Data processing method and device, equipment, medium and program product

Abstract

The embodiment of the invention provides a data processing method and device, equipment, a medium and a program product, and relates to the technical field of chemical production data processing. The method comprises the steps of obtaining refining data of a target refining device, inputting the refining data into a data verification model corresponding to a preset point location to obtain a data verification result for the refining data, the data verification result reflects whether the refinery data is abnormal or not, and the data verification model is a personalized verification model established based on historical refinery data of the point location under different production conditions. Through the data verification model corresponding to each point location of the target refining device, the refining data corresponding to each point location can be verified more accurately, and the accuracy and reliability of the data verification result of the refining data are ensured.

Description

Technical Field

[0001] This application relates to the field of chemical production data processing technology, and in particular to a data processing method, apparatus, equipment, medium and program product. Background Technology

[0002] In recent years, with the rapid development of technology and the intensification of market competition, refining and chemical enterprises have faced increasing challenges. As a typical representative of the process manufacturing industry, refining and chemical enterprises are facing multiple challenges, including complex raw material properties, complex production processes, complex production equipment, and high safety and environmental protection requirements. To achieve the upgrading of the traditional process industry chain, in addition to introducing new equipment, new processes, and new catalysts, it is also necessary to leverage new-generation information technologies such as big data and artificial intelligence, deeply integrating them with operational and manufacturing technologies to bring about revolutionary changes in production methods, thereby improving the production management level of refining and chemical enterprises. However, when using big data and artificial intelligence algorithms to perform production forecasting or algorithm optimization based on refining and chemical data collected from refining and chemical units, the premise is that the refining and chemical data is accurate. If the refining and chemical data is abnormal, it may lead to low accuracy of the prediction results or that the optimized algorithm is not optimal, thus affecting production decisions, and in more serious cases, may cause production accidents. Therefore, refining and chemical enterprises need to verify the correctness of the refining and chemical data to ensure the accuracy of the prediction results or algorithm optimization results.

[0003] In related technologies, upper and lower thresholds are usually set in advance for each point of the refining and chemical unit, and the refining and chemical data corresponding to each point is judged to be abnormal based on the upper and lower thresholds corresponding to each point; or the relevant technical personnel judge whether the refining and chemical data is abnormal based on their own experience and the production conditions of the refining and chemical unit.

[0004] However, the data verification results obtained through the above data verification methods are inaccurate. Summary of the Invention

[0005] This application provides a data processing method, apparatus, device, medium, and program product to solve the problem of inaccurate data verification results when using data verification methods in related technologies for refining data verification.

[0006] In a first aspect, embodiments of this application provide a data processing method, including:

[0007] The refining data of the target refining unit is obtained through data acquisition equipment installed at the locations of the target refining unit.

[0008] The refining data is input into the data verification model corresponding to the preset location to obtain the data verification result for the refining data. The data verification result reflects whether there are any anomalies in the refining data. The data verification model is a personalized verification model established based on the historical refining data of the location under different production conditions.

[0009] In one possible implementation, the data processing method further includes: if the data verification result reflects that there are no anomalies in the refining data, then inputting the refining data into the application model to obtain a first production plan corresponding to the refining data; if the data verification result reflects that there are anomalies in the refining data, then performing anomaly removal processing on the refining data corresponding to the location to obtain processed data, wherein the anomaly removal data processing includes at least one of time lag alignment, data format conversion, data index calculation, data unit conversion, discarding outliers, and replacing outliers; and inputting the processed data into the application model to obtain a second production plan corresponding to the refining data.

[0010] In one possible implementation, the data verification model is constructed as follows: acquiring historical refining data corresponding to the location; based on the pre-defined correspondence between each location of the target refining unit and the data verification parameters, matching the data verification parameters corresponding to the location according to the historical refining data, the data verification parameters including the method and parameters for data verification calls; and determining the data verification model corresponding to the location based on the data verification parameters corresponding to the location.

[0011] In one possible implementation, the data verification call method includes at least one or more of the following: local outlier factor, maximum normalized residual, box plot, Gaussian distribution, mean difference, density distribution, and outlier algorithm, or any combination thereof.

[0012] In one possible implementation, the data verification parameters include data verification parameters under different production conditions. Based on the preset correspondence between each point of the target refining unit and the data verification parameters, the data verification parameters corresponding to the points are matched according to the historical refining data corresponding to the points. This includes: determining the historical refining data corresponding to each point of the target refining unit based on the preset order of each point of the target refining unit; and matching the data verification parameters corresponding to the production conditions of the points according to the production conditions of the historical refining data corresponding to the points.

[0013] In one possible implementation, determining the target data verification model for a given location based on the data verification parameters for that location includes: matching the data verification parameters corresponding to the refining data at different times for the location of the target refining unit, thereby obtaining multiple data verification parameters for the historical refining data of the location; constructing multiple data verification models for the location based on the multiple data verification parameters; verifying the historical refining data of the location based on the multiple data verification models, thereby obtaining multiple verification results for the historical refining data of the location; and determining the data verification model corresponding to the optimal verification result among the multiple verification results as the data verification model for the application of the location.

[0014] Secondly, this application provides a data processing apparatus, comprising:

[0015] The acquisition module is used to acquire refining data from the target refining unit. The refining data is obtained through data acquisition devices installed at the locations of the target refining unit.

[0016] The processing module is used to input refining data into the data verification model corresponding to the preset location, and obtain the data verification result for the refining data. The data verification result reflects whether there are any anomalies in the refining data. The data verification model is a personalized verification model established based on the historical refining data of the location under different production conditions.

[0017] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0018] Memory is used to store instructions executed by the computer;

[0019] A processor for executing computer-executable instructions stored in memory to implement the method described in any of the first aspects.

[0020] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the method described in any of the first aspects.

[0021] Fifthly, this application provides a computer program product, including a computer program that, when executed, implements the method described in any of the first aspects.

[0022] The data processing method, apparatus, equipment, medium, and program products provided in this application acquire refining data from a target refining unit. This data is obtained through data acquisition devices installed at various points within the target refining unit. The data is then input into a preset data verification model corresponding to each point, yielding a data verification result. This result reflects whether any anomalies exist in the refining data. The data verification model is a personalized verification model established based on historical refining data from each point under different production conditions. In this process, by using the data verification models corresponding to each point within the target refining unit, the refining data at each point can be verified more accurately, ensuring the accuracy and reliability of the data verification results. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0024] Figure 1 A flowchart illustrating a data processing method provided for an exemplary embodiment of this application;

[0025] Figure 2 Another schematic diagram of the data processing method provided for an exemplary embodiment of this application;

[0026] Figure 3 A schematic diagram of the data processing architecture provided for an exemplary embodiment of this application;

[0027] Figure 4 A schematic diagram of the structure of a data processing apparatus provided for an exemplary embodiment of this application;

[0028] Figure 5 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application.

[0029] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0030] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0031] The terms “first,” “second,” etc., used in the specification and claims of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, products, or apparatus.

[0032] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0033] During their research, the inventors discovered two main issues. First, refining data from chemical processing units is collected via instruments at specific points. However, as these instruments age, their sensitivity gradually decreases, and they may even malfunction, leading to inaccurate data reflecting the true state of the unit. Second, refining data is collected in real-time from various points. Changes in the unit's production operations can cause fluctuations and non-linear changes in these values, resulting in abnormal instantaneous data values. Therefore, chemical processing companies need to implement relevant verification procedures to ensure the accuracy of their data. While experienced technicians can subjectively judge the correctness of refining data based on their technical expertise, the data from refining units is usually accurate, making manual real-time verification of anomalies impractical. Furthermore, inexperienced technicians lack the necessary business and operational experience to quickly and accurately verify the refining data.

[0034] In related technologies, when using upper and lower threshold values ​​corresponding to each data point to determine whether the refining data at each point is abnormal, the threshold values ​​are often set very broadly because production conditions usually change. While this method can avoid misclassifying normal refining data as abnormal, it also means that only extreme anomalies can be detected. For example, setting the upper and lower threshold values ​​for some data points to non-negative numbers obviously fails to identify outliers within the positive range. Furthermore, when technicians judge whether the refining data is abnormal based on their experience and the production conditions of the refining unit, the method of manual judgment is inherently lagging because the refining data is collected in real time. This lag prevents the refining data from being applied in real time to production forecasting or algorithm optimization.

[0035] Based on the above, this application provides a data processing scheme that establishes a personalized data verification model based on historical refining data of various locations within the target refining unit under different production conditions. By using the data verification model corresponding to each location within the target refining unit, the refining data at each location is verified more accurately, ensuring the accuracy and reliability of the data verification results. Furthermore, since the refining data at each location can be verified in real time and automatically, the verification results can be obtained in real time. This allows for production forecasting or algorithm optimization using the verified refining data. The automated verification method significantly improves the efficiency of refining data verification and reduces labor costs, thereby improving the production management level and production efficiency of refining enterprises.

[0036] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0037] Figure 1 This is a flowchart illustrating a data processing method provided for an exemplary embodiment of this application. Figure 1 As shown, the data processing method in this application embodiment includes the following steps:

[0038] S101. Obtain refining data of the target refining unit. The refining data is obtained through data acquisition equipment installed at the location of the target refining unit.

[0039] In this context, "points" refer to the specific locations or measurement points on the target refining unit where data acquisition equipment is installed. These are typically key locations selected based on the process flow and monitoring requirements. Data acquisition equipment refers to the devices used to acquire data from the target refining unit. These devices are installed at various points within the unit and are responsible for real-time monitoring and recording of various parameters during the refining process. Specifically, data acquisition equipment typically includes the following types: instrumentation equipment, sensors, data loggers, and monitoring systems. Refining data includes Manufacturing Execution System (MES) data and Laboratory Information Management System (LIMS) data used for production prediction or algorithm optimization of the target refining unit. MES data consists of real-time data collected by data acquisition equipment deployed at various points within the target refining unit, such as temperature, pressure, and flow rate. LIMS data consists of chemical analysis data from various points within the target refining unit, such as the concentration and yield of certain substances.

[0040] For example, in one implementation, data acquisition devices deployed at various locations within the target refining unit collect corresponding refining data in real time, and report the refining data to a server used to execute the data processing method of this application, either in real time or at preset time intervals. Correspondingly, the server obtains the refining data of the target refining unit.

[0041] In another implementation, data acquisition devices deployed at various locations within the target refining unit collect corresponding refining data in real time and store the data in a local database or local data storage system. The data is then reported to the server used to execute the data processing method of this application at preset time intervals. Correspondingly, the server obtains the refining data from the target refining unit.

[0042] S102. Input the refining data into the data verification model corresponding to the preset location to obtain the data verification result for the refining data. The data verification result reflects whether there are any abnormalities in the refining data. The data verification model is a personalized verification model established based on the historical refining data of the location under different production conditions.

[0043] For example, the refining data corresponding to point A of the target refining unit is input into the data verification model corresponding to point A. The data verification model corresponding to point A is a personalized verification model established based on historical refining data of point A under different production conditions. Further, the refining data corresponding to point A is verified based on the data verification model corresponding to point A to obtain the data verification result of the refining data corresponding to point A. The data verification result reflects whether there are any abnormalities in the refining data corresponding to point A.

[0044] The data processing method provided in this application, through a data verification model corresponding to each point of the target refining unit, can more accurately verify the refining data corresponding to each point, ensuring the accuracy and reliability of the data verification results. Furthermore, since the refining data corresponding to each point can be verified in real time and automatically, the verification results can be obtained in real time. This allows for production forecasting or algorithm optimization using the verified refining data. The automated verification method significantly improves the efficiency of refining data verification and reduces labor costs, thereby improving the production management level and production efficiency of refining enterprises.

[0045] Based on the above embodiments, in some embodiments, the data processing method further includes: if the data verification result reflects that there is no abnormality in the refining data, then inputting the refining data into the application model to obtain a first production plan corresponding to the refining data; if the data verification result reflects that there is an abnormality in the refining data, then performing anomaly removal processing on the refining data corresponding to the location to obtain processed data, wherein the anomaly removal data processing includes at least one of time lag alignment, data format conversion, data index calculation, data unit conversion, discarding outliers, and replacing outliers; and inputting the processed data into the application model to obtain a second production plan corresponding to the refining data.

[0046] Among these, time lag alignment refers to adjusting the timestamps of the data to synchronize them with other relevant data; data format conversion refers to converting the data into a unified format for easier subsequent processing; data indicator calculation refers to calculating statistical indicators of the data, such as mean and variance; data unit conversion refers to converting the data into a unified unit for easier comparison and analysis; outlier rejection refers to removing obvious outliers to improve data quality; and outlier replacement refers to replacing outliers with reasonable values, such as the mean or median. It should be noted that in practical applications, before performing outlier removal operations, the types of anomalies in the refining data should be confirmed, and corresponding outlier removal operations should be performed according to the type of anomaly. Specific operations can be one of the following: time lag alignment, data format conversion, data indicator calculation, data unit conversion, outlier rejection, and outlier replacement; or a combination of these operations, depending on the actual situation. No specific limitations are made here.

[0047] For example, if the data verification results indicate that the refining data is normal, the refining data is input into the product yield prediction application model. For instance, based on the reaction product yields included in the input refining data, corresponding operating conditions are predicted, such as low-grade oil flow rate, furnace temperature, and reaction temperature. Furthermore, a corresponding production plan is formulated based on the predicted operating conditions. Conversely, if the data verification results indicate that the refining data is abnormal, the refining data corresponding to the specified point is processed to obtain processed data. This processed data is then input into the instrument maintenance prediction application model, and a production plan for relevant instrument maintenance or repair is formulated based on the prediction results.

[0048] In some embodiments, the data verification model is constructed as follows: acquiring historical refining data corresponding to the location; based on the pre-defined correspondence between each location of the target refining unit and the data verification parameters, matching the data verification parameters corresponding to the location according to the historical refining data corresponding to the location, the data verification parameters including the method and parameters for data verification calls; and determining the data verification model corresponding to the location based on the data verification parameters corresponding to the location.

[0049] For example, historical refining data for each point in the target refining unit is obtained from a database or data storage system. Based on the process flow and monitoring requirements of the refining unit, the correspondence between each point and the data verification parameters is preset. The data verification parameters include the method and parameters for data verification. For example, a data verification parameter corresponding to a certain point is {"method for data verification": Grubbs' check method", "sample quantity": 9713, "detection level": 0.14, "critical value": 3.238, "standard value": 3.122, "average value": 17.888, "minimum value": 7.778, "maximum value": 27.997}. That is, the data verification parameters include the method for detecting the data verification at this point as Grubbs' check method, as well as the sample quantity, detection level, critical value, standard value, average value, and other parameters of the method for data verification, and the minimum and maximum values ​​of the upper and lower limits for detecting anomalies. In practical applications, corresponding data validation parameters can be set according to the type of measurement value at each location. For example, the mean and standard deviation may be used as validation parameters for temperature data. Furthermore, based on the historical refining data corresponding to each location, the corresponding data validation parameters can be matched. For example, for temperature data at the reactor outlet, validation parameters for temperature data (such as mean, standard deviation, anomaly detection methods, etc.) can be matched. Further, based on the data validation parameters corresponding to each location, a data validation model can be constructed. This model can be based on statistical methods (such as mean or variance) or on machine learning algorithms (such as anomaly detection algorithms, regression models, etc.). For example, for temperature data, a validation model based on the historical data mean and standard deviation can be constructed.

[0050] In this embodiment of the application, by acquiring historical refining data corresponding to the points and based on the correspondence between each point of the target refining unit and the data verification parameters, it is possible to ensure that the construction of the data verification model is based on real historical data and process requirements, avoid setting the verification threshold of the points too broadly, thereby improving the accuracy of the data verification results and reducing false alarms and missed alarms.

[0051] In some embodiments, the data verification call method includes at least one or more of the following: local anomaly factor, maximum normalized residual, box plot, Gaussian distribution, mean difference, density distribution, and outlier algorithm, or any combination thereof.

[0052] Among these methods, Local Outlier Detection (LOD) is used to detect outliers with low local density; Maximum Normalized Residual (MNR) is used to detect the degree of data deviation from the mean; Box Plot is used to detect the interquartile range and outliers; Gaussian Distribution is used to detect whether the data conforms to a normal distribution and to identify outliers; Mean Difference is used to detect the deviation of the data from the mean; Density Distribution is used to detect the distribution density of the data and to identify outliers; and Outlier Detection Algorithm (ODA) is used to detect outliers in the data. It should be noted that the methods used for data validation include, but are not limited to, Local Outlier Detection, MNR, Box Plot, Gaussian Distribution, Mean Difference, Density Distribution, and Outlier Detection Algorithm, and can be any one of these methods or any combination thereof.

[0053] Based on the above embodiments, in some embodiments, the data verification parameters include data verification parameters under different production conditions. Based on the preset correspondence between each point of the target refining unit and the data verification parameters, the data verification parameters corresponding to the points are matched according to the historical refining data corresponding to the points. This includes: determining the historical refining data corresponding to the points of the target refining unit based on the preset order of each point of the target refining unit; and matching the data verification parameters corresponding to the production conditions of the points according to the production conditions of the historical refining data corresponding to the points.

[0054] For example, the pre-defined correspondence between various points of the target refining unit and data verification parameters is stored in a database or file system. Based on the pre-defined order of the various points of the target refining unit, the historical refining data corresponding to each point of the target refining unit is determined. The corresponding production status is obtained based on the historical refining data of each point, and further, data verification parameters corresponding to the production status of the point are matched from the data verification parameters under different production statuses. For example, point B is a temperature acquisition point, and its data verification parameters include data verification parameters under three different production statuses: normal production status, start-up status, and shutdown status. In the normal production status, the mean and standard deviation are used as data verification parameters; in the start-up status, a more lenient parameter range, such as the mean, is used as the data verification parameter; and in the shutdown status, specific shutdown parameters, such as the temperature change rate, are used as the data verification parameter.

[0055] In this embodiment, data verification parameters are matched with different locations and corresponding to those locations. A data verification model is constructed based on the data verification parameters under the corresponding production conditions. This allows the data verification model to be flexibly adjusted according to different production conditions, which can further improve the accuracy and reliability of the data verification results, enhance the adaptability and flexibility of the model, and provide a foundation for data analysis and mining, thereby ensuring the safe, stable and efficient operation of the refining and chemical plant.

[0056] In some embodiments, determining the target data verification model corresponding to a location based on the data verification parameters corresponding to the location includes: matching the data verification parameters corresponding to the refining data at different times for the location of the target refining unit to obtain multiple data verification parameters for the historical refining data corresponding to the location; constructing multiple data verification models corresponding to the location based on the multiple data verification parameters; verifying the historical refining data corresponding to the location based on the multiple data verification models to obtain multiple verification results for the historical refining data corresponding to the location; and determining the data verification model corresponding to the optimal verification result among the multiple verification results as the data verification model for the application of the location.

[0057] For example, point A of the target refining unit corresponds to refining data at the first, second, and third time points. Data verification parameters are matched for the refining data at the first time point, the second time point, and the third time point, resulting in three data verification parameters for the historical refining data corresponding to point A. Based on these three data verification parameters, three data verification models are constructed for point A: a first data verification model, a second data verification model, and a third data verification model. Based on these three data verification models, the historical refining data corresponding to point A is verified, resulting in three verification results. The data verification model corresponding to the optimal verification result among the three is determined as the data verification model for the application at that point. It should be noted that the above example of point A corresponding to the first, second, and third time points is merely for illustrative purposes; in actual applications, the target refining unit's points correspond to refining data at multiple time points.

[0058] In this embodiment, corresponding data verification parameters are matched to refining data at different times, and multiple data verification models are constructed. By evaluating and selecting multiple data verification models, the optimal data verification model is determined as the data verification model for application. This ensures that the determined data verification model for application can fully cover various operating states of the refining unit, thereby further improving the effectiveness and reliability of data verification.

[0059] Figure 2 Another flowchart illustrating the data processing method provided for an exemplary embodiment of this application. For example... Figure 2 As shown, the data processing method in this application embodiment includes the following steps:

[0060] S201. Obtain historical refining data of the target refining unit.

[0061] For example, Figure 3 This is a schematic diagram of the data processing architecture provided for an exemplary embodiment of this application. Correspondingly, refer to... Figure 3 The system retrieves historical refining data of the target refining unit from the database of the library module using the data retrieval function in the data processing module. This historical refining data includes MES data, LIMS data, and user input data corresponding to specific locations, used for production forecasting or algorithm optimization. Before storing the historical refining data in the library module's database, preprocessing operations are performed on the historical refining data. Optionally, preprocessing operations include at least one of the following: data classification, data cleaning, data transformation, data normalization and standardization, and data labeling.

[0062] S202. Based on historical refining data, establish a data verification model for each location of the target refining unit.

[0063] like Figure 3 As shown, the data processing module includes modules for data retrieval, verification configuration, data analysis, point anomaly detection configuration, and data verification; the data flow module includes modules for importing data, MES data, LIMS data, and real-time data; the library module includes modules for logs, databases, and drivers; and the modeling module includes modules for modeling configuration, data generation, and point modeling time delay configuration. For example, through... Figure 3 The data processing module's data analysis function pre-defines the correspondence between various points of the target refining unit and data verification parameters. Based on the historical refining data corresponding to each point, it matches the corresponding data verification parameters. These parameters include the data verification call method and parameters. The data verification call method is deployed on the algorithm platform's server and is invoked in real-time during the implementation of the data processing method. The data verification call method includes at least one or more of the following: local anomaly factor, maximum normalized residual, box plot, Gaussian distribution, mean difference, density distribution, and outlier algorithm, in any combination. Furthermore, for the refining data corresponding to the points of the target refining unit at different times, it matches the data verification parameters corresponding to the refining data at each time point. The system obtains multiple data verification parameters for the historical refining data corresponding to the location. Based on these parameters, it constructs multiple data verification models for the location using a modeling module. Using these models, it calls a data verification module to verify the historical refining data for the location, obtaining multiple verification results. The system then determines the data verification model corresponding to the optimal verification result among these results as the applicable data verification model for the location. For refining data with normal verification results, it directly stores the data as offline data for model training. For refining data with abnormal verification results, it performs anomaly removal processing and stores the processed data as offline data for model training.

[0064] S203. Obtain real-time refining data of the target refining unit.

[0065] For example, by Figure 3 The data retrieval function in the data processing module calls the data flow module to obtain real-time values ​​of MES and LIMS data, which are to be used for production prediction or algorithm optimization of the target refining unit.

[0066] S204. Input the refining data into the data verification model corresponding to the location to obtain the data verification results for the refining data. The data verification results reflect whether there are any abnormalities in the refining data.

[0067] For example, the data verification model corresponding to each point is obtained through the data verification function of the data processing module. The data verification model is used to perform real-time verification on the data type of the real-time refining data at each point of the target refining unit and whether the data exceeds the normal range. Among them, the data type detection includes whether it is a string format and whether it is a numerical data, etc.

[0068] S205. Determine if there are any abnormalities in the data verification results.

[0069] If not, proceed to S206;

[0070] If so, execute S207.

[0071] S206. Input the refining data into the application model to obtain the first production plan corresponding to the refining data.

[0072] Correspondingly, the refining data is input into application models such as production forecasting or algorithm optimization to obtain the production plan corresponding to the refining data.

[0073] S207. Perform anomaly removal processing on the refining data corresponding to the location to obtain the processed data.

[0074] Correspondingly, for refining data with abnormal verification results, real-time anomaly removal processing is performed on the abnormal real-time refining data. Specifically, through... Figure 3 The various functions of the modeling module involve data processing related to the data format required for data verification calls, including data format conversion, calculation of individual data indicators, and data unit conversion. Combined with actual production conditions, if real-time refining data verification shows anomalies, the data verification model provides the verification results in real time and performs anomaly removal. Ultimately, it generates data for production prediction or algorithm optimization operations for the target refining unit.

[0075] S208. Input the processed data into the application model to obtain the second production plan corresponding to the refining data.

[0076] For example, the processed data can be input into application models such as production forecasting or algorithm optimization, or stored as offline data for model training.

[0077] In summary, this application has at least the following advantages:

[0078] First, by using data verification models corresponding to various points within the target refining unit, the refining data at each point can be verified more accurately, ensuring the accuracy and reliability of the verification results. Furthermore, because the refining data at each point can be verified in real time and automatically, the verification results can be obtained in real time. This verified data can then be used for production forecasting or algorithm optimization, and the automated verification method significantly improves the efficiency of refining data verification while reducing labor costs, thereby enhancing the production management level and efficiency of refining enterprises.

[0079] Second, by acquiring historical refining data corresponding to the points, and based on the correspondence between each point of the target refining unit and the data verification parameters, it can be ensured that the construction of the data verification model is based on real historical data and process requirements, avoiding setting the verification threshold of the points too broadly, thereby improving the accuracy of the data verification results and reducing false alarms and missed alarms.

[0080] Third, for different locations, matching and corresponding data verification parameters are used, and a data verification model is built based on the data verification parameters under the corresponding production conditions. This allows the data verification model to be flexibly adjusted according to different production conditions, which can further improve the accuracy and reliability of data verification results, enhance the adaptability and flexibility of the model, and provide a foundation for data analysis and mining, thereby ensuring the safe, stable and efficient operation of the refining and chemical plant.

[0081] Fourth, by matching corresponding data verification parameters to refining data at different times and constructing multiple data verification models, the optimal data verification model is determined as the data verification model for application by evaluating and selecting multiple data verification models. This ensures that the determined data verification model for application can fully cover various operating states of the refining unit, thereby further improving the effectiveness and reliability of data verification.

[0082] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0083] Figure 4 This is a schematic diagram of a data processing apparatus provided for an exemplary embodiment of this application. Figure 4 As shown, the data processing device 40 includes an acquisition module 41 and a processing module 42, wherein:

[0084] The acquisition module 41 is used to acquire refining data of the target refining unit. The refining data is obtained through data acquisition devices installed at the locations of the target refining unit.

[0085] The processing module 42 is used to input the refining data into the data verification model corresponding to the preset location to obtain the data verification result for the refining data. The data verification result reflects whether there is any abnormality in the refining data. The data verification model is a personalized verification model established based on the historical refining data of the location under different production conditions.

[0086] In one possible implementation, the processing module 42 may be specifically used to: input the refining data into the application model when the data verification result indicates that there are no anomalies in the refining data, to obtain a first production plan corresponding to the refining data; when the data verification result indicates that there are anomalies in the refining data, perform anomaly removal processing on the refining data corresponding to the location to obtain processed data, wherein the anomaly removal data processing includes at least one of time lag alignment, data format conversion, data index calculation, data unit conversion, discarding outliers, and replacing outliers; and input the processed data into the application model to obtain a second production plan corresponding to the refining data.

[0087] In one possible implementation, the data verification model is constructed as follows: acquiring historical refining data corresponding to the location; based on the pre-defined correspondence between each location of the target refining unit and the data verification parameters, matching the data verification parameters corresponding to the location according to the historical refining data, the data verification parameters including the method and parameters for data verification calls; and determining the data verification model corresponding to the location based on the data verification parameters corresponding to the location.

[0088] In one possible implementation, the data verification call method includes at least one or more of the following: local outlier factor, maximum normalized residual, box plot, Gaussian distribution, mean difference, density distribution, and outlier algorithm, or any combination thereof.

[0089] In one possible implementation, the data verification parameters include data verification parameters under different production conditions. The processing module 42 can also be used to: determine the historical refining data corresponding to the points of the target refining unit based on the preset sequence of each point of the target refining unit; and match the data verification parameters corresponding to the production conditions of the points according to the production conditions of the historical refining data corresponding to the points.

[0090] In one possible implementation, the processing module 42 can also be used to: match the data verification parameters corresponding to the refining data at different times for the location of the target refining unit, and obtain multiple data verification parameters for the historical refining data corresponding to the location; construct multiple data verification models corresponding to the location based on the multiple data verification parameters; verify the historical refining data corresponding to the location based on the multiple data verification models, and obtain multiple verification results for the historical refining data corresponding to the location; and determine the data verification model corresponding to the optimal verification result among the multiple verification results as the data verification model for the application corresponding to the location.

[0091] The data processing apparatus provided in this application embodiment can execute the technical solution shown in the above data processing method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0092] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, the prediction module can be a separate processing element, or it can be integrated into a chip in the above device. Alternatively, it can be stored as program code in the memory of the above device, and its function can be called and executed by a processing element. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0093] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a System-On-a-Chip (SOC).

[0094] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Video Discs, DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0095] Figure 5 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application. For example... Figure 5 As shown, the electronic device 50 in this embodiment includes:

[0096] At least one processor 51; and a memory 52 communicatively connected to said at least one processor;

[0097] The memory 52 stores instructions that can be executed by the at least one processor 51 to cause the electronic device to perform the method as described in any of the above embodiments.

[0098] Alternatively, the memory 52 can be either standalone or integrated with the processor 51.

[0099] The memory 52 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0100] The processor 51 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. Specifically, when implementing the data processing method described in the foregoing method embodiments, the electronic device may be, for example, an electronic device with processing capabilities such as a server.

[0101] Optionally, the electronic device may also include a communication interface 53. In specific implementations, if the communication interface 53, memory 52, and processor 51 are implemented independently, they can be interconnected via a bus to complete communication. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc., but this does not imply that there is only one bus or one type of bus.

[0102] Optionally, in a specific implementation, if the communication interface 53, memory 52 and processor 51 are integrated on a single chip, then the communication interface 53, memory 52 and processor 51 can communicate through an internal interface.

[0103] The implementation principle and technical effects of the electronic device provided in this embodiment can be found in the foregoing embodiments, and will not be repeated here.

[0104] This application also provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are executed, they are used to implement the method steps as described in the above method embodiments. The specific implementation methods and technical effects are similar and will not be repeated here.

[0105] The aforementioned computer-readable storage media can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0106] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in a data processing device.

[0107] This application also provides a computer program product, including a computer program, which, when executed, implements the method steps as described in the above method embodiments. The specific implementation and technical effects are similar and will not be repeated here.

[0108] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0109] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A data processing method, characterized in that, include: The refining data of the target refining unit is obtained through data acquisition devices installed at the locations of the target refining unit. The refining data is input into a preset data verification model corresponding to the location to obtain a data verification result for the refining data. The data verification result reflects whether there is any abnormality in the refining data. The data verification model is a personalized verification model established based on historical refining data of the location under different production conditions.

2. The data processing method according to claim 1, characterized in that, Also includes: If the data verification result reflects that there is no abnormality in the refining data, then the refining data is input into the application model to obtain the first production plan corresponding to the refining data; If the data verification result reflects that there is an anomaly in the refining data, then the refining data corresponding to the point is subjected to anomaly removal processing to obtain processed data. The anomaly removal data processing includes at least one of time lag alignment, data format conversion, data index calculation, data unit conversion, discarding outliers, and replacing outliers; and the processed data is input into the application model to obtain the second production plan corresponding to the refining data.

3. The data processing method according to claim 1 or 2, characterized in that, The data verification model is constructed in the following way: Obtain the historical refining data corresponding to the location; Based on the pre-defined correspondence between each point of the target refining unit and the data verification parameters, the data verification parameters corresponding to the points are matched according to the historical refining data corresponding to the points. The data verification parameters include the method and parameters for data verification invocation. Based on the data verification parameters corresponding to the location, the data verification model corresponding to the location is determined.

4. The data processing method according to claim 3, characterized in that, The data verification call method includes at least one or more of the following: local anomaly factor, maximum normalized residual, box plot, Gaussian distribution, mean difference, density distribution, and outlier algorithm, or any combination thereof.

5. The data processing method according to claim 3, characterized in that, The data verification parameters include data verification parameters under different production conditions. The process involves matching the data verification parameters corresponding to each point in the target refining unit based on a preset correspondence between the points and the data verification parameters, and according to the historical refining data corresponding to each point. Based on the preset sequence of each location of the target refining unit, the historical refining data corresponding to the location of the target refining unit is determined. Based on the production status of the historical refining data corresponding to the location, match the data verification parameters corresponding to the production status of the location.

6. The data processing method according to claim 3, characterized in that, The step of determining the target data verification model corresponding to the point based on the data verification parameters corresponding to the point includes: For the refining data at different times corresponding to the location of the target refining unit, the data verification parameters corresponding to the refining data at each time are matched to obtain multiple data verification parameters for the historical refining data corresponding to the location. Based on the multiple data verification parameters, construct multiple data verification models corresponding to the points; Based on multiple data verification models, the historical refining data corresponding to the location is verified to obtain multiple verification results of the historical refining data corresponding to the location. The data verification model corresponding to the optimal verification result among the multiple verification results is determined as the data verification model for the application corresponding to the point.

7. A data processing apparatus, characterized in that, include: The acquisition module is used to acquire refining data of the target refining unit, which is obtained through data acquisition devices installed at the locations of the target refining unit. The processing module is used to input the refining data into a preset data verification model corresponding to the location, and obtain a data verification result for the refining data. The data verification result reflects whether there is any abnormality in the refining data. The data verification model is a personalized verification model established based on historical refining data of the location under different production conditions.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory is used to store computer-executed instructions; The processor is configured to execute the computer execution instructions to implement the data processing method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the data processing method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed, it implements the data processing method as described in any one of claims 1 to 6.

Images