Mass flow detection model training and liquid-solid two-phase flow mass flow detection method

Abstract

The invention discloses a mass flow detection model training and liquid-solid two-phase flow mass flow detection method, which is applied to the field of liquid-solid two-phase flow mass flow detection, and comprises the following steps: obtaining a liquid-solid two-phase flow measurement signal set with a mass flow label; constructing a mass flow detection model; and training a mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model. Based on a deep learning method, the mass flow detection model is trained through the liquid-solid two-phase flow measurement signals under each mass flow, the mass flow of the liquid-solid two-phase flow is measured through the trained mass flow detection model, and due to the fact that the liquid-solid two-phase flow measurement signals are sensitive to the weak change of the mass flow, the mass flow of the liquid-solid two-phase flow is measured. Compared with the prior art, the method has the advantage that the accuracy of measuring the mass flow rate of the liquid-solid two-phase flow is improved.

Description

Technical Field

[0001] The present invention relates to the field of liquid-solid two-phase flow mass flow detection, and in particular to a mass flow detection model training method, a liquid-solid two-phase flow mass flow detection method, a device, an electronic device and a computer-readable storage medium. Background Art

[0002] Liquid-solid two-phase flow is one of the most representative flow forms in multiphase flow, and is commonly found in industrial production in many industries such as chemical industry, metallurgy, and power generation. The transportation of materials such as ore mud is a typical application of liquid-solid two-phase flow, especially for mass flow measurement in cement slurry. If the mass flow rate of liquid-solid two-phase flow suddenly decreases during the production process, the particle flow will be unstable, especially for modified pneumatic transportation; if the mass flow rate suddenly increases, more energy will be consumed, which will cause serious pipeline wear and particle breakage. In addition, since the shape and distribution of the phase interface are randomly variable in time and space, the flow pattern of liquid-solid two-phase flow is complex and diverse, and the complexity and variability of the flow pattern brings great difficulties to the accurate measurement of the mass flow rate of liquid-solid two-phase flow.

[0003] The existing technology generally uses instruments to measure the mass flow rate of liquid-solid two-phase flow. It is difficult to capture subtle changes in the mass flow rate of liquid-solid two-phase flow through instrument measurement, and the error is large and the measurement accuracy is low. Summary of the invention

[0004] The purpose of the present invention is to provide a mass flow detection model training method, a liquid-solid two-phase flow mass flow detection method and related devices, which are applied to the field of liquid-solid two-phase flow mass flow detection. The method is based on a deep learning method, and the mass flow detection model is trained by the liquid-solid two-phase flow measurement signal under each mass flow rate. The mass flow rate of the liquid-solid two-phase flow is measured by the trained mass flow detection model. Since the liquid-solid two-phase flow measurement signal is more sensitive to the slight change of the mass flow rate, compared with the prior art, the method of the present invention improves the accuracy of the measured liquid-solid two-phase flow mass flow rate.

[0005] In order to solve the above technical problems, the present invention provides a mass flow detection model training method, comprising:

[0006] Obtain a liquid-solid two-phase flow measurement signal set with a mass flow label;

[0007] Construct a mass flow detection model;

[0008] Training the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model;

[0009] The mass flow detection model includes a first feature extraction layer, a feature fusion layer, a second feature extraction layer and a fully connected layer connected in sequence;

[0010] The first feature extraction layer is used to extract multiple signal features of different scales of the liquid-solid two-phase flow signal; the first feature extraction layer includes multiple feature extraction branches, each of the feature extraction branches includes multiple convolutional layers connected in sequence, an expansion convolution layer and a global average pooling layer, and the expansion convolution coefficient of each expansion convolution layer is different;

[0011] The feature fusion layer is used to fuse the multiple signal features to obtain a fusion feature;

[0012] The second feature extraction layer is used to extract the fused features to obtain target features; the second feature extraction layer includes a plurality of convolutional layers and a global average pooling layer connected in sequence;

[0013] The fully connected layer is used to output a mass flow prediction value based on the target feature; the activation function of the fully connected layer is a first sigmoid function.

[0014] Optionally, the feature fusion layer is used to input the multiple signal features into a second sigmoid function to calculate corresponding feature weights; and to perform feature fusion based on the multiple signal features and the corresponding feature weights to obtain the fused feature.

[0015] Optionally, the training of the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model includes:

[0016] Inputting the liquid-solid two-phase flow measurement signal in the liquid-solid two-phase flow measurement signal set into the mass flow detection model to obtain the mass flow prediction value;

[0017] Calculating focus loss based on the mass flow label and the mass flow prediction value;

[0018] adjusting a model parameter of the mass flow detection model based on the focus loss;

[0019] The focus loss is recalculated and the model parameters are adjusted based on the focus loss until the model parameters converge to obtain a target mass flow detection model.

[0020] Optionally, the training of the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model includes:

[0021] The mass flow detection model is trained based on the liquid-solid two-phase flow measurement signal set to obtain the target mass flow detection model, and during the training process, the accuracy of the target mass flow model is verified based on a ten-fold cross validation method.

[0022] Optionally, the first feature extraction layer includes three feature extraction branches, each of the feature extraction branches includes a first convolution layer with a convolution kernel size of 16, a second convolution layer with a convolution kernel size of 32, an expanded convolution layer and a global average pooling layer, which are connected in sequence, and the expanded convolution coefficients of the three expanded convolution layers are 1, 2 and 5, respectively.

[0023] Optionally, the second feature extraction layer includes a third convolution layer with a convolution kernel size of 32, a fourth convolution layer with a convolution kernel size of 64, and a global average pooling layer, which are connected in sequence.

[0024] In order to solve the above technical problems, the present invention provides a liquid-solid two-phase flow mass flow detection method, comprising:

[0025] Acquire a liquid-solid two-phase flow measurement signal to be detected;

[0026] Inputting the liquid-solid two-phase flow measurement signal to be detected into a target mass flow detection model to obtain a mass flow prediction value;

[0027] Wherein, the target mass flow detection model is a model trained according to any one of the mass flow detection model training methods.

[0028] In order to solve the above technical problems, the present invention provides a mass flow detection model training device, comprising:

[0029] The first module is used to obtain a liquid-solid two-phase flow measurement signal set with a mass flow label;

[0030] The second module is used to build a mass flow detection model;

[0031] A third module is used to train the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model;

[0032] The mass flow detection model includes a first feature extraction layer, a feature fusion layer, a second feature extraction layer and a fully connected layer connected in sequence;

[0033] The first feature extraction layer is used to extract multiple signal features of different scales of the liquid-solid two-phase flow signal; the first feature extraction layer includes multiple feature extraction branches, each of the feature extraction branches includes multiple convolutional layers connected in sequence, an expansion convolution layer and a global average pooling layer, and the expansion convolution coefficient of each expansion convolution layer is different;

[0034] The feature fusion layer is used to fuse the multiple signal features to obtain a fusion feature;

[0035] The second feature extraction layer is used to extract the fused features to obtain target features; the second feature extraction layer includes a plurality of convolutional layers and a global average pooling layer connected in sequence;

[0036] The fully connected layer is used to output a mass flow prediction value based on the target feature; the activation function of the fully connected layer is a first sigmoid function.

[0037] In order to solve the above technical problems, the present invention provides an electronic device, comprising:

[0038] Memory, for storing computer programs;

[0039] A processor is used to implement any one of the mass flow detection model training methods and / or the liquid-solid two-phase flow mass flow detection methods when executing the computer program.

[0040] In order to solve the above technical problems, the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, any one of the mass flow detection model training methods and / or the liquid-solid two-phase flow mass flow detection method is implemented.

[0041] It can be seen that the method of the present invention obtains a liquid-solid two-phase flow measurement signal set with a mass flow label; constructs a mass flow detection model; trains the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model; based on a deep learning method, the present invention trains the mass flow detection model through liquid-solid two-phase flow measurement signals at various mass flow rates, and measures the liquid-solid two-phase flow mass flow rate through the trained mass flow detection model. Since the liquid-solid two-phase flow measurement signal is more sensitive to slight changes in the mass flow rate, compared with the prior art, the method of the present invention improves the accuracy of the measured liquid-solid two-phase flow mass flow rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0043] Figure 1 A flow chart of a mass flow detection model training method provided by an embodiment of the present invention;

[0044] Figure 2 A flow chart of a liquid-solid two-phase flow mass flow detection method provided by an embodiment of the present invention;

[0045] Figure 3 A structural schematic diagram of a mass flow detection model provided by an embodiment of the present invention;

[0046] Figure 4 This is a structural block diagram of a mass flow detection model training device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] The following combination Figure 1 , Figure 1 A flow chart of a mass flow detection model training method provided by an embodiment of the present invention, the method may include:

[0049] S101: Acquire a liquid-solid two-phase flow measurement signal set with a mass flow label.

[0050] This embodiment can obtain a liquid-solid two-phase flow measurement signal set with a mass flow label, and the liquid-solid two-phase flow measurement signal set includes liquid-solid two-phase flow measurement signals at each mass flow rate. This embodiment does not limit the method of obtaining the liquid-solid two-phase flow measurement signal, which can be a voltage signal read from a sensor. The liquid-solid two-phase flow measurement signal set in this embodiment can be used as a data set for training a mass flow detection model.

[0051] S102: Construct a mass flow detection model.

[0052] This embodiment can construct a mass flow detection model. The mass flow detection model in this embodiment can include a first feature extraction layer, a feature fusion layer, a second feature extraction layer and a fully connected layer connected in sequence.

[0053] The first feature extraction layer in this embodiment is used to extract multiple signal features of different scales of liquid-solid two-phase flow signals. The first feature extraction layer may include multiple feature extraction branches, each feature extraction branch includes multiple convolutional layers connected in sequence, an expanded convolution layer and a global average pooling layer, and in this embodiment, the expanded convolution coefficient of the expanded convolution layer of each feature extraction branch is not the same.

[0054] In this embodiment, in order to reduce the waste of computing resources while ensuring the accuracy of the model, the first feature extraction layer of this embodiment may include three feature extraction branches, namely, a first feature extraction branch, a second feature extraction branch and a third extraction branch, each feature extraction branch includes a first convolution layer with a convolution kernel size of 16, a second convolution layer with a convolution kernel size of 32, an expanded convolution layer and a global average pooling layer connected in sequence, and in this embodiment, the expanded convolution coefficient of the expanded convolution layer in the first feature extraction branch can be 1, the expanded convolution coefficient of the expanded convolution layer in the second feature extraction branch can be 2, and the expanded convolution coefficient of the expanded convolution layer in the third feature extraction branch can be 5.

[0055] The feature fusion layer of this embodiment is used to fuse multiple signal features to obtain a fused feature. This embodiment does not limit the specific fusion method. Generally, in the feature fusion layer, multiple signal features can be input into the second sigmoid function to calculate the feature weight corresponding to each signal feature, and the signal feature is multiplied by the corresponding feature weight to obtain the feature to be fused, and the features to be fused are further multiplied to obtain the fused feature.

[0056] The second feature extraction layer in this embodiment is used to further extract features from the fused features to obtain target features. The second feature extraction layer in this embodiment may include multiple convolutional layers connected in sequence and a global average pooling layer. Generally, it may include a third convolutional layer with a convolution kernel size of 32, a fourth convolutional layer with a convolution kernel size of 64, and a global average pooling layer connected in sequence.

[0057] The fully connected layer in this embodiment is used to output a mass flow prediction value based on the target feature. The target feature is input into the fully connected layer to obtain the output mass flow prediction value. The activation function of the fully connected layer in this embodiment is the first sigmoid function.

[0058] S103: Training a mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model.

[0059] After the mass flow detection model is constructed, the liquid-solid two-phase flow measurement signal set can be used as a data set to train the model. The present embodiment does not limit the specific training method. Generally, the liquid-solid two-phase flow measurement signal in the liquid-solid two-phase flow measurement signal set can be input into the mass flow detection model to obtain the mass flow prediction value; the focus loss is calculated based on the mass flow label and the mass flow prediction value, and the model parameters of the mass flow detection model are adjusted based on the focus loss. When the model parameters have not converged, the mass flow detection model can be iteratively trained based on the liquid-solid two-phase flow measurement signal set, the focus loss is recalculated, and the model parameters are adjusted based on the focus loss until the model parameters converge. The mass flow detection model after training is determined as the target mass flow detection model. Furthermore, after the model training is completed, in order to verify the accuracy of the model, the present embodiment can use the ten-fold cross validation method to verify the accuracy of the model.

[0060] This embodiment is based on a deep learning method. The mass flow detection model is trained by the liquid-solid two-phase flow measurement signal at each mass flow rate. The mass flow rate of the liquid-solid two-phase flow is measured by the trained mass flow detection model. Compared with the prior art, the method of the present invention improves the accuracy of the measured mass flow rate of the liquid-solid two-phase flow.

[0061] The following combination Figure 2 , Figure 2 A flow chart of a liquid-solid two-phase flow mass flow detection method provided in an embodiment of the present invention, the method may include:

[0062] S201: Acquire a liquid-solid two-phase flow measurement signal to be detected.

[0063] S202: Inputting the liquid-solid two-phase flow measurement signal to be detected into the target mass flow detection model to obtain a mass flow prediction value.

[0064] The target mass flow detection model is a model trained according to any mass flow detection model training method.

[0065] After the target detection model is trained according to any of the mass flow detection model training methods, this embodiment can obtain the liquid-solid two-phase flow measurement signal to be detected, and input the liquid-solid two-phase flow measurement signal into the target mass flow detection model to obtain the mass flow prediction value. Compared with using instruments for measurement, the accuracy is higher and the problem of instrument cleaning is avoided.

[0066] The following is a specific embodiment of a liquid-solid two-phase flow mass flow measurement method provided by an embodiment of the present invention. The structural schematic diagram of the mass flow detection model constructed by the specific implementation can be as follows: Figure 3As shown, the first feature extraction layer includes three feature extraction branches, each feature extraction branch includes a convolution layer with a convolution kernel size of 16, a convolution layer with a convolution kernel size of 32, a dilated convolution layer and a global average pooling layer connected in sequence, and the dilated convolution coefficients of the dilated convolution layer are 1, 2 and 5 respectively, the second feature extraction layer includes a convolution layer with a convolution kernel size of 32, a convolution layer with a convolution kernel size of 64 and a global average pooling layer connected in sequence, and the activation function of the fully connected layer is a sigmoid function. The specific embodiment can be:

[0067] Obtain a liquid-solid two-phase flow measurement signal set with a mass flow label;

[0068] Inputting the liquid-solid two-phase flow measurement signal set into three feature extraction branches of the first feature extraction layer to obtain three signal features;

[0069] In the feature fusion layer, the three signal features can be input into the sigmoid function to calculate the corresponding feature weights;

[0070] Multiply the signal feature with the corresponding feature weight to obtain the feature to be fused, and multiply each feature to be fused to obtain the fused feature;

[0071] The fused features are passed through the second feature extraction layer to obtain the target features, and the target features are input into the fully connected layer to obtain the mass flow prediction value corresponding to the liquid-solid two-phase flow measurement signal;

[0072] Calculating a focus loss based on the mass flow label and the mass flow prediction value, and adjusting a model parameter of a mass flow detection model based on the focus loss;

[0073] When the model parameters have not converged, the mass flow detection model is iteratively trained based on the liquid-solid two-phase flow measurement signal set, the focus loss is recalculated, and the model parameters are adjusted based on the focus loss until the model parameters converge;

[0074] The trained mass flow detection model is determined as a target mass flow detection model;

[0075] The liquid-solid two-phase flow measurement signal to be detected is input into the target mass flow detection model to obtain the mass flow prediction value.

[0076] The following combination Figure 4 , Figure 4 A structural block diagram of a mass flow detection model training device provided by an embodiment of the present invention, the device may include:

[0077] The first module 100 is used to obtain a liquid-solid two-phase flow measurement signal set with a mass flow label;

[0078] The second module 200 is used to construct a mass flow detection model;

[0079] The third module 300 is used to train the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model;

[0080] Wherein, the target mass flow detection model comprises a first feature extraction layer, a feature fusion layer, a second feature extraction layer and a fully connected layer connected in sequence;

[0081] The first feature extraction layer is used to extract multiple signal features of different scales of the liquid-solid two-phase flow signal; the first feature extraction layer includes multiple feature extraction branches, each of the feature extraction branches includes multiple convolutional layers connected in sequence, an expansion convolution layer and a global average pooling layer, and the expansion convolution coefficient of each expansion convolution layer is different;

[0082] The feature fusion layer is used to fuse the multiple signal features to obtain a fusion feature;

[0083] The second feature extraction layer is used to extract the fused features to obtain target features; the second feature extraction layer includes a plurality of convolutional layers and a global average pooling layer connected in sequence;

[0084] The fully connected layer is used to output a mass flow prediction value based on the target feature; the activation function of the fully connected layer is a first sigmoid function.

[0085] Based on the above embodiments, the present invention is based on a deep learning method, and a mass flow detection model is trained by using the liquid-solid two-phase flow measurement signal at each mass flow rate. The mass flow rate of the liquid-solid two-phase flow is measured by using the trained mass flow detection model. Compared with the prior art, the accuracy of the measured liquid-solid two-phase flow mass flow rate is improved.

[0086] Based on the above embodiment, the feature fusion layer is used to input the multiple signal features into the second sigmoid function to calculate the corresponding feature weights; and perform feature fusion based on the multiple signal features and the corresponding feature weights to obtain the fused feature.

[0087] Based on the above embodiments, the third module 300 may include:

[0088] The first unit is used to input the liquid-solid two-phase flow measurement signal in the liquid-solid two-phase flow measurement signal set into the mass flow detection model to obtain the mass flow prediction value;

[0089] A second unit is used to calculate the focus loss based on the mass flow label and the mass flow prediction value;

[0090] A third unit, configured to adjust a model parameter of the mass flow detection model based on the focus loss;

[0091] The fourth unit is used to recalculate the focus loss and adjust the model parameters based on the focus loss until the model parameters converge to obtain a target mass flow detection model.

[0092] Based on the above embodiments, the third module 300 may include:

[0093] The fifth unit is used to train the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain the target mass flow detection model, and verify the accuracy of the target mass flow model based on the ten-fold cross validation method during the training process.

[0094] Based on the above embodiments, the first feature extraction layer includes three feature extraction branches, each of the feature extraction branches includes a first convolution layer with a convolution kernel size of 16, a second convolution layer with a convolution kernel size of 32, an expanded convolution layer and a global average pooling layer connected in sequence, and the expanded convolution coefficients of the three expanded convolution layers are 1, 2 and 5, respectively.

[0095] Based on the above embodiments, the second feature extraction layer includes a third convolution layer with a convolution kernel size of 32, a fourth convolution layer with a convolution kernel size of 64, and a global average pooling layer, which are connected in sequence.

[0096] The following is a liquid-solid two-phase flow mass flow measurement device provided by an embodiment of the present invention, which may include:

[0097] The fourth module is used to obtain the measurement signal of the liquid-solid two-phase flow to be detected;

[0098] A fifth module is used to input the liquid-solid two-phase flow measurement signal to be detected into a target mass flow detection model to obtain a mass flow prediction value;

[0099] Wherein, the target mass flow detection model is a model trained by any of the mass flow detection model training devices.

[0100] Based on the above embodiments, the present invention further provides an electronic device, which may include a memory and a processor, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, the steps provided in the above embodiments may be implemented. Of course, the device may also include various necessary network interfaces, power supplies, and other components.

[0101] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by an execution terminal or a processor, the method provided in the embodiment of the present invention can be implemented; the storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0102] In this article, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

Claims

1. A mass flow detection model training method, characterized in that: include: Obtain a liquid-solid two-phase flow measurement signal set with a mass flow label; Construct a mass flow detection model; Training the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model; The mass flow detection model includes a first feature extraction layer, a feature fusion layer, a second feature extraction layer and a fully connected layer connected in sequence; The first feature extraction layer is used to extract multiple signal features of different scales of the liquid-solid two-phase flow signal; the first feature extraction layer includes multiple feature extraction branches, each of the feature extraction branches includes multiple convolutional layers connected in sequence, an expansion convolution layer and a global average pooling layer, and the expansion convolution coefficient of each expansion convolution layer is different; The feature fusion layer is used to fuse the multiple signal features to obtain a fusion feature; The second feature extraction layer is used to extract the fused features to obtain target features; the second feature extraction layer includes a plurality of convolutional layers and a global average pooling layer connected in sequence; The fully connected layer is used to output a mass flow prediction value based on the target feature; the activation function of the fully connected layer is a first sigmoid function.

2. The mass flow detection model training method according to claim 1, characterized in that: The feature fusion layer is used to input the multiple signal features into the second sigmoid function to calculate the corresponding feature weights; and perform feature fusion based on the multiple signal features and the corresponding feature weights to obtain the fused feature.

3. The mass flow detection model training method according to claim 1 is characterized in that: The step of training the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model includes: Inputting the liquid-solid two-phase flow measurement signal in the liquid-solid two-phase flow measurement signal set into the mass flow detection model to obtain the mass flow prediction value; Calculating focus loss based on the mass flow label and the mass flow prediction value; adjusting a model parameter of the mass flow detection model based on the focus loss; The focus loss is recalculated and the model parameters are adjusted based on the focus loss until the model parameters converge to obtain a target mass flow detection model.

4. The mass flow detection model training method according to claim 1 is characterized in that: The step of training the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model includes: The mass flow detection model is trained based on the liquid-solid two-phase flow measurement signal set to obtain the target mass flow detection model, and during the training process, the accuracy of the target mass flow model is verified based on a ten-fold cross validation method.

5. The mass flow detection model training method according to claim 1, characterized in that: The first feature extraction layer includes three feature extraction branches, each of which includes a first convolution layer with a convolution kernel size of 16, a second convolution layer with a convolution kernel size of 32, an expanded convolution layer and a global average pooling layer connected in sequence, and the expanded convolution coefficients of the three expanded convolution layers are 1, 2 and 5, respectively.

6. The mass flow detection model training method according to claim 5 is characterized in that: The second feature extraction layer includes a third convolution layer with a convolution kernel size of 32, a fourth convolution layer with a convolution kernel size of 64, and a global average pooling layer, which are connected in sequence.

7. A liquid-solid two-phase flow mass flow detection method, characterized in that: include: Acquire a liquid-solid two-phase flow measurement signal to be detected; Inputting the liquid-solid two-phase flow measurement signal to be detected into a target mass flow detection model to obtain a mass flow prediction value; Wherein, the target mass flow detection model is a model trained according to the mass flow detection model training method according to any one of claims 1 to 6.

8. A mass flow detection model training device, characterized in that: include: The first module is used to obtain a liquid-solid two-phase flow measurement signal set with a mass flow label; The second module is used to build a mass flow detection model; A third module is used to train the mass flow detection model based on the liquid-solid two-phase flow measurement signal set to obtain a target mass flow detection model; Wherein, the target mass flow detection model comprises a first feature extraction layer, a feature fusion layer, a second feature extraction layer and a fully connected layer connected in sequence; The first feature extraction layer is used to extract multiple signal features of different scales of the liquid-solid two-phase flow signal; the first feature extraction layer includes multiple feature extraction branches, each of the feature extraction branches includes multiple convolutional layers connected in sequence, an expansion convolution layer and a global average pooling layer, and the expansion convolution coefficient of each expansion convolution layer is different; The feature fusion layer is used to fuse the multiple signal features to obtain a fusion feature; The second feature extraction layer is used to extract the fused features to obtain target features; the second feature extraction layer includes a plurality of convolutional layers and a global average pooling layer connected in sequence; The fully connected layer is used to output a mass flow prediction value based on the target feature; the activation function of the fully connected layer is a first sigmoid function.

9. An electronic device, characterized in that: include: Memory, for storing computer programs; A processor, used to implement the mass flow detection model training method as described in any one of claims 1 to 6 and / or the liquid-solid two-phase flow mass flow detection method as described in claim 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by the processor, the mass flow detection model training method according to any one of claims 1 to 6 and / or the liquid-solid two-phase flow mass flow detection method according to claim 7 are implemented.

Images