A method and system for evaluating the life of cable corroded steel wire

Abstract

The present invention discloses a method and system for assessing the life of corroded steel wire of a cable. The method comprises: obtaining fatigue test data and corrosion-related parameters of the corroded steel wire, constructing a data set based on the fatigue test data of the corroded steel wire, constructing an initial prediction model, training the initial prediction model based on the data set, obtaining a target life prediction model, inputting the physical parameters of the cable to be predicted into the target life prediction model for life prediction, and assessing the life of the corroded steel wire of the cable to be predicted based on the life prediction result. The life prediction result includes a fatigue life prediction value and a confidence level corresponding to the fatigue life prediction value. Since the present invention constructs a target life prediction model based on corrosion-related parameters and data of multiple dimensions, the life prediction of the cable steel wire is achieved based on the target life prediction model and the uncertainty of the prediction result is quantified, thereby ensuring the accuracy of the life assessment and providing reliable assessment results for cable maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of bridges, and in particular to a method and system for evaluating the life of corroded steel wires of a cable. Background Art

[0002] Cable-supported bridges are widely used in long-span bridges due to their beautiful architectural shape and superior spanning capacity. However, under the coupling of adverse factors such as harsh service environment, complex loads and improper maintenance, cables are inevitably damaged, resulting in premature replacement of cables. Therefore, as the key load-bearing component of cable-supported bridges, the performance evaluation of cables during service is of great significance to the scientific management and safe operation of bridges.

[0003] The main reason for cable breakage and early retirement is the corrosion fatigue disease that occurs inside the cable. That is, after the cable sheath is damaged and cracked, moisture and air enter the cable, causing corrosion of the internal steel wire. Under the action of complex alternating loads, fatigue cracks form on the surface of the steel wire and continue to expand inward, causing brittle failure of the steel wire. The damage caused by corrosion fatigue disease is sudden and unpredictable, which is a pain point and difficulty in bridge maintenance. In actual service scenarios, the factors that cause bridge cables to suffer from corrosion fatigue damage are diverse, and the current cable life assessment process ignores the diversity of variables in the actual application scenarios of the cable, and cannot quantify the uncertainty of the prediction results, resulting in the inability to accurately assess the life of the cable steel wire. Summary of the invention

[0004] The main purpose of the present invention is to provide a method and system for assessing the life of corroded cable wires, aiming to solve the technical problem that the prior art ignores the diversity of variables in the actual application scenarios of cables during the cable life assessment process, fails to quantify the uncertainty of the prediction results, and thus fails to accurately assess the life of cable wires.

[0005] To achieve the above object, the present invention provides a method for evaluating the life of a cable corroded steel wire, the method comprising the following steps:

[0006] Acquire corrosion steel wire fatigue test data, wherein the corrosion steel wire fatigue test data includes corrosion-related parameters of the cable steel wire, wherein the corrosion-related parameters include: stress amplitude parameter, corrosion depth, stress ratio parameter, steel wire diameter, tensile strength parameter and steel wire fatigue life parameter;

[0007] Constructing a data set based on the corrosion steel wire fatigue test data;

[0008] Build an initial prediction model;

[0009] Training the initial prediction model based on the data set to obtain a target life prediction model;

[0010] The physical parameters of the cable to be predicted are input into the target life prediction model for life prediction, and the corrosion wire life of the cable to be predicted is evaluated based on the life prediction result, wherein the life prediction result includes a fatigue life prediction value and a confidence level corresponding to the fatigue life prediction value.

[0011] Optionally, the constructing of the initial prediction model includes:

[0012] Constructing an original physical model, wherein the original physical model includes a Bayesian physical model;

[0013] The physical constraint conditions of the cable are obtained based on the fatigue test data of the corroded steel wire, and the physical constraint conditions of the cable include:

[0014] ;

[0015] in, is the crack depth, N is the number of loading cycles, C is the material crack growth rate parameter, m is the material stress sensitivity parameter, is the stress intensity factor range, is the stress intensity threshold, R is the stress ratio parameter;

[0016] The cable physical constraint conditions are embedded into the original physical model to obtain an initial prediction model.

[0017] Optionally, the obtaining of physical constraint conditions of the cable based on the corrosion steel wire fatigue test data includes:

[0018] Preprocessing the corrosion steel wire fatigue test data, wherein the preprocessing includes data cleaning processing and data standardization processing;

[0019] Determine the geometry and crack morphology of each cable steel wire based on the fatigue test data of the pre-treated corroded steel wire;

[0020] determining a geometric correction factor based on the geometric shape and the crack morphology;

[0021] Obtaining the stress range and crack depth of each cable steel wire based on the pretreated corroded steel wire fatigue test data;

[0022] Determine a stress intensity factor range according to the geometric correction factor, the stress range and the crack depth:

[0023] ;

[0024] in, is the stress intensity factor range, Y is the geometric correction factor, S is the stress range, is the crack depth;

[0025] The physical constraint conditions of the cable are obtained according to the stress intensity factor range and the pre-treated corrosion steel wire fatigue test data.

[0026] Optionally, embedding the cable physical constraint condition into the original physical model to obtain an initial prediction model includes:

[0027] Embedding the cable physical constraint condition into the original physical model to obtain an original prediction model;

[0028] Construct a data likelihood function based on the original prediction model:

[0029] ;

[0030] in, is the data loss term, is the corrosion observation value, is the corrosion prediction value;

[0031] Based on the physical constraints of the cable, a physical constraint likelihood function is constructed:

[0032] ;

[0033] in, is the physical loss term, To predict the crack growth rate, is the crack depth, N is the number of loading cycles, C is the material crack growth rate parameter, m is the material stress sensitivity parameter, is the stress intensity factor range, is the stress intensity threshold, R is the stress ratio parameter;

[0034] A joint loss function is constructed according to the data likelihood function and the physical constraint likelihood function:

[0035] ;

[0036] in, is the physical loss term, is the data loss term, is the physical constraint weight coefficient, is the prior loss term;

[0037] The original prediction model is optimized based on the joint loss function to obtain an initial prediction model.

[0038] Optionally, constructing a data likelihood function based on the original prediction model includes:

[0039] Acquiring corrosion observation data based on the corrosion steel wire fatigue test data;

[0040] Predicting steel wire corrosion based on the physical constraints of the cable to obtain corrosion prediction data;

[0041] Performing error analysis on the corrosion observation data and the corrosion prediction data according to the original prediction model to obtain probability distribution information of prediction errors;

[0042] A data likelihood function is constructed based on the probability distribution information.

[0043] Optionally, the physical parameters include crack depth, corrosion level, stress range, stress ratio parameter, steel wire diameter and material ultimate strength parameter; the physical parameters of the cable to be predicted are input into the target life prediction model for life prediction, and the corrosion steel wire life of the cable to be predicted is evaluated based on the life prediction result, including:

[0044] Preprocessing the physical parameters, wherein the preprocessing includes data cleaning and data standardization;

[0045] Inputting the preprocessed physical parameters into the target life prediction model to perform life prediction, and obtaining fatigue life prediction values ​​and uncertainty quantification parameters;

[0046] Determining the confidence level corresponding to the fatigue life prediction value according to the uncertainty quantification parameter;

[0047] The corrosion wire life of the cable to be predicted is evaluated based on the application scenario information of the cable to be predicted, the fatigue life prediction value and the confidence level. The application scenario information includes the environmental climate type, location altitude information, temperature change information, humidity change information and bridge application type of the application scenario of the cable to be predicted.

[0048] In addition, to achieve the above-mentioned purpose, the present invention also proposes a cable corroded steel wire life assessment system, the cable corroded steel wire life assessment system comprising:

[0049] A data acquisition module, used to acquire corrosion steel wire fatigue test data, wherein the corrosion steel wire fatigue test data includes corrosion-related parameters of the cable steel wire, wherein the corrosion-related parameters include: stress amplitude parameter, corrosion depth, stress ratio parameter, steel wire diameter, tensile strength parameter and steel wire fatigue life parameter;

[0050] A data set construction module, used to construct a data set based on the corrosion steel wire fatigue test data;

[0051] Model building module, used to build the initial prediction model;

[0052] A model training module, used to train the initial prediction model based on the data set to obtain a target life prediction model;

[0053] The life assessment module is used to input the physical parameters of the cable to be predicted into the target life prediction model for life prediction, and to assess the corroded steel wire life of the cable to be predicted based on the life prediction result, wherein the life prediction result includes a fatigue life prediction value and a confidence level corresponding to the fatigue life prediction value.

[0054] In addition, to achieve the above-mentioned objectives, the present application also proposes a cable corroded steel wire life assessment device, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the cable corroded steel wire life assessment method as described above.

[0055] In addition, to achieve the above objectives, the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the cable corroded wire life assessment method as described above are implemented.

[0056] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the cable corroded wire life assessment method as described above.

[0057] The present invention obtains corrosion steel wire fatigue test data, wherein the corrosion steel wire fatigue test data includes corrosion-related parameters of the cable steel wire, and the corrosion-related parameters include: stress amplitude parameter, corrosion depth, stress ratio parameter, steel wire diameter, tensile strength parameter and steel wire fatigue life parameter; constructs a data set based on the corrosion steel wire fatigue test data; constructs an initial prediction model; trains the initial prediction model based on the data set to obtain a target life prediction model; inputs the physical parameters of the cable to be predicted into the target life prediction model for life prediction, and evaluates the corrosion steel wire life of the cable to be predicted based on the life prediction result, wherein the life prediction result includes a fatigue life prediction value and a confidence level corresponding to the fatigue life prediction value; because the present invention constructs a target life prediction model based on cable corrosion steel wire related parameters and data in multiple dimensions, the life prediction of the cable steel wire is achieved based on the target life prediction model, and the uncertainty of the prediction result is quantified, thereby ensuring the accuracy of the cable steel wire life evaluation and providing reliable evaluation results for cable maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0059] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0060] Figure 1 It is a structural schematic diagram of a cable corrosion wire life assessment device in a hardware operating environment involved in an embodiment of the present invention;

[0061] Figure 2 It is a schematic diagram of the process of the first embodiment of the cable corroded steel wire life assessment method of the present invention;

[0062] Figure 3 It is a schematic flow chart of a second embodiment of a method for assessing the life of a cable corroded steel wire according to the present invention;

[0063] Figure 4 It is a structural block diagram of the first embodiment of the cable corrosion wire life assessment system of the present invention.

[0064] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0066] Reference Figure 1 , Figure 1 It is a schematic diagram of the structure of a cable corrosion wire life assessment device in the hardware operating environment involved in an embodiment of the present invention.

[0067] like Figure 1As shown, the cable corrosion wire life assessment device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity Wireless-Fidelity, WI-FI interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage system independent of the aforementioned processor 1001.

[0068] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the cable corrosion wire life assessment device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0069] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a cable corrosion wire life assessment program.

[0070] exist Figure 1 In the cable corroded steel wire life assessment device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the cable corroded steel wire life assessment device of the present invention can be arranged in the cable corroded steel wire life assessment device, and the cable corroded steel wire life assessment device calls the cable corroded steel wire life assessment program stored in the memory 1005 through the processor 1001, and executes the cable corroded steel wire life assessment method provided in the embodiment of the present invention.

[0071] The embodiment of the present invention provides a method for evaluating the life of a cable corroded steel wire, referring to Figure 2 , Figure 2 It is a schematic flow chart of the first embodiment of the cable corroded steel wire life assessment method of the present invention.

[0072] In this embodiment, the cable corroded steel wire life assessment method comprises the following steps:

[0073] Step S10: Obtaining corrosion steel wire fatigue test data.

[0074] It should be understood that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a terminal electronic device capable of realizing the above functions, etc. The following takes the cable corroded steel wire life assessment device (hereinafter referred to as the assessment device) as an example to illustrate this embodiment and the following embodiments.

[0075] It should be noted that the above-mentioned corrosion steel wire fatigue test data include corrosion-related parameters of the cable steel wire, and the above-mentioned corrosion-related parameters include: stress amplitude parameter, corrosion depth, stress ratio parameter, steel wire diameter, tensile strength parameter and steel wire fatigue life parameter.

[0076] It should be noted that stress amplitude refers to half of the difference between the maximum stress and the minimum stress in a stress cycle, and is used to describe the degree of stress change. For the steel wires in bridge cables, the stress amplitude reflects the severity of the alternating loads that the steel wires are subjected to during use.

[0077] The above corrosion depth may be the maximum corrosion pit depth, which refers to the depth of the deepest depression or pit formed on the surface of the steel wire under corrosion. The corrosion pit may weaken the effective cross-sectional area of ​​the steel wire, thereby reducing its mechanical strength, and may become the location for crack initiation, affecting the safety of the steel wire and the entire cable structure.

[0078] The stress ratio parameter R may refer to the ratio of the minimum stress to the maximum stress in a stress cycle ( ). This parameter is very important to understand how a material behaves under different types of alternating loads, especially when studying the fatigue properties of a material. Different stress ratios can affect the fatigue life of a material.

[0079] The tensile strength parameter mentioned above refers to the maximum tensile stress that the cable wire can withstand until it breaks. Tensile strength is an important indicator of material strength. For the steel wire in the bridge cable, it is directly related to the maximum load that the cable can bear.

[0080] The fatigue life parameter of the steel wire can be the number of stress cycles that the steel wire undergoes from the beginning of use to the occurrence of failure under the action of repeatedly applied alternating loads. When the steel wire is affected by corrosion, its fatigue life is usually shortened because corrosion causes the material properties to deteriorate and increases the risk of crack formation and propagation.

[0081] In some embodiments, the evaluation device may collect corrosion wire fatigue test data, perform data cleaning and normalization on the corrosion wire fatigue test data, and obtain parameters related to cable wire corrosion.

[0082] In some embodiments, the evaluation device can collect fatigue tests of corroded steel wires in existing literature to establish a fatigue life data set for corroded steel wires, wherein the correlation parameters of the corroded steel wires in the data set include stress amplitude, , maximum corrosion pit depth a, stress ratio R, diameter d 0 , steel wire tensile strength , and the fatigue life N of the corroded steel wire.

[0083] Step S20: constructing a data set based on the corrosion steel wire fatigue test data.

[0084] It is understandable that the data set includes a training set, a validation set, and a test set. The evaluation device can divide the data set based on a preset division ratio to obtain a training set, a validation set, and a test set. For example, the training set is used to train the model and accounts for 80% of the entire data set; the validation set accounts for 10% of the data set, and the test set accounts for 10% of the data set; the initial learning rate is 0.001, and the regularization strength is 0.0001.

[0085] Step S30: construct an initial prediction model.

[0086] It should be noted that the initial prediction model can be a neural network model that introduces physical mechanisms. For example, the initial prediction model can be a Bayesian Physics-Informed Neural Networks (BPINN) model, or it can be other neural network models (such as ANN model, BNN model, PINN model, etc.).

[0087] In some embodiments, the evaluation device can construct an original physical model, optimize the original physical model by introducing physical mechanisms, and combine the physical mechanisms of fatigue crack extension, thereby building an initial prediction model based on data and physical mechanisms and modeling a neural network based on physical information.

[0088] Step S40: training the initial prediction model based on the data set to obtain a target life prediction model.

[0089] It is understandable that the output of the target life prediction model can include two parts: one is the fatigue life prediction value, and the other is the uncertainty of the quantitative prediction result. Through the quantification of uncertainty, the model can not only give an estimate of the fatigue life, but also reflect the confidence of the prediction. This is especially important for the assessment of the life of steel wire in a corrosive environment, because uncertainty can help engineers better assess risks.

[0090] It should be understood that the target life prediction model may include an input layer, a hidden layer and an output layer. The input variables of the input layer may include crack depth, corrosion level, stress range, stress ratio parameter, steel wire diameter and material ultimate strength parameter; the above-mentioned hidden layer captures the nonlinear relationship of the input variables through a multi-layer neural network, and the output layer predicts the fatigue life N and the crack growth rate.

[0091] It can be understood that the model established by combining data and physical mechanisms in this embodiment can learn the characteristic relationship in the data while maintaining physical rationality. Not only can the comprehensive influence of material properties, environmental conditions and loading conditions be fully considered through data, but also the physical mechanism of fatigue crack growth can be ensured.

[0092] Step S50: inputting the physical parameters of the cable to be predicted into the target life prediction model to perform life prediction, and evaluating the corrosion wire life of the cable to be predicted based on the life prediction result.

[0093] It should be noted that the above life prediction results include fatigue life prediction values ​​and confidence levels corresponding to the fatigue life prediction values.

[0094] It should be noted that the above confidence level can be an uncertainty quantification parameter for the fatigue life prediction value. This embodiment outputs the fatigue life prediction value and the uncertainty quantification parameter through the target life prediction model, which can not only predict the fatigue life of the corroded steel wire, but also quantify the uncertainty of the prediction results, which can help users better assess risks.

[0095] In some embodiments, the evaluation device can evaluate the model based on the life prediction results output by the target life prediction model. The performance of the model is measured by evaluation indicators, such as root mean square error (RMSE) and coefficient of determination. These indicators can reflect the degree of fit between the model prediction value and the experimental data, thereby verifying the effectiveness of the target life prediction model in the fatigue life prediction of corroded steel wire.

[0096] In some embodiments, if the cable wire to be predicted is an uncorroded wire, it is assumed that the wire surface is smooth and has no obvious corrosion defects. The wire characteristics are determined according to the physical parameters of the cable to be predicted. For example, the physical parameters of the cable wire to be predicted include the initial crack depth a 0 =0.1mm, material crack growth rate parameter C=10-2, material stress sensitivity parameter m=3.0, stress intensity threshold The crack propagates slowly, showing a stable linear growth stage. The above physical parameters are input into the target life prediction model for life prediction, and the prediction results are as follows: when the stress range is S=300MPa and the stress ratio is R=0.5, the crack propagation rate is small.

[0097] It can be understood that during the prediction phase, the evaluation device samples weights W and bias b from the posterior distribution of the model, calculates fatigue life N for each set of sampled values, and obtains the distribution of predicted values ​​after multiple samplings.

[0098] It should be noted that the sources of uncertainty in the target life prediction model can be data noise and model uncertainty. The data noise can be caused by experimental errors and random fluctuations in data. The model uncertainty is caused by limited data or incomplete physical mechanisms of the model and is quantified by sampling the distribution of model parameters.

[0099] In some embodiments, the fatigue life prediction value Refer to the following formula:

[0100] ;

[0101] Uncertainty Quantification Parameters Refer to the following formula:

[0102] ;

[0103] in, is the initial crack depth, is the final crack depth.

[0104] The above life prediction results may include fatigue life prediction value and uncertainty quantification parameter. The fatigue life prediction value may be the average value of the model output, such as The uncertainty quantification parameter can be the model output prediction variance, such as .

[0105] Furthermore, in order to accurately evaluate the life of the steel wire, the above step S50 may include:

[0106] Step S501: preprocessing the physical parameters, wherein the preprocessing includes data cleaning and data standardization;

[0107] Step S502: inputting the preprocessed physical parameters into the target life prediction model to perform life prediction, and obtaining fatigue life prediction values ​​and uncertainty quantification parameters;

[0108] Step S503: determining the confidence level corresponding to the fatigue life prediction value according to the uncertainty quantification parameter;

[0109] Step S504: Evaluate the corroded steel wire life of the cable to be predicted based on the application scenario information of the cable to be predicted, the fatigue life prediction value and the confidence level.

[0110] It should be noted that the above physical parameters include crack depth, corrosion level, stress range, stress ratio parameter, wire diameter and material ultimate strength parameter. The above application scenario information includes the environmental climate type, location altitude information, temperature change information, humidity change information and bridge application type of the application scenario of the cable to be predicted.

[0111] It should be understood that this embodiment accurately evaluates the life of the corroded steel wire by combining the application scenario information of the cable to be predicted and the prediction results of the target life prediction model. The above-mentioned environmental climate type is used to identify the climate characteristics of the area where the bridge is located, such as marine climate, continental climate, etc., which will affect humidity, rainfall and salt content.

[0112] The evaluation equipment obtains the specific geographical location and altitude of the bridge based on the location altitude information, because the altitude affects the air pressure, temperature and humidity. Based on the above temperature change information and humidity change information, the day and night temperature and humidity fluctuation information of the cable to be predicted is determined, so as to analyze the influence factors of day and night temperature and humidity on the corrosion of steel wire. The structural characteristics, working load and exposure conditions of the cable to be predicted are determined based on the bridge application type (such as highway bridge, railway bridge, etc.).

[0113] In a specific implementation, the evaluation device can integrate the above application scenario information into a unified data set, thereby achieving normalization and standardization of the data and ensuring the time series consistency and integrity of the data.

[0114] In some embodiments, the evaluation equipment can divide the area where the bridge is located into different climate zones based on climate classification to evaluate the impact of long-term climate conditions, and determine the condensation conditions of the cables to be predicted in combination with the location altitude, and analyze the relationship between temperature and humidity based on temperature change information and humidity change information. In particular, under high temperature and high humidity conditions, the corrosion rate may increase significantly.

[0115] In this embodiment, the corrosion steel wire fatigue test data is obtained, and the corrosion steel wire fatigue test data includes corrosion-related parameters of the cable steel wire, and the corrosion-related parameters include: stress amplitude parameter, corrosion depth, stress ratio parameter, steel wire diameter, tensile strength parameter and steel wire fatigue life parameter; a data set is constructed based on the corrosion steel wire fatigue test data; an initial prediction model is constructed; the initial prediction model is trained based on the data set to obtain a target life prediction model; the physical parameters of the cable to be predicted are input into the target life prediction model for life prediction, and the corrosion steel wire life of the cable to be predicted is evaluated based on the life prediction result, and the life prediction result includes a fatigue life prediction value and a confidence level corresponding to the fatigue life prediction value; because this embodiment constructs a target life prediction model based on cable corrosion steel wire related parameters and data in multiple dimensions, the life prediction of the cable steel wire is realized based on the target life prediction model, and the uncertainty of the prediction result is quantified, thereby ensuring the accuracy of the cable steel wire life evaluation and providing reliable evaluation results for cable maintenance.

[0116] refer to Figure 3 , Figure 3 It is a schematic flow chart of the second embodiment of the cable corroded steel wire life assessment method of the present invention.

[0117] Based on the above first embodiment, in this embodiment, step S30 further includes:

[0118] Step S31: constructing an original physical model.

[0119] It should be noted that the original physical model may include a Bayesian physical model, and the above-mentioned Bayesian physical model may be a Bayesian Physics-Informed Neural Networks (BPINN) model. The original physical model may also be other neural network models (such as ANN model, BNN model, PINN model, etc.).

[0120] Step S32: obtaining physical constraint conditions of the cable based on the corrosion steel wire fatigue test data.

[0121] It should be noted that the above cable physical constraints include:

[0122] ;

[0123] in, is the crack depth, N is the number of loading cycles, C is the material crack growth rate parameter, m is the material stress sensitivity parameter, is the stress intensity factor range, is the stress intensity threshold, and R is the stress ratio parameter.

[0124] It should be noted that the crack depth can describe the progress of crack extension in the steel wire, the number of loading cycles can be the number of stress loading and unloading cycles experienced by the cable steel wire in fatigue, and the material stress sensitivity parameter can reflect the sensitivity of the cable steel wire to different stress levels. The material crack growth rate parameter can reflect the speed of crack growth in the cable steel wire under cyclic loading.

[0125] It can be understood that the above-mentioned cable physical constraint conditions can be physical mechanism constraint conditions of crack extension, and the cable physical constraint conditions can represent the variation of the crack depth of the cable steel wire with the number of loading cycles.

[0126] Furthermore, in order to effectively provide the model with physical constraints for crack propagation, the above step S32 may include:

[0127] Step S321: preprocessing the corrosion steel wire fatigue test data;

[0128] Step S322: determining the geometric shape and crack morphology of each cable steel wire according to the pre-processed corrosion steel wire fatigue test data;

[0129] Step S323: determining a geometric correction factor according to the geometric shape and the crack morphology;

[0130] Step S324: obtaining the stress range and crack depth of each cable steel wire based on the pre-treated corrosion steel wire fatigue test data;

[0131] Step S325: determining a stress intensity factor range according to the geometric correction factor, the stress range and the crack depth:

[0132] ;

[0133] in, is the stress intensity factor range, Y is the geometric correction factor, S is the stress range, is the crack depth;

[0134] Step S326: obtaining physical constraint conditions of the cable according to the stress intensity factor range and the pre-processed corrosion steel wire fatigue test data.

[0135] It should be noted that the above preprocessing includes data cleaning and data standardization. The above data cleaning includes removing invalid data and duplicate data from the fatigue test data of the corroded steel wire, and supplementing or replacing missing values ​​and abnormal values. The above data standardization refers to the following formula:

[0136] ;

[0137] in, is the standardized parameter, is the parameter before standardization, is the mean of the training set, is the standard deviation of the training set.

[0138] It should be noted that the above stress intensity factor range is related to the stress field at the crack tip, and the above geometric correction factor is a coefficient used to correct the theoretical stress intensity factor to take into account the influence of the geometric conditions around the crack in the actual structure. The above geometric correction factor can be determined based on the geometric shape of the cable wire and the influence of the crack morphology. For example, the geometric shape of the cable may include: cross-sectional shape, diameter change shape, winding structure, etc.

[0139] The cross-sectional shape mentioned above (e.g. round, oval or flat) will affect the stress concentration at the crack tip; different parts of the cable may have different diameters, which will lead to uneven stress distribution. The effect of the diameter variation shape can be that in areas with smaller diameters, stress concentration is more significant and crack propagation may be faster. The winding structure can be a structure in which the cable is made of multiple strands of steel wire. Different cables have different winding numbers and types. This complex internal structure can introduce additional stress concentration points, especially at intersections or contact surfaces.

[0140] In some embodiments, the pre-processed fatigue test data of the corroded steel wire may include crack depth, number of loading cycles, steel wire fracture toughness parameter, stress ratio parameter, material crack growth rate parameter and material stress sensitivity parameter. The physical constraint conditions of the cable are obtained according to the stress intensity factor range and the pre-processed fatigue test data of the corroded steel wire, referring to the following formula:

[0141] ;

[0142] in, is the crack depth, N is the number of loading cycles, C is the material crack growth rate parameter, m is the material stress sensitivity parameter, is the stress intensity factor range, is the stress intensity threshold, R is the stress ratio parameter, and the above-mentioned material crack growth rate parameter and material stress sensitivity parameter are determined based on the material properties of the cable steel wire.

[0143] The above stress ratio parameter can be the ratio of the minimum stress to the maximum stress, referring to the following formula, where is the minimum stress, is the maximum stress:

[0144] ;

[0145] Step S33: embedding the cable physical constraint conditions into the original physical model to obtain an initial prediction model.

[0146] It can be understood that the evaluation device can embed the physical constraints of the cable as physical constraints into the hidden layer of the original physical model, so that the model can learn the feature relationship in the data while maintaining physical rationality.

[0147] Furthermore, in order to improve the model performance, the above step S33 may include:

[0148] Step S331: embedding the cable physical constraint condition into the original physical model to obtain an original prediction model;

[0149] Step S332: constructing a data likelihood function based on the original prediction model;

[0150] Step S333: constructing a physical constraint likelihood function based on the cable physical constraint condition;

[0151] Step S334: constructing a joint loss function according to the data likelihood function and the physical constraint likelihood function;

[0152] Step S335: Optimizing the original prediction model based on the joint loss function to obtain an initial prediction model.

[0153] It should be noted that the data likelihood function is constructed according to the following formula:

[0154] ;

[0155] in, is the data loss term, is the corrosion observation value, is the corrosion prediction value.

[0156] It should be noted that the physical constraint likelihood function is constructed according to the following formula:

[0157] ;

[0158] in, is the physical loss term, To predict the crack growth rate, is the crack depth, N is the number of loading cycles, C is the material crack growth rate parameter, m is the material stress sensitivity parameter, is the stress intensity factor range, is the stress intensity threshold, and R is the stress ratio parameter.

[0159] It should be noted that the construction of the joint loss function refers to the following formula:

[0160] ;

[0161] in, is the physical loss term, is the data loss term, is the physical constraint weight coefficient, is the prior loss term (regularization).

[0162] It should be understood that the evaluation device can be used to evaluate the variable parameters in the physical constraints of the cable (the random variable parameters may include the material crack growth rate parameter C, the material stress sensitivity parameter m, the stress intensity threshold ) is defined as a random variable and given a prior distribution, for example:

[0163] For the material crack growth rate parameter C, it is assumed to follow a normal distribution. ,in is the mean, is the standard deviation;

[0164] Material stress sensitivity parameter m, assuming it follows a normal distribution ,in is the mean, is the standard deviation;

[0165] Stress intensity threshold , assuming it follows a normal distribution ,in is the mean, is the standard deviation.

[0166] It should be noted that the above data likelihood function can reflect the matching degree between the observed data (i.e. the experimental results in the fatigue test data of the corroded steel wire) and the model prediction value. The above physical constraint likelihood function can reflect whether the model prediction value (i.e. the crack growth rate) meets the physical constraint conditions of the cable.

[0167] It should be noted that the above-mentioned joint loss function can be a loss function that integrates the data likelihood function and the physical constraint likelihood function. The joint loss function can be used to train and optimize the original prediction model:

[0168] ;

[0169] in, is the posterior probability, is the data likelihood function, is the physical constraint likelihood function, is the prior distribution.

[0170] The joint loss function can be the negative posterior probability in logarithmic form:

[0171] ;

[0172] Further expanded to:

[0173] ;

[0174] in, is the physical loss term, is the data loss term, is the physical constraint weight coefficient, is the prior loss term:

[0175] ;

[0176] Among them, W can be a variable parameter of the model input, such as the material crack growth rate parameter C, the material stress sensitivity parameter m, the stress intensity threshold wait.

[0177] It can be understood that the above-mentioned physical loss term is used to guide the model to fit the fatigue life, and the above-mentioned physical loss term is used to ensure that the model output conforms to the physical laws. By jointly training the data likelihood function and the physical constraint likelihood function, in each iteration, the data loss term and the physical loss term are minimized at the same time.

[0178] In some embodiments, the evaluation device may update the model parameters W and the bias b according to the joint loss function through a backpropagation algorithm.

[0179] Furthermore, in order to accurately construct the data likelihood function and improve the model training and optimization efficiency, the above step S332 may include:

[0180] Step S3321: acquiring corrosion observation data based on the corrosion steel wire fatigue test data;

[0181] Step S3322: Predicting steel wire corrosion based on the physical constraints of the cable to obtain corrosion prediction data;

[0182] Step S3323: performing error analysis on the corrosion observation data and the corrosion prediction data according to the original prediction model to obtain probability distribution information of prediction errors;

[0183] Step S3324: construct a data likelihood function based on the probability distribution information.

[0184] It should be noted that the data likelihood function reflects the matching degree between the corrosion observation data and the corrosion prediction data, thereby obtaining the probability distribution information of the prediction error, assuming that the data error follows a normal distribution:

[0185] ;

[0186] Where D is the dataset of corrosion observation data, W is the model parameters (such as the weight and bias of the original prediction model), is the observed fatigue life of the ith sample, is the predicted fatigue life of the ith sample, is the variance of the observation noise. The data likelihood function can be used to measure whether the model prediction value is close to the observed value, encouraging the model to fit the data.

[0187] In some embodiments, the data likelihood function may be constructed based on the following formula:

[0188] ;

[0189] in, is the observed fatigue life of the ith sample, is the predicted fatigue life of the i-th sample.

[0190] This embodiment constructs an original physical model, obtains the physical constraints of the cable based on the corrosion steel wire fatigue test data, embeds the physical constraints of the cable into the original physical model, and obtains an initial prediction model, thereby realizing a model established by combining data and physical mechanisms. It is able to learn the characteristic relationships in the data while maintaining physical rationality, ensure that the model meets the physical mechanism of fatigue crack propagation, and improve the accuracy of life assessment.

[0191] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which a cable corroded steel wire life assessment program is stored. When the cable corroded steel wire life assessment program is executed by a processor, the steps of the cable corroded steel wire life assessment method as described above are implemented.

[0192] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0193] The above-mentioned computer-readable storage medium may be included in the cable corroded steel wire life assessment device; or it may exist independently without being assembled into the cable corroded steel wire life assessment device.

[0194] In addition, an embodiment of the present invention further provides a computer program product, including a cable corroded steel wire life assessment program, which implements the steps of the cable corroded steel wire life assessment method as described above when executed by a processor.

[0195] The specific implementation of the computer program product of the present invention is basically the same as the various embodiments of the cable corroded steel wire life assessment method described above, and will not be repeated here.

[0196] Reference Figure 4 , Figure 4 It is a structural block diagram of the first embodiment of the cable corrosion wire life assessment system of the present invention.

[0197] like Figure 4 As shown, the cable corrosion wire life assessment system proposed in the embodiment of the present invention includes:

[0198] The data acquisition module 10 is used to acquire the corrosion steel wire fatigue test data, wherein the corrosion steel wire fatigue test data includes corrosion-related parameters of the cable steel wire, wherein the corrosion-related parameters include: stress amplitude parameter, corrosion depth, stress ratio parameter, steel wire diameter, tensile strength parameter and steel wire fatigue life parameter;

[0199] A data set construction module 20, used to construct a data set based on the corrosion steel wire fatigue test data;

[0200] A model building module 30, used to build an initial prediction model;

[0201] A model training module 40 is used to train the initial prediction model based on the data set to obtain a target life prediction model;

[0202] The life assessment module 50 is used to input the physical parameters of the cable to be predicted into the target life prediction model for life prediction, and to assess the corroded steel wire life of the cable to be predicted based on the life prediction result, wherein the life prediction result includes a fatigue life prediction value and a confidence level corresponding to the fatigue life prediction value.

[0203] Furthermore, the model building module 30 is also used to build an original physical model, which includes a Bayesian physical model; and to obtain cable physical constraints based on the corroded steel wire fatigue test data, wherein the cable physical constraints include:

[0204] ;

[0205] in, is the crack depth, N is the number of loading cycles, C is the material crack growth rate parameter, m is the material stress sensitivity parameter, is the stress intensity factor range, is the stress intensity threshold, R is the stress ratio parameter;

[0206] The cable physical constraint conditions are embedded into the original physical model to obtain an initial prediction model.

[0207] Furthermore, the model building module 30 is also used to preprocess the corrosion steel wire fatigue test data, and the preprocessing includes data cleaning processing and data standardization processing; determine the geometric shape and crack morphology of each cable steel wire according to the preprocessed corrosion steel wire fatigue test data; determine the geometric correction factor according to the geometric shape and the crack morphology; obtain the stress range and crack depth of each cable steel wire based on the preprocessed corrosion steel wire fatigue test data; determine the stress intensity factor range according to the geometric correction factor, the stress range and the crack depth:

[0208] ;

[0209] in, is the stress intensity factor range, Y is the geometric correction factor, S is the stress range, is the crack depth;

[0210] The physical constraint conditions of the cable are obtained according to the stress intensity factor range and the pre-treated corrosion steel wire fatigue test data.

[0211] Furthermore, the model building module 30 is also used to embed the cable physical constraint condition into the original physical model to obtain an original prediction model; and to build a data likelihood function based on the original prediction model:

[0212] ;

[0213] in, is the data loss term, is the corrosion observation value, is the corrosion prediction value;

[0214] Based on the physical constraints of the cable, a physical constraint likelihood function is constructed:

[0215] ;

[0216] in, is the physical loss term, To predict the crack growth rate, is the crack depth, N is the number of loading cycles, C is the material crack growth rate parameter, m is the material stress sensitivity parameter, is the stress intensity factor range, is the stress intensity threshold, R is the stress ratio parameter;

[0217] A joint loss function is constructed according to the data likelihood function and the physical constraint likelihood function:

[0218] ;

[0219] in, is the physical loss term, is the data loss term, is the physical constraint weight coefficient, is the prior loss term;

[0220] The original prediction model is optimized based on the joint loss function to obtain an initial prediction model.

[0221] Furthermore, the model building module 30 is also used to obtain corrosion observation data based on the corroded steel wire fatigue test data; perform steel wire corrosion prediction based on the physical constraints of the cable to obtain corrosion prediction data; perform error analysis on the corrosion observation data and the corrosion prediction data according to the original prediction model to obtain probability distribution information of the prediction error; and construct a data likelihood function based on the probability distribution information.

[0222] Furthermore, the life assessment module 50 is also used to preprocess the physical parameters, and the preprocessing includes data cleaning and data standardization; input the preprocessed physical parameters into the target life prediction model for life prediction to obtain fatigue life prediction values ​​and uncertainty quantification parameters; determine the confidence level corresponding to the fatigue life prediction values ​​according to the uncertainty quantification parameters; and assess the corroded steel wire life of the cable to be predicted based on the application scenario information of the cable to be predicted, the fatigue life prediction value and the confidence level, wherein the application scenario information includes the environmental climate type, location altitude information, temperature change information, humidity change information and bridge application type of the application scenario of the cable to be predicted.

[0223] In this embodiment, the corrosion steel wire fatigue test data is obtained, and the corrosion steel wire fatigue test data includes corrosion-related parameters of the cable steel wire, and the corrosion-related parameters include: stress amplitude parameter, corrosion depth, stress ratio parameter, steel wire diameter, tensile strength parameter and steel wire fatigue life parameter; a data set is constructed based on the corrosion steel wire fatigue test data; an initial prediction model is constructed; the initial prediction model is trained based on the data set to obtain a target life prediction model; the physical parameters of the cable to be predicted are input into the target life prediction model for life prediction, and the corrosion steel wire life of the cable to be predicted is evaluated based on the life prediction result, and the life prediction result includes a fatigue life prediction value and a confidence level corresponding to the fatigue life prediction value; because this embodiment constructs a target life prediction model based on cable corrosion steel wire related parameters and data in multiple dimensions, the life prediction of the cable steel wire is realized based on the target life prediction model, and the uncertainty of the prediction result is quantified, thereby ensuring the accuracy of the cable steel wire life evaluation and providing reliable evaluation results for cable maintenance.

[0224] The cable corroded steel wire life assessment system provided by the present application adopts the cable corroded steel wire life assessment method in the above embodiment, which can solve the technical problem of cable corroded steel wire life assessment. Compared with the prior art, the cable corroded steel wire life assessment system provided by the present application has the same beneficial effects as the cable corroded steel wire life assessment method provided by the above embodiment, and other technical features in the cable corroded steel wire life assessment system are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0225] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0226] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0227] In addition, for technical details not fully described in this embodiment, reference can be made to the cable corroded steel wire life assessment method provided in any embodiment of the present invention, and will not be repeated here.

[0228] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0229] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0230] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0231] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for evaluating the life of a cable corroded steel wire, characterized in that: The cable corrosion wire life assessment method comprises: Acquire corrosion steel wire fatigue test data, wherein the corrosion steel wire fatigue test data includes corrosion-related parameters of the cable steel wire, wherein the corrosion-related parameters include: stress amplitude parameter, corrosion depth, stress ratio parameter, steel wire diameter, tensile strength parameter and steel wire fatigue life parameter; Constructing a data set based on the corrosion steel wire fatigue test data; Build an initial prediction model; Training the initial prediction model based on the data set to obtain a target life prediction model; Inputting the physical parameters of the cable to be predicted into the target life prediction model to perform life prediction, and evaluating the corrosion wire life of the cable to be predicted based on the life prediction result, wherein the life prediction result includes a fatigue life prediction value and a confidence level corresponding to the fatigue life prediction value; Wherein, the target life prediction model is used to output fatigue life prediction value and uncertainty quantification parameter, the uncertainty quantification parameter is used to determine the confidence level, and the uncertainty quantification parameter of the target life prediction model is the model output prediction variance; The physical parameters include crack depth, corrosion level, stress range, stress ratio parameter, steel wire diameter and material ultimate strength parameter.

2. The cable corroded wire life assessment method according to claim 1, characterized in that: The constructing of the initial prediction model comprises: Constructing an original physical model, wherein the original physical model includes a Bayesian physical model; The physical constraint conditions of the cable are obtained based on the fatigue test data of the corroded steel wire, and the physical constraint conditions of the cable include: ； in, is the crack depth, N is the number of loading cycles, C is the material crack growth rate parameter, m is the material stress sensitivity parameter, is the stress intensity factor range, is the stress intensity threshold, R is the stress ratio parameter; Embedding the cable physical constraint condition into the original physical model to obtain an initial prediction model; The step of embedding the cable physical constraint condition into the original physical model to obtain an initial prediction model includes: Embedding the cable physical constraint condition into the original physical model to obtain an original prediction model; Construct a data likelihood function based on the original prediction model: ； in, is the data loss term, is the corrosion observation value, is the corrosion prediction value; Based on the physical constraints of the cable, a physical constraint likelihood function is constructed: ； in, is the physical loss term, To predict the crack growth rate, is the crack depth, N is the number of loading cycles, C is the material crack growth rate parameter, m is the material stress sensitivity parameter, is the stress intensity factor range, is the stress intensity threshold, R is the stress ratio parameter; A joint loss function is constructed according to the data likelihood function and the physical constraint likelihood function: ； in, is the physical loss term, is the data loss term, is the physical constraint weight coefficient, is the prior loss term; The original prediction model is optimized based on the joint loss function to obtain an initial prediction model.

3. The cable corroded wire life assessment method according to claim 2, characterized in that: The obtaining of the physical constraint conditions of the cable based on the fatigue test data of the corroded steel wire comprises: Preprocessing the corrosion steel wire fatigue test data, wherein the preprocessing includes data cleaning processing and data standardization processing; Determine the geometry and crack morphology of each cable steel wire based on the fatigue test data of the pre-treated corroded steel wire; determining a geometric correction factor based on the geometric shape and the crack morphology; Obtaining the stress range and crack depth of each cable steel wire based on the pretreated corroded steel wire fatigue test data; Determine a stress intensity factor range according to the geometric correction factor, the stress range and the crack depth: ； in, is the stress intensity factor range, Y is the geometric correction factor, S is the stress range, is the crack depth; The physical constraint conditions of the cable are obtained according to the stress intensity factor range and the pre-treated corrosion steel wire fatigue test data.

4. The cable corroded wire life assessment method according to claim 3, characterized in that: The constructing a data likelihood function based on the original prediction model comprises: Acquiring corrosion observation data based on the corrosion steel wire fatigue test data; Predicting steel wire corrosion based on the physical constraints of the cable to obtain corrosion prediction data; Performing error analysis on the corrosion observation data and the corrosion prediction data according to the original prediction model to obtain probability distribution information of prediction errors; A data likelihood function is constructed based on the probability distribution information.

5. The method for evaluating the life of a cable corroded steel wire according to any one of claims 1 to 4, characterized in that: The physical parameters include crack depth, corrosion level, stress range, stress ratio parameter, steel wire diameter and material ultimate strength parameter; the physical parameters of the cable to be predicted are input into the target life prediction model for life prediction, and the corrosion steel wire life of the cable to be predicted is evaluated based on the life prediction result, including: Preprocessing the physical parameters, wherein the preprocessing includes data cleaning and data standardization; Inputting the preprocessed physical parameters into the target life prediction model to perform life prediction, and obtaining fatigue life prediction values ​​and uncertainty quantification parameters; Determining the confidence level corresponding to the fatigue life prediction value according to the uncertainty quantification parameter; The corrosion wire life of the cable to be predicted is evaluated based on the application scenario information of the cable to be predicted, the fatigue life prediction value and the confidence level. The application scenario information includes the environmental climate type, location altitude information, temperature change information, humidity change information and bridge application type of the application scenario of the cable to be predicted.

6. A cable corrosion wire life assessment system, characterized in that: The cable corrosion wire life assessment system comprises: A data acquisition module, used to acquire corrosion steel wire fatigue test data, wherein the corrosion steel wire fatigue test data includes corrosion-related parameters of the cable steel wire, wherein the corrosion-related parameters include: stress amplitude parameter, corrosion depth, stress ratio parameter, steel wire diameter, tensile strength parameter and steel wire fatigue life parameter; A data set construction module, used to construct a data set based on the corrosion steel wire fatigue test data; Model building module, used to build the initial prediction model; A model training module, used to train the initial prediction model based on the data set to obtain a target life prediction model; A life assessment module, used for inputting the physical parameters of the cable to be predicted into the target life prediction model for life prediction, and performing corrosion wire life assessment on the cable to be predicted based on the life prediction result, wherein the life prediction result includes a fatigue life prediction value and a confidence level corresponding to the fatigue life prediction value; Wherein, the target life prediction model is used to output fatigue life prediction value and uncertainty quantification parameter, the uncertainty quantification parameter is used to determine the confidence level, and the uncertainty quantification parameter of the target life prediction model is the model output prediction variance; The physical parameters include crack depth, corrosion level, stress range, stress ratio parameter, steel wire diameter and material ultimate strength parameter.

7. A cable corrosion wire life assessment device, characterized in that: The cable corroded steel wire life assessment device includes: a memory, a processor, and a cable corroded steel wire life assessment program stored in the memory and executable on the processor, wherein the cable corroded steel wire life assessment program is configured to implement the cable corroded steel wire life assessment method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a cable corroded steel wire life assessment program, and when the cable corroded steel wire life assessment program is executed by a processor, the cable corroded steel wire life assessment method according to any one of claims 1 to 5 is implemented.

9. A computer program product, characterized in that The computer program product comprises a cable corroded steel wire life assessment program, and when the cable corroded steel wire life assessment program is executed by a processor, the steps of the cable corroded steel wire life assessment method according to any one of claims 1 to 5 are implemented.

Images