Long-life composite slab beam bridge vertical temperature gradient fatigue load model and construction method

Abstract

A long-life composite slab beam bridge vertical temperature gradient fatigue load model is provided. The vertical temperature gradient fatigue load model is a three-fold line type. Long-term monitoring data of the vertical temperature field of the composite slab beam is used, and a long-short memory neural network deep learning algorithm is adopted to predict the temperature history within the design service life. In combination with the equal damage equivalent principle, a long-life composite slab beam bridge vertical temperature gradient fatigue load model construction method is proposed, and a composite slab beam bridge vertical temperature gradient fatigue load model with a design service life of 200 years is constructed. The model realizes the rapid calculation of the temperature fatigue stress history of the composite slab beam bridge, and solves the problem of no load model in the temperature fatigue damage analysis of the composite slab beam bridge.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of bridge engineering, and particularly relates to a vertical temperature gradient fatigue load model and a construction method of a long-service-life composite slab beam bridge. BACKGROUND

[0002] The composite slab beam bridge usually uses an I-shaped section steel beam, and there is a certain difference in the heat conduction coefficient between the composite layer and the steel beam. Under the action of solar radiation, a complex nonlinear vertical temperature gradient is formed in the composite beam section. With the alternating change of day and night temperature gradient, the composite beam section will appear a periodic changing cyclic temperature fatigue stress, which contributes to the cumulative fatigue damage of the structure. Existing researches have shown that the coupling effect of temperature load and vehicle load can significantly increase the cumulative fatigue damage of the composite beam bridge details, and the fatigue damage under the action of temperature and vehicle cannot be simply linearly superimposed. Therefore, it is necessary to carry out long-term monitoring of the temperature field of the composite beam, predict the temperature history in the design service life by using a reasonable deep learning algorithm, combine the damage equivalent principle, propose a construction method of the vertical temperature gradient fatigue load model of the long-service-life composite slab beam bridge, construct the vertical temperature gradient fatigue load model of the long-service-life composite slab beam bridge, calculate the temperature fatigue stress history of the composite slab beam bridge, and sequentially couple the vehicle fatigue stress to analyze the temperature-vehicle coupling fatigue damage. SUMMARY

[0003] The technical problem to be solved by the application is to provide a vertical temperature gradient fatigue load model of a long-service-life composite slab beam bridge.

[0004] Another technical problem to be solved by the application is to provide a construction method of the vertical temperature gradient fatigue load model of the long-service-life composite slab beam bridge.

[0005] The vertical temperature gradient fatigue load model of the long-service-life composite slab beam bridge provided by the application is composed of formula (1):

[0006]

[0007] In formula (1), y is the vertical distance from the bottom plate lower surface, h is the composite slab beam height, h s is the steel plate beam height, h c is the composite layer height, T1 is the temperature representative value at the top plate position of the composite slab beam section, in ℃, T2 is the temperature representative value at the position of h c from the top plate of the composite slab beam section, in ℃, T3 is the temperature representative value at the position of 0.7h s from the top plate of the composite slab beam section, in ℃, T4 is the temperature representative value at the bottom plate position of the composite slab beam section, in ℃, β T (h), β T (b), β T (B), β T(k) is an intermediate variable, b is the width of the lower flange of the composite plate beam, in m, B is the width of the concrete deck of the composite plate beam bridge, in m, k is the number of I-beams in the composite plate beam, T1 0 is the initial temperature value at the top plate of the composite plate-beam section, in °C. h is the distance between the composite plate beam section and the top plate c Initial temperature value at position, in °C, T3 0 The distance between the composite plate beam section and the top plate is 0.7h s The initial temperature value at position, in °C, is the initial temperature value at the bottom plate of the composite plate beam section, in °C, N d It is the design service life, which can be 100, 150 or 200, in years.

[0008] In formula (1), preferably, the T1 0 The value range is [4.2,5.4], the unit is ℃, the value range of h is [1.2,4.0], the unit is m, the value of b is [0.3,0.6], the unit is m, the value of B is [1.5,30], the unit is m, the value of k is [2,6], and k is an integer.

[0009] More preferably, T1 in formula (1) 0 The values ​​of h, b, B, k are: T1 0 is 4.8℃, h is 1.41m, b is 0.5m, B is 6m, and k is 4.

[0010] The method for constructing a vertical temperature gradient fatigue load model for a long-life composite plate girder bridge provided by the present invention comprises the following steps:

[0011] (1) Temperature monitoring and preliminary data processing

[0012] Temperature measurement points are arranged inside the concrete composite slab and on the top, bottom and web of the steel plate beam of the composite slab beam bridge to collect temperature, which is recorded as T A (y), the collection time interval is 1 minute to 20 minutes, and the temperature gradient time history T is constructed A (y,t), where t is any moment in the measured temperature history.

[0013] (2) Standardization of raw data

[0014] Temperature gradient time history T A (y, t) is processed as follows to obtain the processing standard data T sta (y,t):

[0015]

[0016] Wherein: E(·) is the mean value of the measured temperature data, D(·) is the variance of the measured temperature data.

[0017] (3) Constructing a long short-term memory neural network

[0018] The long short-term memory neural network comprises a forgetting gate, an input gate and an output gate, and the forgetting gate and the input gate are connected in parallel and then connected in series with the output gate.

[0019] The construction method of the long short-term memory neural network is as follows:

[0020] f t =σ(W f ×(h t-1 ,x t )+b f )

[0021] I t =σ(W I ×(h t-1 ,x t )+b I )

[0022] c t =f t oc t-1 +i t otanh(W c ×(h t-1 ,x t )+b c )

[0023] o t =σ(W o ×(h t-1 ,x t )+b o )

[0024] h t =o t otanh(c t )

[0025] Wherein, f t represents the forgetting gate, I t represents the input gate, c t represents the cell state, the initial cell state matrix is set to an empty matrix, o t represents the output gate, h t represents the final output value, and o represents the element multiplication of the cell; σ(·) is a sigmoid function expression, tanh(·) is a hyperbolic tangent function expression, W f is a weight matrix of the forgetting gate, which is initially set to an identity matrix, b f is a bias term of the forgetting gate, which is initially set to a zero matrix, and W Iis the weight matrix of the input gate, b I is the bias term of the input gate, W c is the weight matrix of the cell state, b c is the bias term of the cell state, W o is the weight matrix of the output gate, b o is the bias term of the output gate.

[0026] (4) Training the long short-term memory neural network

[0027] The standard data T sta (y, t), the weight matrix, the bias term, the initial learning rate a, a e [0.001, 0.01], the number of learning times num2 e [1000, 12000], until the error of the weight matrix and the bias term of the output gate is less than 0.01, the training is completed.

[0028] The error L W of the weight matrix of the output gate is obtained as follows:

[0029]

[0030] In the formula, is the weight matrix of the output gate obtained by the u-th training.

[0031] The error L bo of the bias term of the output gate is obtained as follows:

[0032]

[0033] In the formula, is the bias term obtained by the u-th training.

[0034] (5) Predicting the temperature gradient time course of the design service life

[0035] Based on the constructed long short-term memory neural network, the last temperature data collected is taken as the initial point of prediction and input into the long short-term memory neural network to predict all data within the design service life N d , and the corresponding data standard value d of the design service life N is obtained. The temperature gradient time course corresponding to the design service life N d is obtained as follows:

[0036]

[0037] (6) Determining the equivalent fatigue temperature at the typical position

[0038] The temperature stress time course is obtained as follows:

[0039]

[0040] where σ c (y) is the stress of concrete composite layer, σ s (y) is the stress of steel box girder section, E s is the elastic modulus of steel, α s is the thermal expansion coefficient of steel, E c is the elastic modulus of composite layer material, α c is the thermal expansion coefficient of composite layer material, b s (y) is the thickness of steel beam at y position, b c (y) is the thickness of composite layer at y position, I s is the moment of inertia of steel beam section, I c is the moment of inertia of composite layer section, ρ is the structural system coefficient, M so , N so , M co , M so is the intermediate variable.

[0041] Based on the rainflow counting method, the temperature stress time history is processed to obtain the corresponding temperature stress amplitude vector within the design service life.

[0042] 1) For the stress amplitude vector A ys :

[0043]

[0044] where σ is the m1th stress amplitude at y position, and m1 represents the number of elements in the vector, which is a positive integer.

[0045] 2) For the stress amplitude vector A yc :

[0046]

[0047] where σ is the m2th stress amplitude at y position, and m2 represents the number of elements in the vector, which is a positive integer.

[0048] The equivalent temperature stress is obtained by using the above stress amplitude vector according to the following formula:

[0049] 1) For the equivalent temperature stress of steel beam range

[0050]

[0051] where σ is the i th element in the vector A ys .

[0052] 2) For the equivalent temperature stress within the combined layer

[0053]

[0054] Where, is vector A yc The jth element in .

[0055] The equivalent temperature at a typical location is constructed as follows:

[0056] 1) For the equivalent temperature within the steel beam range

[0057]

[0058] 2) For the equivalent temperature within the combined layer

[0059]

[0060] (7) Constructing a vertical temperature gradient fatigue load model

[0061] Use Matlab software to analyze the different positions y and different design service life N d The equivalent temperature is fitted using the least squares method to establish the vertical temperature gradient fatigue load model of the long-life composite plate girder bridge shown in formula (1).

[0062] The beneficial effects of the present invention are as follows:

[0063] 1. The present invention adopts the long-short-term memory neural network deep learning algorithm and the equivalent fatigue damage principle to propose a method for constructing a vertical temperature gradient fatigue load model for long-life composite plate-girder bridges, realizing the extension of short-term temperature history to long-life design service life.

[0064] 2. This paper uses long-term measured temperature field data of highway composite plate girder bridges to construct a vertical temperature gradient fatigue load model that can be used for fatigue design and evaluation of composite plate girder bridges with a design service life of 200 years. The constructed vertical temperature gradient fatigue load model takes into account the composite plate girder cross-sectional height h, concrete bridge deck width B, bottom plate width b, number of steel plate girders k, and design service life N. d impact. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 The temperature representative value distribution of the vertical temperature gradient fatigue load model for composite plate-girder bridges.

[0066] Figure 2 This is a flow chart for constructing the model of the present invention.

[0067] Figure 3 Temperature history prediction results for long short-term memory neural network.

[0068] Figure 4 Layout of measured temperature measuring points for composite slab girder.

[0069] Figure 5 Measured temperature history curve for composite slab girder bridge.

[0070] Figure 6 Stress amplitude histogram of measured temperature field for composite slab girder bridge. DETAILED DESCRIPTION

[0071] The application will be further described in detail below in conjunction with the drawings and examples, but the application is not limited to these examples.

[0072] Example 1

[0073] The long-life composite slab girder bridge vertical temperature gradient fatigue load model involved in this example is composed of formula (1):

[0074]

[0075] In formula (1), y is the vertical distance from the typical position to the top plate of the cross section, h is the height of the composite slab girder, h s is the height of the steel plate girder, h c is the height of the composite layer, T1 is the representative value of the temperature at the top plate position of the cross section of the composite slab girder, in ℃, T2 is the representative value of the temperature at the position h c from the top plate of the cross section of the composite slab girder, in ℃, T3 is the representative value of the temperature at the position 0.7h s from the top plate of the cross section of the composite slab girder, in ℃, T4 is the representative value of the temperature at the bottom plate position of the cross section of the composite slab girder, in ℃, β T (h), β T (b), β T (B), β T (k) is an intermediate variable, b is the width of the bottom plate of the composite slab girder, in m, B is the width of the concrete deck slab of the composite slab girder bridge, in m, k is the number of I-beams in the composite slab girder, T1 0 is the initial value of the temperature at the top plate position of the cross section of the composite slab girder, in ℃, is the initial value of the temperature at the position h c from the top plate of the cross section of the composite slab girder, in ℃, T3 0 is the initial value of the temperature at the position 0.7h s from the top plate of the cross section of the composite slab girder, in ℃, is the initial value of the temperature at the bottom plate position of the cross section of the composite slab girder, in ℃, N dThe design service life is 100, 150 or 200 years, and the unit is year.

[0076] In the formula (1), the beam height h is 1.41 m, wherein the steel plate beam height h s is 1.2 m, the composite layer height h c is 0.21 m, the concrete bridge deck width B is 6.0 m, the bottom plate width b is 0.5 m, the number of I-beams k is 4, the value of T1 0 is 4.8℃, and the corresponding composite slab beam bridge vertical temperature gradient fatigue load model is constructed, wherein the temperature representative values corresponding to the long-life design service life of 100 years, 150 years and 200 years are shown in Table 1. The temperature representative value distribution in the vertical temperature gradient fatigue load model constructed according to the parameters is shown in Figure 1 .

[0077] Table 1 Temperature representative values of long-life composite slab beam bridge vertical temperature gradient fatigue load model

[0078]

[0079] As shown in Figure 2 , the construction method of the long-life composite slab beam bridge vertical temperature gradient fatigue load model comprises the following steps:

[0080] (1) Temperature monitoring and preliminary data processing

[0081] Temperature measuring points are arranged on the inside of the concrete composite slab and the top plate, bottom plate and web of the steel plate beam of the composite slab beam bridge for temperature collection, denoted as T A (y), the collection time interval is 1 minute to 20 minutes, and a temperature gradient time history T A (y, t) is constructed, wherein t is any time in the measured temperature history, and in this embodiment, t is 5 minutes.

[0082] (2) Standardization processing of original data

[0083] The temperature gradient time history T A (y, t) is processed according to the following formula to obtain the processed standard data T sta (y, t):

[0084]

[0085] In the formula, E(·) is the mean value of the measured temperature data, and D(·) is the variance of the measured temperature data.

[0086] (3) Construction of long short-term memory neural network

[0087] The long short-term memory neural network includes a forgetting gate, an input gate and an output gate, and the forgetting gate and the input gate are connected in parallel and then connected in series with the output gate.

[0088] The construction method of the long short-term memory neural network is as follows:

[0089] f t = σ(W f ×(h t-1 ,x t )+b f )

[0090] I t = σ(W I ×(h t-1 ,x t )+b I )

[0091] c t = f t oc t-1 +i t otanh(W c ×(h t-1 ,x t )+b c )

[0092] o t = σ(W o ×(h t-1 ,x t )+b o )

[0093] h t = o t otanh(c t )

[0094] In the formula, f t represents a forget gate, I t represents an input gate, c t represents a cell state, an initial cell state matrix is set to an empty matrix, o t represents an output gate, h t represents a final output value, o the symbol represents the element multiplication of the cell, σ(·) is a sigmoid function expression, tanh(·) is a hyperbolic tangent function expression, W f is a weight matrix of the forget gate, which is initially set to a unit matrix, b f is a bias term of the forget gate, which is initially set to a zero matrix, W I is a weight matrix of the input gate, b I is a bias term of the input gate, W c is a weight matrix of the cell state, b c is a bias term of the cell state, W o is a weight matrix of the output gate, b o is a bias term of the output gate.

[0095] (4) Training the long short-term memory neural network

[0096] The standard data T sta (y, t), the weight matrix, and the bias term are input into the long short-term memory neural network for training, the initial learning rate a, a ∈ [0.001, 0.01], the number of learning times num2 ∈ [1000, 12000], until the error of the weight matrix and the bias term of the output gate is less than 0.01, the training is completed, in this embodiment, a = 0.01, num2 = 1200.

[0097] The error L W of the weight matrix of the output gate is obtained as follows:

[0098]

[0099] In the formula, is the output gate weight matrix obtained in the u-th training.

[0100] The error L bo of the bias term of the output gate is obtained as follows:

[0101]

[0102] In the formula, is the bias term obtained in the u-th training.

[0103] (5) Predicting the temperature gradient time history of the design service life

[0104] Based on the constructed long short-term memory neural network, the last collected temperature data is input into the long short-term memory neural network as the initial point of prediction to predict all data within the design service life N d , and obtain the corresponding data standard value d of the design service life N d . The prediction result is shown in Table 1. The temperature gradient time history corresponding to the design service life N is obtained as follows: Figure 3

[0105]

[0106] (6) Determining the equivalent fatigue temperature at the typical position

[0107] The temperature stress time history is obtained as follows:

[0108]

[0109] In the formula, σ c (y) is the stress of the concrete composite layer, σ s (y) is the stress of the steel box girder section, E​s E is the elastic modulus of steel material, a s a is the thermal expansion coefficient of steel material, E c E is the elastic modulus of composite layer material, a c a is the thermal expansion coefficient of composite layer material, b s (y) is the thickness of steel beam at y position, b c (y) is the thickness of composite layer at y position, I s I is the moment of inertia of steel beam section, I c I is the moment of inertia of composite layer section, p is the structural system coefficient, M so , N so , M co , M so is an intermediate variable, I c I is the moment of inertia of composite layer section, p is the structural system coefficient, M so , N so , M co , M so is an intermediate variable, E s in the embodiment is 2.06 x 10 5 MPa, a s is 1.1 x 10 -5 ℃ -1 , E c in the embodiment is 3.45 x 10 4 MPa, a s is 1.1 x 10 -5 ℃ -1 .

[0110] The temperature stress time history is processed based on the rainflow counting method to obtain the corresponding temperature stress amplitude vector within the design service life.

[0111] 1) For the stress amplitude vector A ys in the range of steel beam:

[0112]

[0113] In the formula, is the m1th stress amplitude at y position, m1 represents the number of elements in the vector, and is a positive integer.

[0114] 2) For the stress amplitude vector A yc in the range of composite layer:

[0115]

[0116] In the formula, is the m2th stress amplitude at y position, m2 represents the number of elements in the vector, and is a positive integer.

[0117] The equivalent temperature stress is obtained by using the stress amplitude vector as follows:

[0118] 1) For the equivalent temperature stress in the steel beam range

[0119]

[0120] In the formula, is the vector A ys The i-th element in the vector.

[0121] 2) For the equivalent temperature stress in the composite layer range

[0122]

[0123] In the formula, is the vector A yc The j-th element in the vector.

[0124] The equivalent temperature at the typical position is constructed as follows:

[0125] 1) For the equivalent temperature in the steel beam range

[0126]

[0127] 2) For the equivalent temperature in the composite layer range

[0128]

[0129] (7) Construction of vertical temperature gradient fatigue load model

[0130] Using Matlab software, the equivalent temperature at different positions y and different design service life N d is fitted by least squares method to establish the vertical temperature gradient fatigue load model of long-life composite slab beam bridge of formula (1).

[0131] Example 2

[0132] The long-life composite slab beam bridge vertical temperature gradient fatigue load model involved in this embodiment is shown in formula (1), and the construction method is the same as that of example 1.

[0133] In formula (1), the beam height h is selected as 1.2 m, wherein the steel plate beam height h s is 1.0 m, the composite layer height h c is 0.2 m, the concrete deck slab width B is 1.5 m, the bottom plate width b is 0.3 m, the number of I-beams k is 2, T1 04.2℃, and the other parameters are the same as those in Example 1. The vertical temperature gradient fatigue load model of the long-life composite slab girder bridge is constructed, and the temperature representative values corresponding to the design service life of 100 years, 150 years and 200 years are shown in Table 2. The temperature representative values of the vertical temperature gradient fatigue load model constructed according to the parameters are shown in Table 2. Figure 1

[0134] Table 2 Temperature representative values of the vertical temperature gradient fatigue load model of the long-life composite slab girder bridge

[0135]

[0136] Example 3

[0137] The vertical temperature gradient fatigue load model of the long-life composite slab girder bridge involved in this example is shown in formula (1), and the construction method is the same as that in Example 1.

[0138] In formula (1), the beam height h is selected as 4.0 m, wherein the steel plate beam height h s is 3.5 m, the composite layer height h c is 0.5 m, the concrete deck plate width B is 30.0 m, the bottom plate width b is 0.6 m, the number of I-beams k is 6, and the value of T1 0 is 5.4℃, and the other parameters are the same as those in Example 1. The corresponding vertical temperature gradient fatigue load model of the long-life composite slab girder bridge is constructed, and the temperature representative values corresponding to the design service life of 100 years, 150 years and 200 years are shown in Table 3. The temperature representative values of the vertical temperature gradient fatigue load model constructed according to the parameters are shown in Table 3. Figure 1

[0139] Table 3 Temperature representative values of the vertical temperature gradient fatigue load model of the long-life composite slab girder bridge

[0140]

[0141] Test 1

[0142] In order to verify the effect of the long-life composite slab girder bridge vertical temperature gradient fatigue load model, the inventors used the composite slab girder bridge vertical temperature gradient fatigue load model and its construction method of Example 1 to arrange vertical temperature sensors for the composite slab test beam of Chang'an University Wei River Campus and conduct long-term temperature field monitoring. The real bridge photo is shown in

[0143] Figure 4

[0144] I. Long-term monitoring instrument

[0145] The monitoring instrument is a 60-channel JM3813 multifunctional acquisition instrument produced in Yangzhou, Jiangsu, and the temperature measuring point uses a three-wire Pt100 sensor. ​​​

[0146] II. Temperature measurement point arrangement

[0147] Temperature measurement points were arranged on the top plate, bottom plate and web of the test composite steel plate girder, and temperature collection was performed. The time interval for each temperature collection was set to 5 minutes, and the specific arrangement of the measurement points is shown in FIG. 2, which is specifically as follows: the temperature measurement points arranged on the steel webs on both sides of the composite steel plate girder in the height direction are expressed by the vertical distance from the upper surface of the top plate to indicate their positions, which are 0.00 m, 0.12 m, 0.2 m, 0.21 m, 0.26 m, 0.36 m, 0.51 m, 0.96 m, 1.41 m, h, wherein h is the height of the composite steel plate girder. The obtained temperature time history is shown in FIG. 3, which is denoted as T

[0148] Figure 4 Figure 5 te (y, t).

[0149] III. Effect analysis of vertical temperature gradient fatigue load model

[0150] The stress time history at different heights was obtained according to the temperature stress simplified formula, wherein the stress calculation formula is as follows:

[0151]

[0152] In the formula, σ c (y) is the stress of the composite layer of concrete, σ s (y) is the stress of the steel box girder section, E s is the elastic modulus of steel, α s is the thermal expansion coefficient of steel, E c is the elastic modulus of the pavement layer material, α c is the thermal expansion coefficient of the pavement layer material, A s is the cross-sectional area of the flat steel box girder, A c is the cross-sectional area of the pavement layer, I s is the moment of inertia of the flat steel box girder section, I c is the moment of inertia of the pavement layer section, and γ is the structural system coefficient. In this example, E s is 2.06 × 10 5 MPa, α s is 1.1 × 10 -5 ℃ -1 , E c is 3.45 × 10 4 MPa, and α c is 1.1 × 10 -5 ℃ -1 .

[0153] ​​Taking the butt weld of the bottom plate of a composite slab girder bridge as an example, the temperature stress history was plotted based on the measured temperature data, the rainflow counting method was used to count the temperature stress amplitude cycles, and the temperature stress amplitude histogram was obtained, as shown in Figure 6 The equivalent fatigue stress was calculated based on the measured results, and the result was 9.2 MPa.

[0154] Based on the vertical temperature gradient fatigue load model of the composite slab girder bridge, the temperature stress history was constructed and the temperature stress amplitude was analyzed. The height of the girder h is 1.41 m, the width of the concrete bridge deck B is 4.5 m, the width of the bottom plate b is 0.5 m, the number of I-beams k is 2, y=0, the design service life N d is 100 years, and the equivalent fatigue stress is obtained by substituting the following formula;

[0155] σ eq (y)=α s ×E s ×T(y)

[0156] The equivalent temperature fatigue stress is 9.4 MPa, which is basically consistent with the equivalent fatigue stress calculated from the measured results. It shows that the established vertical temperature gradient fatigue load model of the composite slab girder bridge has good applicability and can be used for vertical temperature and temperature-vehicle coupled fatigue damage calculation of the composite slab girder bridge.

Claims

1. A vertical temperature gradient fatigue load model for long-life composite plate girder bridges, characterized by The model is composed of formula (1): In formula (1), y is the vertical distance from the bottom surface of the bottom plate, h is the height of the composite plate beam, and h s is the height of the steel plate beam, h c is the height of the combined layer, T1 is the temperature representative value at the top plate of the combined plate beam section, in °C, and T2 is the distance from the top plate to the combined plate beam section. c The representative value of the temperature at the position, in °C, T3 is the composite plate beam section 0.7h away from the top plate s The temperature representative value at the position, unit is ℃, T4 is the temperature representative value at the bottom plate position of the composite plate beam section, unit is ℃, β T (h), β T (b), β T (B), β T (k) is an intermediate variable, b is the width of the lower flange of the composite plate beam, in m, B is the width of the concrete deck of the composite plate beam bridge, in m, k is the number of I-beams in the composite plate beam, T1 0 is the initial temperature value at the top plate of the composite plate-beam section, in °C. h is the distance between the composite plate beam section and the top plate c Initial temperature value at position, in °C, T3 0 The distance between the composite plate beam section and the top plate is 0.7h s The initial temperature value at position, in °C, is the initial temperature value at the bottom plate of the composite plate beam section, in °C, N d It is the design service life, which can be 100, 150 or 200, in years.

2. The vertical temperature gradient fatigue load model for long-life composite plate girder bridges according to claim 1 is characterized by: In formula (1), the T1 0 The value range is [4.2,5.4], the unit is ℃, the value range of h is [1.2,4.0], the unit is m, the value of b is [0.3,0.6], the unit is m, the value of B is [1.5,30], the unit is m, the value of k is [2,6], and k is an integer.

3. The vertical temperature gradient fatigue load model for long-life composite plate girder bridges according to claim 1 is characterized in that T1 described in formula (1) 0 The values ​​of h, b, B, k are: T1 0 is 4.8℃, h is 1.41m, b is 0.5m, B is 6m, and k is 4.

4. A method for constructing a vertical temperature gradient fatigue load model for a long-life composite plate girder bridge according to claim 1, comprising the following steps: (1) Temperature monitoring and preliminary data processing Temperature measurement points are arranged inside the concrete composite slab and on the top, bottom and web of the steel plate beam of the composite slab beam bridge to collect temperature, which is recorded as T A (y), the collection time interval is 1 minute to 20 minutes, and the temperature gradient time history T is constructed A (y, t), where t is any moment in the measured temperature history; (2) Standardization of raw data Temperature gradient time history T A (y, t) is processed as follows to obtain the processing standard data T sta (y,t): Where: E(·) is the mean of the measured temperature data, D(·) is the variance of the measured temperature data; (3) Constructing a long-short memory neural network The long short-term memory neural network consists of a forget gate, an input gate, and an output gate. The forget gate is connected in parallel with the input gate and then in series with the output gate. The construction method of the long short-term memory neural network is as follows: f t =σ(W f ×(h t-1 ,x t )+b f ) I t =σ(W I ×(h t-1 ,x t )+b I ) c t =f t oc t-1 +i t otanh(W c ×(h t-1 ,x t )+b c ) the t =σ(W o ×(h t-1 ,x t )+b o ) h t =o t otanh(c t ) Where, f t represents the forget gate, I t represents the input gate, c t Represents the cell state, the initial cell state matrix is ​​set to an empty matrix, o t represents the output gate, h t Represents the final output value, the o symbol represents the prime multiplication of the unit; σ(·) is the sigmoid function expression, tanh(·) is the hyperbolic tangent function expression, W f is the weight matrix of the forget gate, which is initially set to the unit matrix, b f is the bias term of the forget gate, initially set to zero matrix, W I is the weight matrix of the input gate, b I is the bias term of the input gate, W c is the weight matrix of the unit state, b c is the bias term of the unit state, W o is the weight matrix of the output gate, b o is the bias term of the output gate; (4) Training long short-term memory neural network The standard data T sta (y, t), weight matrix, and bias term are input into the long short-term memory neural network for training, with an initial learning rate α, α∈[0.001,0.01], and the number of learning times num2∈[1000,12000], until the error between the weight matrix and bias term of the output gate is less than 0.01, and the training is completed; The error L of the weight matrix of the output gate W According to the following formula: Where, is the output gate weight matrix obtained from the u-th training; The error L of the output gate bias term bo According to the following formula: Where, is the bias term obtained from the u-th training; (5) Predicting the temperature gradient time course during the design service life Based on the constructed long short-term memory neural network, the last temperature data collected is used as the initial point of prediction and input into the long short-term memory neural network to calculate the design service life N. d All the data in the prediction are used to obtain the design service life N d Corresponding data standard value The design service life N is obtained by the following formula: d Corresponding temperature gradient time history (6) Determine the equivalent fatigue temperature at typical locations The temperature stress history is obtained from the following formula: Where, σ c (y) is the stress of the concrete composite layer, σ s (y) is the cross-sectional stress of the steel box girder, E s is the elastic modulus of steel, α s is the thermal expansion coefficient of steel, E c is the elastic modulus of the combined layer material, α c is the thermal expansion coefficient of the combined layer material, b s (y) is the thickness of the steel beam at position y, b c (y) is the thickness of the combined layer at position y, I s is the moment of inertia of the steel beam section, I c is the moment of inertia of the combined layer section, ρ is the structural system coefficient, M so 、N so 、M co 、M so is an intermediate variable; The temperature stress time history is processed based on the rain flow counting method to obtain the temperature stress amplitude vector corresponding to the design service life: 1) For the stress amplitude vector A within the steel beam range ys : Where, is the m1th stress amplitude at the y position, where m1 represents the number of elements in the vector and is a positive integer; 2) For the stress amplitude vector A within the combined layer yc : Where, is the m2th stress amplitude at the y position, where m2 represents the number of elements in the vector and is a positive integer; The equivalent temperature stress is obtained by using the above stress amplitude vector as follows: 1) For the equivalent temperature stress within the steel beam range Where, is vector A ys The i-th element in; 2) For the equivalent temperature stress within the combined layer Where, is vector A yc The jth element in ; The equivalent temperature at a typical location is constructed as follows: 1) For the equivalent temperature within the steel beam range 2) For the equivalent temperature within the combined layer (7) Constructing a vertical temperature gradient fatigue load model Use Matlab software to analyze the different positions y and different design service life N d The equivalent temperature is fitted using the least squares method to establish the vertical temperature gradient fatigue load model of the long-life composite plate girder bridge shown in formula (1).

Images