Method and system for designing mix proportion of cement-emulsified asphalt mortar for high-speed railway

Abstract

The invention relates to a high-speed railway cement emulsified asphalt mortar mix proportion design method and system. The method comprises the following steps that design factors of cement emulsified asphalt mortar to be designed are input into a design model; the design factors comprise raw material types, usage and layout environment parameters; predicting and outputting a performance index corresponding to the to-be-designed cement emulsified asphalt mortar through the design model; the performance indexes comprise fluidity, expansion degree, working time, compressive strength, elasticity modulus and fatigue life; according to the performance indexes, the design factors of the cement emulsified asphalt mortar to be designed are adjusted and input into the design model, and the performance indexes corresponding to the adjusted design factors are obtained; and repeating the step of inputting and adjusting for multiple times until the optimal design factor meeting the performance requirement is obtained and output. The system and the equipment are used for executing the method. The method has the advantages of high design efficiency, short period, low cost and high accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of civil construction, and in particular to a method and system for designing a mix ratio of cement emulsified asphalt mortar for high-speed railways. Background Art

[0002] Cement emulsified asphalt mortar (CA mortar) is one of the key structural layers of CRTSⅠ and CRTSⅡ slab ballastless tracks for high-speed railways. It is a viscoelastic organic-inorganic composite material formed by mechanical mixing of multiple components such as emulsified asphalt, cement, fine aggregate (sand), water and appropriate additives, and cement hydration hardening and asphalt demulsification. It plays the role of support, load transmission, vibration reduction, noise reduction, etc. Due to the complex service environment of my country's high-speed railways, the mechanical properties of cement emulsified asphalt mortars are different, such as cement emulsified asphalt mortars used in warm, cold and severe cold regions; in addition, different mix ratio designs are also required for requirements such as frost resistance, fatigue resistance, and corrosion resistance.

[0003] The traditional cement emulsion asphalt mortar mix design method mainly relies on experiments and experience, and has problems such as long design and test cycle, high cost, and lack of accuracy. Summary of the invention

[0004] In order to solve the problems existing in the above-mentioned prior art, the purpose of this application is to provide a high-speed railway cement emulsified asphalt mortar mix ratio design method and system. This application has the advantages of high design efficiency, short cycle, low cost and high accuracy.

[0005] A high-speed railway cement emulsified asphalt mortar mix design method described in the present application comprises the following steps:

[0006] Design factor input: input the design factors of the cement emulsified asphalt mortar to be designed into the design model; the design factors include the type and amount of raw materials and the layout environment parameters;

[0007] Prediction output: predicting and outputting performance indicators corresponding to the cement emulsified asphalt mortar to be designed through the design model; the performance indicators include fluidity, expansion, workable time, compressive strength, elastic modulus and fatigue life;

[0008] Input adjustment: according to the performance index, adjusting the design factors of the cement emulsified asphalt mortar to be designed and inputting them into the design model, so as to obtain the performance index corresponding to the adjusted design factors;

[0009] Optimal design output: Repeat the input adjustment steps multiple times until the optimal design factors that meet the performance requirements are obtained and output.

[0010] Preferably, the design model is obtained by the following steps:

[0011] Data preparation: obtaining multiple sets of test data of cement emulsified asphalt mortar, wherein the test data includes design factors and corresponding performance indicators of cement emulsified asphalt mortar;

[0012] Data preprocessing: performing data cleaning and normalization on the multiple groups of test data, converting the test data into a two-dimensional matrix, and dividing the multiple groups of test data into a training set, a validation set, and a test set;

[0013] Building a model: Selecting a convolutional neural network as the design model;

[0014] Model training: using the test data of the training set to train the constructed design model until a preset convergence condition or number of iterations is reached;

[0015] Model optimization: Use the experimental data of the verification set and the test set to verify and test the trained design model, and optimize the design model according to the results of the verification and testing until the performance of the design model meets the requirements, thereby obtaining the design model.

[0016] Preferably, in the step of inputting adjustment, adjusting the design factors of the cement emulsified asphalt mortar to be designed according to the performance index and inputting them into the design model comprises:

[0017] The standard values ​​of various performance indicators are preset, and the fitness value Va of the performance indicator is calculated according to the following formula: fit :

[0018] V fit =w1*(Va Fa / St Fa )+w2*(Va Spr / St Spr )+w3*(Va W_t /

[0019] St W_t )+w4*(Va C_s / St C_s )+w5*(Va E_m / St E_m )+w6*(Va F_l / St F_l );

[0020] Among them, Va Fa Indicates fluidity, St Fa Indicates the standard value of fluidity, Va Spr Indicates the extension degree, St Spr Indicates the standard value of expansion, Va W_t Indicates the working time, StW_t Indicates the standard value of working time, Va C_s Indicates compressive strength, St C_s Indicates the standard value of compressive strength, Va E_m represents the elastic modulus, St E_m Indicates the standard value of elastic modulus, Va F_l represents fatigue life, St F_l represents the standard value of fatigue life, w1, w2, w3, w4, w5 and w6 represent the first weight, second weight, third weight, fourth weight, fifth weight and sixth weight corresponding to the fluidity, expansion, working time, compressive strength, elastic modulus and fatigue life, respectively;

[0021] Preset about the fitness value Va fit The fitness standard interval, if all performance indicators are greater than the corresponding standard values, and the fitness value Va fit If it is within the fitness standard interval, the design factor corresponding to the performance indicator is judged to be the optimal design factor. If not, the performance indicator that does not reach the standard value is selected, the performance indicator that does not reach the standard value is analyzed, and the design factors that affect the performance indicator that does not reach the standard value are obtained and adjusted.

[0022] Preferably, the initial weight values ​​of the first weight, the second weight, the third weight, the fourth weight, the fifth weight and the sixth weight are configured respectively, and when calculating the fitness value Va fit When the weight adjustment factor is obtained, the weight of each performance indicator is adjusted according to the preset weight adjustment strategy based on the weight adjustment factor, and the weight adjustment factor includes the topography of the high-speed railway layout and the maximum design speed of the train;

[0023] The weight adjustment strategy includes:

[0024] In response to the high-speed railway being laid out on a plain terrain, the first weight and the third weight are increased, and the fourth weight and the fifth weight are decreased;

[0025] In response to the high-speed railway being laid out on a hilly terrain, the fourth weight and the fifth weight are increased, and the first weight and the second weight are decreased;

[0026] In response to the maximum design speed of the train being greater than or equal to a preset speed threshold, the fifth weight and the sixth weight are increased, and the first weight, the second weight and the third weight are decreased;

[0027] In response to the maximum design speed of the train being less than the speed threshold, the third weight and the fourth weight are increased, and the fifth weight and the sixth weight are decreased.

[0028] Preferably, in the step of constructing the model, the type and amount of the raw materials are defined as adjustable factors, and the layout environment parameters are defined as non-adjustable factors, and the layout environment parameters include the number of days of immersion in water, the number of days of freeze-thaw cycles, the construction environment temperature and the application environment temperature coefficient;

[0029] Perform correlation analysis on the deployment environment parameters and the performance indicators, for each deployment environment parameter, traverse the performance indicators, obtain all performance indicators that are associated with the deployment environment parameter, establish a corresponding relationship between the deployment environment parameter and the performance indicators that are associated, and record them as an associated group;

[0030] The design model includes an input layer, a convolutional pooling layer, a fully connected layer and an output layer cascaded in sequence, the input layer includes input nodes whose number is equal to the number of items of the design factors, a branch network is created separately for each of the association groups, and the outputs of multiple branch networks are merged in the fully connected layer.

[0031] Preferably, the construction environment temperature is obtained by the following steps:

[0032] Obtain the construction period of the target road section through the construction plan.

[0033] Obtain historical ambient temperature data of the target road section, predict the ambient temperature during the construction period based on the historical ambient temperature data, and calculate the average value of the predicted ambient temperature during the construction period, which is the construction ambient temperature;

[0034] The application environment temperature coefficient is obtained by the following steps:

[0035] The historical ambient temperature data of the target section within a period is obtained, the maximum temperature, the minimum temperature and the maximum temperature difference per unit time of the target section within the period are analyzed and obtained, and the obtained maximum temperature, minimum temperature and maximum temperature difference per unit time are weighted to obtain the application ambient temperature coefficient.

[0036] Preferably, the input adjustment and optimal design output include the following steps:

[0037] Obtain all possible design factors for high-speed railway cement emulsified asphalt mortar, and use genetic algorithm to initialize the population. Each individual in the population corresponds to a set of possible design factors.

[0038] Each individual in the population is input into the design model to obtain the performance index corresponding to each individual, and further calculate the fitness value Va corresponding to each individual fit ;

[0039] Performing correlation analysis on the adjustable factors and various performance indicators, obtaining adjustable factors having a strong correlation with various performance indicators and establishing a correlation adjustment relationship, and obtaining a correlation result, wherein the strong correlation is represented by the correlation analysis result of the adjustable factors and the performance indicators being not less than a preset correlation threshold, and the correlation result includes the performance indicator, the adjustable factors having a strong correlation with the performance indicator, and the correlation between the performance indicator and the adjustable factors having a strong correlation;

[0040] Individuals in the population whose fitness values ​​are greater than a preset screening threshold are selected as parents, and performance indicators that do not reach the standard values ​​in the individuals serving as parents are screened and marked as unqualified indicators. In the crossover operation, adjustable factors that have a strong correlation with the unqualified indicators are selected as mutation objects, and the mutation direction is determined according to the correlation between the unqualified indicators and the adjustable factors to perform a crossover operation, generate multiple offspring individuals to form a new population, use the new population to replace the initialized population, and repeat the iterative update multiple times until the optimal design factors that meet the energy requirements are obtained and output.

[0041] The present application discloses a high-speed railway cement emulsified asphalt mortar mix design system, comprising:

[0042] An input module, which is used to input the design factors of the cement emulsified asphalt mortar to be designed into the design model; the design factors include the type and amount of raw materials and the layout environment parameters;

[0043] A prediction module, which is used to predict and output performance indicators corresponding to the cement emulsified asphalt mortar to be designed through the design model; the performance indicators include fluidity, expansion, workable time, compressive strength, elastic modulus and fatigue life;

[0044] An input adjustment module is used to adjust the design factors of the cement emulsified asphalt mortar to be designed according to the performance index and input them into the design model to obtain the performance index corresponding to the adjusted design factors, and repeat multiple times until the optimal design factors that meet the performance requirements are obtained;

[0045] The output module is used to output the optimal design factors.

[0046] A computer device of the present application includes a processor and a memory connected by signals, wherein the memory stores at least one instruction or at least one program, and when the at least one instruction or the at least one program is loaded by the processor, the high-speed railway cement emulsified asphalt mortar mix ratio design method as described above is executed.

[0047] A computer-readable storage medium of the present application stores at least one instruction or at least one program, and when the at least one instruction or the at least one program is loaded by a processor, the at least one instruction or the at least one program executes the high-speed railway cement emulsified asphalt mortar mix ratio design method as described above.

[0048] The high-speed railway cement emulsified asphalt mortar mix design method and system described in the present application have the advantages that the present application combines convolutional neural network technology, which can quickly predict the performance indicators corresponding to each mix ratio in different application environments through the convolutional neural network, and iterate through genetic algorithms based on the predicted performance indicators to obtain the optimal mix ratio that meets the performance requirements, thereby completing the rapid and accurate design of CA mortar mix ratios, which helps to improve design efficiency, shorten design cycles, and reduce costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flow chart of the steps of a method for designing a mix ratio of cement emulsified asphalt mortar for high-speed railways described in this embodiment;

[0050] Figure 2 is a flowchart of the steps of constructing a design model according to this embodiment;

[0051] Figure 3 It is a schematic diagram of the structure of the computer device described in this embodiment.

[0052] Description of reference numerals: 101 - processor, 102 - memory. DETAILED DESCRIPTION

[0053] like Figure 1 As shown, a high-speed railway cement emulsified asphalt mortar mix design method described in the present application comprises the following steps:

[0054] Design factor input: input the design factors of the cement emulsified asphalt mortar to be designed into the design model; the design factors include the type and amount of raw materials and the layout environment parameters;

[0055] Prediction output: predicting and outputting performance indicators corresponding to the cement emulsified asphalt mortar to be designed through the design model; the performance indicators include fluidity, expansion, workable time, compressive strength, elastic modulus and fatigue life;

[0056] Input adjustment: according to the performance index, adjusting the design factors of the cement emulsified asphalt mortar to be designed and inputting them into the design model, so as to obtain the performance index corresponding to the adjusted design factors;

[0057] Optimal design output: Repeat the input adjustment steps multiple times until the optimal design factors that meet the performance requirements are obtained and output.

[0058] like Figure 2 As shown, the design model is obtained through the following steps:

[0059] Data preparation: obtain multiple groups of test data of cement emulsified asphalt mortar, including the design factors and corresponding performance indicators of cement emulsified asphalt mortar; for example, use Python crawler technology to obtain relevant test data on cement emulsified asphalt mortar from data websites such as CNKI, Wanfang, Baidu Library, Science Direct, SAGE Journals, Wiley Online Library, Springer Link, etc.; on the other hand, make cement emulsified asphalt mortar specimens with different mix ratios in the laboratory, and conduct tests on construction performance, mechanical properties, durability, fatigue performance, etc., and carry out data collection. The data should cover various properties of cement emulsified asphalt mortar under different raw materials, different mix ratios, and different layout environments, including the aforementioned fluidity, expansion, working time, compressive strength, elastic modulus, and fatigue life. The type of raw materials, dosage, and layout environment parameters are used as characteristic data.

[0060] Data preprocessing: performing data cleaning and normalization on the multiple groups of test data, converting the test data into a two-dimensional matrix, and dividing the multiple groups of test data into a training set, a validation set, and a test set; specifically, performing data cleaning on the test data collected in the aforementioned steps, removing invalid data such as outliers and duplicate values, and normalizing the cleaned data. The normalization process uses the Min-Max normalization method to convert each feature data into the range of [0,1].

[0061] Assuming that there are N sample data in total, the types of raw materials and their corresponding contents in the sample data, such as cement content, emulsified asphalt content, sand content, water content, water reducer content, retarder content, etc., are also included. In addition, the layout environment parameters, such as the number of days of immersion in the layout environment, the number of days of freeze-thaw cycles, the construction environment temperature and the application environment temperature coefficient, are also included. Specifically, the number of days of immersion in water and the number of days of freeze-thaw cycles can be used as a statistical period of one year, and the number of days of immersion and freeze-thaw cycles at the layout site within one year are counted.

[0062] The construction environment temperature is obtained through the following steps:

[0063] The construction period of the target road section is obtained through the construction plan. The construction period of each road section will be recorded in detail in the construction plan. The construction period of the target road section can be directly obtained by reading the construction plan.

[0064] Obtain the historical ambient temperature data of the target road section, for example, obtain the historical ambient temperature data of the target road section in the past week or month, and predict the ambient temperature during the construction period through the historical ambient temperature data. Exemplarily, use a decision tree model to predict the ambient temperature during the construction period. Specifically, use Python's scikit-learn library to build a blank decision tree model, obtain the historical ambient temperature data of the target road section in the past week through meteorological data, perform conventional data cleaning and preprocessing steps on the historical ambient temperature data, convert the historical ambient temperature data into data that can be recognized by the decision tree model, input the converted data into the decision tree model to train the decision tree model, and after the training is completed, optimize the model through cross-validation, thereby obtaining a decision tree model that can predict the ambient temperature of the target road section. Before the actual construction, obtain the ambient temperature data for a certain period of time before the construction period and input it into the decision tree model, so as to predict the changing trend of the ambient temperature during the construction period.

[0065] Since the predicted ambient temperature is time series data and the construction process for a single road section is a short-term continuous operation process, it is considered to use an average value to reflect the temperature conditions of the target road section during the construction period. In this embodiment, by calculating the average value of the ambient temperature predicted during the construction period as the construction ambient temperature, the ambient temperature conditions during the construction period can be better characterized and more in line with actual operations.

[0066] The application environment temperature coefficient is obtained by the following steps:

[0067] Obtain historical environmental temperature data of the target road section in a period, such as a year, analyze and obtain the highest temperature, lowest temperature and maximum temperature difference per unit time of the target road section in the period, perform weighted calculations on the obtained highest temperature, lowest temperature and maximum temperature difference per unit time, and obtain the application environment temperature coefficient. Specifically, through analysis, the design of cement emulsified asphalt mortar can usually meet the working requirements of the conventional temperature range, such as 0°~40°, and the conventional temperature range will not cause excessive damage to the performance of cement emulsified asphalt mortar. Through the collection of actual data analysis, it is found that the performance of cement emulsified asphalt mortar is greatly damaged by extreme temperatures, such as extremely low temperatures and extremely high temperatures, or the maximum temperature difference per unit time, such as a day, is too large. Extreme temperatures can cause obvious damage to the performance of cement emulsified asphalt mortar. For example, extremely low temperatures can cause the strength of cement emulsified asphalt mortar to decrease, toughness to decrease, volume shrinkage to produce cracks, etc., and extremely high temperatures can cause cement emulsified asphalt mortar to soften and deform, while drastic temperature differences per unit time can cause thermal fatigue and internal fatigue of cement emulsified asphalt mortar. The environmental temperature data that will have a greater impact on the cement emulsified asphalt mortar are obtained by collecting actual data analysis, namely the highest temperature, the lowest temperature and the maximum temperature difference per unit time. If the three temperature data are used separately as the input of the design model, the complexity of the model will be greatly increased, the amount of calculation will be increased and the prediction accuracy will be reduced under the premise that the design model already has multiple inputs. Therefore, in this embodiment, the highest temperature, the lowest temperature and the maximum temperature difference per unit time are weighted and summed to obtain the application environment temperature coefficient that can comprehensively characterize the three temperature data. Under the premise of comprehensively considering the three temperature data that have an impact on the construction performance of cement emulsified asphalt mortar, the increase in the complexity of the model can be minimized as much as possible, which is more conducive to practical application.

[0068] After obtaining the design factors, assuming that the design factors include M items in total, the M design factors of N sample data are converted into an N*M two-dimensional matrix. Exemplarily, the two-dimensional matrix is ​​shown in Table 1 below:

[0069] Table 1. Two-dimensional matrix

[0070]

[0071] The obtained sample data is divided into a training set, a validation set, and a test set. For example, the training set data accounts for 80% of the total data volume, and the validation set and test set data each account for 10% of the total data volume. The training set data is used to train the design model, the validation set is used to tune the model and prevent overfitting, and the test set is used to evaluate the final performance of the design model.

[0072] Build a model: Select a convolutional neural network as the design model. Exemplarily, use the deep learning framework Tensor flow or PyTorch to build a convolutional neural network model, including an input layer, multiple convolutional layers, a pooling layer, a fully connected layer, and an output layer. According to the number of rows and columns of the two-dimensional matrix, the input layer of the design model is constructed. Design no less than two convolutional layers to extract data features. Each convolutional layer contains multiple convolution kernels. Each convolution kernel slides on the input data and calculates the convolution result, thereby extracting local features. The size and number of convolution kernels are designed according to the complexity of the input features, such as sampling 3*3 to drive the convolution kernel.

[0073] The sampled ReLu activation function maps the output of the convolution kernel to a nonlinear space, thereby enhancing the expressive power of the model.

[0074] A pooling layer is established after each convolution layer to reduce the dimension and extract the main features of the output of the convolution layer. The pooling function selects the maximum pooling to reduce the dimension of the data.

[0075] After the output of the pooling layer is flattened, it is connected to multiple fully connected layers. The fully connected layers perform nonlinear transformations through multiple layers of neurons to learn the complex relationship between design factors and performance indicators. The ReLU activation function is used for each fully connected layer.

[0076] Finally, according to the required output performance indicators, the corresponding output nodes are designed. For example, six output nodes are configured for fluidity, expansion, working time, compressive strength, elastic modulus and fatigue life respectively to obtain the output layer.

[0077] Model training: Use the test data of the training set to train the constructed design model until the preset convergence condition or number of iterations is reached; Use the training set data to train the model until the preset convergence condition or number of iterations is reached. During the training process, the output value of the model is calculated through forward propagation, and the gradient is calculated through the back-propagation algorithm to update the weight and bias parameters of the model.

[0078] During model training, the mean square error loss function is used to evaluate the gap between the output performance indicators predicted by the model and the actual collected data, and the Adam optimization algorithm is used to update the weight and bias parameters of the model to perform model training.

[0079] Model optimization: Use the experimental data of the verification set and the test set to verify and test the trained design model, and optimize the design model according to the results of the verification and testing until the performance of the design model meets the requirements, thereby obtaining the design model.

[0080] The model is optimized based on the data and performance indicators on the validation dataset, such as using random search or Bayesian optimization methods to adjust hyperparameters, adding regularization terms, using early stopping and other techniques to prevent overfitting, and cross-validation is performed based on the training set, validation set, and test set to evaluate the performance of the model.

[0081] The hyperparameters include learning rate, number of iterations, batch size, etc. The initial learning rate is set to 0.0001, the number of iterations is not less than 100, and the batch size is a power of 2, which is 128. The regularization term is added to limit the complexity of the model parameters. The early stopping technique is used mainly to save training time.

[0082] Through the above steps, a design model is obtained which can predict the performance index corresponding to the design factor based on the input design factor.

[0083] Further, in this embodiment, in the step of adjusting the design factors of the cement emulsified asphalt mortar to be designed according to the performance indicators and inputting them into the design model, it is necessary to express the adaptability of each performance indicator in a quantitative manner, as follows:

[0084] The standard value of each performance indicator is preset. The standard value is usually determined according to the engineering standard or national standard. The fitness value Va of the performance indicator is calculated according to the following formula: fit :

[0085] V fit =w1*(Va Fa / St Fa )+w2*(Va Spr / St Spr )+w3*(Va W_t /

[0086] St W_t )+w4*(Va C_s / St C_s )+w5*(Va E_m / St E_m )+w6*(Va F_l / St F_l );

[0087] Among them, Va Fa Indicates fluidity, St Fa Indicates the standard value of fluidity, Va Spr Indicates the extension degree, St Spr Indicates the standard value of expansion, Va W_t Indicates the working time, St W_t Indicates the standard value of working time, Va C_s Indicates compressive strength, St C_sIndicates the standard value of compressive strength, Va E_m represents the elastic modulus, St E_m Indicates the standard value of elastic modulus, Va F_l represents fatigue life, St F_l represents the standard value of fatigue life, w1, w2, w3, w4, w5 and w6 represent the first weight, second weight, third weight, fourth weight, fifth weight and sixth weight corresponding to the fluidity, expansion, working time, compressive strength, elastic modulus and fatigue life, respectively;

[0088] Preset about the fitness value Va fit The fitness standard interval, if all performance indicators are greater than the corresponding standard values, and the fitness value Va fit If it is within the fitness standard interval, the design factor corresponding to the performance indicator is judged to be the optimal design factor. If not, the performance indicator that does not reach the standard value is selected, the performance indicator that does not reach the standard value is analyzed, and the design factors that affect the performance indicator that does not reach the standard value are obtained and adjusted.

[0089] For high-speed railway construction, first of all, it is necessary to meet the requirements that all performance indicators of cement emulsified asphalt mortar reach the standard value, indicating that the cement emulsified asphalt mortar meets the basic requirements, and then quantify the total fitness value of each performance indicator. The specific method is to obtain the ratio of each performance indicator to the corresponding standard value. For each performance indicator, if it is less than the standard value and the difference with the standard value is large, it will lead to a smaller calculated ratio, and then the calculated fitness value will be smaller. If the performance indicator is equal to the standard value, the ratio result will be close to 1, and the calculated fitness value result will be close to 6, that is, the more the performance indicator exceeds the standard value, the larger the calculated fitness value result will be. Therefore, the larger the calculated fitness value result, the better the performance of the cement emulsified asphalt mortar. However, in actual engineering, marginal benefits need to be considered, specifically, the increase in construction costs and material costs brought about by enhancing the performance of cement emulsified asphalt mortar under the premise of meeting performance requirements. Therefore, in this embodiment, the screening method of the fitness value is selected as interval selection, that is, by presetting the fitness value Va fit The fitness standard interval, for example [1,2], if all performance indicators are greater than the corresponding standard values, and the fitness value Va fit If the fitness index is within the fitness standard interval, the design factor corresponding to the performance index is judged to be the optimal design factor, so that the design and selection of the fitness value can take into account both meeting the standard and combining the actual engineering requirements.

[0090] Furthermore, the weight of each performance index has an important influence on the calculation result of the fitness value. By analyzing the design factors, some of the design factors are adjustable factors, such as the type and content of the materials used. These design factors can be adjusted in the subsequent targeted adjustments, and some design factors are non-adjustable factors, such as topography, maximum design speed of the train, etc. These design factors cannot be adjusted manually, but they also have an important influence on the final performance index and need to be considered in combination. Therefore, in this embodiment, the non-adjustable factors are considered first, and the non-adjustable factors are introduced into the calculation process of the fitness value so that the fitness value can reflect the above factors.

[0091] The specific method is: respectively configure the initial weight values ​​of the first weight, the second weight, the third weight, the fourth weight, the fifth weight and the sixth weight, which can be pre-configured according to the standard terrain and the design speed, etc., and calculate the fitness value Va fit When the weight adjustment factor is obtained, the weight of each performance indicator is adjusted according to the preset weight adjustment strategy based on the weight adjustment factor, and the weight adjustment factor includes the topography of the high-speed railway layout and the maximum design speed of the train;

[0092] The weight adjustment strategy includes:

[0093] In response to the fact that the high-speed railway is laid out in a plain terrain, the first weight and the third weight are increased, and the fourth weight and the fifth weight are reduced; the plain terrain is flat, and the mortar layer is not prone to additional dynamic loads due to terrain changes, so the corresponding weights of compressive strength and elastic modulus can be appropriately reduced. In addition, in order to meet the overall construction period requirements of the high-speed railway, the weights of fluidity and working time can be appropriately increased to adapt to large-scale rapid construction.

[0094] In response to the fact that the terrain where the high-speed railway is laid is hilly, the fourth weight and the fifth weight are increased, and the first weight and the second weight are reduced; the hilly terrain may have slight undulations, and the mortar layer is prone to additional dynamic loads caused by terrain changes. In this terrain, compressive strength and elastic modulus need to be given priority to cope with possible additional dynamic loads. Therefore, the weights of these two performance indicators are increased, and correspondingly, the more secondary first weight and second weight are reduced.

[0095] In response to the maximum design speed of the train being greater than or equal to a preset speed threshold, the fifth weight and the sixth weight are increased, and the first weight, the second weight and the third weight are reduced; in a specific embodiment, the speed threshold can be set to 300 km / h. For high-speed trains whose maximum design speed is greater than or equal to the speed threshold, higher requirements are placed on the dynamic performance and fatigue life of the track. Therefore, the fifth weight and the sixth weight are increased, and the first weight, the second weight and the third weight related to construction are correspondingly reduced.

[0096] In response to the maximum design speed of the train being less than the speed threshold, the third weight and the fourth weight are increased, and the fifth weight and the sixth weight are reduced. For medium and low-speed trains, the requirements for dynamic performance are lower, and they pay more attention to the working time to meet the requirements of large-scale construction. In addition, medium and low-speed trains usually have a larger load or self-weight, and they pay more attention to compressive strength. Therefore, the third weight and the fourth weight are increased, and the fifth weight and the sixth weight are reduced.

[0097] In this step, the calculation of the fitness value is configured according to the unadjustable factors in the design factors, so that the calculated fitness value is closer to the actual construction situation.

[0098] Furthermore, in the step of constructing the model, the type and amount of the raw materials are defined as adjustable factors, and the layout environment parameters are defined as non-adjustable factors, and the layout environment parameters include the number of days of immersion in water, the number of days of freeze-thaw cycles, the construction environment temperature and the application environment temperature coefficient;

[0099] A correlation analysis is performed on the deployment environment parameters and the various performance indicators. For example, a Pearson correlation coefficient analysis is performed on the deployment environment parameters in the sample data and the corresponding performance indicators, and whether there is a correlation between the two parameters is determined based on the calculation result of the Pearson correlation coefficient.

[0100] For each of the deployment environment parameters, traverse the performance indicators, obtain all performance indicators associated with the deployment environment parameter, establish a corresponding relationship between the deployment environment parameter and the performance indicators associated with the parameter, and record them as an associated group;

[0101] The design model includes an input layer, a convolutional pooling layer, a fully connected layer, and an output layer cascaded in sequence. The input layer includes input nodes equal to the number of items of the design factors. A branch network is created separately for each of the association groups, and the outputs of multiple branch networks are merged in the fully connected layer. For example, if there is a correlation between the construction environment temperature and fluidity, the construction environment temperature and fluidity are recorded as an association group, and a branch network is created separately for the association group in the design model. A branch network is created for each performance indicator, and finally multiple branch networks are merged in the fully connected layer to form a complete design model.

[0102] In this embodiment, by analyzing the correlation between the unadjustable factors and the performance indicators and reflecting them in the design model, the prediction results of the performance indicators can fully consider various environmental factors, which helps to improve the prediction accuracy of the performance indicators.

[0103] Furthermore, the input adjustment and optimal design output include the following steps:

[0104] Obtain all possible design factors for high-speed railway cement emulsified asphalt mortar. Possible design factors can be designed based on experience or obtained from existing design data. Use genetic algorithm to initialize the population. Each individual in the population corresponds to a set of possible design factors.

[0105] Each individual in the population is input into the design model to obtain the performance index corresponding to each individual, and further calculate the fitness value Va corresponding to each individual fit ;

[0106] The Pearson correlation coefficient method or the Spearman rank correlation coefficient method is used to perform correlation analysis on the adjustable factors and various performance indicators, and the adjustable factors with strong correlation relationships with various performance indicators are obtained and correlation adjustment relationships are established to obtain correlation results. The strong correlation relationship is represented by the correlation analysis result between the adjustable factors and the performance indicators being not less than a preset correlation threshold, for example, the absolute value of the Pearson correlation coefficient is not less than 0.8, and the correlation result includes the performance indicator, the adjustable factors with strong correlation relationships with the performance indicator, and the correlation between the performance indicator and the adjustable factors with strong correlation relationships; for example, there is a strong correlation between water content and fluidity, and the two are positively correlated.

[0107] Individuals in the population whose fitness values ​​are greater than a preset screening threshold are selected as parents, and performance indicators that do not reach the standard values ​​in the individuals serving as parents are screened and marked as unqualified indicators. In the crossover operation, adjustable factors that have a strong correlation with the unqualified indicators are selected as mutation objects, and the mutation direction is determined according to the correlation between the unqualified indicators and the adjustable factors to perform the crossover operation. For example, if the fluidity of a certain design factor does not meet the standard, it is determined through correlation analysis that the water content and the fluidity have a strong correlation and are positively correlated, then the water content is determined as the mutation object, and a crossover operation is performed with increasing the water content as the mutation direction, to generate multiple offspring individuals to form a new population, use the new population to replace the initialized population, and repeat the iterative update multiple times until the optimal design factor that meets the energy requirements is obtained and output.

[0108] In this embodiment, by performing a correlation analysis between adjustable factors and performance indicators and screening the optimal design factors through a genetic algorithm, the correlation analysis results are introduced into the genetic algorithm, that is, the associated objects are used as mutation objects, and the mutation direction is determined according to the correlation relationship. This can make the mutation of the genetic algorithm more targeted, help reduce the number of iterations, and improve accuracy.

[0109] This embodiment also provides a high-speed railway cement emulsified asphalt mortar mix ratio design system, including:

[0110] An input module, which is used to input the design factors of the cement emulsified asphalt mortar to be designed into the design model; the design factors include the type and amount of raw materials and the layout environment parameters;

[0111] A prediction module, which is used to predict and output performance indicators corresponding to the cement emulsified asphalt mortar to be designed through the design model; the performance indicators include fluidity, expansion, workable time, compressive strength, elastic modulus and fatigue life;

[0112] An input adjustment module is used to adjust the design factors of the cement emulsified asphalt mortar to be designed according to the performance index and input them into the design model to obtain the performance index corresponding to the adjusted design factors, and repeat multiple times until the optimal design factors that meet the performance requirements are obtained;

[0113] The output module is used to output the optimal design factors.

[0114] The system of this embodiment and the above-mentioned method belong to the same inventive concept, which can be understood with reference to the above description and will not be described in detail here.

[0115] like Figure 3As shown, this embodiment also provides a computer device, including a processor 101 and a memory 102 connected by bus signals, wherein the memory 102 stores at least one instruction or at least one program, and the at least one instruction or at least one program is executed by the processor 101 when loaded to perform the high-speed railway cement emulsified asphalt mortar mix design method as described above. The memory 102 can be used to store software programs and modules, and the processor 101 executes various functional applications by running the software programs and modules stored in the memory 102. The memory 102 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory 102 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 102 can also include a memory controller to provide the processor 101 with access to the memory 102.

[0116] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal, a server or a similar computing device, that is, the above-mentioned computer device can include a computer terminal, a server or a similar computing device. The internal structure of the computer device may include but is not limited to: a processor, a network interface and a memory. Among them, the processor, network interface and memory in the computer device can be connected via a bus or other means.

[0117] Among them, the processor 101 (or CPU (Central Processing Unit)) is the computing core and control core of the computer device. The network interface may optionally include a standard wired interface, a wireless interface (such as WI-FI, a mobile communication interface, etc.). The memory 102 (Memory) is a memory device in the computer device for storing programs and data. It can be understood that the memory 102 here can be a high-speed RAM storage device, or a non-volatile storage device (non-volatile memory), such as at least one disk storage device; optionally, it can also be at least one storage device located away from the aforementioned processor 101. The memory 102 provides a storage space, which stores the operating system of the electronic device, which may include but is not limited to: Windows system (an operating system), Linux (an operating system), Android (Android, a mobile operating system) system, IOS (a mobile operating system) system, etc., and this application does not limit this; and, in the storage space, one or more instructions suitable for being loaded and executed by the processor 101 are also stored, and these instructions can be one or more computer programs (including program codes). In the embodiment of the present specification, the processor 101 loads and executes one or more instructions stored in the memory 102 to implement the high-speed railway cement emulsified asphalt mortar mix ratio design method described in the above method embodiment.

[0118] The embodiment of the present application also provides a computer-readable storage medium, on which at least one instruction or at least one program is stored, and when the at least one instruction or the at least one program is loaded by the processor 101, the high-speed railway cement emulsified asphalt mortar mix ratio design method as described above is executed. The above-mentioned computer-readable storage medium carries one or more programs, and when the above-mentioned one or more programs are executed, the method according to the embodiment of the present application is implemented.

[0119] According to an embodiment of the present application, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: 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), 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 application, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0120] For those skilled in the art, various other corresponding changes and deformations can be made according to the technical solutions and concepts described above, and all of these changes and deformations should fall within the protection scope of the claims of this application.

Claims

1. A method for designing the mix ratio of cement emulsified asphalt mortar for high-speed railway, characterized in that: The following steps are involved: Design factor input: input the design factors of the cement emulsified asphalt mortar to be designed into the design model; the design factors include the type and amount of raw materials and the layout environment parameters; Prediction output: predicting and outputting performance indicators corresponding to the cement emulsified asphalt mortar to be designed through the design model; the performance indicators include fluidity, expansion, working time, compressive strength, elastic modulus and fatigue life; Input adjustment: according to the performance index, adjusting the design factors of the cement emulsified asphalt mortar to be designed and inputting them into the design model, so as to obtain the performance index corresponding to the adjusted design factors; Optimal design output: Repeat the input adjustment steps multiple times until the optimal design factors that meet the performance requirements are obtained and output.

2. The method for designing the mix ratio of cement emulsified asphalt mortar for high-speed railway according to claim 1, characterized in that: The design model is obtained through the following steps: Data preparation: obtaining multiple sets of test data of cement emulsified asphalt mortar, wherein the test data includes design factors and corresponding performance indicators of cement emulsified asphalt mortar; Data preprocessing: performing data cleaning and normalization on the multiple groups of test data, converting the test data into a two-dimensional matrix, and dividing the multiple groups of test data into a training set, a validation set, and a test set; Building a model: Selecting a convolutional neural network as the design model; Model training: using the test data of the training set to train the constructed design model until a preset convergence condition or number of iterations is reached; Model optimization: Use the experimental data of the verification set and the test set to verify and test the trained design model, and optimize the design model according to the results of the verification and testing until the performance of the design model meets the requirements, thereby obtaining the design model.

3. The method for designing the mix ratio of cement emulsified asphalt mortar for high-speed railway according to claim 1, characterized in that: In the step of inputting adjustment, adjusting the design factors of the cement emulsified asphalt mortar to be designed and inputting them into the design model according to the performance index comprises: The standard values ​​of various performance indicators are preset, and the fitness value Va of the performance indicator is calculated according to the following formula: fit : will fit =w1*(Will Fa / St Fa )+w2*(Will Spr / St Spr )+w3*(Will W_t / St. W_t )+w4*(Will C_s / St C_s )+w5*(Will E_m / St E_m )+w6*(Will F_l / St F_l ); Among them, Va Fa Indicates fluidity, St Fa Indicates the standard value of fluidity, Va Spr Indicates the extension degree, St Spr Indicates the standard value of expansion, Va W_t Indicates the working time, St W_t Indicates the standard value of working time, Va C_s Indicates compressive strength, St C_s Indicates the standard value of compressive strength, Va E_m represents the elastic modulus, St E_m Indicates the standard value of elastic modulus, Va F_l represents fatigue life, St F_l represents the standard value of fatigue life, w1, w2, w3, w4, w5 and w6 represent the first weight, second weight, third weight, fourth weight, fifth weight and sixth weight corresponding to the fluidity, expansion, working time, compressive strength, elastic modulus and fatigue life, respectively; Preset about the fitness value Va fit The fitness standard interval, if all performance indicators are greater than the corresponding standard values, and the fitness value Va fit If it is within the fitness standard interval, the design factor corresponding to the performance indicator is judged to be the optimal design factor. If not, the performance indicator that does not reach the standard value is selected, the performance indicator that does not reach the standard value is analyzed, and the design factors that affect the performance indicator that does not reach the standard value are obtained and adjusted.

4. The method for designing the mix ratio of cement emulsified asphalt mortar for high-speed railway according to claim 3 is characterized in that: The initial weight values ​​of the first weight, the second weight, the third weight, the fourth weight, the fifth weight and the sixth weight are configured respectively, and the fitness value Va is calculated. fit When the weight adjustment factor is obtained, the weight of each performance indicator is adjusted according to the preset weight adjustment strategy based on the weight adjustment factor, and the weight adjustment factor includes the topography of the high-speed railway layout and the maximum design speed of the train; The weight adjustment strategy includes: In response to the high-speed railway being laid out on a plain terrain, the first weight and the third weight are increased, and the fourth weight and the fifth weight are decreased; In response to the high-speed railway being laid out on a hilly terrain, the fourth weight and the fifth weight are increased, and the first weight and the second weight are decreased; In response to the maximum design speed of the train being greater than or equal to a preset speed threshold, the fifth weight and the sixth weight are increased, and the first weight, the second weight and the third weight are decreased; In response to the maximum design speed of the train being less than the speed threshold, the third weight and the fourth weight are increased, and the fifth weight and the sixth weight are decreased.

5. The method for designing the mix ratio of cement emulsified asphalt mortar for high-speed railway according to claim 3 or 4, characterized in that: In the step of constructing the model, the type and amount of the raw materials are defined as adjustable factors, and the layout environment parameters are defined as non-adjustable factors. The layout environment parameters include the number of days of immersion in water, the number of days of freeze-thaw cycles, the construction environment temperature and the application environment temperature coefficient; Perform correlation analysis on the deployment environment parameters and the performance indicators, for each deployment environment parameter, traverse the performance indicators, obtain all performance indicators that are associated with the deployment environment parameter, establish a corresponding relationship between the deployment environment parameter and the performance indicators that are associated, and record them as an associated group; The design model includes an input layer, a convolutional pooling layer, a fully connected layer and an output layer cascaded in sequence, the input layer includes input nodes whose number is equal to the number of items of the design factors, a branch network is created separately for each of the association groups, and the outputs of multiple branch networks are merged in the fully connected layer.

6. The method for designing the mix ratio of cement emulsified asphalt mortar for high-speed railway according to claim 5, characterized in that: The construction environment temperature is obtained by the following steps: Obtain the construction period of the target road section through the construction plan. Obtain historical ambient temperature data of the target road section, predict the ambient temperature during the construction period based on the historical ambient temperature data, and calculate the average value of the predicted ambient temperature during the construction period, which is the construction ambient temperature; The application environment temperature coefficient is obtained by the following steps: The historical ambient temperature data of the target section within a period is obtained, the maximum temperature, the minimum temperature and the maximum temperature difference per unit time of the target section within the period are analyzed and obtained, and the obtained maximum temperature, minimum temperature and maximum temperature difference per unit time are weighted to obtain the application ambient temperature coefficient.

7. The method for designing the mix ratio of cement emulsified asphalt mortar for high-speed railway according to claim 5, characterized in that: The input adjustment and optimal design output include the following steps: Obtain all possible design factors for high-speed railway cement emulsified asphalt mortar, and use genetic algorithm to initialize the population. Each individual in the population corresponds to a set of possible design factors. Each individual in the population is input into the design model to obtain the performance index corresponding to each individual, and further calculate the fitness value Va corresponding to each individual fit ; Performing correlation analysis on the adjustable factors and various performance indicators, obtaining adjustable factors having a strong correlation with various performance indicators and establishing a correlation adjustment relationship, and obtaining a correlation result, wherein the strong correlation is represented by the correlation analysis result of the adjustable factors and the performance indicators being not less than a preset correlation threshold, and the correlation result includes the performance indicator, the adjustable factors having a strong correlation with the performance indicator, and the correlation between the performance indicator and the adjustable factors having a strong correlation; Individuals in the population whose fitness values ​​are greater than a preset screening threshold are selected as parents, and performance indicators that do not reach the standard values ​​in the individuals serving as parents are screened and marked as unqualified indicators. In the crossover operation, adjustable factors that have a strong correlation with the unqualified indicators are selected as mutation objects, and the mutation direction is determined according to the correlation between the unqualified indicators and the adjustable factors to perform a crossover operation, generate multiple offspring individuals to form a new population, use the new population to replace the initialized population, and repeat the iterative update multiple times until the optimal design factors that meet the energy requirements are obtained and output.

8. A high-speed railway cement emulsified asphalt mortar mix design system, characterized in that: include: An input module, which is used to input the design factors of the cement emulsified asphalt mortar to be designed into the design model; the design factors include the type and amount of raw materials and the layout environment parameters; A prediction module, which is used to predict and output performance indicators corresponding to the cement emulsified asphalt mortar to be designed through the design model; the performance indicators include fluidity, expansion, workable time, compressive strength, elastic modulus and fatigue life; An input adjustment module is used to adjust the design factors of the cement emulsified asphalt mortar to be designed according to the performance index and input them into the design model to obtain the performance index corresponding to the adjusted design factors, and repeat multiple times until the optimal design factors that meet the performance requirements are obtained; The output module is used to output the optimal design factors.

9. A computer device comprising a processor and a memory connected in a signal connection, characterized in that: The memory stores at least one instruction or at least one program, and when the at least one instruction or the at least one program is loaded by the processor, the high-speed railway cement emulsified asphalt mortar mix proportion design method as described in any one of claims 1-7 is executed.

10. A computer-readable storage medium having at least one instruction or at least one program stored thereon, characterized in that: When the at least one instruction or the at least one program is loaded by the processor, the high-speed railway cement emulsified asphalt mortar mix ratio design method as described in any one of claims 1-7 is executed.

Images