A method and system for predicting quality indicators of a catalytic cracking process

Abstract

The application provides a catalytic cracking process quality index prediction method and system, and the method comprises the following steps: obtaining actual production data of a catalytic cracking process in a preset time, pre-processing and selecting features of the data, constructing an input data set of a convolutional neural network for prediction, and confirming a prediction index; inputting the data set into a pre-established convolutional neural network, firstly extracting input feature information by using one-dimensional convolution, retaining the feature information most related to the prediction value in the convolution layer by using a maximum pooling technology, taking a bidirectional gated recurrent unit as a basic unit, processing the output information of the pooling layer in a time forward and backward direction, capturing the time dependence between the features, and selecting the key information extracted from the convolution layer and the pooling layer by using an attention layer, and then inputting the key information into a full connection layer to obtain a prediction value. Based on the method, a catalytic cracking process quality index prediction system is further provided. The application greatly improves the prediction accuracy of the catalytic cracking process quality index.

Description

Technical Field

[0001] The present invention belongs to the technical field of petrochemical industry, and in particular relates to a method and system for predicting quality indicators of a catalytic cracking process. Background Art

[0002] Catalytic cracking is one of the most commonly used technologies in the petrochemical and refining industries. It primarily controls the reaction process by adjusting factors such as reaction temperature, reaction pressure, catalyst type, and catalyst loading to convert heavy petroleum fractions into lighter fractions, such as gasoline and liquefied petroleum gas. To achieve green production, energy conservation and consumption reduction, and improve enterprise profitability, timely monitoring and control of catalytic cracking process performance is crucial. Soft sensing is a common method in this field. It uses mathematical models and easily measurable auxiliary variables to estimate key quality variables, thereby assisting process monitoring. It offers advantages such as fast response, high prediction accuracy, and low cost.

[0003] Soft sensing methods are primarily categorized into mechanistic models and data-driven models. Mechanistic models are based on an understanding and description of the physical and chemical principles of the process being modeled. They predict process behavior and performance by modeling and simulating the process. They enable in-depth analysis and understanding of the process's internal mechanisms, providing quantitative physical and chemical parameters and exhibiting high interpretability and reliability. However, mechanistic models require a deep understanding of the physical and chemical principles of the process being modeled, leading to complex modeling processes. Furthermore, for complex systems, mechanistic models can be difficult to solve and exhibit low model accuracy. Data-driven models, on the other hand, are based on statistical learning theory and machine learning algorithms, predicting process behavior and performance by learning and fitting existing data. They offer greater flexibility, enabling process modeling and prediction without requiring a deep understanding of the physical and chemical principles underlying the process being modeled. Examples include principal component regression (PCR), partial least squares regression (PLSR), and support vector machines (SVR). Over the past few years, many successful applications of soft sensing have been proposed in chemical engineering, biochemical engineering, metallurgy, and pharmaceuticals. However, with the continuous development of industrial technology, the data generated during system control processes has the following characteristics: large data volume, multiple data sources, and high data dimensionality. This makes traditional data-driven methods unable to make more accurate predictions due to their limited representation learning capabilities. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention proposes a method and system for predicting quality indicators of a catalytic cracking process, which improves the prediction accuracy of quality indicators of a catalytic cracking process.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for predicting quality indicators of a catalytic cracking process comprises the following steps:

[0007] Acquiring actual production data of the catalytic cracking process for a preset time, constructing a convolutional neural network input data set for prediction after preprocessing and feature selection of the actual production data, and confirming prediction indicators;

[0008] The dataset is input into a pre-established convolutional neural network. First, one-dimensional convolution is used to extract input feature information. The maximum pooling technique is used to retain the feature information in the convolution layer that is most relevant to the predicted value. The bidirectional gated recurrent unit is used as the basic unit to process the output information of the pooling layer in the forward and backward directions of time to capture the temporal dependency between features. The attention layer is used to selectively focus on the key information extracted by the convolution layer and the pooling layer, which is then handed over to the fully connected layer to fit the predicted value.

[0009] Furthermore, the actual production data of the catalytic cracking process includes: the mass flow rate of each raw oil input in the catalytic cracking process, the pressure and temperature at different positions of each device during the reaction process, and the content of components in the mixed raw materials.

[0010] Furthermore, the process of constructing a convolutional neural network input data set for prediction after preprocessing and feature selection of the actual production data includes:

[0011] Detect missing values ​​and outliers in the data, eliminate data that does not meet the error threshold, and use linear interpolation to supplement the data of the eliminated outlier points;

[0012] A preset proportion of feature variables is randomly selected to build a subtree, which is then summed and averaged according to feature importance and sorted in descending order. Finally, the process variables are retained as the input data set of the convolutional neural network for prediction.

[0013] Furthermore, the prediction indicators include gasoline, diesel, liquefied gas, dry gas and oil slurry yields.

[0014] Furthermore, the method further includes: using a random forest algorithm to calculate the importance of each feature prediction indicator, and the calculation formula is:

[0015]

[0016] Where N is the total number of subtrees generated; err 1i is the characteristic error of the current subtree without adding random noise; err 2i The characteristic error of adding random noise to the current subtree; i is the sequence number of the current subtree;

[0017] Based on the importance of each feature prediction indicator, the corresponding proportion of features is eliminated, and then the feature set with the lowest error rate is selected as the convolutional neural network input data set for prediction.

[0018] Furthermore, the method also includes performing data denoising on the data set using wavelet transform, and inputting the denoised data set into a pre-established convolutional neural network.

[0019] Furthermore, the bidirectional gated recurrent unit is composed of an update gate and a reset gate, which is specifically expressed as follows:

[0020] z t =σ(W z [x t ,h t-1 ]);

[0021] r t =σ(W r [x t ,h t-1 ]);

[0022]

[0023]

[0024] Among them, x t is the current input; z t is the update gate, r t is the reset gate; h t-1 is the hidden layer state before the current time direction; h t is the output of the hidden layer before the current time direction; is the current candidate state; W Z is the weight coefficient of the update gate; W r is the weight coefficient of the reset gate; W is the weight coefficient of the current candidate state; σ is the sigmoid function.

[0025] Furthermore, the bidirectional gated recurrent unit is divided into two layers, and the temporal dependency of features is extracted in two different directions in the chronological order, and finally two sets of hidden variables are obtained, which are calculated and expressed as:

[0026]

[0027]

[0028]

[0029] in, Output hidden variables for the backward layer; Output hidden variables for the forward layer.

[0030] Furthermore, the attention layer is expressed as:

[0031] e t =V Ttanh(W e h t +b e );

[0032]

[0033]

[0034] Among them, V is the first weight parameter, W e is the second weight parameter, b e is the third weight parameter, e t is the probability distribution value of the attention mechanism at time t; a t is the weight of the attention mechanism corresponding to the hidden variable output by the bidirectional gated recurrent unit at time t; t is the output value of the attention mechanism at time t.

[0035] The present invention also proposes a catalytic cracking process quality index prediction system, which includes a pretreatment module and a prediction module;

[0036] The preprocessing module is used to obtain actual production data of the catalytic cracking process at a preset time, construct a convolutional neural network input data set for prediction after preprocessing and feature selection of the actual production data, and confirm the prediction index;

[0037] The prediction module is used to input the data set into a pre-established convolutional neural network. First, one-dimensional convolution is used to extract input feature information, and the maximum pooling technology is used to retain the feature information in the convolution layer that is most relevant to the predicted value. The bidirectional gated recurrent unit is used as the basic unit to process the output information of the pooling layer in the forward and backward directions of time to capture the temporal dependency between features. The attention layer is used to selectively focus on the key information extracted by the convolution layer and the pooling layer, which is then handed over to the fully connected layer to fit the predicted value.

[0038] The effects provided in the summary of the invention are only the effects of the embodiments, not all the effects of the invention. One of the above technical solutions has the following advantages or beneficial effects:

[0039] The present invention proposes a method and system for predicting quality indicators of a catalytic cracking process. The method comprises the following steps: obtaining actual production data from a catalytic cracking process at a preset time; constructing a convolutional neural network input dataset for prediction after preprocessing and feature selection of the actual production data; and determining the predicted indicators. The dataset is then input into a pre-established convolutional neural network. First, one-dimensional convolution is used to extract input feature information. Maximum pooling is employed to retain the features in the convolutional layer that are most relevant to the predicted value. Using a bidirectional gated recurrent unit as the basic unit, the output of the pooling layer is processed in both the forward and backward directions to capture the temporal dependencies between features. An attention layer is then employed to selectively focus on the key information extracted by the convolutional and pooling layers, which is then passed to a fully connected layer for fitting to obtain the predicted value. Based on the method for predicting quality indicators of a catalytic cracking process, a system for predicting quality indicators of a catalytic cracking process is also proposed. The proposed prediction method is simple, fast, and practical. Compared with traditional measurement methods, it significantly shortens detection time and reduces waste of manpower and material resources. Due to the nonlinearity and high coupling of process variables, which results in significant loss of data feature information and poor model fitting, the proposed method significantly improves the model's prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a method for predicting quality indicators of a catalytic cracking process proposed in Example 1 of the present invention;

[0041] Figure 2 This is the catalytic cracking process proposed in Example 1 of the present invention;

[0042] Figure 3 The basic structure of the CNN-BIGRU-ATTENTION model proposed in Example 1 of the present invention;

[0043] Figure 4 The gasoline yield prediction results of the three different methods proposed in Example 1 of the present invention are shown below:

[0044] Figure 5 The prediction errors of gasoline yield by three different methods proposed in Example 1 of the present invention are:

[0045] Figure 6 This is the diesel yield prediction result proposed in Example 1 of the present invention;

[0046] Figure 7 The diesel yield prediction performance proposed in Example 1 of the present invention;

[0047] Figure 8 This is the liquefied gas yield prediction result proposed in Example 1 of the present invention;

[0048] Figure 9 This is the liquefied gas yield prediction performance proposed in Example 1 of the present invention;

[0049] Figure 10 This is the dry gas yield prediction result proposed in Example 1 of the present invention;

[0050] Figure 11 The dry gas yield prediction performance proposed in Example 1 of the present invention;

[0051] Figure 12 This is the prediction result of the slurry yield proposed in Example 1 of the present invention;

[0052] Figure 13 This is the oil slurry yield prediction performance proposed in Example 1 of the present invention;

[0053] Figure 14 This is a schematic diagram of a catalytic cracking process quality index prediction system proposed in Example 2 of the present invention. DETAILED DESCRIPTION

[0054] In order to clearly illustrate the technical features of this solution, the present invention is described in detail below through specific implementation methods and in conjunction with the accompanying drawings. The disclosure below provides many different embodiments or examples for realizing different structures of the present invention. In order to simplify the disclosure of the present invention, the components and settings of specific examples are described below. In addition, the present invention may repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplicity and clarity and does not itself indicate the relationship between the various embodiments and / or settings discussed. It should be noted that the components illustrated in the accompanying drawings are not necessarily drawn to scale. The present invention omits descriptions of well-known components and processing technologies and processes to avoid unnecessary limitations on the present invention.

[0055] Example 1

[0056] The method for predicting quality indicators of a catalytic cracking process proposed in Example 1 of the present invention can more effectively extract industrial process data features, reduce model loss, and improve prediction accuracy.

[0057] Figure 1 This is a flow chart of a method for predicting quality indicators of a catalytic cracking process proposed in Example 1 of the present invention;

[0058] In step S100, actual production data of the catalytic cracking process for a preset time is obtained, and a convolutional neural network input data set for prediction is constructed after preprocessing and feature selection of the actual production data, and prediction indicators are confirmed;

[0059] Figure 2This is the catalytic cracking workflow proposed in Example 1 of the present invention; the catalytic cracking process is one of the important means of lightening heavy oil in the petroleum refining industry, and its products are mainly catalytic gasoline with low olefin content, propylene-rich liquefied gas, catalytic diesel and a small part of oil slurry. It mainly includes a reaction-regeneration system, a fractionation system, and an absorption and stabilization system. Reaction-regeneration system: In the reactor, the raw material contacts the catalyst and a cracking reaction occurs to produce hydrocarbons with smaller molecular weight. The products after the reaction include light oil, heavy oil and catalyst. In the regenerator, the used catalyst is first baked to remove the gas adsorbed on the catalyst, and then the activity of the catalyst is regenerated by hydrogenation reaction. Fractionation system: In the distillation tower, the product is heated and separated into different components; the absorption-stabilization system absorbs unstable components and removes these undesirable components.

[0060] The data collected for this application were taken from a real-time database of an oil refinery over a period of time. Fifty input variables were selected as key variables for a real continuous catalytic cracking process, such as the mass flow rate of the feed (crude oil), the pressure and temperature at the inlet, top, or bottom of each key device during the reaction process, and other key parameters. Table 1 below lists the catalytic cracking process variables.

[0061] Table 1: Catalytic Cracking Process Variables

[0062]

[0063]

[0064]

[0065] The present invention ultimately obtained 3,662 samples, which were divided into training and test sets. Typically, 80% of the data is used to train the model, while the remaining 20% ​​is used to test the model's performance. The present invention uses the first 3,062 samples as training samples and the last 600 samples as prediction samples. The final prediction indicators are gasoline, diesel, liquefied petroleum gas, dry gas, and oil slurry yields.

[0066] The process of preprocessing actual production data includes: first detecting missing values ​​and outliers in historical data, eliminating process variable data with a large number of missing data and data that does not meet the Raida criterion, and using linear interpolation to supplement the abnormal point data that has been eliminated in the data. The average value of the two original data before and after the abnormal point in time sequence is used to replace the abnormality. The abnormal data that cannot be averaged is replaced by the average value of the original data.

[0067] A preset proportion of feature variables is randomly selected to build a subtree, which is then summed and averaged according to feature importance and sorted in descending order. Finally, the process variables are retained as the input data set of the convolutional neural network for prediction.

[0068] In this application, 1 / 3 of the feature variable data is randomly selected to construct a subtree. In this embodiment, the number of subtrees is set to 100. Models are constructed for the five prediction indicators respectively. The features are added and averaged according to their importance and sorted in descending order. Finally, 33 process variables are retained as the input data set of the model.

[0069] The importance of each feature prediction indicator is calculated using the random forest algorithm. The calculation formula is:

[0070]

[0071] Where N is the total number of subtrees generated; err 1i is the characteristic error of the current subtree without adding random noise; err 2i The characteristic error of adding random noise to the current subtree; i is the sequence number of the current subtree;

[0072] Based on the importance of each feature prediction indicator, the corresponding proportion of features is eliminated, and then the feature set with the lowest error rate is selected as the convolutional neural network input data set for prediction.

[0073] This application also includes the use of wavelet transform to reduce data noise on the data set, and inputting the denoised data set into a pre-established convolutional neural network. First, the noise that may be contained in the data set is eliminated, and the denoising effects of the mean filter method and the wavelet transform are compared. The Wavelet function of the pywt package in Python is selected for wavelet transform to reduce data noise. It decomposes the data into a set of wavelet coefficients, which represent the different frequency components of the signal at different scales. The high-frequency coefficients are selected and set to 0 to eliminate noise and regenerate data. The denoised data set is then normalized to the maximum and minimum values ​​and input into the pre-established convolutional neural network.

[0074] In step S200, the data set is input into a pre-established convolutional neural network. First, one-dimensional convolution is used to extract input feature information. The maximum pooling technique is used to retain the feature information in the convolution layer that is most relevant to the predicted value. The bidirectional gated recurrent unit is used as the basic unit to process the output information of the pooling layer in the forward and backward directions of time to capture the temporal dependency between features. The attention layer is used to selectively focus on the key information extracted by the convolution layer and the pooling layer, which is then handed over to the fully connected layer to fit the predicted value.

[0075] Figure 3This is the basic structure of the CNN-BIGRU-ATTENTION model proposed in Example 1 of the present invention; the basic structure of the convolutional neural network is set as convolution layer-pooling layer-convolution layer-pooling layer, and the input data shape is [none,33,1], where none is the batch data length. The convolution layers are all one-dimensional convolutions, and the convolution kernel length is 16. The convolution kernel learns the local information of the features by reading the input data and performing a dot product operation. The filter sizes are set to 32 and 16 respectively. The pooling layer uses maximum pooling, the pooling window size is set to 2, the nonlinear activation function is "relu", and the convolutional neural network output matrix size is [none,1,16], where none is the batch data length.

[0076] The bidirectional gated recurrent unit uses the gated recurrent unit as the basic unit and is divided into two layers, forward and backward. Each layer has 20 gated recurrent units. It learns the temporal dependency of the upper layer output matrix in different directions of the time sequence, extracts temporal features, and outputs hidden variables of shape and size [none, 1, 40], where none is the batch data length. The bidirectional gated recurrent unit consists of an update gate and a reset gate, which are specifically expressed as follows:

[0077] z t =σ(W z [x t ,h t-1 ]);

[0078] r t =σ(W r [x t ,h t-1 ]);

[0079]

[0080]

[0081] Among them, x t is the current input; z t is the update gate, r t is the reset gate; h t-1 is the hidden layer state before the current time direction; h t is the output of the hidden layer before the current time direction; is the current candidate state; W Z is the weight coefficient of the update gate; W r is the weight coefficient of the reset gate; W is the weight coefficient of the current candidate state; σ is the sigmoid function.

[0082] The bidirectional gated recurrent unit is divided into two layers, which extract the temporal dependency of features in two different directions in chronological order, and finally obtain two sets of hidden variables, which are calculated and expressed as:

[0083]

[0084]

[0085]

[0086] in, Output hidden variables for the backward layer; Output hidden variables for the forward layer.

[0087] The attention layer is represented as:

[0088] e t =V T tanh(W e h t +b e );

[0089]

[0090]

[0091] Among them, V is the first weight parameter, W e is the second weight parameter, b e is the third weight parameter, e t is the probability distribution value of the attention mechanism at time t; a t is the weight of the attention mechanism corresponding to the hidden variable output by the bidirectional gated recurrent unit at time t; t is the output value of the attention mechanism at time t.

[0092] The model was run for 200 iterations, with each batch of data having a length of 49. Gasoline is widely used and has high economic benefits. To verify the effectiveness of our proposed method, we used three different methods to compare the results of gasoline yield. Table 2 below shows the comparison of gasoline yield prediction results. Figure 4 The gasoline yield prediction results of the three different methods proposed in Example 1 of the present invention are shown below:

[0093] Table 2: Comparison of gasoline yield prediction results

[0094] FNN LSTM-ATTENTION CNN-BIGRU-ATTENTION RMSE 0.46328 0.19734 0.09127 R2 0.77872 0.90574 0.95640

[0095] Table 3 below shows the prediction results of other indicators.

[0096] Table 3: Prediction results of other indicators

[0097] Training set (RMSE) Training set (R2) Test set (RMSE) Test set (R2) diesel fuel 0.98 0.223 0.96 0.246 Liquefied gas 0.98 0.184 0.979 0.214 dry gas 0.96 0.045 0.92 0.081 Slurry 0.91 0.119 0.90 0.131

[0098] Among them, "RMSE" and "R2" are used to quantify the effectiveness of the method of the present invention. The specific calculation formula is as follows:

[0099]

[0100]

[0101] Among them, m is the number of samples in the test data, y i and are the actual value and predicted value of the forecast indicator respectively; is the average value of the actual value of the predicted indicator in the test data set

[0102] In terms of model prediction results, the fully connected neural network (FNN) structure is relatively simple. When the input-output relationship is complex and the input data has multi-scale feature information, it is difficult to establish an effective mapping relationship. Therefore, the prediction error in the test set is relatively large.

[0103] Figure 5 The prediction errors of gasoline yield by the three different methods proposed in Example 1 of the present invention are shown below. The LSTM-ATTENTION model extracts the temporal dependencies of feature contexts by learning and memorizing long sequences, thereby further improving model performance. The CNN-BIGRU-ATTENTION model combines the advantages of CNN and BIGRU, effectively capturing local features and long-range dependencies of data. At the same time, by introducing the attention mechanism, the model can autonomously learn the important parts of the data, thereby demonstrating superior performance when processing industrial production data and maintaining a high prediction accuracy for different prediction indicators. Specifically: Figure 6 This is the diesel yield prediction result proposed in Example 1 of the present invention; Figure 7 The diesel yield prediction performance proposed in Example 1 of the present invention; Figure 8 This is the liquefied gas yield prediction result proposed in Example 1 of the present invention; Figure 9 This is the liquefied gas yield prediction performance proposed in Example 1 of the present invention; Figure 10 This is the dry gas yield prediction result proposed in Example 1 of the present invention; Figure 11 The dry gas yield prediction performance proposed in Example 1 of the present invention; Figure 12 This is the prediction result of the slurry yield proposed in Example 1 of the present invention; Figure 13 This is the oil slurry yield prediction performance proposed in Example 1 of the present invention.

[0104] The above data prove that the method proposed in this application has been verified in the industrial catalytic cracking process, and the average mean square error of the proposed method is much lower than that of other methods.

[0105] The method for predicting catalytic cracking process quality indicators, proposed in Example 1 of the present invention, is simple, rapid, and practical. Compared with traditional measurement methods, it significantly shortens detection time and reduces waste of manpower and material resources. Because the nonlinear and highly coupled characteristics of process variables lead to significant loss of data feature information, resulting in poor model fitting, the present invention significantly improves the model's prediction accuracy.

[0106] Example 2

[0107] Based on the method for predicting quality indicators of a catalytic cracking process proposed in Example 1 of the present invention, Example 2 of the present invention further proposes a system for predicting quality indicators of a catalytic cracking process. Figure 14 This is a schematic diagram of a catalytic cracking process quality index prediction system proposed in Example 2 of the present invention, including a pretreatment module and a prediction module;

[0108] The preprocessing module is used to obtain the actual production data of the catalytic cracking process at a preset time, construct the convolutional neural network input data set for prediction after preprocessing and feature selection of the actual production data, and confirm the prediction indicators;

[0109] The prediction module is used to input the data set into a pre-established convolutional neural network. First, one-dimensional convolution is used to extract input feature information, and the maximum pooling technology is used to retain the feature information in the convolution layer that is most relevant to the predicted value. The bidirectional gated recurrent unit is used as the basic unit to process the output information of the pooling layer in the forward and backward directions of time to capture the temporal dependency between features. The attention layer is used to selectively focus on the key information extracted by the convolution layer and the pooling layer, which is then handed over to the fully connected layer to fit the predicted value.

[0110] The processes performed by the pretreatment module include: the actual production data of the catalytic cracking process include: the mass flow rate of each raw oil input in the catalytic cracking process, the pressure and temperature at different positions of each device during the reaction process, and the component content in the mixed raw material.

[0111] The process of constructing a convolutional neural network input data set for prediction after preprocessing and feature selection of the actual production data includes:

[0112] Detect missing values ​​and outliers in the data, eliminate data that does not meet the error threshold, and use linear interpolation to supplement the data of the eliminated outlier points;

[0113] A preset proportion of feature variables is randomly selected to build a subtree, which is then summed and averaged according to feature importance and sorted in descending order. Finally, the process variables are retained as the input data set of the convolutional neural network for prediction.

[0114] Predicted indicators include gasoline, diesel, liquefied gas, dry gas and slurry oil yields.

[0115] The importance of each feature prediction indicator is calculated using the random forest algorithm. The calculation formula is:

[0116]

[0117] Where N is the total number of subtrees generated; err 1i is the characteristic error of the current subtree without adding random noise; err 2i The characteristic error of adding random noise to the current subtree; i is the sequence number of the current subtree;

[0118] Based on the importance of each feature prediction indicator, the corresponding proportion of features is eliminated, and then the feature set with the lowest error rate is selected as the convolutional neural network input data set for prediction.

[0119] Wavelet transform is used to perform data denoising on the dataset, and the denoised dataset is input into the pre-established convolutional neural network.

[0120] The prediction module execution process includes: the bidirectional gated recurrent unit is composed of an update gate and a reset gate, which is specifically expressed as:

[0121] z t =σ(W z [x t ,h t-1 ]);

[0122] r t =σ(W r [x t ,h t-1 ]);

[0123]

[0124]

[0125] Among them, x t is the current input; z t is the update gate, r t is the reset gate; h t-1 is the hidden layer state before the current time direction; h t is the output of the hidden layer before the current time direction; is the current candidate state; W Z is the weight coefficient of the update gate; W r is the weight coefficient of the reset gate; W is the weight coefficient of the current candidate state; σ is the sigmoid function.

[0126] The bidirectional gated recurrent unit is divided into two layers, which extract the temporal dependency of features in two different directions in chronological order, and finally obtain two sets of hidden variables, which are calculated and expressed as:

[0127]

[0128]

[0129]

[0130] in, Output hidden variables for the backward layer; Output hidden variables for the forward layer.

[0131] The attention layer is represented as:

[0132] e t =V T tanh(W e h t +b e );

[0133]

[0134]

[0135] Among them, V is the first weight parameter, W e is the second weight parameter, b e is the third weight parameter, e t is the probability distribution value of the attention mechanism at time t; a t is the weight of the attention mechanism corresponding to the hidden variable output by the bidirectional gated recurrent unit at time t; t is the output value of the attention mechanism at time t.

[0136] The catalytic cracking process quality indicator prediction system proposed in Example 2 of the present invention is simple, rapid, and practical. Compared with traditional measurement methods, it significantly shortens detection time and reduces waste of manpower and material resources. Because the nonlinear and highly coupled characteristics of process variables lead to significant loss of data feature information, resulting in poor model fitting, the present invention significantly improves the model's prediction accuracy.

[0137] For the description of the relevant parts of the catalytic cracking process quality index prediction system provided in the embodiment of the present application, please refer to the detailed description of the corresponding parts of the catalytic cracking process quality index prediction method provided in Example 1 of the present application, which will not be repeated here.

[0138] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device comprising a series of elements are inherent to the elements. In the absence of further restrictions, the elements limited by the statement "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device comprising the elements. In addition, the above-mentioned technical solutions provided in the embodiments of the present application are not described in detail in accordance with the corresponding technical solutions in the prior art to achieve the same principle, so as to avoid excessive elaboration.

[0139] Although the above description is of specific embodiments of the present invention in conjunction with the accompanying drawings, it does not limit the scope of protection of the present invention. For those skilled in the art, other different forms of modifications or variations can be made based on the above description. It is not necessary and impossible to list all embodiments here. Based on the technical solution of the present invention, various modifications or variations that can be made by those skilled in the art without expending creative effort are still within the scope of protection of the present invention.

Claims

1. A method for predicting quality indicators of a catalytic cracking process, characterized in that: The following steps are involved: Acquiring actual production data of the catalytic cracking process for a preset time, constructing a convolutional neural network input data set for prediction after preprocessing and feature selection of the actual production data, and confirming prediction indicators; The dataset is input into a pre-established convolutional neural network. First, one-dimensional convolution is used to extract input feature information. The maximum pooling technique is used to retain the feature information in the convolution layer that is most relevant to the predicted value. The bidirectional gated recurrent unit is used as the basic unit to process the output information of the pooling layer in the forward and backward directions of time to capture the temporal dependency between features. The attention layer is used to selectively focus on the key information extracted by the convolution layer and the pooling layer, which is then handed over to the fully connected layer to fit the predicted value.

2. The method for predicting quality indicators of a catalytic cracking process according to claim 1, wherein: The actual production data of the catalytic cracking process includes: the mass flow rate of each raw oil input in the catalytic cracking process, the pressure and temperature at different positions of each device during the reaction process, and the content of components in the mixed raw materials.

3. The method for predicting quality indicators of a catalytic cracking process according to claim 1, wherein: The process of constructing a convolutional neural network input data set for prediction after preprocessing and feature selection of the actual production data includes: Detect missing values ​​and outliers in the data, eliminate data that does not meet the error threshold, and use linear interpolation to supplement the data of the eliminated outlier points; A preset proportion of feature variables is randomly selected to build a subtree, which is then summed and averaged according to feature importance and sorted in descending order. Finally, the process variables are retained as the input data set of the convolutional neural network for prediction.

4. A method for predicting quality indicators of a catalytic cracking process according to claim 3, characterized in that: The prediction indicators include gasoline, diesel, liquefied gas, dry gas and slurry oil yields.

5. A method for predicting quality indicators of a catalytic cracking process according to claim 4, characterized in that: The method further includes: using a random forest algorithm to calculate the importance of each feature prediction indicator, and the calculation formula is: Where N is the total number of subtrees generated; err 1i is the characteristic error of the current subtree without adding random noise; err 2i The characteristic error of adding random noise to the current subtree; i is the sequence number of the current subtree; Based on the importance of each feature prediction indicator, the corresponding proportion of features is eliminated, and then the feature set with the lowest error rate is selected as the convolutional neural network input data set for prediction.

6. A method for predicting quality indicators of a catalytic cracking process according to claim 1, characterized in that: The method further includes performing data denoising on the data set using wavelet transform, and inputting the denoised data set into a pre-established convolutional neural network.

7. The method for predicting quality indicators of a catalytic cracking process according to claim 1, characterized in that: The bidirectional gated recurrent unit is composed of an update gate and a reset gate, which is specifically expressed as: z t =σ(W z [x t ,h t-1 ]); r t =σ(W r [x t ,h t-1 ]); Among them, x t is the current input; z t is the update gate, r t is the reset gate; h t-1 is the hidden layer state before the current time direction; h t is the output of the hidden layer before the current time direction; is the current candidate state; W Z is the weight coefficient of the update gate; W r is the weight coefficient of the reset gate; W is the weight coefficient of the current candidate state; σ is the sigmoid function.

8. A method for predicting quality indicators of a catalytic cracking process according to claim 7, characterized in that: The bidirectional gated recurrent unit is divided into two layers, and the temporal dependency of features is extracted in two different directions in chronological order, and finally two sets of hidden variables are obtained, which are calculated and expressed as: in, Output hidden variables for the backward layer; Output hidden variables for the forward layer.

9. The method for predicting quality indicators of a catalytic cracking process according to claim 1, characterized in that: The attention layer is expressed as: e t =V T fishy(W e h t +b e ); Among them, V is the first weight parameter, W e is the second weight parameter, b e is the third weight parameter, e t is the probability distribution value of the attention mechanism at time t; a t is the weight of the attention mechanism corresponding to the hidden variable output by the bidirectional gated recurrent unit at time t; t is the output value of the attention mechanism at time t.

10. A catalytic cracking process quality index prediction system, characterized in that: Includes preprocessing module and prediction module; The preprocessing module is used to obtain actual production data of the catalytic cracking process at a preset time, construct a convolutional neural network input data set for prediction after preprocessing and feature selection of the actual production data, and confirm the prediction index; The prediction module is used to input the data set into a pre-established convolutional neural network. First, one-dimensional convolution is used to extract input feature information, and the maximum pooling technology is used to retain the feature information in the convolution layer that is most relevant to the predicted value. The bidirectional gated recurrent unit is used as the basic unit to process the output information of the pooling layer in the forward and backward directions of time to capture the temporal dependency between features. The attention layer is used to selectively focus on the key information extracted by the convolution layer and the pooling layer, which is then handed over to the fully connected layer to fit the predicted value.

Images