A method for separating load effects of dedicated rail bridges

Abstract

A method for separating load effects on a dedicated track bridge comprises the following specific steps: 1. Identifying the train passing phase; 2. Using a nonlinear model to separate train load and temperature load effect data; 3. Using an adaptive algorithm with a memory effect to remove temperature load effect data; 4. Using the multi-scale singular value decomposition (MS-SVD) method to process monitoring data; 5. Using a joint distribution model based on probability theory to optimally estimate the separation of temperature and train load effect data; and 6. Describing the temporal dynamics of train load and temperature load using a state transition matrix. The present invention improves the accuracy of monitoring data: Through adaptive data separation technology, the present invention effectively distinguishes between train load effects and temperature load effects in bridge health monitoring data, avoiding interference from slowly changing factors such as degradation effects, and significantly improving the accuracy of bridge structure health assessment results.

Description

Technical Field

[0001] The present invention relates to the field of bridge health status monitoring, and in particular to a method for separating load effects of a dedicated track bridge. Background Art

[0002] In bridge health monitoring systems, real-time structural response information typically includes the superposition of multiple load effects, primarily train load effects, temperature load effects, and degradation effects. These response data reflect the overall performance of the bridge structure under different conditions. Degradation effects, such as concrete shrinkage and creep and steel corrosion, are slow and ongoing processes. Although they have long-term impacts on bridge health, they exhibit minimal short-term changes and can generally be ignored. In contrast, train load effects and temperature load effects exhibit significant differences in signal frequency and amplitude. Train load effects manifest as high-frequency, short-term peak amplitudes, originating from the instantaneous forces exerted by trains passing over bridges. Temperature load effects, on the other hand, gradually accumulate as external climate conditions change, presenting a low-frequency, long-term, and relatively stable response. This difference in frequency and amplitude makes it possible to separate load effects.

[0003] However, existing technologies still have limitations when it comes to separating the effects of train and temperature loads. Due to the complexity of bridge structures and the potential for noise and abnormal fluctuations in monitoring data, accurate separation of load effects based solely on response characteristics is difficult to achieve, thus compromising the accuracy of data analysis. In practice, environmental interference and missing data further complicate separation. Therefore, accurately distinguishing the effects of train and temperature loads under complex bridge loading conditions has become a key issue in bridge structural health assessment and early damage detection. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention proposes a method for separating train load effects and temperature load effects in bridge health monitoring systems. This method can accurately separate train load effects and temperature load effects from the structural response information obtained in real time by the bridge health monitoring system, thereby improving the health assessment accuracy and early damage detection capabilities of the bridge structure. The specific technical solution is as follows:

[0005] A method for separating load effects of a dedicated rail bridge, characterized by the following specific steps:

[0006] Step 1: Identify the train passing stage and mark the bridge train load impact data;

[0007] Step 2: Separate the train load and temperature load effect data using a nonlinear model;

[0008] Step 3: Use an adaptive algorithm with memory effect to remove the data of temperature load effect;

[0009] Step 4: Use the multi-scale singular value decomposition (MS-SVD) method to process the monitoring data to improve the separation effect;

[0010] Step 5: Use a joint distribution model based on probability theory to optimally estimate the separation of temperature and train load effect data;

[0011] Step 6: Use the state transition matrix to describe the temporal dynamic changes of train loads and temperature loads, predict the future response of the bridge under different load conditions, and provide long-term health monitoring data support.

[0012] As an optimization: Step 1 specifically includes, before data processing and load effect separation, first identifying the time period when a train passes by detecting the change in displacement data within a set time. Using a method for detecting the displacement change within each set time, the time period when a train passes is identified. When the displacement change within a set time exceeds a preset threshold ΔD, it is considered that a train has passed. After marking the data affected by the train load, the train load and temperature load effects are separated based on the differences in response characteristics, and the displacement change within each set time is further calculated:

[0013] C(t)=D end -D start

[0014] Among them, C(t) is the change per unit time, D end is the monitoring data at the end of this unit time, D start For the monitoring data at the beginning of this unit time, a change threshold ΔD is defined. When the absolute value of the displacement change within a set time |C(t)| ≥ ΔD, it is considered that a train has passed.

[0015] As an optimization: Step 2 specifically involves using a nonlinear model for the superposition of train load effect and temperature load effect as a combination of multivariable functions. The monitoring data is expressed as:

[0016] y(t)=g(T(t),L(t))+h(T(t),L(t))

[0017] where g(T(t),L(t)) is a nonlinear function that represents the coupling between temperature and train load effects and is expressed as a quadratic polynomial:

[0018] g(T(t),L(t))=a0+a1T(t)+a2L(t)+a3T(t)·L(t)

[0019] Among them, a0~a3 are a set of coefficients, which represent the influence on the objective function; a0: constant term, which represents the base value or offset of the function g(T(t), L(t)) when both temperature T(t) and load L(t) are zero; a1: coefficient of temperature T(t), which represents the degree of influence of temperature on g(T(t), L(t)); a2: coefficient of load L(t), which represents the degree of influence of load on g(T(t), L(t)); a3: interaction coefficient of temperature and load T(t)·L(t), which represents the influence of the interaction effect between temperature and load on g(T(t), L(t));

[0020] h(T(t), L(t)) represents the high-order nonlinear relationship between the two, using a cubic polynomial function, specifically:

[0021] h(T(t),L(t))=b0+b1T(t) 2 +b2L(t) 3

[0022] Among them, b0~b2 are a set of coefficients, which represent the influence on the objective function; b0: constant term, which represents the base value or offset of the function h(T(t), L(t)) when both temperature T(t) and load L(t) are zero; b1: square correlation coefficient, which represents the influence of the square of temperature on h(T(t), L(t)); b2: cubic correlation coefficient of load L(t), which represents the influence of load on h(T(t), L(t)).

[0023] As an optimization: Step 3 specifically involves introducing an algorithm with a memory effect during the load effect separation process, dynamically adjusting parameters, and defining a historical data weight attenuation factor λ to update the calculation parameters of the load response, thereby gradually reducing the impact of past data on the current response;

[0024] The specific algorithm is:

[0025]

[0026] Among them, the decay factor λ∈(0,1) controls the decay rate of historical data; w(t) is the parameter vector (or weight vector) at time t; the learning rate η is used to adjust the update step to ensure that the model reaches the optimal state during the dynamic adaptation process; At time t, the gradient of the loss function E(w(t)) with respect to the parameter vector w(t);

[0027] The calculation formula of mean square error E(w) is as follows:

[0028]

[0029] Where N represents the number of monitoring data, which is the total number of observed data points; y i is the real data or observation value of the i-th monitoring point; w is the parameter vector of the model, which can be a weight coefficient, reflecting the influence of different factors in the model on the results; x i is the input feature vector of the i-th observation data, which is the sensor reading or environmental variable associated with the data point; w T x i To predict the value of the model, we need to combine the parameter w with the input feature x i The result of linear combination.

[0030] As an optimization: Step 4 is specifically to improve the separation effect by using the multi-scale singular value decomposition (MS-SVD) method to decompose the data matrix Y at different time scales. Suppose the data matrix is divided into multiple sub-matrices Y according to time. i , then each sub-matrix is subjected to singular value decomposition:

[0031] Y i =U i Σ i V ii T

[0032] Among them, Y i Represents the original data matrix or system output matrix, representing the data of the i-th sample or observation; U i represents the left singular vector matrix, which represents the spatial pattern of the data; ∑ i represents the singular value matrix, which represents the weight of the main components or features of the data; V i T represents the transpose of the right singular vector matrix, representing the time or direction pattern of the data;

[0033] Then the singular value matrix ∑ of all submatrices i By combining them, signal components at different time scales are obtained, and threshold screening is used to achieve finer separation.

[0034] As an optimization: Step 5 is specifically to further deal with noise and uncertainty. Using a joint distribution model based on probability theory, the randomness of the temperature load effect and the train load effect is assumed to be a joint distribution p(T(t), L(t)), and combined with the observation noise ∈, the probability model of the monitoring data is expressed as:

[0035] p(y(t)|T(t),L(t))=p(y(t)-g(T(t),L(t))-h(T(t),L(t))|0,σ 2 )

[0036] Where, y(t): represents the observed value at time t; T(t): represents the temperature value at time t; L(t): represents the load at time t; G(T(T), L(t)): represents a function related to temperature T(t) and load L(t), representing the influence of temperature and load on the structure; h(T(t), L(t)): represents another function related to temperature T(t) and load L(t), representing the influence of other factors, including noise on the response.

[0037] As an optimization: Step 6 is specifically as follows: suppose the train load effect L(t) and the temperature load effect T(t) follow their respective state transfer matrices P L and P T , then the state transition of the entire system can be expressed as:

[0038]

[0039] in represents the Kronecker product. By analyzing the long-term stable state of the Markov process, the response behavior of the future bridge under different load effects can be predicted.

[0040] The beneficial effects of the present invention are:

[0041] 1. Improve the accuracy of monitoring data: This invention uses adaptive data separation technology to effectively distinguish between train load effects and temperature load effects in bridge health monitoring data, avoiding interference from slowly changing factors such as degradation effects, and significantly improving the accuracy of bridge structure health assessment results.

[0042] 2. Enhanced early damage detection capabilities: By effectively separating the effects of different loads, the present invention can improve the sensitivity of early damage detection in bridge structures, helping to promptly identify potential problems in bridges and prevent further deterioration of the structure.

[0043] 3. Application of Adaptive Data Processing Technology: This invention introduces an innovative algorithm with a memory effect, dynamically adjusting current parameters through a weight decay mechanism based on historical data, enabling greater flexibility in the face of complex load conditions. Furthermore, it combines the gradient descent method to achieve optimization and adjustment, further improving the accuracy of data processing.

[0044]

[0045] Where λ is the historical data attenuation coefficient, which enhances the system's ability to remember and process historical data.

[0046] 4. Strong stability: The method of the present invention has strong noise resistance. It uses a method based on multi-scale singular value decomposition (MS-SVD) to decompose and process the signal, further improving the stability when separating different load effects:

[0047] Y i =U i Σ i V ii T

[0048] Pair matrix Y i The decomposition helps to analyze the load effects at different time scales and ensure the stable operation of the system.

[0049] 5. Wide applicability: This method is particularly suitable for health monitoring of rail transit bridges. It can perform detailed analysis of train load and temperature load effects in complex environments and has high versatility. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is the measured value of the vertical displacement of the main beam in the embodiment of the present invention.

[0051] Figure 2 The vertical displacement change data of the main beam under the train load in the embodiment of the present invention.

[0052] Figure 3 is the vertical displacement of the main beam under temperature load in the embodiment of the present invention.

[0053] Figure 4 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0054] The preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more precise definition of the protection scope of the present invention.

[0055] like Figures 1 to 4 As shown in the working conditions of this embodiment, the main bridge of this bridge adopts a five-span high-low tower double-cable plane semi-floating cable-stayed bridge system. The longitudinal layout is 34.5 + 180.5 + 480 + 215.5 + 94.5 = 1005.0m, and the cross-sectional layout is: 2.8m (cable area and maintenance road) + 16.2m (track area) + 2.8m (cable area and maintenance road) = 21.8m (excluding air nozzles). The main beam adopts a steel-concrete composite beam type with a beam height of 3.3m. The main steel beam structure is made of Q345qD, and the precast bridge deck is made of C60 concrete. The main tower adopts a portal frame structure with three cross beams at the top, middle, and bottom. The P2 tower is 158m high and the P3 tower is 227m high. The material is C50 concrete. There are 16 pairs of inclined cables on the P2 tower side and 27 pairs of inclined cables on the P3 tower side. The inclined cables are made of Φ7.0mm galvanized high-strength low-relaxation parallel steel wire HDPE sheathed finished cables with a tensile strength of not less than 1770MPa and a tensile elastic modulus of not less than 195GPa. Figure 1The original monitoring data is presented, showing the vertical displacement response of a bridge girder under different load conditions. It can be seen that the data includes the combined effects of train and temperature loads, which increases the complexity of the response signal and makes it difficult to clearly distinguish between the individual load effects.

[0056] A method for separating load effects of a dedicated rail bridge, comprising the following specific steps:

[0057] S1. Collection and processing of main beam vertical displacement data. Taking the vertical displacement data of the main beam of a bridge as an example, the system collects the main beam response data under different environmental and load conditions through data collected on November 1, 2023 (08:00-20:00). First, the displacement data collected by the sensor is segmented and calculated according to the time period of each minute, and the displacement difference at the beginning and end of each minute is calculated. When the absolute value of the difference is greater than or equal to ΔD, the system marks the period as a train passing period. Subsequently, the marked period is used to separate and analyze the displacement data, thereby screening out the data period affected by the train load.

[0058] S2. Preliminary determination of train load effect: Based on the collected displacement data, a nonlinear model is used to superimpose the train load effect and the temperature load effect, which is regarded as a combination of multivariable functions. The monitoring data can be expressed as:

[0059] y(t)=g(T(t),L(t))+h(T(t),L(t))

[0060] Among them, g(T(t),L(t)) is a nonlinear function that represents the coupling between temperature and train load effects, which can be expressed by a quadratic polynomial, such as:

[0061] g(T(t),L(t))=a0+a1T(t)+a2L(t)+a3T(t)·L(t)

[0062] h(T(t), L(t)) represents the high-order nonlinear relationship between the two, which can be expressed as a cubic polynomial or a more complex function, specifically:

[0063] h(T(t),L(t))=b0+b1T(t) 2 +b2L(t) 3

[0064] The nonlinear model better captures the complex relationship between temperature and train load effects through the aforementioned quadratic and cubic polynomial forms. This model allows the system to precisely isolate data that may be affected by train load under different loading conditions, providing more accurate support for subsequent load effect analysis.

[0065] S4. Process the monitoring data by using the multi-scale singular value decomposition (MS-SVD) method. i The signal components of different load effects are decomposed and screened out through singular value analysis to ensure the fineness and stability of the final separation effect.

[0066] S5. To address noise and data uncertainty, a probabilistic model is used to describe load effects. By maximizing the joint probability distribution, the separation of train and temperature load effects can be optimized, thereby improving the reliability of data analysis.

[0067] S6. Finally, the time dynamic changes of train load and temperature load are described by the state transition matrix. The system state transition is: The model can effectively predict the future response of bridges under different load conditions and provide long-term health monitoring data support.

[0068] Taking the vertical displacement data of the bridge main beam in this embodiment as an example, the system collects the main beam response data under different environmental and load conditions through the data collected on November 1, 2023 (8:00-20:00), such as Figure 1 According to the above method, the data is processed as follows:

[0069] 1. Preliminary determination of train load effects: Based on the collected displacement data, use the nonlinear model in step 2 to make a preliminary determination of the train load effects and filter out data that may be affected by the train load.

[0070] 2. Finite element model calculation verification: Use the finite element model of the bridge to calculate the theoretical response under the train load and confirm that the calculation results are consistent with the monitoring data, such as Figure 2 Figure 2 shows the train load effect data extracted using a nonlinear load effect separation method. During data processing, we used a nonlinear model based on temperature and train load to successfully isolate the high-frequency, short-term vibration response caused by the train load. The train load effect is characterized by high-frequency, transient shocks, and this data reflects the vertical displacement response of the main beam when a train passes.

[0071] 3. Removal of Temperature Load Effects: By introducing an adaptive algorithm to process train load effect data and optimizing it with historical data, the interference of temperature load effects can be effectively removed, thereby effectively separating load effects. This process ensures that the impact of train loads on bridge health monitoring data can be accurately identified and analyzed, thereby improving the accuracy and reliability of bridge structural health assessments.

[0072] 4. Separation effect display: After data processing, the temperature load effect is separated, and the corrected vertical displacement data of the bridge is finally obtained, such as Figure 3 Figure 2 shows the temperature load effect data separated from the original data. The temperature load effect exhibits low-frequency, steady variations. Over time, the vertical displacement of the bridge girder is gradually affected by temperature fluctuations. During the data separation process, the temperature load model was used to extract this long-term temperature response.

Claims

1. A method for separating load effects of a dedicated rail bridge, characterized in that: The specific steps are: Step 1: Identify the train passing stage and mark the bridge train load impact data; Step 2: Separate the train load and temperature load effect data using a nonlinear model; Step 3: Use an adaptive algorithm with memory effect to remove the data of temperature load effect; Step 4: Use the multi-scale singular value decomposition (MSVD) method to process the data after removing the temperature load effect in step 3 to improve the separation effect; Step 5: Use a joint distribution model based on probability theory to optimally estimate the separation of temperature and train load effect data; Step 6: Use the state transition matrix to describe the temporal dynamic changes of train loads and temperature loads, predict the future response of the bridge under different load conditions, and provide long-term health monitoring data support.

2. The method for separating the load effects of a dedicated rail bridge according to claim 1, characterized in that: Specifically, step one includes, before data processing and load effect separation, first identifying the time period during which a train has passed by detecting the change in displacement data within a set time. The time period during which a train has passed is identified by detecting the displacement change within each set time. When the displacement change within a set time exceeds a preset threshold ΔD, it is considered that a train has passed. After marking the data affected by the train load, the train load and temperature load effects are separated based on the differences in response characteristics, and the displacement change within each set time is further calculated: C(t)=y end -y start Among them, C(t) is the change of displacement per unit time, y end is the displacement monitoring data at the end of this unit time, y start For the displacement monitoring data at the beginning of this unit time, a change threshold ΔD is defined. When the absolute value of the displacement change within a set time |C(t)| ≥ ΔD, it is considered that a train has passed.

3. The method for separating the load effects of a dedicated rail bridge according to claim 1, characterized in that: Specifically, the second step is to use a nonlinear model as a combination of multivariable functions for the superposition of train load effect and temperature load effect, and to express the superimposed displacement monitoring data as follows: y(t)=g(T(t),L(t))+h(T(t),L(t)) where g(T(t),L(t)) is a nonlinear function that represents the coupling between temperature and train load effects and is expressed as a quadratic polynomial: g(T(t),L(t))=a0+a1T(t)+a2L(t)+a3T(t)·L(t) Among them, a0~a3 are a set of coefficients, which represent the influence on the objective function; a0: constant term, which represents the base value or offset of the function g(T(t), L(t)) when both temperature T(t) and load L(t) are zero; a1: coefficient of temperature T(t), which represents the degree of influence of temperature on g(T(t), L(t)); a2: coefficient of load L(t), which represents the degree of influence of load on g(T(t), L(t)); a3: interaction coefficient of temperature and load T(t)·L(t), which represents the influence of the interaction effect between temperature and load on g(T(t), L(t)); h(T(t), L(t)) represents the high-order nonlinear relationship between the two, using a cubic polynomial function, specifically: h(T(t),L(t))=b0+b1T(t) 2 +b2L(t) 3 Among them, b0~b2 are a set of coefficients, which represent the influence on the objective function; b0: constant term, which represents the base value or offset of the function h(T(t), L(t)) when both temperature T(t) and load L(t) are zero; b1: square correlation coefficient, which represents the influence of the square of temperature on h(T(t), L(t)); b2: cubic correlation coefficient of load L(t), which represents the influence of load on h(T(t), L(t)).

4. The method for separating the load effects of a dedicated rail bridge according to claim 1, characterized in that: Specifically, step three includes introducing an algorithm with a memory effect during the load effect separation process, dynamically adjusting parameters, and defining a historical data weight attenuation factor λ to update the calculation parameters of the load response, thereby gradually reducing the impact of past data on the current response. The specific algorithm is: Among them, the decay factor λ∈(0,1) controls the decay rate of historical data; w(t) is the weight vector at time t; the learning rate η is used to adjust the update step to ensure that the model reaches the optimal state during the dynamic adaptation process; At time t, the gradient of the loss function E(w(t)) with respect to the weight vector w(t); The calculation formula of mean square error E(w) is as follows: Where N represents the number of monitoring data, which is the total number of monitored data points; y i is the monitoring data of the i-th monitoring point; w is the weight vector of the model, which is the weight coefficient and reflects the influence of different factors in the model on the results; x i is the input feature vector of the i-th monitoring data, which is the sensor reading or environmental variable related to the monitoring data point; w T x i To predict the value of the model, we need to combine the parameter w with the input feature x i The result of linear combination.

5. The method for separating the load effects of a dedicated rail bridge according to claim 1, characterized in that: Specifically, in order to improve the separation effect, the multi-scale singular value decomposition (MSVD) method is used to decompose the data matrix Y at different time scales. The data matrix is divided into multiple sub-matrices Y according to time. i , then each sub-matrix is subjected to singular value decomposition: Y i =U i Σ i V i T Among them, Y i represents the original data matrix or system output matrix, which represents the displacement monitoring data of the i-th sample; U i represents the left singular vector matrix, which represents the spatial pattern of displacement monitoring data; Σ i represents the singular value matrix, which represents the weight of the main components or features of the displacement monitoring data; V i T represents the transpose of the right singular vector matrix, which represents the time or direction pattern of the displacement monitoring data; Then the singular value matrix ∑ of all submatrices i By combining them, signal components at different time scales are obtained, and threshold screening is used to achieve finer separation.

6. The method for separating the load effects of a dedicated rail bridge according to claim 1, characterized in that: Specifically, step five further processes noise and uncertainty using a joint distribution model based on probability theory. Assuming the randomness of the temperature load effect and the train load effect is represented by a joint distribution p(T(t), L(t)), and combined with the observation noise ∈, the probability model of the displacement monitoring data is expressed as: p(y(t)|T(t),L(t))=p(y(t)-g(T(t),L(t))-h(T(t),L(t))|0,σ 2 ) Where, y(t): represents the displacement monitoring data at time t; T(t): represents the temperature value at time t; L(t): represents the load at time t; g(T(t), L(t)): represents a function related to temperature T(t) and load L(t), representing the influence of temperature and load on the structure; h(T(t), L(t)): represents another function related to temperature T(t) and load L(t), representing the influence of other factors, including noise on the response.

7. The method for separating the load effects of a dedicated rail bridge according to claim 1, characterized in that: Specifically, the sixth step is to assume that the train load effect L(t) and the temperature load effect T(t) follow their respective state transfer matrices P L and P T , then the state transition of the entire system can be expressed as: in represents the Kronecker product. By analyzing the long-term stable state of the Markov process, the response behavior of the future bridge under different load effects can be predicted.

Images