Concrete carbonization depth prediction method and device, electronic equipment and medium

Abstract

The invention relates to a concrete carbonization depth prediction method and device, electronic equipment and a medium. The method comprises the following steps: acquiring concrete carbonization depth influence parameters for a pipeline buttress in a target pipeline; the concrete carbonization depth influence parameters are input into a pre-trained target prediction model, the concrete carbonization depth of a pipeline buttress corresponding to the target pipeline is obtained, and the target prediction model is a model obtained after a BP neural network is optimized based on a Whale Optimization algorithm. Through the method of the invention, the traditional BP neural network is optimized, and the problems of low convergence speed, easy falling into a local optimal solution, easy influence by an abnormal value, lack of adaptability and generalization ability, difficult explanation and adjustment and the like when the traditional neural network algorithm is used for processing similar problems are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline transportation engineering, and in particular to a method, device, electronic equipment and medium for predicting the carbonation depth of concrete. Background Art

[0002] When oil and gas pipelines pass through mountainous and hilly areas, tunnel crossing can effectively avoid the impact of terrain undulations on pipeline layout. Generally speaking, the overhead laying method supported by concrete piers in tunnels can provide stable support and fixation to ensure the safe operation of pipelines. However, over time, concrete piers will suffer varying degrees of damage, especially the increase in carbonization depth has an important impact on the durability of the pier structure. Therefore, it is necessary to predict the carbonization depth of the concrete of the pipeline piers in the tunnel so as to repair or replace the pipeline piers before they become unstable.

[0003] The existing patent literature on the prediction methods of concrete carbonization depth includes:

[0004] Patent document 1 provides a concrete carbonation prediction method based on an extreme learning machine (publication number: CN108710968A), which specifically uses an extreme learning machine (ELM) algorithm to predict the carbonation depth of concrete. However, the following problems still exist: (1) The extreme learning machine method randomly initializes weights, which may result in different weights for each training, thereby affecting the stability and reproducibility of the model; (2) The extreme learning machine method has a large randomness in the selection of hidden layer parameters, and inappropriate parameter selection may lead to a decrease in prediction performance or even failure.

[0005] Patent document 2 discloses a concrete carbonation depth prediction method and prediction system (publication number: CN112858644A), which is based on the concrete carbonation depth time series data and combined with the neural network model to obtain a concrete carbonation depth steady time series data prediction model. However, the following problems still exist: (1) The time series data does not consider the influence of external loads, and it is impossible to predict the carbonation depth of concrete subjected to external loads; (2) The constructed model has a lower accuracy of prediction results for data with a large prediction time span.

[0006] The journal article "High-Performance Concrete Carbonation Test and Artificial Neural Network Carbonation Depth Prediction Model" (Xu Fei, Concrete, Issue 08, 2022, pp. 57-60) discloses a method for predicting the carbonation depth of high-performance concrete. Based on the BP neural network, a prediction model with water-cement ratio, fly ash parameters, and slag output as input and carbonation depth as output was constructed. However, there are still the following problems: (1) The training of the BP neural network depends on the gradient descent algorithm, and the gradient descent is prone to fall into local minima, resulting in unsatisfactory model training results; (2) The BP neural network usually requires a lot of time and computing resources to train.

[0007] Therefore, a better prediction method for the carbonization depth of pipeline pier concrete is needed, which can accurately and efficiently predict the carbonization depth of pipeline pier concrete. Summary of the invention

[0008] The technical problem to be solved by the present invention is to provide a method, device, electronic equipment and medium for predicting the carbonization depth of concrete, aiming to solve at least one of the above technical problems.

[0009] In the first aspect, the technical solution of the present invention to solve the above technical problem is as follows: a method for predicting the carbonization depth of concrete, the method comprising:

[0010] Obtaining a parameter affecting the concrete carbonization depth of a pipe support in a target pipe;

[0011] The concrete carbonization depth influencing parameters are input into a pre-trained target prediction model to obtain the concrete carbonization depth of the pipeline pier corresponding to the target pipeline, wherein the target prediction model is a model obtained by optimizing the BP neural network based on the WhaleOptimization algorithm.

[0012] The beneficial effects of the present invention are as follows: the method proposed by the present invention is based on the analysis of a large amount of measured data, and the WhaleOptimization algorithm is used to optimize the traditional BP neural network, thereby overcoming the problems of slow convergence speed, easy to fall into local optimal solution, easy to be affected by outliers, lack of adaptability and generalization ability, and difficult to explain and adjust when the traditional neural network algorithm is used to deal with similar problems. At the same time, the method has high computational efficiency, and can quickly predict the carbonization depth of pipeline pier concrete in actual engineering applications, providing a scientific basis for the safe operation of the pipeline.

[0013] Based on the above technical solution, the present invention can also be improved as follows.

[0014] Furthermore, the target prediction model is trained based on the following method:

[0015] S1, obtaining data samples of factors affecting the carbonation depth of concrete of sample pipeline piers;

[0016] S2, optimize the BP neural network based on the Whale Optimization algorithm to obtain the initial model;

[0017] S3, optimizing the initial model by using the idea of ​​crossover mutation in the genetic algorithm to obtain an optimized model;

[0018] S4, training the optimization model according to the data samples to obtain the target prediction model.

[0019] Furthermore, the BP neural network is optimized based on the Whale Optimization algorithm to obtain an initial model, including:

[0020] Based on the first to sixth formulas corresponding to the Whale Optimization algorithm, the BP neural network is optimized to obtain an initial model, wherein the first to sixth formulas are respectively:

[0021]

[0022] A=2a·r1-a (2)

[0023] C=2r2 (3)

[0024] D=|X(t)-CX best (t)| (4)

[0025] D*=|X best (t)-X(t)| (5)

[0026]

[0027] Where t is the number of algorithm iterations; A and C are coefficient vectors; X best (t) is the optimal solution of each iteration; X(t) is the concrete carbonization depth of the current pipeline pier; a is the convergence factor; r1 and r2 are both random numbers in the interval [0,1], b is the characteristic constant; l is a random number in the interval [-1,1]; t max represents the maximum number of iterations; β is the rate of change of the control convergence factor.

[0028] Further, in S4, the optimization model is trained according to the data sample to obtain the target prediction model, including:

[0029] S41, dividing the data sample into a training sample and a test sample;

[0030] S42, training the optimization model according to the training samples to obtain an initial prediction model;

[0031] S43, testing the initial prediction model according to the test sample, and evaluating the accuracy of the prediction model according to the test result;

[0032] S44, when the accuracy of the initial prediction model reaches the preset requirements, the initial prediction model that reaches the preset requirements is used as the target prediction model; when the accuracy of the initial prediction model does not reach the preset requirements, the data sample is readjusted, and S42 to S44 are repeated according to the adjusted data until the accuracy of the initial prediction model reaches the preset requirements.

[0033] Furthermore, the BP neural network includes a three-layer network topology structure consisting of an input layer, a hidden layer and an output layer, and the number of nodes in the hidden layer is determined based on the following method:

[0034]

[0035] Where m is the number of nodes in the hidden layer, n is the number of nodes in the input layer, and α is the adjustment constant, which ranges from 1 to 10.

[0036] Furthermore, the parameters affecting the carbonation depth of concrete include operating years, compressive strength, operating temperature, operating humidity, CO2 concentration influence coefficient and working stress influence factors.

[0037] In a second aspect, in order to solve the above technical problems, the present invention also provides a concrete carbonization depth prediction device, which comprises:

[0038] An acquisition module, used for acquiring a concrete carbonization depth influencing parameter of a pipeline support in a target pipeline;

[0039] The prediction module is used to input the concrete carbonization depth influencing parameters into a pre-trained target prediction model to obtain the concrete carbonization depth of the pipeline pier corresponding to the target pipeline, wherein the target prediction model is a model obtained by optimizing the BP neural network based on the Whale Optimization algorithm.

[0040] In a third aspect, in order to solve the above-mentioned technical problem, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the concrete carbonization depth prediction method of the present application is implemented.

[0041] In a fourth aspect, in order to solve the above-mentioned technical problem, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the concrete carbonization depth prediction method of the present application is implemented.

[0042] Additional aspects and advantages of the present application will be partially given in the following description, which will become apparent from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for describing the embodiments of the present invention are briefly introduced below.

[0044] Figure 1 A schematic diagram of a flow chart of a method for predicting carbonization depth of concrete provided by one embodiment of the present invention;

[0045] Figure 2 A schematic diagram of a structural diagram of a target prediction model provided by one embodiment of the present invention;

[0046] Figure 3 A schematic diagram of the error distribution between a predicted value and an expected value of carbonation depth of concrete provided by an embodiment of the present invention;

[0047] Figure 4 A schematic diagram of the structure of a concrete carbonization depth prediction device provided by one embodiment of the present invention;

[0048] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0050] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0051] The solution provided by the embodiment of the present invention can be applied to any application scenario where the concrete carbonization depth of the pipe pier in the tunnel needs to be predicted. The solution provided by the embodiment of the present invention can be executed by any electronic device, including at least one of the following: a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart TV, and a smart car device.

[0052] The embodiment of the present invention provides a possible implementation method, such as Figure 1 As shown, a flowchart of a method for predicting the carbonization depth of concrete is provided. The scheme can be executed by any electronic device, for example, a terminal device, or a terminal device and a server. For the convenience of description, the method provided by the embodiment of the present invention will be described below by taking the terminal device as the execution subject as an example. Figure 1 The method may include the following steps:

[0053] Step S10, obtaining a parameter affecting the carbonization depth of concrete of a pipe support in a target pipe;

[0054] Step S20, inputting the concrete carbonization depth influencing parameter into a pre-trained target prediction model to obtain the concrete carbonization depth of the pipeline pier corresponding to the target pipeline, wherein the target prediction model is a model obtained by optimizing the BP neural network based on the WhaleOptimization algorithm.

[0055] The method proposed in the present invention is based on the analysis of a large amount of measured data, and the Whale Optimization algorithm is used to optimize the traditional BP neural network, which overcomes the problems of slow convergence speed, easy to fall into local optimal solution, susceptibility to outliers, lack of adaptability and generalization ability, and difficulty in interpretation and adjustment when the traditional neural network algorithm is used to deal with similar problems. At the same time, the method has high computational efficiency, and can quickly predict the carbonization depth of pipeline pier concrete in actual engineering applications, providing a scientific basis for the safe operation of the pipeline.

[0056] The solution of the present invention is further described below in conjunction with the following specific embodiments. In this embodiment, a method for predicting the carbonization depth of concrete is provided, which may include the following steps:

[0057] Step S10, obtaining a parameter affecting the carbonization depth of concrete of a pipe support in a target pipe;

[0058] The target pipeline refers to the pipeline installed in the tunnel, most of which are oil and gas pipelines passing through mountainous and hilly areas. Pipeline piers usually refer to piers that can provide stable support and fixation for the pipeline in the tunnel, usually made of concrete.

[0059] Optionally, the above-mentioned parameters affecting the carbonation depth of concrete include operating life (operating life of the target pipeline), compressive strength (compressive strength of the target pipeline), operating temperature (operating temperature of the target pipeline), operating humidity (operating humidity of the target pipeline), CO2 concentration influence coefficient and working stress influencing factors.

[0060] Step S20, inputting the concrete carbonization depth influencing parameter into a pre-trained target prediction model to obtain the concrete carbonization depth of the pipeline pier corresponding to the target pipeline, wherein the target prediction model is a model obtained by optimizing the BP neural network based on the WhaleOptimization algorithm.

[0061] Optionally, the target prediction model is trained based on the following method:

[0062] S1, obtaining data samples of factors affecting the carbonization depth of concrete of sample pipeline piers; before executing S2, the data samples may also be normalized.

[0063] S2, optimize the BP neural network based on the Whale Optimization algorithm to obtain the initial model;

[0064] S3, optimizing the initial model by using the idea of ​​crossover mutation in the genetic algorithm to obtain an optimized model;

[0065] S4, training the optimization model according to the data samples to obtain the target prediction model.

[0066] In the present application, in order to further improve the performance of the optimized BP neural network (initial model), the idea of ​​crossover mutation in the genetic algorithm can also be used to further improve its global optimization capability and obtain a more optimized network structure (optimization model).

[0067] Optionally, in the above S2, the BP neural network is optimized based on the Whale Optimization algorithm to obtain an initial model, including:

[0068] Based on the first to sixth formulas corresponding to the Whale Optimization algorithm, the BP neural network is optimized to obtain an initial model, wherein the first to sixth formulas are respectively:

[0069]

[0070] A=2a·r1-a (2)

[0071] C=2r2 (3)

[0072] D=|X(t)-CX best (t)| (4)

[0073] D*=|X best (t)-X(t)| (5)

[0074]

[0075] Where t is the number of algorithm iterations; A and C are coefficient vectors; X best (t) is the optimal solution of each iteration; X(t) is the concrete carbonization depth of the current pipeline pier; a is the convergence factor; r1 and r2 are both random numbers in the interval [0,1], b is the characteristic constant; l is a random number in the interval [-1,1]; t max represents the maximum number of iterations; β is the rate of change of the control convergence factor.

[0076] The concrete carbonization depth of the current pipeline pier may be determined based on the data sample, and refers to the concrete carbonization depth of the pipeline pier used corresponding to the t-th iteration number.

[0077] Optionally, in the above S4, training the optimization model according to the data sample to obtain the target prediction model includes:

[0078] S41, dividing the data sample into a training sample and a test sample;

[0079] S42, training the optimization model according to the training samples to obtain an initial prediction model;

[0080] S43, testing the initial prediction model according to the test sample, and evaluating the accuracy of the prediction model according to the test result;

[0081] S44, when the accuracy of the initial prediction model reaches the preset requirements, the initial prediction model that reaches the preset requirements is used as the target prediction model; when the accuracy of the initial prediction model does not reach the preset requirements, the data sample is readjusted, and S42 to S44 are repeated according to the adjusted data until the accuracy of the initial prediction model reaches the preset requirements.

[0082] Optionally, an implementation of S43 to S44 is:

[0083] S431, input the test sample into the initial prediction model for testing, and obtain the predicted value of the test sample;

[0084] S432. Calculate the relative error between the predicted value and the expected value (true value, i.e., true depth) of the test sample. When the relative error of the test sample meets the preset requirement, it is considered that the initial prediction model meets the accuracy requirement, and the concrete carbonization depth of the pipe pier in the target pipe can be predicted. Otherwise, readjust the sample data, redetermine the training sample and the test sample, obtain a new training sample and a new test sample, and repeat the above steps S42 to S44 based on the new training sample and the new test sample until the accuracy of the initial prediction model meets the preset requirement.

[0085] Optional, see Figure 2 As shown, the above BP neural network includes a three-layer network topology consisting of an input layer, a hidden layer and an output layer. Figure 2 In , 1 represents the input layer, 2 represents the hidden layer, and 3 represents the output layer. The number of nodes in the hidden layer is determined based on the following method:

[0086]

[0087] Among them, m is the number of nodes in the hidden layer, n is the number of nodes in the input layer, and α is an adjustment constant ranging from 1 to 10. The number of nodes in the hidden layer determined based on the above method is not unique, but within a range.

[0088] Optionally, the number of nodes in the input layer and the number of nodes in the output layer of the above-mentioned BP neural network can be adjusted according to the type of input data and the type of output data. For example, if the number of input data types is n and the number of output data types is m, then the corresponding number of nodes in the input layer is n and the number of nodes in the output layer is m.

[0089] Optionally, in the above S42, one implementation of training the optimization model according to the training samples to obtain the initial prediction model is:

[0090] The training samples are input into the optimization model to obtain the predicted values ​​corresponding to the training samples. When the error between the expected value and the predicted value corresponding to the training samples meets the error accuracy requirement, the optimized BP neural network structure is output as the initial prediction model. It is considered that the prediction model of the carbonization depth of the concrete of the pipe pier in the tunnel is initially obtained at this time.

[0091] In order to better illustrate and understand the principle of the method provided by the present invention, the scheme of the present invention is described below in conjunction with an optional specific embodiment. It should be noted that the specific implementation of each step in the specific embodiment should not be understood as a limitation to the scheme of the present invention. On the basis of the principle of the scheme provided by the present invention, other implementations that can be thought of by those skilled in the art should also be considered within the scope of protection of the present invention.

[0092] In this embodiment, a pipeline concrete pier in a domestic tunnel is used as a target pier, and the concrete carbonization depth of the target pier is predicted. The target pier was put into operation in July 2009. The concrete material of the target pier is C20, the compressive strength is 20MPa, the operating temperature is 17.8℃, the operating humidity is 0.78, the CO2 concentration influence factor is 1.5, and the working stress influence factor is 1.0. The prediction method specifically includes:

[0093] Step S201, obtaining the measured data of the concrete carbonization depth of the target pier (including the influencing parameters of the concrete carbonization depth of the target pier and the carbonization depth data of the target pier), a total of 69 sets of measured data.

[0094] Step S202: taking 69 groups of measured data of concrete carbonization depth as data samples of factor variables, and randomly dividing them into 59 groups of training samples and 10 groups of test samples;

[0095] Step S203: Input the 59 sets of training samples into the optimized BP neural network (optimization model), establish an initial prediction model for the carbonization depth of the concrete of the tunnel pier, and verify the accuracy of the initial prediction model. The specific steps are as follows:

[0096] Step S2031, since the structure of the optimized BP neural network model is: input layer, hidden layer, output layer, it can be expressed by the following formula:

[0097] Concrete carbonization depth (carbonization depth of pier concrete) = f (compressive strength of concrete pier, operating temperature, operating humidity, CO2 concentration influence coefficient, operating years, working stress influence factors)

[0098] That is, by inputting the above six factors, the predicted concrete carbonation depth can be obtained. That is, the number of neuron nodes in the input layer is 6, the number of neuron nodes in the output layer is 1, and the optimal number of neuron nodes in the hidden layer is determined to be 9 through the empirical formula (8).

[0099]

[0100] Among them, m is the number of hidden layer nodes, n is the number of input layer nodes, and α is the adjustment constant, which ranges from 1 to 10. After calculation, the value of m is 3 to 12, which are substituted into the initial prediction model respectively. The specific calculation results are shown in Table 1.

[0101] Table 1 The training mean square error of different n values

[0102] m value Mean square error m value Mean square error 3 0.071 8 0.206 4 0.092 9 0.040 5 0.110 10 0.098 6 0.087 11 0.056 7 0.105 12 0.226

[0103] Step S2032, BP neural network parameter configuration, set the BP neural network training times to 1000, the learning rate to 0.01, and the training target minimum error to 10 -5 , momentum factor 0.01, minimum performance gradient 10-6, maximum number of failures 6 times; and set the optimization algorithm related parameters.

[0104] Step S2033: input 59 training sets into the optimized BP neural network to establish an initial prediction model for the carbonization depth of concrete in the tunnel pipe piers, and input the remaining 10 test sets into the initial prediction model to verify the accuracy of the model.

[0105] Step S301: input the concrete carbonization depth influencing parameters of the target pier into the target prediction model to obtain the concrete carbonization depth corresponding to the target pipeline.

[0106] In order to further verify the generalization ability of the previously established prediction model for the carbonization depth of concrete of pipeline piers in tunnels based on the optimized BP neural network (target prediction model), the traditional BP neural network was also used to predict the carbonization depth of concrete of 69 groups of pipeline piers.

[0107] Figure 3 is the prediction error of the two prediction methods, according to Figure 3 The results show that the average relative error of the prediction using the optimized BP neural network is 4.72%, the maximum relative error is 9.66%, and the minimum relative error is 0.43%, while the average relative error of the prediction using BP is 14.94%. The maximum relative error is 31.48%, and the minimum relative error is 3.31%. This shows that the prediction effect based on the target prediction model is better than the prediction result obtained by the traditional BP neural network.

[0108] In order to further study the practicality of the optimized BP neural network algorithm, the machine time consumed by the two methods was studied, and the time required for the two methods to predict the carbonization depth of pipeline pier concrete was recorded. The result showed that the optimized BP neural network method consumed 1.24 seconds of machine time, while the traditional BP neural network method consumed 10.23 seconds of machine time. It can be seen that the efficiency of the target prediction model is significantly better than that of the traditional BP neural network.

[0109] The solution of the present invention has the following beneficial effects:

[0110] (1) The present invention solves the problem of randomness of initial weight and threshold by optimizing the traditional BP neural network through algorithm. For the prediction of carbonization depth of concrete in tunnel, the average relative error of the traditional BP neural network is 14.94%, while the average relative error of the optimized BP neural network is 4.72%.

[0111] (2) Compared with the traditional BP neural network, the optimized BP neural network has significantly better solution speed and performance in predicting the carbonation depth of concrete in tunnels. The optimized BP neural network prediction consumes 1.24 seconds, while the traditional BP neural network prediction consumes 10.23 seconds.

[0112] Based on Figure 1 Based on the same principle as the method shown in , the embodiment of the present invention also provides a concrete carbonization depth prediction device 20, such as Figure 4 As shown in , the concrete carbonization depth prediction device 20 may include an acquisition module 210 and a prediction module 220, wherein:

[0113] An acquisition module 210 is used to acquire a concrete carbonization depth influencing parameter of a pipeline support in a target pipeline;

[0114] The prediction module 220 is used to input the concrete carbonization depth influencing parameter into the pre-trained target prediction model to obtain the concrete carbonization depth of the pipeline pier corresponding to the target pipeline, wherein the target prediction model is a model obtained by optimizing the BP neural network based on the Whale Optimization algorithm.

[0115] Optionally, the target prediction model is obtained through training based on a training module, and the training module includes:

[0116] A sample acquisition unit, used to acquire data samples of factors affecting the carbonation depth of concrete of a sample pipeline pier;

[0117] The first optimization unit is used to optimize the BP neural network based on the Whale Optimization algorithm to obtain the initial model;

[0118] The second optimization unit is used to optimize the initial model by using the idea of ​​crossover mutation in the genetic algorithm to obtain an optimized model;

[0119] A training unit is used to train the optimization model according to the data sample to obtain the target prediction model.

[0120] Optionally, when the first optimization unit optimizes the BP neural network based on the Whale Optimization algorithm to obtain an initial model, it is specifically used for:

[0121] Based on the first to sixth formulas corresponding to the Whale Optimization algorithm, the BP neural network is optimized to obtain an initial model, wherein the first to sixth formulas are respectively:

[0122]

[0123] A=2a·r1-a (2)

[0124] C=2r2 (3)

[0125] D=|X(t)-CX best (t)| (4)

[0126] D*=|X best (t)-X(t)| (5)

[0127]

[0128] Where t is the number of algorithm iterations; A and C are coefficient vectors; X best (t) is the optimal solution of each iteration; X(t) is the concrete carbonization depth of the current pipeline pier; a is the convergence factor; r1 and r2 are both random numbers in the interval [0,1], b is the characteristic constant; l is a random number in the interval [-1,1]; t max represents the maximum number of iterations; β is the rate of change of the control convergence factor.

[0129] Optionally, when the training unit trains the optimization model according to the data sample to obtain the target prediction model, it is specifically used to perform the following steps:

[0130] S41, dividing the data sample into a training sample and a test sample;

[0131] S42, training the optimization model according to the training samples to obtain an initial prediction model;

[0132] S43, testing the initial prediction model according to the test sample, and evaluating the accuracy of the prediction model according to the test result;

[0133] S44, when the accuracy of the initial prediction model reaches the preset requirements, the initial prediction model that reaches the preset requirements is used as the target prediction model; when the accuracy of the initial prediction model does not reach the preset requirements, the data sample is readjusted, and S42 to S44 are repeated according to the adjusted data until the accuracy of the initial prediction model reaches the preset requirements.

[0134] Optionally, the BP neural network comprises a three-layer network topology structure consisting of an input layer, a hidden layer and an output layer, and the number of nodes in the hidden layer is determined based on the following method:

[0135]

[0136] Where m is the number of nodes in the hidden layer, n is the number of nodes in the input layer, and α is the adjustment constant, which ranges from 1 to 10.

[0137] Optionally, the above parameters affecting the carbonation depth of concrete include operating years, compressive strength, operating temperature, operating humidity, CO2 concentration influence coefficient and working stress influence factor.

[0138] The concrete carbonization depth prediction device of the embodiment of the present invention can execute the concrete carbonization depth prediction method provided by the embodiment of the present invention, and its implementation principle is similar. The actions performed by each module and unit in the concrete carbonization depth prediction device in each embodiment of the present invention correspond to the steps in the concrete carbonization depth prediction method in each embodiment of the present invention. For the detailed functional description of each module of the concrete carbonization depth prediction device, please refer to the description in the corresponding concrete carbonization depth prediction method shown in the previous text, which will not be repeated here.

[0139] Among them, the above-mentioned concrete carbonization depth prediction device can be a computer program (including program code) running in a computer device, for example, the concrete carbonization depth prediction device is an application software; the device can be used to execute the corresponding steps in the method provided in the embodiment of the present invention.

[0140] In some embodiments, the concrete carbonization depth prediction device provided by the embodiment of the present invention can be implemented in a combination of software and hardware. As an example, the concrete carbonization depth prediction device provided by the embodiment of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the concrete carbonization depth prediction method provided by the embodiment of the present invention. For example, the processor in the form of a hardware decoding processor can adopt one or more application specific integrated circuits (ASIC, Application Specific Integrated Circuit), DSP, programmable logic device (PLD, Programmable Logic Device), complex programmable logic device (CPLD, Complex Programmable Logic Device), field programmable gate array (FPGA, Field-Programmable Gate Array) or other electronic components.

[0141] In other embodiments, the concrete carbonization depth prediction device provided by the embodiments of the present invention can be implemented in a software manner. Figure 4 A concrete carbonization depth prediction device stored in a memory is shown, which may be software in the form of a program and a plug-in, and includes a series of modules, including an acquisition module 210 and a prediction module 220, for implementing the concrete carbonization depth prediction method provided in an embodiment of the present invention.

[0142] The modules involved in the embodiments of the present invention may be implemented by software or hardware, wherein the name of a module does not limit the module itself in some cases.

[0143] Based on the same principle as the method shown in the embodiments of the present invention, an electronic device is also provided in the embodiments of the present invention, which may include but is not limited to: a processor and a memory; the memory is used to store a computer program; the processor is used to execute the method shown in any embodiment of the present invention by calling the computer program.

[0144] In an alternative embodiment, an electronic device is provided, such as Figure 5 As shown, Figure 5 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0145] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0146] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0147] The memory 4003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0148] The memory 4003 is used to store application code (computer program) for executing the solution of the present invention, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the application code stored in the memory 4003 to implement the content shown in the above method embodiment.

[0149] The electronic device may also be a terminal device. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0150] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents of the aforementioned method embodiment.

[0151] According to another aspect of the present invention, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the implementation modes of the above-mentioned various embodiments.

[0152] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0153] It should be understood that the flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the module, the program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0154] The computer-readable storage medium provided by the embodiment of the present invention may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. 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), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0155] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0156] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the disclosure scope involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

Claims

1. A method for predicting the carbonation depth of concrete, characterized in that: The following steps are involved: Obtaining a parameter affecting the concrete carbonization depth of a pipe support in a target pipe; The concrete carbonization depth influencing parameters are input into a pre-trained target prediction model to obtain the concrete carbonization depth of the pipeline pier corresponding to the target pipeline, wherein the target prediction model is a model obtained by optimizing the BP neural network based on the Whale Optimization algorithm.

2. The method according to claim 1, characterized in that: The target prediction model is trained based on the following method: S1, obtaining data samples of factors affecting the carbonation depth of concrete of sample pipeline piers; S2, optimize the BP neural network based on the Whale Optimization algorithm to obtain the initial model; S3, optimizing the initial model by using the idea of ​​crossover mutation in the genetic algorithm to obtain an optimized model; S4, training the optimization model according to the data samples to obtain the target prediction model.

3. The method according to claim 2, characterized in that The BP neural network is optimized based on the Whale Optimization algorithm to obtain an initial model, including: Based on the first to sixth formulas corresponding to the Whale Optimization algorithm, the BP neural network is optimized to obtain an initial model, wherein the first to sixth formulas are respectively: A=2a·r1-a C＝2r2 D=|X(t)-CX best (t) D*=|X best (t)-X(t) Where t is the number of algorithm iterations; A and C are coefficient vectors; X best (t) is the optimal solution of each iteration; X(t) is the concrete carbonization depth of the current pipeline pier; a is the convergence factor; r1 and r2 are both random numbers in the interval [0,1], b is the characteristic constant; l is a random number in the interval [-1,1]; t max represents the maximum number of iterations; β is the rate of change of the control convergence factor.

4. The method according to claim 2, characterized in that: In S4, the optimization model is trained according to the data sample to obtain the target prediction model, including: S41, dividing the data sample into a training sample and a test sample; S42, training the optimization model according to the training samples to obtain an initial prediction model; S43, testing the initial prediction model according to the test sample, and evaluating the accuracy of the prediction model according to the test result; S44, when the accuracy of the initial prediction model reaches the preset requirements, the initial prediction model that reaches the preset requirements is used as the target prediction model; when the accuracy of the initial prediction model does not reach the preset requirements, the data sample is readjusted, and S42 to S44 are repeated according to the adjusted data until the accuracy of the initial prediction model reaches the preset requirements.

5. The method according to any one of claims 1 to 4, characterized in that The BP neural network includes a three-layer network topology structure consisting of an input layer, a hidden layer and an output layer, and the number of nodes in the hidden layer is determined based on the following method: Where m is the number of nodes in the hidden layer, n is the number of nodes in the input layer, and α is the adjustment constant, which ranges from 1 to 10.

6. The method according to any one of claims 1 to 4, characterized in that The parameters affecting the carbonation depth of concrete include operating years, compressive strength, operating temperature, operating humidity, CO2 concentration influence coefficient and working stress influence factor.

7. A concrete carbonization depth prediction device, characterized in that: include: An acquisition module, used for acquiring a concrete carbonization depth influencing parameter of a pipeline support in a target pipeline; A prediction module is used to input the concrete carbonization depth influencing parameters into a pre-trained target prediction model to obtain the concrete carbonization depth of the pipeline pier corresponding to the target pipeline, wherein the target prediction model is a model obtained by optimizing the BP neural network based on the WhaleOptimization algorithm.

8. The device according to claim 7, characterized in that The parameters affecting the carbonation depth of concrete include operating years, compressive strength, operating temperature, operating humidity, CO2 concentration influence coefficient and working stress influence factor.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images