Data processing method of chemical device, electronic equipment and storage medium
By classifying, filtering, supplementing, and processing abnormal data in the DCS data of chemical plants, the problems of insufficient data accuracy and reliability in traditional methods have been solved, thereby improving data quality and increasing the accuracy of process simulation calculations.
Patent Information
- Application Number
- CN202410530369.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-29
- Publication Date
- 2025-10-31
AI Technical Summary
Traditional process simulation methods require high accuracy of chemical plant data, involve large amounts of computation, and require high levels of professional knowledge from operators. Furthermore, data acquisition is prone to problems such as missing data, anomalies, and duplication, which affect the accuracy and reliability of the simulation data.
By classifying, filtering, supplementing missing values, identifying and removing abnormal data from the initial DCS data of the chemical plant, wavelet decomposition and transformation algorithm is used to process abnormal data, and material conservation algorithm is used to adjust flow data to ensure data quality.
It improves the accuracy and reliability of data, reduces the impact of on-site equipment status and human operation on data, and enhances the accuracy of process simulation calculations.
Smart Images
Figure CN120873704A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of chemical process simulation technology, specifically to a data processing method, electronic equipment, storage medium, and computer equipment for a chemical plant. Background Technology
[0002] In the field of chemical engineering, process simulation is widely used in process design, optimization, reducing trial-and-error costs, and assessing safety. Furthermore, it can guide energy-saving optimization, production increase, and consumption reduction in existing plants. Especially under the major trends of intelligent, digital, and clean production, the application of real-time, full-process simulation is of great significance to the production of chemical plants.
[0003] The first step in process simulation is ensuring the accuracy of data from the chemical plant. The accuracy of the plant data directly impacts model optimization. However, traditional process simulation methods may have limitations, such as high requirements for data accuracy, large computational load, and high demands on the professional knowledge of operators. Furthermore, due to factors such as equipment failure, measurement errors, instrument malfunctions, and abnormal situations, data acquisition may result in missing data, data anomalies, and data duplication, thus affecting the accuracy and reliability of the simulation data. Summary of the Invention
[0004] The purpose of this application is to provide a data processing method, electronic device, storage medium, and computer device for improving data quality in chemical plants.
[0005] To achieve the above objectives, embodiments of this application provide a data processing method for a chemical plant, the method comprising:
[0006] Acquire initial DCS data for the chemical plant;
[0007] The initial DCS data is classified by tag number to obtain the DCS data to be processed corresponding to each tag number type;
[0008] For each type of DCS data to be processed, the DCS data to be processed is filtered to obtain the first dataset;
[0009] Missing values in each first dataset are padded according to the first preset rule to obtain multiple second datasets;
[0010] Identify outlier and non-outlier data values within each second dataset;
[0011] For each second dataset, outlier data values are removed, and non-outlier data values are processed according to a second preset rule to obtain target DCS data corresponding to each tag type.
[0012] In this embodiment of the application, filtering the DCS data to be processed for each type of DCS data to obtain a first dataset includes: identifying duplicate records in the DCS data to be processed for each type of DCS data; retaining the first record of the duplicate records and removing other data except for the first record to obtain the first dataset.
[0013] In this embodiment of the application, filling missing values in each first dataset to obtain multiple second datasets according to a first preset rule includes: selecting the preceding or following non-missing value of the missing value as imputation data to fill the missing value; or determining a first average of the preceding and following non-missing values of the missing value and using the first average as imputation data to fill the missing value; or determining a second average of a preset number of non-missing values before and a preset number of non-missing values after the missing value and using the second average as imputation data to fill the missing value.
[0014] In this embodiment of the application, identifying anomalous and non-nominal data values within each second dataset includes: for each second dataset, using a wavelet decomposition transform algorithm to decompose the second dataset to obtain approximate components and detail components; for each second dataset, determining the detail components as anomalous data values within the second dataset, and determining the approximate components as non-nominal data values within the second dataset.
[0015] In this embodiment of the application, for each second dataset, abnormal data values are removed from the second dataset, and non-abnormal data values are processed according to a second preset rule to obtain target DCS data corresponding to each tag type. This includes: for each second dataset, restoring non-abnormal data values according to a wavelet decomposition transform algorithm to obtain target DCS data corresponding to each tag type.
[0016] In this embodiment of the application, the chemical plant includes a liquid flow meter and a gas flow meter, and the tag type includes mass flow rate. The method further includes: after obtaining the target DCS data corresponding to each tag type, evaluating the target DCS data of mass flow rate based on the material conservation algorithm to determine whether the target DCS data of mass flow rate is accurate; if the target DCS data of mass flow rate is inaccurate, acquiring the actual flow data collected by the liquid flow meter and the gas flow meter, and adjusting the target DCS data of mass flow rate according to the actual flow data.
[0017] In this embodiment of the application, the mass flow rate includes liquid phase flow rate and gas phase flow rate. The method further includes: before evaluating the target DCS data of the mass flow rate based on the material conservation algorithm, converting the unit of the target DCS data corresponding to the gas phase flow rate to the same unit of measurement as the unit of the target DCS data corresponding to the liquid phase flow rate.
[0018] A second aspect of this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;
[0019] The memory stores the instructions that the computer executes;
[0020] The processor executes computer execution instructions stored in memory to implement the data processing method of the chemical plant as described in any of the above embodiments.
[0021] A third aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform a data processing method of a chemical apparatus according to any of the above embodiments.
[0022] A fourth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements a data processing method for a chemical apparatus according to any of the above embodiments.
[0023] By employing the aforementioned technical solutions, the initial DCS data of the chemical plant is classified, cleaned, filled, and abnormal data is processed, thereby improving data quality and reducing the impact of on-site equipment status, human operation, and feed fluctuations on data accuracy. This ensures the accuracy, reliability, and effectiveness of the data, providing data quality assurance for real-time chemical process simulation calculations and improving the accuracy of subsequent process simulation calculations.
[0024] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description
[0025] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of the invention, but do not constitute a limitation on the embodiments of the invention. In the drawings:
[0026] Figure 1 A schematic flowchart illustrating a data processing method for a chemical apparatus according to an embodiment of this application is shown.
[0027] Figure 2 This illustration schematically shows a first dataset corresponding to a tag type of mass flow rate according to an embodiment of this application;
[0028] Figure 3 This illustration schematically shows a second dataset corresponding to a tag type of mass flow rate according to an embodiment of this application;
[0029] Figure 4This illustration schematically shows the raw data of a second dataset corresponding to a tag type of mass flow rate according to an embodiment of this application;
[0030] Figure 5 This illustration schematically shows the denoised data of mass flow rate according to an embodiment of this application;
[0031] Figure 6 A schematic diagram of a chemical plant according to an embodiment of this application is shown.
[0032] Figure 7 This illustration schematically shows a target DCS data corresponding to the mass flow rate according to an embodiment of this application;
[0033] Figure 8 This illustration schematically shows the adjusted target DCS data corresponding to the mass flow rate according to an embodiment of this application;
[0034] Figure 9 This schematic diagram illustrates a structural block diagram of an electronic device according to an embodiment of the present application;
[0035] Figure 10 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation
[0036] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0037] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.
[0038] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.
[0039] The acquisition, transmission, storage, use, and processing of data in this application comply with relevant national laws and regulations. Furthermore, it should be noted that existing industry solutions such as software, components, and models may be mentioned in the embodiments of this application. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.
[0040] Figure 1 A schematic flowchart illustrating a data processing method for a chemical apparatus according to an embodiment of this application is shown. Figure 1 As shown in one embodiment of this application, a data processing method for a chemical plant is provided, comprising the following steps:
[0041] Step 101: Obtain the initial DCS data of the chemical plant;
[0042] Step 102: Classify the initial DCS data by tag number to obtain the DCS data to be processed corresponding to each tag number type;
[0043] Step 103: For each type of DCS data to be processed, filter the DCS data to be processed to obtain the first dataset;
[0044] Step 104: Fill in the missing values in each first dataset according to the first preset rule to obtain multiple second datasets;
[0045] Step 105: Identify anomalous and non-anomalous data values within each second dataset;
[0046] Step 106: For each second dataset, remove the abnormal data values in the second dataset and process the non-abnormal data values according to the second preset rule to obtain the target DCS data corresponding to each tag type.
[0047] The processor can acquire initial DCS data from the chemical plant. This DCS data can be production control data and sensor data from a real-time database within the plant. After acquiring the initial DCS data, the processor can classify it by tag number. Tag number types can include pressure, temperature, mass flow rate, and liquid level, etc. After classifying the initial DCS data by tag number, the processor can obtain the DCS data to be processed corresponding to each tag number type, as shown in Table 1.
[0048] Table 1
[0049]
[0050]
[0051] For each tag type of DCS data to be processed, the processor can filter the data to obtain a first dataset. Then, according to a first preset rule, missing values in the filtered first dataset are supplemented to obtain a second dataset. For each tag type of the second dataset, the processor can identify anomalous and non-anomalous data values. The processor can remove the identified anomalous data values and process the non-anomalous data values according to the second preset rule, thereby obtaining the target DCS data corresponding to each tag type. By processing the initial DCS data obtained from the chemical plant, the quality of the DCS data is improved, providing high-quality data for process simulation of the chemical plant.
[0052] In one embodiment, filtering the DCS data to be processed for each type of DCS data to obtain a first dataset includes: identifying duplicate records in the DCS data to be processed for each type of DCS data; retaining the first record of the duplicate records and removing all other data except the first record, to obtain the first dataset. The processor can perform filtering on the DCS data to be processed for each tag type. The processor can identify duplicate records in the DCS data to be processed. For duplicate records, the processor can retain the first record of the duplicate records and remove the remaining duplicate records, thereby obtaining the first dataset corresponding to each tag type. Alternatively, the processor can retain any one of the duplicate records and remove the rest.
[0053] In one embodiment, imputing missing values in each first dataset according to a first preset rule to obtain multiple second datasets includes: selecting the preceding or following non-missing value of the missing value as imputation data to impute the missing value; or determining a first average of the preceding and following non-missing values of the missing value and using the first average as imputation data to impute the missing value; or determining a second average of a preset number of non-missing values preceding and a preset number of non-missing values following the missing value and using the second average as imputation data to impute the missing value.
[0054] The processor filters duplicate records in the DCS data to be processed for each tag type to obtain a first dataset for each tag type. For each first dataset, the processor can identify missing values and fill them in according to a first preset rule. The processor can select the preceding or following non-missing value as the imputation data, or it can determine the first average of the preceding and following non-missing values and use this average as the imputation data. For example, if a missing value is present, and both the preceding and following non-missing values are non-missing values, and the difference between them is within a preset difference range, the processor can select either the preceding or following non-missing value as the imputation data. If the processor determines that the difference between the preceding and following non-missing values is outside the preset difference range, it can determine the first average of the preceding and following non-missing values as the imputation data. The processor can also determine a second average of a preset number of non-missing values before and a preset number of non-missing values after the missing value, and use this second average as imputation data to fill in the missing value. For example, when multiple missing values appear consecutively, the processor can determine the second average of the multiple non-missing values before and after the missing value as the imputation data. Figure 2 The tag type shown is the first dataset corresponding to mass flow rate, which contains multiple missing values. The processor can process the data according to the above technical solution. Figure 2 Missing values in the data are filled in to obtain the following result: Figure 3 The second dataset corresponding to the mass flow rate shown.
[0055] In one embodiment, identifying anomalous and non-anomalous data values within each second dataset includes: for each second dataset, decomposing the second dataset using a wavelet decomposition transform algorithm to obtain approximate components and detail components; for each second dataset, determining the detail components as anomalous data values within the second dataset, and determining the approximate components as non-anomalous data values within the second dataset.
[0056] In one embodiment, for each second dataset, outlier data values are removed and non-outlier data values are processed according to a second preset rule to obtain target DCS data corresponding to each tag type. This includes: for each second dataset, restoring non-outlier data values according to a wavelet decomposition transform algorithm to obtain target DCS data corresponding to each tag type.
[0057] The processor obtains a second dataset corresponding to each tag type by filtering and supplementing the DCS data to be processed for each tag type. The processor uses time as the x-axis and the second dataset corresponding to each tag type as the y-axis, and employs a wavelet decomposition algorithm to decompose the second dataset, thereby obtaining approximate and detail components. The processor identifies detail components as outlier values in the second dataset and approximate components as non-outlier values. The processor removes outlier values from the second dataset, i.e., removes detail components, and reconstructs the remaining non-outlier values (approximate components) using wavelet decomposition to obtain the target DCS data corresponding to each tag type. For detail components, in addition to direct removal, the processor can also filter out detail components based on a user-defined preset threshold to retain valuable detail components. The second dataset after removing outlier data is then reconstructed to obtain the target DCS data corresponding to each tag type. For example... Figure 4 The tag type shown is the raw data of the second dataset corresponding to the mass flow rate. The processor uses the above technical solution to... Figure 4 After processing the outliers in the original data of the second dataset shown, we can obtain the following: Figure 5 The denoised mass flow data shown is the target DCS data for mass flow, compared to... Figure 4 , Figure 5 The data after denoising is shown to have reduced overall fluctuations and is smoother, improving data quality and accuracy and reducing data errors.
[0058] In one embodiment, the chemical plant includes a liquid flow meter and a gas flow meter, and the tag type includes mass flow rate. The method further includes: after obtaining target DCS data corresponding to each tag type, evaluating the target DCS data of mass flow rate based on a material conservation algorithm to determine whether the target DCS data of mass flow rate is accurate; if the target DCS data of mass flow rate is inaccurate, acquiring the actual flow data collected by the liquid flow meter and the gas flow meter, and adjusting the target DCS data of mass flow rate according to the actual flow data.
[0059] In one embodiment, the mass flow rate includes liquid flow rate and gas flow rate, and the method further includes: converting the units of the target DCS data corresponding to the gas flow rate to the same units of the target DCS data corresponding to the liquid flow rate before evaluating the target DCS data of the mass flow rate based on the material conservation algorithm.
[0060] After obtaining the target DCS data corresponding to each tag type, the processor needs to unify the units of the target DCS data corresponding to the tag type "mass flow rate" since mass flow rate includes both liquid and gaseous flow rates, which have different units of measurement. The processor can convert the units of the target DCS data corresponding to gaseous flow rate to the same units as those corresponding to liquid flow rate. After unifying the units of the target DCS data corresponding to mass flow rate, the processor can evaluate the target DCS data based on a material conservation algorithm. The material conservation algorithm is: Total Input Material Quantity = Total Output Material Quantity + Total Material Loss + Total Material Accumulation. The total material loss and total material accumulation can be set according to user input. The processor can then determine the accuracy of the total input and total output material data in the target DCS data corresponding to mass flow rate based on the material conservation algorithm.
[0061] Chemical plants may include liquid flow meters and gas flow meters. The processor can collect accurate actual flow data of the chemical plant through the liquid flow meters and gas flow meters. If the processor determines that the total input material data and / or total output material data in the target DCS data corresponding to the mass flow rate are inaccurate, the processor can adjust the target DCS data of the mass flow rate based on the accurate actual flow data collected by the liquid flow meters and gas flow meters to obtain accurate target DCS data corresponding to the mass flow rate tag type, thereby improving the accuracy of the data.
[0062] For example Figure 6The schematic diagram of the chemical plant shown includes a stripping tower T1101, a butane removal tower T1203, a pentane oil tower T1205, reforming reactors R1, R2, R3, and R4, separating tanks V1201 and V1202, a re-contact tank V1901, a hydrogen dechlorination tank V1902, a product oil hydrotreating reactor, a pentane removal tower T1201, a heavy oil removal tower T1202, a heptane removal tower T1503, and a xylene tower T315. Taking the heavy oil removal tower T1202 as an example, assume that the total feed data in the target DCS data for the mass flow rate of T1202 is T1202_FEED, and the total discharge data is T1202_OUT. According to the material conservation algorithm, T1202_FEED = T1202_OUT + total material loss + total material accumulation. The processor can evaluate the total feed data T1202_FEED and total discharge data T1202_OUT of the target DCS data for mass flow rate based on this algorithm. If the material conservation equation holds, the processor can determine that the target DCS data for mass flow rate is accurate; if the equation does not hold, the processor can determine that the target DCS data for mass flow rate is inaccurate. The processor can acquire data from liquid flow meters and gas flow meters, for example... Figure 6 The chemical plant shown is equipped with liquid flow meters and gas flow meters (not shown in the figure). The liquid flow meters can detect the top oil of T1202, T1503, T315, and T315 bottom oil, while the gas flow meters can detect the gas flow rates of T1202, T1503, and T315. The processor can adjust inaccurate target DCS data for mass flow rates based on the accurate actual flow rates collected by the liquid and gas flow meters. Figure 6 As shown, T1202_OUT_SUM = T1202_bot_Liq + T1202_top_Liq + T1202_top_Vap, where T1202_OUT_SUM is the actual total output flow rate of T1202, T1202_bot_Liq is the bottom oil flow rate of T1202, T1202_top_Liq is the top oil flow rate of T1202, and T1202_top_Vap is the gas phase flow rate of T1202. The actual flow rate data for T1202_bot_Liq (bottom oil flow rate of T1202) cannot be obtained from the liquid phase flow meter; the processor can determine T1202_bot_Liq (bottom oil flow rate of T1202) using other actual flow rate data. According to... Figure 6As shown, T1202_bot_Liq = T1503_top_Vap + T1503_top_Liq + T315_top_Vap + T315_top_Liq + T315_bot_Liq, where T1503_top_Vap is the gas phase flow rate of T1503, T1503_top_Liq is the top oil flow rate of T1503, T315_top_Vap is the gas phase flow rate of T315, T315_top_Liq is the top oil flow rate of T315, and T315_bot_Liq is the bottom oil flow rate of T315. In other words, after adjusting the total discharge data in the target DCS data for mass flow rate from the liquid and gas flow meters, the processor can obtain: T1202_OUT_SUM = T1503_top_Vap + T1503_top_Liq + T315_top_Vap + T315_top_Liq + T315_bot_Liq + T1202_top_Liq + T1202_top_Vap. Based on the material conservation algorithm, the processor can determine the adjusted total feed data T1202_FEED_SUM based on the adjusted total discharge data T1202_OUT_SUM, where T1202_FEED_SUM = T1202_OUT_SUM + total material loss + total material accumulation. For example... Figure 7 The total feed data T1202_FEED and total discharge data T1202_OUT in the target DCS data of the mass flow rate shown have a large discrepancy. Therefore, this data cannot be used directly. The processor needs to use the actual flow data collected by the liquid flow meter and the gas flow meter, and process it according to the technical solution shown in the above embodiment to obtain the adjusted total discharge data T1202_OUT_SUM. Assuming that the user sets the sum of material loss and the sum of material accumulation to 0, according to the material conservation algorithm, the adjusted total feed data T1202_FEED_SUM is equal to the total discharge data T1202_OUT_SUM. The adjusted target DCS data of T1202 is as follows. Figure 8 As shown.
[0063] In one embodiment, such as Figure 9 As shown, an electronic device 900 is provided, including: a processor 901 and a memory 902 communicatively connected to the processor 901; the memory 902 stores computer-executable instructions; the processor 901 executes the computer-executable instructions stored in the memory 902 to implement the data processing method of the chemical apparatus as described in any of the above embodiments.
[0064] The above technical solution improves data quality by classifying, cleaning, filling, processing abnormal data, and adjusting deviation values of the initial DCS data of the chemical plant. It reduces the impact of on-site equipment status, human operation, and feed fluctuations on data accuracy, ensuring the accuracy, reliability, and effectiveness of the data. This provides data quality assurance for real-time chemical process simulation calculations and improves the accuracy of process simulation calculations.
[0065] The memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip. Those skilled in the art will understand that... Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0066] In one embodiment, a machine-readable storage medium is provided that stores instructions that, when executed by a processor, cause the processor to perform a data processing method of a chemical apparatus according to any of the above embodiments.
[0067] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements a data processing method for a chemical apparatus according to any of the above embodiments.
[0068] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The database of the computer device stores relevant data during the operation of the chemical plant. The network interface A02 of the computer device is used for communication with external terminals via a network connection. When the computer program B02 is executed by the processor A01, it implements a data processing method for a chemical plant.
[0069] This application provides an apparatus including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring initial DCS data of a chemical plant; classifying the initial DCS data by tag number to obtain DCS data to be processed corresponding to each tag number type; filtering the DCS data to be processed for each type of DCS data to obtain a first dataset; supplementing missing values in each first dataset according to a first preset rule to obtain multiple second datasets; identifying abnormal and non-abnormal data values in each second dataset; for each second dataset, removing abnormal data values and processing non-abnormal data values according to a second preset rule to obtain target DCS data corresponding to each tag number type.
[0070] In one embodiment, filtering the DCS data to be processed for each type of DCS data to obtain a first dataset includes: identifying duplicate records in the DCS data to be processed for each type of DCS data; retaining the first record of the duplicate records and removing other data except for the first record to obtain the first dataset.
[0071] In one embodiment, imputing missing values in each first dataset according to a first preset rule to obtain multiple second datasets includes: selecting the preceding or following non-missing value of the missing value as imputation data to impute the missing value; or determining a first average of the preceding and following non-missing values of the missing value and using the first average as imputation data to impute the missing value; or determining a second average of a preset number of non-missing values preceding and a preset number of non-missing values following the missing value and using the second average as imputation data to impute the missing value.
[0072] In one embodiment, identifying anomalous and non-anomalous data values within each second dataset includes: for each second dataset, decomposing the second dataset using a wavelet decomposition transform algorithm to obtain approximate components and detail components; for each second dataset, determining the detail components as anomalous data values within the second dataset, and determining the approximate components as non-anomalous data values within the second dataset.
[0073] In one embodiment, for each second dataset, outlier data values are removed and non-outlier data values are processed according to a second preset rule to obtain target DCS data corresponding to each tag type. This includes: for each second dataset, restoring non-outlier data values according to a wavelet decomposition transform algorithm to obtain target DCS data corresponding to each tag type.
[0074] In one embodiment, the chemical plant includes a liquid flow meter and a gas flow meter, and the tag type includes mass flow rate. The method further includes: after obtaining target DCS data corresponding to each tag type, evaluating the target DCS data of mass flow rate based on a material conservation algorithm to determine whether the target DCS data of mass flow rate is accurate; if the target DCS data of mass flow rate is inaccurate, acquiring the actual flow data collected by the liquid flow meter and the gas flow meter, and adjusting the target DCS data of mass flow rate according to the actual flow data.
[0075] In one embodiment, the mass flow rate includes liquid flow rate and gas flow rate, and the method further includes: converting the units of the target DCS data corresponding to the gas flow rate to the same units of the target DCS data corresponding to the liquid flow rate before evaluating the target DCS data of the mass flow rate based on the material conservation algorithm.
[0076] Those skilled in the art will understand that the embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The acquisition, transmission, storage, use, and processing of data in the technical solutions of this application all comply with relevant national laws and regulations. It should be noted that certain software, components, models, and other existing industry solutions may be mentioned in the embodiments of this application. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solutions of this application, and do not imply that the applicant has already used or necessarily used such solutions.
[0077] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0078] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0079] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0080] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0081] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0082] Computer-readable media include both permanent and non-permanent, removable and non-removable media, which can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0083] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0084] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A data processing method for a chemical plant, characterized in that, The method includes: Obtain the initial DCS data of the chemical plant; The initial DCS data is classified by tag number to obtain the DCS data to be processed corresponding to each tag number type; For each type of DCS data to be processed, the DCS data to be processed is filtered to obtain the first dataset; Missing values in each first dataset are padded according to the first preset rule to obtain multiple second datasets; Identify outlier and non-outlier data values within each second dataset; For each second dataset, outlier data values are removed, and non-outlier data values are processed according to a second preset rule to obtain target DCS data corresponding to each tag type.
2. The data processing method for a chemical plant according to claim 1, characterized in that, The step of filtering the DCS data to be processed for each type of DCS data to obtain the first dataset includes: For each type of DCS data to be processed, identify the data in the DCS data that are duplicated; The data recorded for the first time in the repeated records is retained, and all other data except for the first recorded data is removed to obtain the first dataset.
3. The data processing method for a chemical plant according to claim 1, characterized in that, The step of imputing missing values in each first dataset according to a first preset rule to obtain multiple second datasets includes: The missing value is filled by selecting either the preceding or following non-missing value as the imputation data; or Determine the first average of the preceding and following non-missing values of the missing value, and use the first average as imputation data to fill in the missing value; or Determine the second average of a preset number of non-missing values before and a preset number of non-missing values after the missing value, and use the second average as the imputation data to impute the missing value.
4. The data processing method for a chemical plant according to claim 1, characterized in that, The identification of anomalous and non-anomalous data values within each second dataset includes: For each second dataset, the wavelet decomposition transform algorithm is used to decompose the second dataset to obtain approximate components and detail components; For each second dataset, the detail component is determined as the outlier data value within the second dataset, and the approximation component is determined as the non-outlier data value within the second dataset.
5. The data processing method for a chemical plant according to claim 4, characterized in that, For each second dataset, outlier data values are removed, and non-outlier data values are processed according to a second preset rule to obtain target DCS data corresponding to each tag type, including: For each second dataset, the non-abnormal data values are restored according to the wavelet decomposition and transformation algorithm to obtain the target DCS data corresponding to each tag type.
6. The data processing method for a chemical plant according to claim 1, characterized in that, The chemical plant includes a liquid flow meter and a gas flow meter, the tag type includes mass flow rate, and the method further includes: After obtaining the target DCS data corresponding to each tag type, the target DCS data of mass flow rate is evaluated based on the material conservation algorithm to determine whether the target DCS data of mass flow rate is accurate. If the target DCS data for the mass flow rate is inaccurate, the actual flow rate data collected by the liquid flow meter and the gas flow meter is obtained, and the target DCS data for the mass flow rate is adjusted based on the actual flow rate data.
7. The data processing method for a chemical plant according to claim 6, characterized in that, The mass flow rate includes liquid phase flow rate and gas phase flow rate, and the method further includes: Before evaluating the target DCS data of the mass flow rate based on the material conservation algorithm, the units of the target DCS data corresponding to the gas phase flow rate are converted to the same units of measurement as the units of the target DCS data corresponding to the liquid phase flow rate.
8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the data processing method of the chemical plant as described in any one of claims 1 to 7.
9. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, this instruction causes the processor to be configured to perform the data processing method for a chemical plant according to any one of claims 1 to 7.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the data processing method for the chemical plant according to any one of claims 1 to 7.