increase of the number of freeze-thaw cycles. Based on the above theories, the bubble spacing, 28d compressive strength, permeability, daily cooling rate, saturation and annual freeze-thaw cycles are selected as evaluation indicators in this embodiment.
[0045] Among them, the bubble spacing representing the concrete index can be obtained using the "T 0584-2020 Test method for bubble spacing coefficient of cement concrete (wire method)" in the "Test Code for Cement and Cement Concrete for Highway Engineering" (JTG 3420-2020) or the British Standard "Determination of air void characteristics in hardened concrete" (BSEN 480-11-2005); the compressive strength is obtained using the "T 0553-2005 Test method for compressive strength of cement concrete" in the "Test Code for Cement and Cement Concrete for Highway Engineering" (JTG 3420-2020); the permeability coefficient is obtained using the "6.7 The permeability coefficient of fully graded concrete is obtained by the test. The daily cooling rate is obtained by dividing the difference between the maximum temperature of the coldest day of the year and the minimum temperature of the same day by the time difference between the minimum temperature and the maximum temperature. The annual freeze-thaw times are obtained from the "National Meteorological Science Data Center". The saturation test requires sampling of concrete, recording the mass m1 of the fresh sample, drying it at 105 degrees Celsius for 24 hours to obtain the dry mass m0, and then vacuum saturating it with water for 24 hours to obtain the saturated mass m2. The saturation degree is calculated according to the following formula :
[0046]
[0047] Step 102: convert each freeze-thaw damage evaluation index value into an RGB value, generate a graph corresponding to each freeze-thaw damage evaluation index value based on each RGB value, and combine the graphs corresponding to each freeze-thaw damage evaluation index value to obtain a freeze-thaw damage evaluation image of the concrete to be evaluated.
[0048] In this embodiment, the risk of freeze-thaw damage to concrete depends on the values of the above six indicators, or there is a functional relationship between the freeze-thaw damage risk and the above six indicators. Once the six indicators are determined, the freeze-thaw damage risk is also uniquely determined. Since the neural network system can approximate any function with arbitrary precision, the present invention is inspired to use neural networks as a tool to achieve risk assessment. In recent years, in the field of deep learning, convolutional neural networks have achieved remarkable development. Currently, dozens of convolutional neural network models have achieved satisfactory accuracy in image classification. However, the factors of freeze-thaw risk, or the evaluation indicators selected by the present invention are quantitative indicators, and convolutional neural networks cannot be used. The inventor creatively converts each quantitative indicator into a picture represented by three color values of red (R), green (G), and blue (B) according to certain rules, so that the powerful tool of convolutional neural network can be used to achieve effective and intelligent evaluation of concrete freeze-thaw damage risk.
[0049] Specifically, each freeze-thaw damage evaluation index may correspond to a graph, and each graph may be filled with color using the RGB value corresponding to each freeze-thaw damage evaluation index value to obtain a plurality of color graphs, and finally the color graphs are combined into a freeze-thaw damage evaluation image, and used as input data of a deep convolutional neural network to evaluate the freeze-thaw damage of the concrete to be evaluated. Exemplarily, the graph corresponding to each freeze-thaw damage evaluation index may be a graphic bar.
[0050] Step 103: input the freeze-thaw damage assessment image into a trained deep convolutional neural network to obtain a freeze-thaw damage assessment result of the concrete to be assessed.
[0051] In this embodiment, the convolutional neural network includes at least three convolutional layers and pooling layers, and the number of parameters is not less than 3 million. In terms of network structure, lightweight network models that can be used for reference include SqueezeNet, MobileNet, ShuffleNet, Xception, etc.
[0052] The intelligent evaluation levels of freeze-thaw damage risk are negligible, low, medium, relatively high, and high. The categories of freeze-thaw damage risk evaluation results can also be set according to the functional changes of concrete affected by freeze-thaw damage.
[0053] The embodiment of the present invention utilizes the functional relationship between concrete freeze-thaw damage risk and related indicators, takes the freeze-thaw damage evaluation index value of the concrete to be evaluated as the input value, and utilizes the advantage that the neural network system can approximate any function with arbitrary precision to accurately determine the freeze-thaw damage evaluation result of the concrete to be evaluated, and obtains a more objective evaluation result. At the same time, the present invention addresses the problem that the input parameters of the deep convolutional neural network are usually images, converts each freeze-thaw damage evaluation index value into an RGB value and then into an image, so that the deep convolutional neural network can be used to complete the freeze-thaw damage evaluation of concrete, and realize the effective and intelligent evaluation of the freeze-thaw damage risk of concrete.
[0054] Compared with the prior art, the present invention improves the objectivity and efficiency of the intelligent evaluation of freeze-thaw damage risk, which is conducive to optimizing the concrete mix ratio in tunnel sections with large temperature differences, thereby increasing the service life of transportation infrastructure.
[0055] In a possible implementation, each freeze-thaw damage evaluation index value is converted into an RGB value, including:
[0056] For each freeze-thaw damage evaluation index value, the proportion of the freeze-thaw damage evaluation index value in the corresponding index value range is calculated, and the RGB value corresponding to the freeze-thaw damage evaluation index is determined based on the index value proportion and the RGB value range corresponding to the freeze-thaw damage evaluation index value; wherein, the RGB value ranges corresponding to the freeze-thaw damage evaluation index values do not overlap with each other.
[0057] In this embodiment, the range of values of the freeze-thaw damage evaluation indexes can be: the range of the bubble spacing index is (10-300 μm), the range of the 28d compressive strength index is (30-80 MPa), and the range of the permeability coefficient index is (0.05×10 -10 ~10×10 -10 The range of daily cooling rate index is (0.5 degrees Celsius / hour to 5 degrees Celsius / hour), the range of saturation index is (60% to 100%), and the range of annual freezing and thawing times is (5 to 50 times).
[0058] Correspondingly, the RGB value ranges corresponding to each freeze-thaw damage evaluation index can be: the color map RGB range of the bubble spacing index is (0, 0, 1~255), the color map RGB range of the 28d compressive strength index is (0, 1~255, 0), the color map RGB range of the permeability coefficient index is (1~255, 0, 0), the color map RGB range of the daily cooling rate index is (0, 1~255, 255), the color map RGB range of the saturation degree index is (255, 1~255, 0), and the color map RGB range of the annual freeze-thaw number index is (255, 0, 1~255).
[0059] The range of the above indicators corresponds to the size of the color spectrum RGB range, and is evenly spaced within the color spectrum RGB range. For example, for concrete with a bubble spacing of 200 microns, the blue value (B) of its color spectrum RGB value is 1+(255-1)×(100-10) / 200=115, that is, its color spectrum RGB value is (0, 0, 115). In this way, the values of each indicator can be converted into RGB values, and the RGB values of each indicator value do not conflict with each other.
[0060] In a possible implementation, before inputting the freeze-thaw damage assessment image into the trained deep convolutional neural network, the method further includes:
[0061] Acquire a freeze-thaw damage image sample set;
[0062] The initial deep convolutional neural network is trained based on the freeze-thaw damage image sample set to obtain a trained deep convolutional neural network.
[0063] In this embodiment, before using the trained deep convolutional neural network to evaluate freeze-thaw damage, the initial deep convolutional neural network needs to be trained so that the deep convolutional neural network can learn the functional relationship between each freeze-thaw damage evaluation index and the freeze-thaw damage risk.
[0064] In a possible implementation, obtaining a freeze-thaw damage image sample set includes:
[0065] Acquire multiple groups of freeze-thaw damage data; wherein each group of freeze-thaw damage data corresponds to a concrete freeze-thaw damage evaluation instance, including a concrete freeze-thaw damage evaluation index value and a freeze-thaw damage evaluation result;
[0066] For each group of freeze-thaw damage data, each freeze-thaw damage evaluation index value of the group of freeze-thaw damage data is converted into an RGB value, and a graph corresponding to each freeze-thaw damage evaluation index value is generated based on each RGB value, and the graphs corresponding to each freeze-thaw damage evaluation index value are combined to obtain a freeze-thaw damage evaluation image of the group of freeze-thaw damage data as a freeze-thaw damage image sample, and the freeze-thaw damage evaluation result of the group of freeze-thaw damage data is used as a sample label;
[0067] The freeze-thaw damage image samples are combined to obtain a freeze-thaw damage image sample set.
[0068] In this embodiment, multiple concrete freeze-thaw damage instances can be retrieved from channels such as China National Knowledge Infrastructure, Wanfang Database, Elsevier, and Springer Database, from which freeze-thaw damage data can be extracted. Based on the steps in the above embodiment, the freeze-thaw damage data is converted into freeze-thaw damage image samples, i.e., sample labels, to construct a freeze-thaw damage image sample set.
[0069] In a possible implementation, obtaining a freeze-thaw damage image sample set also includes:
[0070] Each freeze-thaw damage image sample is randomly turned upside down to obtain an expanded freeze-thaw damage image sample;
[0071] Each freeze-thaw damage image sample and each expanded freeze-thaw damage image sample are combined to obtain a freeze-thaw damage image sample set.
[0072] In this embodiment, data enhancement and sample expansion can be performed by randomly inverting each freeze-thaw damage image sample and randomly exchanging the positions of indicator graphics in each freeze-thaw damage image sample to increase the number of training samples and improve the training effect of the convolutional neural network.
[0073] In one possible implementation, the deep convolutional neural network includes a first convolutional layer, a first maximum pooling layer, a second convolutional layer, a second maximum pooling layer, a third convolutional layer, a fourth convolutional layer, a fifth convolutional layer, a third maximum pooling layer and three fully connected layers, which are connected in sequence.
[0074] In this embodiment, the structure of the deep convolutional neural network can be as follows: Figure 4 As shown, the sizes of each layer are:
[0075] The first convolution layer is 96×11×11, with a stride of 4, the first maximum pooling layer is 3×3, with a stride of 2, the second convolution layer is 256×5×5, with a padding of 2, the second maximum pooling layer is 3×3, with a stride of 2, the third convolution layer is 384×3×3, with a padding of 1, the fourth convolution layer is 384×3×3, with a padding of 1, the fifth convolution layer is 256×3×3, with a padding of 1, and the third maximum pooling layer is 3×3, with a stride of 2.
[0076] Depend on Figure 4 It can be seen that after the freeze-thaw damage evaluation image with a size of 227×227 is input into the deep convolutional neural network, the final output is data indicating the risk level of freeze-thaw damage, with a size of 5.
[0077] In a specific embodiment, Figure 2 As shown in Figure 1, the complete steps for implementing freeze-thaw damage risk assessment include:
[0078] 1) Select indicators representing the micro- and macro-properties of concrete and indicators of environmental effects to construct an evaluation index system;
[0079] 2) Select no less than 2,000 examples with clear freeze-thaw damage risk ratings;
[0080] 3) According to the specified rules, the above indicators are transformed into Figure 2 The colored graphic bar on the left side of the middle is expressed;
[0081] 4) Build a deep convolutional neural network with a certain number of convolutional layers and pooling layers;
[0082] 5) Perform network parameter training to obtain the optimal parameter set;
[0083] 6) Convert the indicators of concrete to be evaluated into Figure 2 The colored graph bar on the left side of the figure is input into the above trained network for risk assessment. The processing process of the deep convolutional neural network is as follows: Figure 2 As shown in the middle part, we get Figure 2 The risk assessment results on the right.
[0084] Based on the above steps, taking the freeze-thaw damage risk assessment of a highway tunnel in Northeast China as an example, the specific implementation steps include:
[0085] (1) Determine the freeze-thaw damage risk index system and index value. The project used air-entrained concrete as the lining, with an air content of 6%. The bubble spacing coefficient measured by the wire method was 106 microns, the 28d compressive strength was 52 MPa, and the permeability coefficient was 0.67×10 -10 centimeters per second, the daily cooling rate index is 1.1 degrees Celsius per hour, the water saturation degree is 93%, and the annual freezing and thawing times are 46 times.
[0086] (2) A total of 2,500 concrete examples were retrieved from CNKI, Wanfang Database, Elsevier, and Springer databases, and their six index values and freeze-thaw damage evaluation were sorted out and made into colored graphs.
[0087] (3) Build Figure 4 The convolutional neural network shown.
[0088] (4) The colored graphic strips generated by step 3 for each concrete instance are randomly inverted to form a graphic dataset. The corresponding evaluations are used as labels to train the convolutional neural network built in step 4).
[0089] (5) Convert the indicators of the concrete to be evaluated into RGB values and generate a graphic bar. According to the conversion rules given in the above steps, the color map RGB value of the bubble spacing indicator of the concrete to be tested is calculated to be (0, 0, 85), the color map RGB value of the 28d compressive strength indicator is (0, 103, 0), the color map RGB value of the permeability index is (17, 0, 0), the color map RGB value of the daily cooling rate index is (0, 35, 255), the color map RGB value of the saturation index is (255, 211, 0), and the color map RGB value of the annual freeze-thaw number index is (255, 0, 232). The generated color graphic bar is as follows: Figure 3 The above trained network is input for risk assessment, and the evaluation conclusion is "low".
[0090] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0091] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.
[0092] Figure 5 The schematic diagram of the structure of the freeze-thaw damage assessment device for concrete in a large temperature difference section of a tunnel provided by an embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:
[0093] like Figure 5 As shown, the freeze-thaw damage evaluation device 5 for concrete in a tunnel with a large temperature difference comprises:
[0094] An acquisition module 51 is used to obtain the freeze-thaw damage evaluation index value of the concrete to be evaluated;
[0095] A conversion module 52 is used to convert each freeze-thaw damage evaluation index value into an RGB value, generate a graph corresponding to each freeze-thaw damage evaluation index value based on each RGB value, and combine the graphs corresponding to each freeze-thaw damage evaluation index value to obtain a freeze-thaw damage evaluation image of the concrete to be evaluated;
[0096] The evaluation module 53 is used to input the freeze-thaw damage evaluation image into the trained deep convolutional neural network to obtain the freeze-thaw damage evaluation result of the concrete to be evaluated.
[0097] In a possible implementation, the freeze-thaw damage evaluation index includes one or more of bubble spacing, 28d compressive strength, permeability coefficient, daily cooling rate, saturation degree and annual freeze-thaw times.
[0098] In a possible implementation, the conversion module 52 is specifically configured to:
[0099] For each freeze-thaw damage evaluation index value, the proportion of the freeze-thaw damage evaluation index value in the corresponding index value range is calculated, and the RGB value corresponding to the freeze-thaw damage evaluation index is determined based on the index value proportion and the RGB value range corresponding to the freeze-thaw damage evaluation index value; wherein, the RGB value ranges corresponding to the freeze-thaw damage evaluation index values do not overlap with each other.
[0100] In a possible implementation, the evaluation module 53 is further used to:
[0101] Before inputting the freeze-thaw damage assessment images into the trained deep convolutional neural network, a sample set of freeze-thaw damage images is obtained;
[0102] The initial deep convolutional neural network is trained based on the freeze-thaw damage image sample set to obtain a trained deep convolutional neural network.
[0103] In a possible implementation, the evaluation module 53 is specifically used for:
[0104] Acquire multiple groups of freeze-thaw damage data; wherein each group of freeze-thaw damage data corresponds to a concrete freeze-thaw damage evaluation instance, including a concrete freeze-thaw damage evaluation index value and a freeze-thaw damage evaluation result;
[0105] For each group of freeze-thaw damage data, each freeze-thaw damage evaluation index value of the group of freeze-thaw damage data is converted into an RGB value, and a graph corresponding to each freeze-thaw damage evaluation index value is generated based on each RGB value, and the graphs corresponding to each freeze-thaw damage evaluation index value are combined to obtain a freeze-thaw damage evaluation image of the group of freeze-thaw damage data as a freeze-thaw damage image sample, and the freeze-thaw damage evaluation result of the group of freeze-thaw damage data is used as a sample label;
[0106] The freeze-thaw damage image samples are combined to obtain a freeze-thaw damage image sample set.
[0107] In a possible implementation, the evaluation module 53 is further used to:
[0108] Each freeze-thaw damage image sample is randomly turned upside down to obtain an expanded freeze-thaw damage image sample;
[0109] Each freeze-thaw damage image sample and each expanded freeze-thaw damage image sample are combined to obtain a freeze-thaw damage image sample set.
[0110] In one possible implementation, the deep convolutional neural network includes a first convolutional layer, a first maximum pooling layer, a second convolutional layer, a second maximum pooling layer, a third convolutional layer, a fourth convolutional layer, a fifth convolutional layer, a third maximum pooling layer and three fully connected layers, which are connected in sequence.
[0111] The embodiment of the present invention utilizes the functional relationship between concrete freeze-thaw damage risk and related indicators, takes the freeze-thaw damage evaluation index value of the concrete to be evaluated as the input value, and utilizes the advantage that the neural network system can approximate any function with arbitrary precision to accurately determine the freeze-thaw damage evaluation result of the concrete to be evaluated, and obtains a more objective evaluation result. At the same time, the present invention addresses the problem that the input parameters of the deep convolutional neural network are usually images, converts each freeze-thaw damage evaluation index value into an RGB value and then into an image, so that the deep convolutional neural network can be used to complete the freeze-thaw damage evaluation of concrete, and realize the effective and intelligent evaluation of the freeze-thaw damage risk of concrete.
[0112] Figure 6 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 6As shown, the electronic device 6 of this embodiment includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and executable on the processor 60. When the processor 60 executes the computer program 62, the steps in the above-mentioned embodiments of the method for evaluating freeze-thaw damage of concrete in a large temperature difference section of a tunnel are implemented, for example Figure 1 Alternatively, when the processor 60 executes the computer program 62, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 5 Functions of modules / units 51 to 53 are shown.
[0113] Exemplarily, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 62 in the electronic device 6. For example, the computer program 62 may be divided into Figure 5 Modules / units 51 to 53 are shown.
[0114] The electronic device 6 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will appreciate that Figure 6 It is only an example of the electronic device 6 and does not constitute a limitation of the electronic device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.
[0115] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0116] The memory 61 may be an internal storage unit of the electronic device 6, such as a hard disk or memory of the electronic device 6. The memory 61 may also be an external storage device of the electronic device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the electronic device 6. The memory 61 is used to store the computer program and other programs and data required by the electronic device. The memory 61 may also be used to temporarily store data that has been output or is to be output.
[0117] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0118] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0119] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0120] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0121] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0122] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0123] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned embodiments of the freeze-thaw damage evaluation method for concrete in a large temperature difference section of a tunnel can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.
[0124] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A method for evaluating freeze-thaw damage of concrete in a tunnel with a large temperature difference, characterized in that: include: Obtain freeze-thaw damage evaluation index values of the concrete to be evaluated; wherein the freeze-thaw damage evaluation index includes one or more of bubble spacing, 28d compressive strength, permeability coefficient, daily cooling rate, saturation degree, and annual freeze-thaw times; Convert each freeze-thaw damage evaluation index value into an RGB value, generate a graph corresponding to each freeze-thaw damage evaluation index value based on each RGB value, and combine the graphs corresponding to each freeze-thaw damage evaluation index value to obtain a freeze-thaw damage evaluation image of the concrete to be evaluated; Inputting the freeze-thaw damage evaluation image into a trained deep convolutional neural network to obtain a freeze-thaw damage evaluation result of the concrete to be evaluated; The step of converting each freeze-thaw damage evaluation index value into an RGB value includes: For each freeze-thaw damage evaluation index value, the proportion of the freeze-thaw damage evaluation index value in the corresponding index value range is calculated, and the RGB value corresponding to the freeze-thaw damage evaluation index is determined based on the index value proportion and the RGB value range corresponding to the freeze-thaw damage evaluation index value; wherein, the RGB value ranges corresponding to the freeze-thaw damage evaluation index values do not overlap with each other.
2. The method for evaluating freeze-thaw damage of concrete in a tunnel with a large temperature difference according to claim 1 is characterized in that: Before inputting the freeze-thaw damage assessment image into a trained deep convolutional neural network, the method further includes: Acquire a freeze-thaw damage image sample set; The initial deep convolutional neural network is trained based on the freeze-thaw damage image sample set to obtain a trained deep convolutional neural network.
3. The freeze-thaw damage evaluation method for concrete in a tunnel with a large temperature difference according to claim 2 is characterized in that: The method of obtaining a freeze-thaw damage image sample set comprises: Acquire multiple groups of freeze-thaw damage data; wherein each group of freeze-thaw damage data corresponds to a concrete freeze-thaw damage evaluation instance, including a concrete freeze-thaw damage evaluation index value and a freeze-thaw damage evaluation result; For each group of freeze-thaw damage data, each freeze-thaw damage evaluation index value of the group of freeze-thaw damage data is converted into an RGB value, and a graph corresponding to each freeze-thaw damage evaluation index value is generated based on each RGB value, and the graphs corresponding to each freeze-thaw damage evaluation index value are combined to obtain a freeze-thaw damage evaluation image of the group of freeze-thaw damage data as a freeze-thaw damage image sample, and the freeze-thaw damage evaluation result of the group of freeze-thaw damage data is used as a sample label; The freeze-thaw damage image samples are combined to obtain a freeze-thaw damage image sample set.
4. The method for evaluating freeze-thaw damage of concrete in a tunnel with a large temperature difference according to claim 3 is characterized in that: The method of acquiring a freeze-thaw damage image sample set further includes: Each freeze-thaw damage image sample is randomly turned upside down to obtain an expanded freeze-thaw damage image sample; Each freeze-thaw damage image sample and each expanded freeze-thaw damage image sample are combined to obtain a freeze-thaw damage image sample set.
5. The freeze-thaw damage evaluation method for concrete in a tunnel with a large temperature difference according to any one of claims 1 to 4, characterized in that: The deep convolutional neural network includes a first convolutional layer, a first maximum pooling layer, a second convolutional layer, a second maximum pooling layer, a third convolutional layer, a fourth convolutional layer, a fifth convolutional layer, a third maximum pooling layer and three fully connected layers, which are connected in sequence.
6. A device for evaluating freeze-thaw damage of concrete in a tunnel with a large temperature difference, characterized in that: include: An acquisition module is used to obtain freeze-thaw damage evaluation index values of concrete to be evaluated; wherein the freeze-thaw damage evaluation index includes one or more of bubble spacing, 28d compressive strength, permeability coefficient, daily cooling rate, saturation degree and annual freeze-thaw times; A conversion module, used to convert each freeze-thaw damage evaluation index value into an RGB value, and generate a graph corresponding to each freeze-thaw damage evaluation index value based on each RGB value, and combine the graphs corresponding to each freeze-thaw damage evaluation index value to obtain a freeze-thaw damage evaluation image of the concrete to be evaluated; An evaluation module, used for inputting the freeze-thaw damage evaluation image into a trained deep convolutional neural network to obtain a freeze-thaw damage evaluation result of the concrete to be evaluated; The conversion module is specifically used for: For each freeze-thaw damage evaluation index value, the proportion of the freeze-thaw damage evaluation index value in the corresponding index value range is calculated, and the RGB value corresponding to the freeze-thaw damage evaluation index is determined based on the index value proportion and the RGB value range corresponding to the freeze-thaw damage evaluation index value; wherein, the RGB value ranges corresponding to the freeze-thaw damage evaluation index values do not overlap with each other.
7. An electronic 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, the steps of the method according to any one of claims 1 to 5 are implemented.
8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.
