Hydrocracking production process data preprocessing method and system

Abstract

The invention belongs to but not limited to the technical field of data preprocessing, and discloses a hydrocracking production process data preprocessing method and system, and the method comprises the steps: collecting production data with missing data in a hydrocracking production process; key missing data in the production data is complemented by using a missing data complementing method of multiple interpolation of a mask denoising auto-encoder based on a self-attention mechanism; according to the missing data completion method based on the self-attention mechanism mask denoising auto-encoder multi-interpolation, part of missing data is accurately filled through a mask auto-encoder based on the self-attention mechanism, and then overall improvement is carried out through a multi-interpolation method. According to the missing data complementation technology of the mask auto-encoder based on the self-attention mechanism, similar data are screened through the self-attention mechanism, and then missing data with the similar data are complemented through the mask auto-encoder. According to the method, the calculation difficulty is reduced while the data completion accuracy is improved.

Description

Technical Field

[0001] The present invention belongs to but is not limited to the technical field of data preprocessing, and in particular relates to a method and system for preprocessing data in a hydrocracking production process. Background Art

[0002] In industrial production, the reliability and accuracy of data preprocessing are crucial to the efficient, profitable and safe operation of the plant. As a continuous and complex industrial production process, the hydrocracking process is affected by fluctuations in the taste and flow of inlet raw materials, changes in product specification requirements, and degradation of equipment operating performance. The production process usually includes multiple working conditions. Under complex working conditions, during the collection of industrial data, the collected data may be missing due to hardware or network-related problems. The lack of input data has a great impact on the subsequent hydrocracking data modeling and optimization adjustments. At this time, it is necessary to develop management technology to complete the missing data collected and make it suitable for the complex working conditions in the hydrocracking process.

[0003] Scholars at home and abroad have conducted extensive research on data preprocessing of industrial data collection. Existing missing data completion techniques include the historical average (HA) method and the linear interpolation (LI) method. The historical average (HA) method fills in missing values ​​by observing highly correlated time slots and calculating the average value. This method is effective for aggregated energy data, but its performance is poor in high volatility modes; the linear interpolation (LI) method estimates the missing values ​​of the input data by connecting the two measured values ​​before and after the missing data. This method works well for short-term missing values, but its effect will be significantly reduced when the missing values ​​are extended. At the same time, domestic and foreign academic circles have designed a variety of methods for the accuracy of data preprocessing in industrial production processes, such as common data preprocessing methods such as correlation coefficient, mutual information, Euclidean distance and Bayesian reasoning. However, most of these methods are suitable for simple processes rather than complex industrial production processes.

[0004] In response to the shortcomings of HA and LI, the academic community has proposed self-attention mechanism (Self-Attention), masked autoencoder (MAE) and multiple interpolation (MI) to complete missing data. The self-attention mechanism (Self-Attention) calculates the weight between each element and all other elements in the sequence data, aiming to reflect the relationship between elements through weights, thereby displaying related data with similarity, and facilitating the subsequent processing of missing data. However, there is a problem that the self-attention mechanism will lead to data consistency and poor data fitting effect when completing data; the basic idea of ​​the masked autoencoder (MAE) is to train the original missing data values ​​to recover from the remaining similar input data, and to train the completion of the original missing data by learning the similar structure of the remaining collected data. However, there is a problem that some data is omitted when the masked autoencoder (MAE) is used for data completion. Using multiple interpolation (MI) to complete the data can fill all missing values, but there are problems such as low completion accuracy and high computational difficulty.

[0005] Therefore, there is a need for a missing data completion technology that combines the advantages of self-attention mechanism (Self-Attention), masked autoencoder (MAE) and multiple interpolation (MI), which can also improve the processing of missing data in restrictive settings. Summary of the invention

[0006] In response to the problems existing in the prior art, the present invention provides a data preprocessing method and system for a hydrocracking production process, which first screens similar data in the input data and then learns the similar data to accurately complete some missing data, thereby reducing the calculation difficulty of subsequent overall data completion and improving the accuracy of missing data completion.

[0007] The present invention is implemented as follows: a method for preprocessing data in a hydrocracking production process, comprising the following steps:

[0008] Step 1, collecting production data with missing data in the hydrocracking production process;

[0009] Step 2: Use the missing data completion method of masked denoising autoencoder multiple interpolation based on self-attention mechanism (MI-SAMAE) to complete the key missing data in the production data;

[0010] The missing data completion method of the masked denoising autoencoder multiple interpolation (MI-SAMAE) based on the self-attention mechanism accurately fills part of the missing data through the masked autoencoder based on the self-attention mechanism, and then improves the whole through the multiple interpolation method; the missing value estimated by the masked denoising autoencoder multiple interpolation (MI-SAMAE) based on the self-attention mechanism can be expressed as:

[0011]

[0012] Among them, Z in Represents an incomplete sample set;

[0013] The missing data completion technology of the masked autoencoder based on the self-attention mechanism screens similar data through the self-attention mechanism, and then completes the missing data with similar data through the masked autoencoder; the minimized total objective function of the missing data completion technology of the masked autoencoder based on the self-attention mechanism (SAMAE) can be expressed as:

[0014]

[0015] Further, the production data includes production data with missing data output by each controller in the hydrocracking production process.

[0016] Furthermore, the self-attention mechanism calculates the weights between the elements in the sequence data, understands the context information in the sequence, and marks data with similar change trends;

[0017] The self-attention mechanism calculates the attention weights of elements in the sequence through the softmax function:

[0018] w ij =softmax(score(Q i ,K j ))

[0019] Among them, score(Q i ,K j ) represents the attention score, Q i represents the query vector, K i Represents a key vector.

[0020] Furthermore, the masked autoencoder (MAE) recovers the missing values ​​of the original data from the input data with similar change trends by additionally setting a mask on the original data;

[0021] In a high missing rate environment, the input vector of masked autoencoders (MAEs) can be a partial observation vector. By learning from similar input data, the missing values ​​of the input data can be completed.

[0022] Furthermore, during the MAE learning process, the masked autoencoder (MAEs) defines a new error term And only consider the contribution of the observed value, as follows:

[0023]

[0024] Among them, i represents the set of observations on the i-th day, 1 represents the indicator function, when x ij ≠0 is equivalent to 1, otherwise it is 0.

[0025] Furthermore, the multiple interpolation (MI) method uses a single imputation method of mean imputation, linear regression imputation, deductive imputation, nearest distance imputation, hot card imputation and cold card imputation to repeatedly carry out several rounds of imputation to obtain multiple different complete data sets, and to fill in the missing data that does not exist in similar data under a high missing rate environment. Finally, the missing data is integrated to obtain complete data.

[0026] Another object of the present invention is to provide a hydrocracking production process data preprocessing method and a hydrocracking production process data preprocessing system, comprising:

[0027] Production data collection module, which collects production data with missing data in the hydrocracking production process;

[0028] The missing data completion module uses the missing data completion method of masked denoising autoencoder multiple interpolation based on self-attention mechanism (MI-SAMAE) to complete the key missing data in the production data;

[0029] The missing data completion method of the masked denoising autoencoder multiple interpolation (MI-SAMAE) based on the self-attention mechanism accurately fills part of the missing data through the masked autoencoder based on the self-attention mechanism, and then improves the whole through the multiple interpolation method; the missing value estimated by the masked denoising autoencoder multiple interpolation (MI-SAMAE) based on the self-attention mechanism can be expressed as:

[0030]

[0031] Among them, Z in Represents an incomplete sample set;

[0032] The missing data completion technology of the masked autoencoder based on the self-attention mechanism screens similar data through the self-attention mechanism, and then completes the missing data with similar data through the masked autoencoder; the minimized total objective function of the missing data completion technology of the masked autoencoder based on the self-attention mechanism (SAMAE) can be expressed as:

[0033]

[0034] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the hydrocracking production process data preprocessing method.

[0035] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to execute the steps of the hydrocracking production process data preprocessing method.

[0036] Another object of the present invention is to provide an information data processing terminal, which includes the hydrocracking production process data preprocessing system.

[0037] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0038] First, the present invention collects a set of industrial production data with missing values ​​output by each controller in the hydrocracking production process; Generate additional missing values ​​for the industrial production data, with the original data as output, Through the self-attention mechanism, the correlation between the elements of the original sequence is calculated, the relationship between the data context is understood, and the model is helped to process the missing data of the sequence more accurately; then the masked autoencoder (MAE) method is used to train the original missing data values ​​to recover from the remaining similar input data; the two methods are combined to form a masked denoising autoencoder (SAMAE) based on the self-attention mechanism to perform preliminary filling of missing data in the industrial process; the multiple interpolation method (MI) uses a single filling method to further fill the missing values ​​omitted in the preliminary filling, and obtains a more complete industrial temperature input data; the masked autoencoder multiple interpolation method (MI-SAMAE) based on the self-attention mechanism is applied to the data preprocessing of the hydrocracking industrial process to ensure that the data filling can accurately and completely fill the missing data in the case of high missing rate data. Compared with the existing technology, the MI-SAMAE method combines the advantages of the self-attention mechanism, MAE and multiple interpolation methods, and can also improve the processing of missing data in restrictive settings, and can be applied to the hydrocracking process flow that is more complex than the simple process.

[0039] Second, the technical solution of the present invention has made a certain contribution to improving the production efficiency of the hydrocracking industry after transformation. The technical solution of the present invention performs data preprocessing on the industrial production data collected by the sensors of the hydrocracking industrial production process, and accurately completes the missing industrial production data, which is conducive to the smooth advancement of the subsequent data modeling optimization process, improves the accurate analysis of industrial data, strengthens the online control of the hydrocracking industrial process, is conducive to subsequent industrial manual intervention, improves the hydrocracking industrial production standards and is conducive to the greening of the industrial production process.

[0040] In addition, the technical solution of the present invention improves the completion ability of the traditional masked autoencoder (MAE) by using the self-attention mechanism (SA) and completes the production data that cannot be completed by using the multiple interpolation method (MI). The technical solution of the present invention can further improve and enhance the data completion process based on the traditional method, and can also achieve more complete and accurate completion for the missing data in the production data, providing convenience for subsequent industrial production. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a flow chart of a method for preprocessing data in a hydrocracking production process provided by an embodiment of the present invention;

[0042] Figure 2 It is a structural diagram of a hydrocracking production process data preprocessing system provided by an embodiment of the present invention;

[0043] Figure 3 It is a MI-SAMAE simulation training effect diagram provided by an embodiment of the present invention;

[0044] Figure 4 It is a diagram showing the effect of partial data simulation training of MI-SAMAE provided by an embodiment of the present invention;

[0045] Figure 5 It is a diagram showing the effect of the MAE simulation training result provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] like Figure 1 As shown, an embodiment of the present invention provides a method for preprocessing data of a hydrocracking production process, which is applied to complete missing data of a hydrocracking production process and solve the problem of accuracy of data collected in a hydrocracking production process, and specifically includes:

[0048] S101, collecting production data with missing data in a hydrocracking production process, wherein the production data includes production data with missing data output by each controller in the hydrocracking production process;

[0049] S102, calculate the weights between the elements in the sequence data through the self-attention mechanism, understand the context information in the sequence, and mark the data with similar change trends, so as to process the sequence data more accurately;

[0050] S103, since there are missing data values ​​in the collected data, a mask is additionally set on the original data through a masked autoencoder (MAE) to restore the missing values ​​of the original data from the output data with similar change trends;

[0051] S104, by combining the two processes in S102 and S103 to form a missing data completion technology based on a masked autoencoder (SAMAE) of a self-attention mechanism, the missing data of key variables in the hydrocracking process are completed, and the key missing data in the production data are completed;

[0052] S105, since the mask denoising autoencoder cannot fill in the missing data where there is no similar data in the high missing rate environment, multiple interpolation (MI) is used to repeatedly expand several rounds of filling using a single filling method to obtain multiple different complete data sets, and finally integrate them to obtain complete data;

[0053] S106, by combining the two methods in S104 and S105, a missing data completion method based on multiple interpolation of masked denoising autoencoders (MI-SAMAE) is formed, which improves the accuracy of data completion while reducing the difficulty of calculation.

[0054] Specifically, S101 includes:

[0055] The embodiment of the present invention randomly collects industrial production data with missing data output by the hydrocracking production process at a sampling interval of 1 min. A set of industrial production data consists of production data with missing data output by each controller in the hydrocracking production process.

[0056] Specifically, S102 includes:

[0057] The self-attention mechanism calculates the weight between each element and all other elements in the sequence data, aiming to reflect the relationship between elements through weights, thereby displaying related data with similarities, facilitating the subsequent processing of missing data;

[0058] The self-attention mechanism calculates the attention weights of elements in the sequence through the softmax function:

[0059] w ij =softmax(score(Q i ,K j ))

[0060] Among them, score(Q i ,K j ) represents the attention score, and the specific calculation process is as follows:

[0061]

[0062] in, represents the scaling factor, Q i represents the query vector, K i Represents the key vector. The query vector Q is obtained by learning the weight matrix and linear transformation of the input elements in the self-attention mechanism. i , key vector K i and the value vector V i Specifically, it can be expressed as:

[0063] Q i =W Q ·x i

[0064] K i =W K ·x i

[0065] V i =W V ·x i

[0066] Among them, W Q , W K and W V There are three trainable parameter matrices, through the value vector V j Multiply and sum the corresponding attention weights to get the output:

[0067]

[0068] Specifically, S103 includes:

[0069] The masked autoencoder (MAE) can fill in the missing values ​​of the data by learning the rest of the data similar groups; however, when the missing rate is high, it is difficult for the masked autoencoder to learn similar data and thus difficult to completely fill in the missing values ​​of the data.

[0070] In a high missing rate environment, the input vector of masked autoencoders (MAEs) can be a partial observation vector. By learning similar input data, the missing values ​​of the input data are supplemented. In the MAE learning process, the missing values ​​replaced by zero values ​​do not participate in the reconstruction process. In this process, a new error term is defined. Only the contribution of the observed value is considered. As follows:

[0071]

[0072] Among them, x i represents the input vector, x ij represents the jth element of the input vector, i represents the set of observations on the i-th day, g(f(x i )) represents the reconstructed output vector, g(f(x i )) j represents the jth element of the reconstructed output vector, 1 represents the indicator function, when x ij When ≠0, it is equivalent to 1, otherwise it is 0. This type of loss is called masked reconstruction loss, because the missing values ​​will be masked during the reconstruction phase. If only the observations are restored, there will still be missing data. MAE allows finding similar data to learn and complete the missing data during the reconstruction process.

[0073] Specifically, S104 includes:

[0074] Combining the advantages of the self-attention mechanism (Self-Attention) and the masked autoencoder (MAE), a masked autoencoder missing data completion technology (SAMAE) based on the self-attention mechanism is formed. The self-attention mechanism is used to screen similar data, and then the masked autoencoder is used to complete the missing data with similar data.

[0075] The minimized total objective function of the masked autoencoder missing data completion technology (SAMAE) based on the self-attention mechanism can be expressed as:

[0076]

[0077] Among them, z i represents the input vector, z ij represents the jth element of the input vector, i represents the set of observations on the i-th day, g(f(z i )) represents the reconstructed output vector, g(f(z i )) j represents the jth element of the reconstructed output vector, 1 represents the indicator function, when z ij ≠0 is equivalent to 1 otherwise 0. This type of loss is called masked reconstruction loss because missing values ​​will be masked during the reconstruction phase.

[0078] Specifically, S105 includes:

[0079] Through the multiple interpolation method (MI), several rounds of imputation are repeated using single imputation methods such as mean imputation, linear regression imputation, deductive imputation, nearest distance imputation, hot card imputation and cold card imputation to obtain multiple different complete data sets. The missing data that cannot be filled by the masked denoising autoencoder in a high missing rate environment and does not have similar data are filled, and finally integrated to obtain complete data.

[0080] For an incomplete data set, a single imputation method is used to perform m imputation operations to obtain m groups of imputation values ​​and generate m complete data sets. The same analysis algorithm is then used to independently analyze all complete data sets, and m analysis results are obtained. A classification model is built based on each data set and the model parameters are obtained. Finally, all model parameters are merged into one set of parameters through the idea of ​​​​de-meaning.

[0081] Taking the linear regression imputation method as an example, first, a linear regression model is established:

[0082]

[0083] Among them, X co represents the complete sample set, x ij represents the sample in the complete sample set, y i represents the dependent variable, β j represents the model parameters, β0 represents the constant term, also called the intercept, and ε j Represents the error. The linear model used to estimate the missing value can be expressed as:

[0084]

[0085] in, represents the estimated value of the model parameters based on the complete sample, represents the least squares estimate of β0, X in Represents an incomplete sample set.

[0086] Specifically, S106 includes:

[0087] Combining the advantages of the masked autoencoder based on self-attention mechanism (SAMAE) and multiple interpolation method (MI), a missing data completion method of masked denoising autoencoder multiple interpolation based on self-attention mechanism (MI-SAMAE) is formed. The masked autoencoder based on self-attention mechanism is used to accurately fill in some missing data, and then the multiple interpolation method is used to improve the overall data completion accuracy while reducing the calculation difficulty. It is used to solve the accuracy problem of data collected in the hydrocracking production process.

[0088] Estimating missing values ​​through multiple interpolation of masked denoising autoencoders based on self-attention mechanism (MI-SAMAE) can be expressed as:

[0089]

[0090] Among them, Z in Represents an incomplete sample set.

[0091] like Figure 2 As shown, an embodiment of the present invention provides a hydrocracking production process data preprocessing method and a hydrocracking production process data preprocessing system, comprising:

[0092] Production data collection module, which collects production data with missing data in the hydrocracking production process;

[0093] The missing data completion module uses the missing data completion method of masked denoising autoencoder multiple interpolation based on self-attention mechanism (MI-SAMAE) to complete the key missing data in the production data;

[0094] The missing data completion method of the masked denoising autoencoder multiple interpolation (MI-SAMAE) based on the self-attention mechanism accurately fills part of the missing data through the masked autoencoder based on the self-attention mechanism, and then improves the whole through the multiple interpolation method; the missing value estimated by the masked denoising autoencoder multiple interpolation (MI-SAMAE) based on the self-attention mechanism can be expressed as:

[0095]

[0096] Among them, Z in Represents an incomplete sample set;

[0097] The missing data completion technology of the masked autoencoder based on the self-attention mechanism screens similar data through the self-attention mechanism, and then completes the missing data with similar data through the masked autoencoder; the minimized total objective function of the missing data completion technology of the masked autoencoder based on the self-attention mechanism (SAMAE) can be expressed as:

[0098]

[0099] 1. Specific application fields or related products of the present invention.

[0100] The present invention provides a software platform for data preprocessing in the hydrocracking industrial production process. The software uses a self-attention mechanism (SA) to perform context analysis on industrial production data and mark similar data; then uses a masked autoencoder (MAE) to accurately complete some missing data, which has a good data fitting effect; finally, multiple interpolation (MI) is used to complete the remaining missing data to ensure the integrity of the data. Based on the above ideas, the software constructs a masked denoising autoencoder multiple interpolation (MI-SAMAE) training model based on a self-attention mechanism to complete missing data for production data in the hydrocracking industrial production process.

[0101] Through simulation training and comparative experiments, it is proved that the software platform can be effectively used to complete the missing data in the initial distillation point data of diesel in the hydrocracking industrial production process; through comparative experiments with masked autoencoders (MAE), it is verified that it has a good data fitting effect; and through the calculation of the root mean square error (RMSE), it is verified that its completion error is small and it is more consistent with the original data.

[0102] 2. Relevant evidence of the technical effects obtained by the embodiments of the present invention.

[0103] The present invention constructs a model and performs simulation training on the proposed masked denoising autoencoder multiple interpolation (MI-SAMAE) method based on self-attention mechanism, and applies the training model to complete the missing data in the diesel initial distillation point data in the hydrocracking industrial production process. The simulation results are shown in Figure 2. Figure 3 , Figure 4 :

[0104] By observing the simulation training effect diagram, it can be seen that the data fitting effect and data filling effect of the model are good. In order to further verify its effectiveness and feasibility, the masked denoising autoencoder multiple interpolation based on self-attention mechanism (MI-SAMAE) and the masked autoencoder (MAE) method are compared. The results of the comparison test are shown in Figure 2. Figure 5 :

[0105] method RMSE MI-SAMAE 3.73 MAE 10.47

[0106] Table 1 Root mean square error of MI-SAMAE and MAE

[0107] The comparative experimental results show that the masked denoising autoencoder multiple interpolation (MI-SAMAE) method based on self-attention mechanism has stronger data fitting and smaller error than the traditional masked autoencoder (MAE) method, and is more comprehensive and accurate in completing missing data.

[0108] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0109] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. A method for preprocessing data in a hydrocracking production process, characterized in that: The following steps are involved: Step 1, collecting production data with missing data in the hydrocracking production process, wherein the production data includes production data with missing data output by each controller in the hydrocracking production process; Step 2: Calculate the weights between elements in the sequence data through the self-attention mechanism, understand the context information in the sequence, and mark data with similar change trends to facilitate more accurate processing of the sequence data; Step 3: Since there are missing data values ​​in the collected data, a mask is additionally set on the original data through a masked autoencoder (MAE) to restore the missing values ​​of the original data from the output data with similar change trends; Step 4, by combining the two processes in step 2 and step 3 to form a missing data completion technology based on a masked autoencoder (SAMAE) of a self-attention mechanism, the missing data of key variables in the hydrocracking process are completed, and the key missing data in the production data are completed; Step 5: Since the mask denoising autoencoder cannot fill in the missing data when there is no similar data in the high missing rate environment, multiple interpolation (MI) is used to repeatedly expand several rounds of filling using a single filling method to obtain multiple different complete data sets, and finally integrate them to obtain complete data; Step 6, by combining the two methods in step 4 and step 5, a missing data completion method based on multiple interpolation of masked denoising autoencoders (MI-SAMAE) is formed, which improves the accuracy of data completion while reducing the difficulty of calculation; Use the missing data completion method based on the self-attention mechanism masked denoising autoencoder multiple interpolation (MI-SAMAE) to complete the key missing data in the production data; The missing data completion method of the masked denoising autoencoder multiple interpolation (MI-SAMAE) based on the self-attention mechanism accurately fills part of the missing data through the masked autoencoder based on the self-attention mechanism, and then performs overall improvement through the multiple interpolation method (MI); wherein, the missing value estimated by the masked denoising autoencoder multiple interpolation (MI-SAMAE) based on the self-attention mechanism is expressed as: In the formula, Z in Represents an incomplete sample set; The missing data completion technology of the masked autoencoder based on the self-attention mechanism (SAMAE) screens similar data through the self-attention mechanism, and then completes the missing data with similar data through the masked autoencoder; wherein the minimization total objective function of the missing data completion technology of the masked autoencoder based on the self-attention mechanism is expressed as:

2. The method for preprocessing data of the hydrocracking production process according to claim 1, characterized in that: The production data includes production data with missing data output by each controller in the hydrocracking production process.

3. The method for preprocessing data of the hydrocracking production process according to claim 1, characterized in that: The self-attention mechanism calculates the weights between the elements in the sequence data, understands the context information in the sequence, and marks data with similar change trends; The self-attention mechanism calculates the attention weights of elements in the sequence through the softmax function: w ij =softmax(score(Q i ,K j )) Among them, score(Q i ,K j ) represents the attention score, Q i represents the query vector, K i Represents a key vector.

4. The method for preprocessing data of the hydrocracking production process according to claim 1, characterized in that: The masked autoencoder (MAE) recovers the missing values ​​of the original data from the output data with similar change trends by additionally setting a mask on the original data; In a high missing rate environment, the input vector of masked autoencoders (MAEs) can be a partial observation vector. By learning from similar input data, the missing values ​​of the input data can be completed.

5. The method for preprocessing data of the hydrocracking production process according to claim 4, characterized in that: During the MAE learning process, the masked autoencoders (MAEs) define a new error term And only consider the contribution of the observed value, as follows: Among them, i represents the set of observations on the i-th day, 1 represents the indicator function, when x ij ≠0 is equivalent to 1, otherwise it is 0.

6. The method for preprocessing data of the hydrocracking production process according to claim 1, characterized in that: The multiple interpolation (MI) method uses a single imputation method of mean imputation, linear regression imputation, deductive imputation, nearest distance imputation, hot card imputation and cold card imputation to repeatedly carry out several rounds of imputation to obtain multiple different complete data sets, and imputes the missing data that cannot be imputed by the mask denoising autoencoder in a high missing rate environment and does not have similar data, and finally integrates them to obtain complete data.

7. A hydrocracking production process data preprocessing system according to any one of claims 1 to 6, characterized in that: include: Production data collection module, which collects production data with missing data in the hydrocracking production process; The missing data completion module uses the missing data completion method of masked denoising autoencoder multiple interpolation based on self-attention mechanism (MI-SAMAE) to complete the key missing data in the production data; The missing data completion method of the masked denoising autoencoder multiple interpolation (MI-SAMAE) based on the self-attention mechanism accurately fills part of the missing data through the masked autoencoder based on the self-attention mechanism, and then performs overall improvement through the multiple interpolation method (MI); wherein, the missing value estimated by the masked denoising autoencoder multiple interpolation (MI-SAMAE) based on the self-attention mechanism is expressed as: In the formula, Z in Represents an incomplete sample set; The missing data completion technology of the masked autoencoder based on the self-attention mechanism (SAMAE) screens similar data through the self-attention mechanism, and then completes the missing data with similar data through the masked autoencoder; wherein the minimization total objective function of the missing data completion technology of the masked autoencoder based on the self-attention mechanism is expressed as:

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the hydrocracking production process data preprocessing method as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to execute the steps of the method for preprocessing data in a hydrocracking production process as described in any one of claims 1 to 6.

10. An information data processing terminal, characterized in that: The information data processing terminal includes the hydrocracking production process data preprocessing system as described in claim 7.

Images