Gas explosion shock wave overpressure process deduction method based on optimized multi-layer perceptron

Abstract

The invention discloses a gas explosion shock wave overpressure process deduction method based on an optimized multi-layer perceptron, and the method comprises the steps: obtaining initial parameters, and dividing the initial parameters into a training set and a test set; constructing a multi-layer perceptron regression model based on the training set and the test set; optimizing a learning rate and a regularization factor of an initial parameter of the multi-layer perceptron regression model through an improved particle swarm algorithm to obtain a globally optimal solution; outputting a result of the multi-layer perceptron regression model by adopting a self-service algorithm so as to obtain a confidence interval for deducing an overpressure value; and inputting the globally optimal solution into the multi-layer perceptron regression model, and carrying out overpressure deduction analysis in the obtained confidence interval. According to the method, adaptive optimization is carried out on the key hyper-parameters of the multi-layer perceptron regression model according to the data features, the convergence efficiency and accuracy of the model are improved, and technical support is provided for mastering the explosion radiation range and intensity in a short time after a gas explosion accident occurs.

Description

Technical Field

[0001] The present application relates to a method for deducing a gas explosion shock wave overpressure process based on an optimized multi-layer perceptron, and belongs to the technical field of gas explosion process deduction. Background Art

[0002] Gas explosion is a common industrial accident, and the casualties and property losses it causes are often incalculable. Therefore, the study of the deduction method of the gas explosion process has important practical significance. The research of this method aims to analyze the pressure evolution law of the explosion shock wave at the accident site, and to deduce the process of the possible explosion location, so as to obtain the accurate explosion radiation range, thereby providing effective support for the formulation of scientific emergency plans. In recent years, with the continuous maturity of computer technology, the development of coal mine intelligence has accelerated, and various algorithms for disaster prediction, early warning and deduction analysis have been widely used in the daily safety production process of coal mines. Many machine learning algorithm models represented by neural networks have gradually increased their adaptability to data after continuous optimization and iteration, and can explain many nonlinear complex problems in key scientific issues. However, the deduction method of the gas explosion process is a complex process. The existing machine learning algorithm model needs to invert the gas explosion process by establishing a mathematical model, resulting in a relatively delayed acquisition of the calculation results. With the development of intelligent coal mines, higher requirements are placed on the ability to quickly obtain and analyze disaster information. How to quickly deduce the explosion process before and after the explosion and provide auxiliary decision-making information for early prevention and rapid formulation of scientific and effective rescue plans after the disaster is a difficult problem that urgently needs to be overcome. Summary of the invention

[0003] In view of this, the present application provides a method for deducing the overpressure process of gas explosion shock wave based on an optimized multi-layer perceptron, which is used to solve the problem in the prior art that in the deduction of the gas explosion process, the machine learning algorithm model needs to invert the gas explosion process by establishing a mathematical model, resulting in a relatively delayed acquisition of the calculation results. The specific scheme is:

[0004] A method for deducing a gas explosion shock wave overpressure process based on an optimized multi-layer perceptron comprises the following steps:

[0005] Step 1: Get the initial parameters and divide them into training set and test set;

[0006] Step 2: Build a multi-layer perceptron regression model (MLPRegressor) based on the training set and the test set;

[0007] Step 3: Optimize the learning rate and regularization factor (Alpha) of the initial parameters input to the multilayer perceptron regression model (MLPRegressor) through the improved particle swarm algorithm (POS) to obtain the global optimal solution;

[0008] Step 4: Use the bootstrap algorithm (BootStrap) to output the results of the multilayer perceptron regression model (MLPRegressor) to obtain the confidence interval of the deduced overpressure value;

[0009] Step 5: Input the global optimal solution into the multi-layer perceptron regression model (MLPRegressor) to perform overpressure deduction analysis within the obtained confidence interval.

[0010] Preferably, the activation function in the multilayer perceptron regression model is a tanh function;

[0011] The error function uses the mean absolute error (MAE), and the error calculation is a back-to-forward back-propagation algorithm.

[0012] Preferably, in the multilayer perceptron regression model, all nodes except the input node are neurons with a nonlinear activation function;

[0013] The initial parameters include: explosion source location coordinates, tunnel parameters and explosion initial pressure.

[0014] Preferably, the optimization process of the improved particle swarm algorithm (POS) for the learning rate (Learning rate) and the regularization factor (Alpha) of the initial parameters input to the multilayer perceptron regression model (MLPRegressor) is:

[0015] First, each particle is randomly initialized;

[0016] Subsequently, each particle is evaluated and the global optimal particle is obtained;

[0017] Finally, determine whether the iteration meets the end condition;

[0018] If yes, then end; if no, continue to iterate until the end condition is met and the process ends;

[0019] The value corresponding to when the end condition is met is the global optimal solution.

[0020] Preferably, the iterative process includes the following steps: updating the speed and position of each particle, evaluating the function fitness value of each particle, updating the historical optimal position of each particle, and updating the global optimal position of the group.

[0021] Preferably, the process of determining whether the iteration meets the termination condition is:

[0022] (1) Data preparation: Obtain preprocessed standard data to ensure that the data has been preprocessed; preprocessing includes normalizing or standardizing the feature data to ensure that the model is not sensitive to the data range;

[0023] (2) Import necessary libraries: Import the Scikit-learn library, especially the neural_network module, which contains the MLPRegressor class;

[0024] (3) Define a multilayer perceptron regression model (MLPRegressor): Create an MLPRegressor object and specify the hyperparameters of the multilayer perceptron regression model;

[0025] (4) Train the multi-layer perceptron regression model (MLPRegressor): Use the training set (features and target values) to fit the multi-layer perceptron regression model;

[0026] (5) Evaluate the MLPRegressor model: Use the test set to evaluate the performance of the MLPRegressor model to select the best hyperparameter combination;

[0027] (6) Prediction of Multilayer Perceptron Regressor Model (MLPRegressor): Use the trained multilayer perceptron regression model to predict new data, that is, input the features of the new data into the multilayer perceptron regression model to obtain the prediction results;

[0028] (7) Multilayer Perceptron Regressor (MLPRegressor) optimization: Determine whether the performance of the multilayer perceptron regression model (MLPRegressor) is ideal based on the prediction results. If the performance of the multilayer perceptron regression model (MLPRegressor) is not ideal, try to adjust the hyperparameters, increase the number of hidden layers or neurons, try different activation functions or optimizers, etc.

[0029] (8) Saving and loading the multilayer perceptron regression model (MLPRegressor). Save the trained multilayer perceptron regression model (MLPRegressor) to a file for subsequent use or deployment. Use libraries such as joblib or pickle to save and load the model.

[0030] Preferably, the improvement process of the particle swarm algorithm (POS) is:

[0031] (1) Analyze the problem: First, you need to analyze the problem to be solved to determine whether there is a risk of premature convergence or falling into a local optimal solution. This can be done by observing the performance of the algorithm in previous iterations.

[0032] (2) Determine the improvement goal: Based on the results of the problem analysis, determine the goal of improving the inertia weight model, which may include improving the global search ability of the algorithm, avoiding premature convergence, or improving the quality of the solution;

[0033] (3) Adopting adaptive inertia weight algorithm to improve particle swarm optimization (POS): dynamically adjust the inertia weight according to the fitness of particles or the topological structure of search space to balance the global search and local search capabilities;

[0034] (4) Implementing the improvement method: According to the selected improvement method, modify the particle swarm algorithm (PSO). This process includes: modifying the particle velocity update equation, adding new parameters, or using different strategies to select the inertia weight value;

[0035] (5) Testing and verification: Use the modified PSO to solve a series of test problems and compare the test results with those of the original algorithm to test and verify the modified PSO. The evaluation indicators of the test results may include convergence speed, solution quality and robustness.

[0036] (6) Based on the test results, further adjust and optimize the parameters or strategies of the improved method in the adaptive inertia weight model to achieve the global optimal solution. This may be an iterative process that requires multiple attempts based on the specific problem and algorithm performance.

[0037] Preferably, in the optimization of the adaptive inertia weight model, after the inertia factor ω is adaptively optimized, the inertia factor ω is associated with the number of iterations and the fitness of each particle:

[0038] 1) Assuming that the problem of finding the minimum fitness value is solved, the fitness expression is formula (1):

[0039]

[0040] 2) Assuming the problem of finding the maximum fitness, the fitness expression is formula (2):

[0041]

[0042] In equations (1) and (2): min and ω max is the preset minimum inertia coefficient and maximum inertia coefficient, then the average fitness of all particles at the dth iteration is expressed as formula (3):

[0043]

[0044] The maximum fitness of all particles at the dth iteration It is expressed as formula (4):

[0045]

[0046] Preferably, the deduction and analysis steps are:

[0047] The training is completed and the optimal parameters are obtained;

[0048] Input relevant test initial data sets for overpressure simulation analysis;

[0049] At the same time, it is assumed that the deduced initial overpressure value is the maximum value during the explosion process;

[0050] The bootstrap algorithm (BootStrap) is used to estimate the confidence interval of the deduced overpressure value.

[0051] Preferably, the process of obtaining the confidence interval of the deduced overpressure value by the bootstrap algorithm is: The process of obtaining the confidence interval of the deduced overpressure value by the bootstrap algorithm is:

[0052] In the sampling process, the bootstrap algorithm ensures that the probability of each element in the sampling result being drawn is the same. N elements are drawn each time and repeated B times to obtain B groups of sample matrices containing N elements. The eigenvalues ​​of each group of samples are calculated to obtain the bootstrap sample probability eigenvalues. Suppose the original sample S is expressed as formula (5):

[0053] S=(S1,S2,S3,…S i ,…,S n ) Formula (5);

[0054] In formula (5): S i is the i-th data of the sample, S n It means there are n elements in total, and B elements are extracted from them, each time with N data. Finally, each extracted sample set P can be expressed as formula (6):

[0055] P=(P1,P2,P3,…P b ,…,P b ) Formula (6);

[0056] In formula (6): P b is the b-th self-service sample set, expressed as formula (7):

[0057] P b =P b (i), i=1,2,…,N Formula (7);

[0058] In formula (7): P b (i) is represented by P b The i-th element of , so the bootstrap sample set P b The mean The calculation formula is expressed as formula (8):

[0059]

[0060] The bootstrap sample mean is It can be expressed as formula (9):

[0061]

[0062] Bootstrap sample variance σ 2 It is expressed as formula (10):

[0063]

[0064] In machine learning, the bootstrap algorithm can be used to solve the confidence interval. By estimating the sample eigenvalues, different confidence intervals can be obtained. Assuming that the bootstrap algorithm is used to obtain the sample parameter estimate, the sample parameter θ is expressed as formula (11):

[0065]

[0066] Arrange them from small to large, and we get formula (12):

[0067]

[0068] Assuming the significance level is α, α∈[0,1], the confidence level is expressed as formula (13):

[0069]

[0070] Let K1 and K2 represent the upper confidence limit and lower confidence limit respectively, as shown in formula (14):

[0071]

[0072] and is the quantile and The estimation of can be obtained as formula (15):

[0073]

[0074] The final confidence interval is expressed as formula (16):

[0075]

[0076] The beneficial effects of this application include:

[0077] This application uses an improved particle swarm algorithm to optimize the learning rate and regularization factor of the initial parameters input into the multilayer perceptron regression model (MLPRegressor), and the appropriate learning rate and regularization factor will enable the algorithm to complete convergence efficiently, increase the robustness of the model, and be more adaptable to data, avoid overfitting of the model, and greatly improve the operating efficiency and accuracy of the model. By establishing a correlation between the inertia weight and the number of iterations and the particle fitness, the key hyperparameters of the multilayer perceptron regression model (MLPRegressor) are adaptively optimized according to the data characteristics, thereby improving the convergence efficiency and accuracy of the model.

[0078] A self-help algorithm is used to output the results of a multilayer perceptron regression model (MLPRegressor) to obtain a confidence interval of the deduced overpressure value, and an overpressure deduction analysis is performed within the confidence interval to obtain the explosion radiation range and intensity after a gas explosion accident occurs in a coal mine. This application optimizes the parameters of the multilayer perceptron regression model (MLPRegressor) through an improved particle swarm algorithm, and combines the use of a self-help algorithm to output the results of the multilayer perceptron regression model (MLPRegressor), so as to provide certain technical support for being able to grasp the explosion radiation range and intensity in a short time after a gas explosion accident occurs in a coal mine, so as to achieve the ability to quickly grasp the explosion range and further judge the degree of underground damage once an accident occurs, and provide effective support for post-disaster emergency response work. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 This application optimizes the explosion deduction structure diagram of the multi-layer perceptron regression model (MLPRegressor);

[0080] Figure 2 This is a flow chart of the parameters optimization of the self-service algorithm (PSO) in this application;

[0081] Figure 3 is the fitness value corresponding to the global optimal solution of the multilayer perceptron regression model (MLPRegressor);

[0082] Figure 4 This is a diagram of the parameter optimization process of the multilayer perceptron regression model (MLPRegressor);

[0083] Figure 5 This is a visualization diagram of the deduction results of the optimized multilayer perceptron regression model (MLPRegressor) in Example 1;

[0084] Figure 6A comparison chart of the true value, deduced value and confidence interval of the straight pipe model in Example 1 of the present application;

[0085] Figure 7 Comparison chart of the true value, deduced value and confidence interval of the pipeline model of Chongqing Coal Research Institute

[0086] Figure 8 This is a model diagram for the 60° bifurcated pipeline deduction in Example 2;

[0087] Fig. 9 This is a schematic diagram of the explosion source location deduced by overpressure in Example 2;

[0088] Fig.10 This is a visualization diagram of the 60° bifurcated pipeline simulation in Example 2. DETAILED DESCRIPTION

[0089] Step 1, obtaining initial parameters, and dividing the initial parameters into a training set and a test set in chronological order; in this application, the initial parameters specifically refer to the explosion source location coordinates, tunnel parameters, and explosion initial pressure;

[0090] Step 2: Build a multi-layer perceptron regression model (MLPRegressor) based on the training set and the test set;

[0091] Step 3: Optimize the learning rate and regularization factor (Alpha) of the initial parameters input to the multilayer perceptron regression model (MLPRegressor) through the improved particle swarm algorithm (POS) to obtain the global optimal solution;

[0092] In this application, the purpose of optimizing the learning rate and regularization factor (Alpha) is that appropriate learning rate and regularization factor will enable the algorithm to converge efficiently, increase model robustness, and be more adaptable to data, thereby avoiding overfitting of the model and significantly improving the operating efficiency and accuracy of the multilayer perceptron regression model.

[0093] Since the learning rate represents the speed of information accumulation over time in the algorithm, it is the most critical parameter in the algorithm. A suitable learning rate will enable the algorithm to converge efficiently. The regularization factor (Alpha) is a factor that reduces the overfitting phenomenon of the model. When the parameters in the training set are close to the optimal value, a penalty term will be added to limit the change in the parameters. Selecting a suitable regularization factor (Alpha) can increase the robustness of the model, make it more adaptable to data, and avoid overfitting of the model. Therefore, this application optimizes the learning rate (Learning rate) and regularization factor (Alpha) of the initial parameters through the particle swarm algorithm to avoid overfitting of the multilayer perceptron regression model (MLPRegressor). The specific optimization process is as follows: Figure 2 As shown:

[0094] First, each particle is randomly initialized; then, each particle is evaluated to obtain the global optimum; then, it is determined whether the iteration can reach the end condition. If so, it ends. If not, it repeats the process of updating the speed and position of each particle, evaluating the function fitness value of each particle, updating the historical optimal position of each particle, and updating the global optimal position of the group. Finally, the process ends when the judgment result is yes.

[0095] Step 4: Use the bootstrap algorithm (BootStrap) to output the results of the multilayer perceptron regression model (MLPRegressor) to obtain the confidence interval of the deduced overpressure value;

[0096] Step 5: Input the global optimal solution into the multi-layer perceptron regression model (MLPRegressor) to perform overpressure deduction analysis within the obtained confidence interval. The deduction analysis steps are as follows:

[0097] The training is completed and the optimal parameters are obtained;

[0098] Input optimal parameters for overpressure simulation analysis;

[0099] At the same time, it is assumed that the deduced initial overpressure value is the maximum value during the explosion process;

[0100] The confidence interval of the deduced overpressure value is estimated using a bootstrap algorithm.

[0101] It should be noted that:

[0102] In this application:

[0103] The criteria for determining whether an iteration meets the end condition are:

[0104] (1) Data preparation: Obtain preprocessed standard data to ensure that the data has been preprocessed; preprocessing includes normalizing or standardizing the feature data to ensure that the model is not sensitive to the data range;

[0105] (2) Import necessary libraries: Import the Scikit-learn library, especially the neural_network module, which contains the MLPRegressor class;

[0106] (3) Define the multilayer perceptron regression model (MLPRegressor): Create an MLPRegressor object and specify the hyperparameters of the multilayer perceptron regression model (MLPRegressor);

[0107] (4) Train the multilayer perceptron regression model (MLPRegressor): Use the training set (features and target values) to fit the multilayer perceptron regression model (MLPRegressor);

[0108] (5) Evaluate the MLPRegressor model: Use the test set to evaluate the performance of the MLPRegressor model to select the best hyperparameter combination;

[0109] (6) Predicting the multilayer perceptron regression model (MLPRegressor): Use the trained multilayer perceptron regression model (MLPRegressor) to predict the new data, that is, input the features of the new data into the multilayer perceptron regression model (MLPRegressor) to obtain the prediction results;

[0110] (7) Multilayer Perceptron Regressor (MLPRegressor) optimization: Determine whether the performance of the multilayer perceptron regression model (MLPRegressor) is ideal based on the prediction results. If the performance of the multilayer perceptron regression model (MLPRegressor) is not ideal, try to adjust the hyperparameters, increase the number of hidden layers or neurons, try different activation functions or optimizers, etc.

[0111] (8) Saving and loading the multilayer perceptron regression model (MLPRegressor). Save the trained multilayer perceptron regression model (MLPRegressor) to a file for subsequent use or deployment. Use libraries such as joblib or pickle to save and load the model.

[0112] like Figure 2 The figure shows the optimization flow chart of the particle swarm algorithm (PSO). The improvement process of the particle swarm algorithm (PSO) is as follows:

[0113] (1) Analyze the problem: First, you need to analyze the problem to be solved to determine whether there is a risk of premature convergence or falling into a local optimal solution. This can be done by observing the performance of the algorithm in previous iterations.

[0114] (2) Determine the improvement goal: Based on the results of the problem analysis, determine the goal of improving the inertia weight model, which may include improving the global search ability of the algorithm, avoiding premature convergence, or improving the quality of the solution;

[0115] (3) An adaptive inertia weight model is used to improve the particle swarm algorithm (POS): the inertia weight is dynamically adjusted according to the fitness of the particles or the topological structure of the search space to balance the global search and local search capabilities;

[0116] (4) Implementing the improvement method: According to the selected improvement method, modify the particle swarm algorithm (PSO). This process includes: modifying the particle velocity update equation, adding new parameters, or using different strategies to select the inertia weight value;

[0117] (5) Testing and verification: Use the modified PSO to solve a series of test problems and compare the test results with those of the original algorithm to test and verify the modified PSO. The evaluation indicators of the test results may include convergence speed, solution quality and robustness.

[0118] (6) Based on the test results, further adjust and optimize the parameters or strategies of the improved method to achieve the global optimal solution. This may be an iterative process that requires multiple attempts based on the specific problem and algorithm performance.

[0119] In the optimization of the adaptive inertia weight model, after the inertia factor ω is adaptively optimized, the inertia factor ω is associated with the number of iterations and the fitness of each particle:

[0120] 3) Assuming that the problem of finding the minimum fitness value is solved, the fitness expression is formula (1):

[0121]

[0122] 4) Assuming the problem of finding the maximum fitness, the fitness expression is formula (2):

[0123]

[0124] In equations (1) and (2): min and ω max is the preset minimum inertia coefficient and maximum inertia coefficient, then the average fitness of all particles at the dth iteration is expressed as formula (3):

[0125]

[0126] The maximum fitness of all particles at the dth iteration It is expressed as formula (4):

[0127]

[0128] In this application, an adaptive inertia weight improvement method is used in the improvement of the particle swarm algorithm (pso), and the adaptive inertia weight is correlated with the number of iterations and the particle fitness. Furthermore, the purpose of the particle swarm algorithm is to optimize the key hyperparameters of the multilayer perceptron regression model (MLPRegressor), thereby realizing the adaptive optimization of the key hyperparameters of the multilayer perceptron regression model (MLPRegressor) according to data characteristics.

[0129] Furthermore, the deduction and analysis steps are:

[0130] The training is completed and the optimal parameters are obtained;

[0131] Input relevant test initial data sets for overpressure simulation analysis;

[0132] At the same time, it is assumed that the deduced initial overpressure value is the maximum value during the explosion process;

[0133] The bootstrap algorithm (BootStrap) is used to estimate the confidence interval of the deduced overpressure value.

[0134] Furthermore, the process of obtaining the confidence interval of the deduced overpressure value by the bootstrap algorithm is as follows: The process of obtaining the confidence interval of the deduced overpressure value by the bootstrap algorithm is as follows:

[0135] In the sampling process, the bootstrap algorithm ensures that the probability of each element in the sampling result being drawn is the same. N elements are drawn each time and repeated B times to obtain B groups of sample matrices containing N elements. The eigenvalues ​​of each group of samples are calculated to obtain the bootstrap sample probability eigenvalues. Suppose the original sample S is expressed as formula (5):

[0136] S=(S1,S2,S3,…S i ,…,S n ) Formula (5);

[0137] In formula (5): S i is the i-th data of the sample; S n It means there are n elements in total, and B elements are extracted from them, each time with N data. Finally, each extracted sample set P can be expressed as formula (6):

[0138] P=(P1,P2,P3,…P b ,…,P b) Formula (6);

[0139] In formula (6): P b is the b-th self-service sample set, expressed as formula (7):

[0140] P b =P b (i), i=1,2,…,N Formula (7);

[0141] In formula (7): P b (i) is represented by P b The i-th element of , so the bootstrap sample set P b The mean The calculation formula is expressed as formula (8):

[0142]

[0143] The bootstrap sample mean is It can be expressed as formula (9):

[0144]

[0145] Bootstrap sample variance σ 2 It is expressed as formula (10):

[0146]

[0147] In machine learning, the bootstrap algorithm can be used to solve the confidence interval. By estimating the sample eigenvalues, different confidence intervals can be obtained. Assuming that the bootstrap algorithm is used to obtain the sample parameter estimate, the sample parameter θ is expressed as formula (11):

[0148]

[0149] Arrange them from small to large, and we get formula (12):

[0150]

[0151] Assuming the significance level is α, α∈[0,1], the confidence level is expressed as formula (13):

[0152]

[0153] Let K1 and K2 represent the upper confidence limit and lower confidence limit respectively, as shown in formula (14):

[0154]

[0155] and is the quantile and The estimation of can be obtained as formula (15):

[0156]

[0157] The final confidence interval is expressed as formula (16):

[0158]

[0159] Furthermore, the construction process of the multi-layer perceptron regression model (Multi-layer Perceptron Regressor, MLPRegressor) is:

[0160] like Figure 1 As shown in the figure, the Multi-layer Perceptron Regressor (MLPRegressor) model belongs to a feedforward artificial neural network model, which maps a set of input vectors to a set of output vectors. It is a directed graph consisting of multiple node layers, and each layer is connected to the next layer. Except for the input node, each node is a neuron with a nonlinear activation function, which is trained by a supervised learning method of a back-propagation algorithm.

[0161] The multilayer perceptron regression model (MLPRegressor) follows the principle of the human nervous system. Its basic structure consists of three layers: input layer, hidden layer (in this application, the hidden layer includes hidden layer 1 and hidden layer 2) and output layer. The product of the input element and the weight is fed back to the summation node with neuron bias. The main advantage lies in its ability to quickly solve complex problems. It overcomes the weakness of the perceptron that it cannot identify linearly inseparable data, and performs well in processing complex data and nonlinear data.

[0162] Assuming there are n features in m samples, the input layer X∈R m×n , assuming there are H neurons, then the weight of the hidden layer is W h and deviation b h It can be expressed as W h ∈R h×n , b h ∈R 1×n , if there are q output label values, the weight of the output layer is W o and the deviation parameter b h Respectively represented as W o ∈R h×q , b h ∈R 1×q , then the outputs of the hidden layer and the output layer are expressed as Equation (17) and Equation (18) respectively, which only performs a linear transformation on the data;

[0163] H=XW h +b h Formula (17);

[0164] O=XW o +b o Formula (18);

[0165] After the linear transformation, the data needs to be transformed nonlinearly. Commonly used nonlinear activation functions include Relu function, sigmoid function and tanh function. The Relu function sets the numbers greater than 0 in the output result to x and sets the numbers less than 0 to 0; the Sigmoid function maps the output result to between 0 and 1; the tanh function maps the output result to between -1 and 1. The tanh function is selected as the activation function in this application.

[0166] Assume that the output of layer l before activation by the activation function is z l , after activation, it is represented as a l , σ is represented as the activation function, then the output of the previous layer after activation can be set as the input of this layer, and the output of this layer before and after activation is expressed as formula (19) and formula (20) respectively:

[0167] z l =W l a l-1 +b l Formula (19);

[0168] a l =σz l Formula (20);

[0169] In equations (19) and (20), W l represents the weight of layer l; b l represents the deviation of layer l.

[0170] In the calculation process, the multilayer perceptron regression model (MLPRegressor) uses cross entropy to solve the loss function. Since some data may be close to 0, resulting in large deviations, the mean absolute error (MAE) is used as the error function, and the error calculation is a back-to-forward back propagation algorithm, as shown in formula (21):

[0171]

[0172] In formula (21): X represents the matrix; h represents the prediction function; x i represents the true value; y i Represents the predicted value.

[0173] The present application is described in detail below with reference to embodiments, but the present application is not limited to these embodiments.

[0174] The initial data of the following embodiments are collected from experimental platform data obtained under different working conditions and parameters from Chongqing Coal Research Institute, the United States Bureau of Mines, etc., and these platform data have been verified for reliability. In the following implementation, 8 particles are selected for 100 iterations during the initial parameter optimization process, and the acceleration factors c1 and c2 are set to 1.1 and 1.3 respectively, and r1 and r2 are set to random numbers in the interval [0, 1]. The process of finding the global optimal solution is as shown in the attached figure. Figure 3 As shown in the attached Figure 3 It can be seen that when searching for the global optimal solution during the optimization process, the fitness value shows an overall downward trend. When the global optimal solution appears and remains unchanged, the fitness value is 0.6837.

[0175] The optimization process of the multi-layer perceptron regression model (MLPRegressor) is as follows Figure 4 As shown, it can be seen that the self-service algorithm (PSO) calculates the fitness value once each time it sets the learning rate (Learning rate) and the regularization factor (Alpha) value. When the global optimal solution appears and does not change, the two parameter values ​​corresponding to the fitness value are optimal. At this time, the learning rate (Learning rate) and the regularization factor (Alpha) value results are 0.002967 and 0.0001. In the subsequent deduction process, the parameters of the multilayer perceptron regression model (MLPRegressor) are all carried out under this value.

[0176] Example 1

[0177] This example performs overpressure simulation analysis on a straight pipeline:

[0178] The overpressure deduction of straight pipelines is mainly carried out by setting the initial overpressure value of the explosion. After the training is completed and the optimal parameters are obtained, the relevant test initial data set is input for overpressure deduction analysis, and it is assumed that the deduced initial overpressure value is the maximum value during the explosion. Two sets of experimental data, the Chongqing Coal Research Institute model and the optimized multi-layer perceptron regression model in this application, are selected for cross-validation, and the bootstrap algorithm (BootStrap) is used to estimate the confidence interval of the deduced overpressure value. The results are shown in Tables 1 and 2.

[0179] Tables 1 and 2 show the deduced values, confidence intervals, mean absolute errors between the deduced values ​​and the true values, and the maximum absolute error and minimum absolute error within the confidence interval obtained by the deduction explosion of the optimized multilayer perceptron regression model (MLPRegressor) and the Chongqing Coal Research Institute model, respectively.

[0180] Table 1 Optimized multilayer perceptron regression model (MLPRegressor) deduction results

[0181]

[0182] Table 2 Optimized regression model (MLPRegressor) deduction Chongqing Institute model results

[0183]

[0184] In order to verify the scientificity and effectiveness of the optimized multi-layer perceptron regression model (MLPRegressor), this embodiment visualizes the results of the 9.5% gas concentration explosion in a straight pipeline, such as Figure 5 The figure shows the visualization of the results of the explosion simulation of a 9.5% gas concentration in a straight pipeline using the multilayer perceptron regression model (MLPRegressor) optimized in this application. Figure 6 and Figure 7 The results are respectively the comparison of the deduced value, true value, upper confidence limit and lower confidence limit of the multilayer perceptron regression model (MLPRegressor) optimized in this application and the deduced value of the Chongqing Coal Research Institute pipeline model. Figure 5 and Figure 6 It can be obtained that the overall error between the deduction results of the optimized multilayer perceptron regression model (MLPRegressor) and the true value is small, and the average absolute errors of the two groups of results are 0.0722 and 0.032 respectively; and it can be seen that the deduced value of each sample can fall within the confidence interval estimated by the bootstrap algorithm (BootStrap), and the minimum average absolute error in the confidence interval is 0.1052 and 0.024 respectively, and the maximum average absolute error in the confidence interval is 0.2328 and 0.042 respectively. The small error in the interval shows that the confidence interval is more reasonable and the accuracy is higher. It can be concluded that the confidence interval of the optimized multilayer perceptron regression model (MLPRegressor) is more reasonable and has higher accuracy.

[0185] Example 2

[0186] This example performs deduction and analysis on a bifurcated pipeline:

[0187] The overpressure deduction method for a pipeline with a bifurcation angle is different from that for a straight pipeline. It is necessary to first determine the bifurcation position and bifurcation angle of the pipeline, so as to determine the attenuation characteristics of the overpressure at different bifurcation angles. This application takes a 60° bifurcation pipeline as an example. First, a bifurcation pipeline coordinate system is established, with the closed end as the coordinate origin O, the direction along the open end of the straight pipe as the x-axis, and the vertical straight pipe section as the y-axis. Figure 8There are two main overpressure propagation paths, which are represented by measuring point connection, i.e., along the straight pipe section: G1→G2→G3→G4→G5→G6, along the branch pipe section: G1→G2→G7→G8. The initial input information of overpressure deduction (specifically: the distance from each measuring point to the explosion source, the coordinates of each point and the pipeline information) is calculated according to the overpressure deduction theoretical model as shown in Table 3:

[0188] Table 3 Initial input information table for overpressure simulation

[0189]

[0190] The overpressure deduction theoretical model is constructed as follows:

[0191] In the overpressure simulation theoretical model, the overpressure propagation path is pre-set and characterized by node connection. At the same time, parameters such as the distance between nodes, the bifurcation angle between nodes, and the initial overpressure size are set.

[0192] For overpressure simulation, it is first necessary to characterize the explosion source location, such as Fig. 9 As shown, taking the bifurcated angle pipeline in this embodiment as an example, it is necessary to first take the end of the explosion tunnel as the source point, set the rightward propagation direction of the shock wave as the positive direction, and establish a one-dimensional coordinate system for the explosion tunnel. The coordinates of each monitoring point can be expressed as g i (i=1,2,3…n), assuming that the explosion source position coordinate is f0, the shock wave attenuation distance of each measuring point can be expressed by the coordinate x i =(g i ﹣f0)m, the overpressure currently monitored at each measuring point can be expressed as p i (i=1,2,3…n).

[0193] Then the attenuation equation of the shock wave with propagation distance can be expressed as formula (22):

[0194]

[0195] In formula (22), y is the volume of gas; L is the propagation distance; A is the cross-sectional area; ρ is the gas density; k is the adiabatic coefficient; E0 is the released energy. However, this formula fails to clearly characterize the explosion source position. Therefore, the shock wave attenuation distance expressed by the coordinates is substituted into formula (22) to obtain the shock wave attenuation theoretical mathematical model with the explosion source position coordinate parameters, which is expressed as formula (23):

[0196]

[0197] In formula (23), A is the cross-sectional area; ρ0 is the gas density; k is the adiabatic coefficient; and E0 is the released energy.

[0198] Table 4 shows the deduced values, confidence intervals, average absolute errors between the deduced values ​​and the true values, and the maximum absolute error and minimum absolute error results within the confidence interval obtained by using the optimized multilayer perceptron regression model (MLPRegressor) to deduce the 60° bifurcation pipeline explosion model of this embodiment.

[0199] Table 4. Optimized MLPRegressor model deduction model results

[0200]

[0201] From Table 4, we can see that the average absolute error of the deduced overpressure value is 0.106. The errors at other path points after point G2 are relatively large. Although they all fall within the confidence interval, the confidence interval deviates greatly from the true value. The main reason is that the model training set contains gas explosion experimental values ​​and simulation values ​​of bifurcated pipes with different inner diameters. In the gas explosion experiment, due to differences in pipe material, inner diameter, etc., the energy lost by the overpressure when passing through the bifurcation is also different, resulting in a large error in the deduction after passing through the bifurcation. In view of this, it is necessary to add the overpressure loss coefficient ξ when calculating the bifurcation node in the overpressure deduction theoretical model, ignore the influence of the experimental pipe material, and assume that ξ is a power function of the pipe inner diameter r, that is, ξ=r x , where x is a constant, and through Matlab fitting, x is -0.12, that is, ξ=r -0.12 .

[0202] The overpressure loss coefficient ξ is used to correct the overpressure at the bifurcation node of the model, and the following is obtained: Fig.10 The deduction visualization diagram of the modified model is shown in FIG. 5 , and the deduction results of the modified model are shown in Table 5 .

[0203] Table 5 Deduction results after correcting the model

[0204]

[0205]

[0206] From Table 5, it can be seen that the error between the deduced results of the revised model and the true value of the 60° bifurcation pipeline is relatively small, and the average absolute errors of the two groups of results of the true overpressure value and the deduced overpressure value are 0.054 respectively; the deduced value of each sample also falls well within the confidence interval estimated by the bootstrap algorithm (BootStrap), and the minimum average absolute error within the confidence interval is 0.02, and the maximum average absolute error within the confidence interval is 0.08 respectively. The small error within the interval proves that the revised model has better applicability in the 60° bifurcation pipeline.

[0207] Based on the optimized multi-layer perceptron regression model (MLPRegressor) gas explosion shock wave overpressure deduction model, the overpressure evolution process of the straight pipeline in Example 1 and the pipeline with a 60° angle bifurcation in Example 2 were deduced respectively, and the model deduction results were compared with the true values. It was found that compared with the true values, the mean absolute error, the maximum and minimum errors of the confidence interval of the deduction results were smaller, which proved the reliability of the calculation results of the proposed gas explosion shock wave overpressure deduction model.

[0208] The above are only a few embodiments of the present application and do not constitute any form of limitation to the present application. Although the present application is disclosed as above with preferred embodiments, it is not intended to limit the present application. Any technician familiar with the profession, without departing from the scope of the technical solution of the present application, using the technical content disclosed above to make slight changes or modifications are equivalent to equivalent implementation cases and fall within the scope of the technical solution.

Claims

1. A method for deducing the overpressure process of gas explosion shock wave based on optimized multi-layer perceptron, characterized in that: The following steps are involved: Step 1: Get the initial parameters and divide them into training set and test set; Step 2: Build a multilayer perceptron regression model based on the training set and the test set; Step 3: Optimize the learning rate and regularization factor of the initial parameters input to the multilayer perceptron regression model through the improved particle swarm algorithm to obtain the global optimal solution; Step 4: Use a self-help algorithm to output the results of the multilayer perceptron regression model to obtain the confidence interval of the deduced overpressure value; Step 5: Input the global optimal solution into the multi-layer perceptron regression model to perform overpressure deduction analysis within the obtained confidence interval.

2. The method for deducing the overpressure process of gas explosion shock wave based on optimized multi-layer perceptron according to claim 1 is characterized in that: In the multilayer perceptron regression model: The activation function is the tanh function; The error function uses the mean absolute error (MAE), and the error calculation is a back-to-forward back-propagation algorithm.

3. The method for deducing the overpressure process of gas explosion shock wave based on optimized multi-layer perceptron according to claim 2 is characterized in that: In the multilayer perceptron regression model, all nodes except the input node are neurons with a nonlinear activation function; The initial parameters include: explosion source location coordinates, tunnel parameters and explosion initial pressure.

4. The method for simulating the overpressure process of gas explosion shock wave based on optimized multi-layer perceptron according to claim 1 is characterized in that: The optimization process of the improved particle swarm algorithm for the learning rate and regularization factor of the initial parameters input to the multilayer perceptron regression model is: First, each particle is randomly initialized; Subsequently, each particle is evaluated and the global optimal particle is obtained; Finally, determine whether the iteration meets the end condition; If yes, then end; if no, continue to iterate until the end condition is met and the process ends; The value corresponding to when the end condition is met is the global optimal solution.

5. The method for simulating the overpressure process of gas explosion shock wave based on optimized multi-layer perceptron according to claim 4 is characterized in that: The iterative process includes the following steps: updating the speed and position of each particle, evaluating the function fitness value of each particle, updating the historical optimal position of each particle, and updating the global optimal position of the group.

6. The method for simulating the overpressure process of gas explosion shock wave based on optimized multi-layer perceptron according to claim 4 is characterized in that: The process of judging whether the iteration meets the end condition is: (1) Obtaining preprocessed standard data; (2) Import necessary libraries; (3) Define a multilayer perceptron regression model and specify the model's hyperparameters; (4) fitting the multilayer perceptron regression model using the training set to train the multilayer perceptron regression model; (5) Use the test dataset to evaluate the performance of the multilayer perceptron regression model to select the best hyperparameter combination; (6) Use the trained multi-layer perceptron regression model to predict new data to obtain prediction results; (7) Determine whether the performance of the model is ideal based on the prediction results. If the performance of the multilayer perceptron regression model is not ideal, improve the ideality of the multilayer perceptron regression model by adjusting hyperparameters, increasing the number of hidden layers or neurons, or trying different activation functions or optimizers; (8) It is judged that the performance of the multilayer perceptron regression model is ideal, that is, the iteration end condition is met.

7. The method for simulating the overpressure process of gas explosion shock wave based on optimized multi-layer perceptron according to claim 4 is characterized in that: The improvement process of the particle swarm algorithm is as follows: (1) Analyze the problem to be solved to determine whether there is a risk of premature convergence or falling into a local optimal solution; (2) Determine the goal of improving the inertia weight model based on the results of the problem analysis; (3) Use the adaptive inertia weight model to further improve the particle swarm algorithm; (4) Modify the particle swarm algorithm according to the selected improvement method; (5) Testing and verification: Use the modified particle swarm algorithm to solve a series of test problems and compare the test results with the original algorithm to test and verify the modified particle swarm algorithm; (6) Based on the test results, further adjust and optimize the parameters or strategies of the improved method in the adaptive inertia weight model to obtain the global optimal solution.

8. The method for simulating the overpressure process of gas explosion shock wave based on optimized multi-layer perceptron according to claim 7 is characterized in that: In the optimization of the adaptive inertia weight model, after the inertia factor ω is adaptively optimized, the inertia factor ω is associated with the number of iterations and the fitness of each particle: 1) Assuming that the problem of finding the minimum fitness value is solved, the fitness expression is formula (1): 2) Assuming the problem of finding the maximum fitness, the fitness expression is formula (2): In equations (1) and (2): min and ω max is the preset minimum inertia coefficient and maximum inertia coefficient, then the average fitness of all particles at the dth iteration is expressed as formula (3): The maximum fitness of all particles at the dth iteration It is expressed as formula (4):

9. The method for simulating the overpressure process of gas explosion shock wave based on optimized multi-layer perceptron according to claim 6 is characterized in that: The deduction and analysis steps are: The training is completed and the optimal parameters are obtained; Input optimal parameters for overpressure simulation analysis; At the same time, it is assumed that the deduced initial overpressure value is the maximum value during the explosion process; A bootstrap algorithm is used to obtain the confidence interval of the deduced overpressure value.

10. The method for simulating the overpressure process of gas explosion shock wave based on optimized multi-layer perceptron according to claim 9, characterized in that: The process of obtaining the confidence interval of the deduced overpressure value through the bootstrap algorithm is as follows: In the sampling process, the bootstrap algorithm ensures that the probability of each element in the sampling result being drawn is the same. N elements are drawn each time and repeated B times to obtain B groups of sample matrices containing N elements. The eigenvalues ​​of each group of samples are calculated to obtain the bootstrap sample probability eigenvalues. Suppose the original sample S is expressed as formula (5): S=(S1,S2,S3,…S i ,…,S n ) Formula (5); In formula (5): S i is the i-th data of the sample, S n It means there are n elements in total, and B elements are extracted from them, each time with N data. Finally, each extracted sample set P can be expressed as formula (6): P=(P1,P2,P3,…P b ,…,P b ) Formula (6); In formula (6): P b is the b-th self-service sample set, expressed as formula (7): P b = P b (i), where i = 1, 2, …, N, Equation (7); In formula (7): P b (i) is represented by P b The i-th element of , so the bootstrap sample set P b The mean P b The calculation formula is expressed as formula (8): The bootstrap sample mean is It can be expressed as formula (9): Bootstrap sample variance σ 2 It is expressed as formula (10): In machine learning, the bootstrap algorithm is used to solve the confidence interval. By estimating the sample eigenvalues, different confidence intervals are obtained. Assuming that the bootstrap algorithm is used to obtain the sample parameter estimate, the sample parameter θ is expressed as formula (11): Arrange them from small to large, and we get formula (12): Assuming the significance level is α, α∈[0,1], the confidence level is expressed as formula (13): Let K1 and K2 represent the upper confidence limit and lower confidence limit respectively, as shown in formula (14): and is the quantile and The estimation of can be obtained as formula (15): The final confidence interval is expressed as formula (16):

Images