Yield prediction simulation system and method for chemical process

Abstract

According to one embodiment of the invention, a yield prediction simulation method is disclosed. The yield prediction simulation method for predicting the yield of a second period based on the yield prediction data of the first period of the chemical process comprises the following steps: preprocessing the data of the first period; a step of splitting a first cycle into a plurality of sections on the basis of the preprocessed data; and respectively modeling a yield prediction model according to the plurality of split different sections, and predicting the yield of the second period.

Description

Technical Field

[0001] The present invention relates to a yield prediction of a chemical process, and more specifically, to a yield prediction simulation system and method characterized by the following contents, namely, the yield during a second cycle can be predicted based on process operation data during a first cycle, and label changes can be reflected to simulate the yield prediction. Background Art

[0002] When implementing a series of processes consisting of multiple steps, it is very important to ensure the integrity and reliability of the organic connection of each process. In order to achieve this integrity, it is necessary to develop an effective process management system so that the input values ​​of the main equipment in the process can be used to determine whether each process has abnormalities and diagnose the causes.

[0003] Most of the historical data generated by industrial processes usually have a small number of variables and a linear data structure, so existing algorithms can also obtain sufficient prediction / classification results. However, due to the development of ICT and sensor technology, the field of manufacturing processes has begun to generate data with hundreds or thousands of variables. In particular, modern industrial processes, such as chemical and manufacturing processes, and power plants, have made various efforts to reduce costs and pursue maximum profits while meeting safety, health and environmental regulations, which has led to an increasing size and complexity of data.

[0004] Therefore, it is extremely important to filter out and manage the data that has a greater impact on profit creation from the above complex and large-scale data. For example, in commercial chemical processes, process operating conditions have an impact on catalyst activity in the short / long term, and catalyst activity is directly related to product output. Therefore, it is extremely important to predict catalyst activity from a short / long-term perspective.

[0005] From a short-term perspective, it is necessary to understand the changes in catalyst activity according to process operating conditions, and to increase the output of products by optimizing the operating conditions to improve catalyst activity. From a long-term perspective, in commercial chemical processes using catalysts, the longer the process runs, the less active the catalyst becomes, resulting in reduced activity, so it is necessary to replace it after a period of time. In this way, replacing the catalyst is time-consuming and expensive, so it is important to predict the future catalyst activity and determine the life / replacement timing of the catalyst.

[0006] Therefore, it is necessary to develop new technologies in order to understand the process operating conditions (key factors) that have a great impact on catalyst activity and reflect them, thereby improving the prediction accuracy of catalyst reaction activity.

[0007]

Prior technical literature

[0008] [Patent Literature]

[0009] (Patent Document 1) Korean Patent Publication No. 10-2018-0029114 (20180320)

[0010] (Patent Document 2) Korean Registered Patent No. 10-2222125 (20210303)

[0011] (Patent Document 3) Korean Patent Publication No. 10-2018-0061769 (20180608)

[0012] (Patent Document 4) Japanese Patent Publication No. 2020-166749 (20201008)

[0013] (Patent Document 5) Korean Patent Publication No. 10-2019-0060547 (20190603)

[0014] (Patent Document 6) Japanese Patent Publication No. 2022-520643 (20220331)

[0015] (Patent Document 7) Korean Registered Patent Gazette No. 10-2218287 (20210222) Summary of the invention

[0016] Issues to be solved

[0017] The object of the present invention is to provide a yield prediction simulation system and method, which predicts the yield during the second cycle based on the process operation data during the first cycle, reflects the label change, and simulates the yield prediction.

[0018] The purpose of the present invention is to provide a yield prediction simulation system and method, which divides the first cycle into multiple sections based on the catalyst life and the corresponding yield changes, and implements key factor analysis, yield prediction and label change analysis according to each different section. Based on this, a yield prediction simulation is implemented for the second cycle, and the prediction accuracy is further improved during the entire cycle.

[0019] Another object of the present invention is not limited to the above-mentioned object, and a person skilled in the art can clearly understand another object not mentioned from the following content.

[0020] Problem Solution

[0021] An embodiment of the present invention discloses a yield prediction simulation method, which is a yield prediction simulation method for predicting the yield of a second cycle based on the yield prediction data of the first cycle in a chemical process, and includes the following steps: preprocessing the first cycle data; splitting the first cycle into multiple segments based on the preprocessed data; and modeling the yield prediction model according to the multiple different segments to predict the yield of the second cycle.

[0022] One embodiment of the present invention discloses a computer-readable recording medium having a computer program recorded thereon, for implementing the yield prediction simulation method.

[0023] Effects of the Invention

[0024] The technical effect of the present invention is that the yield during the second cycle can be predicted based on the process operation data during the first cycle, the label change can be reflected, and the yield prediction can be simulated.

[0025] The technical effect of the present invention is that the first cycle period can be divided into multiple sections based on the catalyst life and the corresponding yield changes, and key factor analysis, yield prediction and label change analysis can be implemented according to each different section. Based on this, yield prediction simulation is implemented for the second cycle period to improve the prediction accuracy during the entire cycle.

[0026] Furthermore, the present invention can screen out key factors according to process operating conditions and apply them to prediction models, thereby improving the accuracy of predictions of catalyst activity changes. Through accurate catalyst activity predictions, the sales plan of the product and the timing of catalyst replacement can be determined, and the time and cost required for product production and catalyst replacement can be effectively managed. Changes in catalyst activity can be grasped according to process operating conditions, and catalyst activity can be improved and product output can be increased by optimizing operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic block diagram of a yield prediction simulation system according to an embodiment of the present invention.

[0028] Figure 2 It is a schematic flow chart of the yield prediction simulation method described in one embodiment.

[0029] Figure 3 It is a schematic flow chart of a data preprocessing method according to an embodiment.

[0030] Figure 4 It is a schematic flow chart of a segment analysis method described in an embodiment.

[0031] Figures 5 to 10 1 is a schematic diagram of a segment analysis process according to an embodiment.

[0032] Fig.11 and Fig.12 This is a schematic diagram of a data realization method described in an embodiment.

[0033] Figures 13 to 15 It is a schematic diagram of a method for reflecting catalyst aging factors described in an embodiment.

[0034] Fig.16 It is a schematic diagram of the yield prediction results described in an embodiment.

[0035] Fig.17 The figure is a schematic diagram of a user interface (UI) for analyzing tag variation according to an embodiment.

[0036] Fig.18 It is a schematic diagram of the yield prediction simulation results described in an embodiment.

[0037] * Reference Numbers *

[0038] 100: Yield prediction simulation system 110: Data preprocessing unit

[0039] 120: Segment Analysis Unit 130: Data Realization Processing Unit

[0040] 140: Aging Factor Analysis Department 150: Key Factor Analysis Department

[0041] 160: Yield prediction unit 170: Label change analysis unit

[0042] 180: Yield prediction simulation device 200: Data storage unit DETAILED DESCRIPTION

[0043] [Preferred form of the embodiment of the invention]

[0044] According to one embodiment of the present invention, a yield prediction simulation method is disclosed, which is a yield prediction simulation method for predicting the yield of a second cycle based on the yield prediction data of the first cycle in a chemical process, and includes the following steps: preprocessing the first cycle data; splitting the first cycle into multiple segments based on the preprocessed data; and modeling the yield prediction model according to the multiple segments that have been split, respectively, to predict the yield of the second cycle. [Specific implementation method]

[0046] The above-mentioned several objects, other several objects, several features and several advantages of the present invention can be easily understood through the following preferred embodiments related to the accompanying drawings. However, the present invention is not limited to the embodiments described here, but is specifically implemented through other forms. On the contrary, the embodiments introduced here are provided to make the disclosed content comprehensive and complete, and to fully convey the ideas of the present invention to those skilled in the art.

[0047] In this specification, when the terms first, second, etc. are used to describe components, the components should not be limited to the terms. The terms are only used to distinguish a component from other components. The embodiments described and illustrated herein include their complementary embodiments.

[0048] Unless otherwise specifically mentioned in the context of this specification, the singular form also includes the plural form. In the expressions used in the specification, "comprising", "consisting of" and "presenting" do not exclude the existence or addition of one or more other components other than the mentioned components.

[0049] In this specification, the term "software" means technology for running hardware in a computer, the term "hardware" means a device or machine that constitutes a computer (CPU, memory, input device, output device, peripheral device, etc.), the term "step" means a series of processing or operations connected in time series in order to achieve a given purpose, the term "computer program", "program" or "algorithm" means an instruction set suitable for computer processing, and the term "program recording medium" means a computer-readable recording medium that sets a program and executes or records a stream of general programs.

[0050] In this specification, terms such as "part", "module", "unit", "block", "board", etc. used to indicate components of the invention may mean a physical, functional or logical unit for processing at least one function or action, which may be presented as more than one hardware or software or firmware, or may be presented as a combination of hardware, software and / or firmware.

[0051] In this specification, "processing device", "computer", "computing device", "server device", "server" can be presented as a system with an operating system such as Windows, Mac, Linux, a computer program, a memory, an application, and a memory device (for example, HDD, SSD). For example, the computer can be a desktop computer or a laptop computer, a mobile terminal, etc., but it is illustrative and not limited to this. The mobile terminal can be one of the mobile wireless communication devices, such as a smart phone, a tablet computer or a PDA.

[0052] Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. Various specific contents written in the process of describing the following specific embodiments are used to describe in more detail and help understand the invention. However, it can be understood that those skilled in the art of the present invention should be able to know that it can be adopted even without these multiple specific contents. And it is forewarned that in order to prevent confusion when explaining the invention, parts that belong to the well-known or well-known conventional technology and have little to do with the invention will not be described.

[0053] Figure 11 is a schematic block diagram of a yield prediction simulation system according to an embodiment of the present invention. In the following description of this specification, it is assumed that the yield prediction simulation system according to the present invention (hereinafter referred to as "yield prediction system" or "simulation system") is applied to an olefin production process for explanation. For example, the simulation system according to the present invention can be applied to a PDH (Propane DeHydration) process for preparing propylene using propane as a raw material, through which hydrogen can be extracted from propane to generate one of the olefins, namely, propylene.

[0054] In one embodiment of the present invention, the yield prediction simulation system can predict the yield during the second cycle based on the process operation data collected during the first cycle. At this time, the first and second cycles can be periods of the same length or different lengths. In the embodiments of this specification, it is schematically assumed to be 4 years. Preferably, a cycle can be related to the life of the catalyst used in the chemical process. For example, when the life of the catalyst is 4 years, a cycle can be set to 4 years.

[0055] like Figure 1 As shown, the yield prediction simulation system 100 described in one embodiment may include a data preprocessing unit 110, a segment analysis unit 120, a data realization processing unit 130, an aging factor analysis unit 140, a key factor analysis unit 150, a yield prediction unit 160, a label variation analysis unit 170 and a yield prediction simulation device 180. Each of these components (110 to 180) may be implemented as programmable software that can be run in a computer device, and may be implemented in combination with firmware and software implementation parts as needed.

[0056] The data preprocessing unit 110 is a functional unit that collects and extracts data from the data storage unit 200 and performs preprocessing. Figure 3 The operation of the data preprocessing unit 110 will be described.

[0057] The segment analysis unit 120 can divide a period into multiple segments based on the preprocessed data. For example, for a period (e.g., 4 years), based on the change in given factors such as process temperature and yield caused by the life (aging) of the catalyst used in the process, the period is divided into multiple periods. Figures 4 to 10 The schematic operation of the section analysis unit 120 is described below.

[0058] The data actualization processing unit 130 is a functional unit that realizes the data used for yield prediction and generates it into a form suitable for input into the yield prediction model. The yield prediction simulation system described in the present invention uses the data of the previous cycle (first cycle) to predict the next cycle (second cycle). At this time, the data of the second cycle can be generated based on the data of the first cycle and input into the yield prediction model. Fig.11and Fig.12 The schematic operation of the data actualization processing unit 130 is described.

[0059] The aging factor analysis unit 140 is a functional unit for reflecting the aging of the catalyst used in the process in order to more accurately predict the process yield. Generally, catalysts have different lifespans depending on their type, and the aging trends during their lifespans are also diverse. In particular, as the catalyst ages faster in the latter half of its life, it may be difficult to accurately reflect it in the yield prediction model. Therefore, one embodiment of the present invention will further consider the aging factor. For example, it can be reflected in the process data as a weighted value. The process data is the aging factor of the catalyst calculated based on time, and its value is input into the yield prediction model. Through this process, the yield prediction performance can be improved. Below, refer to Figures 13 to 15 The schematic operation of the aging factor analysis unit 150 is described below.

[0060] The key factor analysis unit 150 extracts the process key factors using the preprocessed data in the data preprocessing unit 110. For example, the key factor analysis unit 150 can be implemented as a well-known machine learning algorithm, for example, a machine learning algorithm using a feature selection method.

[0061] The yield prediction unit 160 is a functional unit that uses preprocessed data and extracted key factors to predict the process yield. In one embodiment, the yield prediction unit 160 is implemented as a learning model based on machine learning, which can use the preprocessed data and key factors to learn the yield prediction model, and use the learned yield prediction model to predict the yield. For example, when preprocessing the data of the first cycle and the first half of the data of the second cycle, the preprocessed data and key factors can be used to learn the yield prediction model, and then the yield prediction results for the remaining period of the second cycle are output.

[0062] The label variation analysis unit 170 is a functional unit that calculates the variation of labels (input variables of the input yield prediction model). In the present invention, "labels" are input variables of the input yield prediction model, for example, various operating conditions such as temperature, pressure, flow rate, etc. in chemical processes. Among the labels, there are labels (hereinafter referred to as "control labels") that can be controlled and adjusted by users (for example, process operators or staff of a factory, etc.). As long as the staff changes the label value of such control labels, the label values ​​of other labels can be changed. The label variation analysis unit 170 can calculate the variation of at least a part of the remaining labels caused by the change of one or more control labels. For example, it can be implemented as a machine learning algorithm that uses the process operation data stored in the data storage unit 200 for learning.

[0063] The yield prediction simulation device 180 is a functional unit that simulates the change in yield based on the yield predicted by the yield prediction unit 160 and the label change analysis result calculated by the label change analysis unit 170. The yield prediction unit 160 statically predicts the yield during the second cycle based on the data stored at the current time point (the data of the first cycle or the data of the first cycle and the first half of the second cycle). On the contrary, the yield prediction simulation device 180 can simulate the future yield change when the process conditions (temperature, pressure, flow rate, etc.) are changed. To this end, the yield prediction simulation device 180 receives the predicted yield calculated by the yield prediction unit 160 and the analysis result calculated by the label change analysis unit 170 together, and simulates the yield change.

[0064] Below, reference Figure 2 Describe the schematic operation of the yield prediction simulation system. Figure 2 It is a flow chart of the yield prediction simulation method described in one embodiment. Figure 2 As shown, the yield prediction simulation method described in one embodiment includes: a step of preprocessing the yield prediction data including the first cycle data (S10), a segment analysis step of splitting one cycle into multiple segments based on the preprocessed data (S20), a data realization step of generating and realizing the second cycle data based on the first cycle data and the first half of the second cycle data (S30), and an aging factor analysis step of calculating the aging factor of the catalyst used in the process (S40).

[0065] Furthermore, the yield prediction simulation method includes: a step of analyzing key factors according to different sections based on the section analysis results (S50) and a step of building a yield prediction model according to different sections to predict the yield of the second cycle (S60).

[0066] Furthermore, the yield prediction simulation method may further include: when the user changes the label value of the control label, a label change analysis step (S70) is performed to calculate the change in the remaining labels, and a yield prediction simulation step (S80) is performed to reflect the label value thus changed in the predicted yield predicted in the yield prediction step (S60), and to simulate the change in the yield.

[0067] The following will further describe Figure 2 The individual steps are shown. Figure 3 FIG. 2 shows a schematic method of the data preprocessing step (S10) according to an embodiment. Figure 3As shown, the data preprocessing step (S10) may include: a step of preprocessing the data for yield prediction in units of minutes (S110), a step of selecting an analysis object label (S120), a step of extracting time and daily unit data for the data of the selected label in the data preprocessed in units of minutes (S130), and a step of performing outlier processing and missing value interpolation on the daily unit data (S140).

[0068] In order to pre-process the data in step (S110), the data storage unit 200 collects and extracts the data required for yield prediction. At this time, for example, the data storage unit 200 can be implemented as a database, but the data form is not particularly limited. In one embodiment, the yield prediction data extracted by the data storage unit 200 may include: (i) process operation data of olefin producers, (ii) laboratory data including LIMS data, (iii) plant event data including data related to the time when the plant is not operating normally; and (iv) historical yield, conversion rate and selectivity data related to olefin production.

[0069] The process operation data of the olefin producer (PDH plant) may be sensor data collected from sensors installed in various equipment (e.g., reactors, flow paths, etc.) of the plant. For example, each sensor may be a variable detection sensor that can observe process operation conditions such as temperature, pressure, flow, and components, and data may be collected from each sensor in units of minutes.

[0070] The process operation data can be stored in the data storage unit 200 according to different sections, units and tags. At this time, the unit is a mid-size collection of tags gathered in the factory, and the section is a large-size collection of units gathered. Multiple sections are gathered together to form the entire PDH factory. In addition, the tag can serve as an identifier to identify the various sensors installed in the factory. That is, each sensor is assigned a unique tag. For example, when the PDH factory is equipped with more than 9,000 sensors, there may be tags equivalent to this number. In the following description, unless there is a particular concern of confusion, the data output by the sensor corresponding to each tag is referred to as a "tag" or "tag data."

[0071] Laboratory data may include laboratory information management system (LIMS) data. In one embodiment, for accurate yield prediction, not only actual observation data (label data) but also laboratory data may be applied. Moreover, when label data has abnormal values ​​or missing values, laboratory data may also be used for processing, i.e., interpolation. As an alternative embodiment, laboratory data may also be omitted.

[0072] For example, plant event data may include data related to the time of non-normal operation (shut-down history), major overhaul / minor overhaul and other data, which can be used to analyze and process abnormal values ​​or missing values ​​of tag data. Historical yield values ​​include historical yield data related to olefin production. And at this time, in addition to historical yields, conversion and selectivity values ​​may be further included. In the following description of this specification, unless there is a concern of confusion, yield, conversion rate and selectivity are collectively referred to as "yield", and, from the perspective of machine learning, yield (i.e., yield, conversion rate, selectivity) is sometimes referred to as "target".

[0073] As described above, the data stored in the data storage unit 200 is continuously accumulated in units of a given set period, and can be data pushed forward from the current time point to the past for more than one period. At this time, the set period unit can be a second unit or a minute unit. For example, data can be collected in units of 30 seconds, and then converted into minute units and / or time units for analysis and stored. However, this set period unit is schematic and is not limited to a specific period. In addition, a period can be set in relation to the life of the catalyst. It should be understood that one embodiment can be set to 4 years, but this is schematic.

[0074] The yield prediction data extracted from the data storage unit 200 is preprocessed into minute-based data in step S110. For example, when receiving second-based data from the data storage unit 200, it is converted into minute-based data, and when an abnormal value or missing value occurs, abnormal value processing and missing value interpolation are performed.

[0075] Next, in step (S120), the target label for analysis is selected. For example, all label data received from all sensors set up in the factory can be used to implement the following key factor analysis and yield prediction, etc., but, preferably, part of the label data in the entire label data can be screened out, and the screened label data can be used to implement subsequent (for example, after step S130) time / day unit data extraction, key factor analysis and yield prediction. At this time, the target label for analysis is selected in step (S120). For example, label selection can be based on previous research and the knowledge and experience of field technicians to select labels that are considered to be helpful for analysis.

[0076] In one embodiment, the step of selecting the analysis target label (S120) may be performed before the step of preprocessing the minute unit data (S110). In this case, the minute unit data preprocessing (S110) may be performed only on the label selected as the analysis target.

[0077] When the analysis target label is selected in step (S120), in the subsequent step (S130), the time unit data is extracted and processed again to extract the day unit data. At this time, for data integration, the factory data (label data) and LIMS data can also be used for data integration. And, as an alternative embodiment, the analysis target label selection step (S120) can also be implemented after the time unit data is extracted. At this time, after the time unit data is extracted for all process data, only the analysis target label can be extracted into day unit data.

[0078] After step (S130) extracts the daily unit data, step (S140) implements data preprocessing. For example, data preprocessing includes outlier processing and missing value interpolation. Outlier processing is to screen outliers and remove or correct them, and then only apply the sorted values ​​as valid input values. In addition, for the sections that are screened as outliers and removed or the sections that do not have process data due to factory interruption, missing value interpolation is implemented. For example, missing value interpolation is to generate new data through linear regression and distribution-based random number generation to perform interpolation.

[0079] The yield prediction data preprocessed through the above steps is sorted and converted into a learning model data format for machine learning, and then stored in the data storage unit 200 or any other storage unit.

[0080] Figures 4 to 10 is a segment analysis step described in an embodiment ( Figure 2 S20) is a schematic diagram of a schematic method, Figure 4 is a schematic flow chart of an illustrative method of the segment analysis step, Figures 5 to 10 Schematic diagram of a segment analysis process according to an embodiment.

[0081] The segment analysis step (S20) divides a cycle into multiple segments based on the preprocessed data. In one embodiment, the segments can be divided into segments according to the inflection point where the yield trend changes sharply and the degree of yield change, and the segments are divided into segments showing similar yield increase and decrease trends during the process operation period of a cycle. Different segments are applied in various modeling such as key factor extraction, yield prediction, and yield prediction simulation in the future, thereby improving the accuracy of yield prediction.

[0082] like Figure 4 As shown, the segment analysis step (S20) described in one embodiment may further include: a step of selecting the main factors required for segment analysis (S210), a step of selecting the inflection point of the main factors, and a step of determining the segment once (S220). In addition, in one embodiment, after step (S220), a step of integrating or separating the segments through variability analysis, and a step of determining the segments twice (S230) may be included. In addition, in one embodiment, after step (S230), a step of determining the segments three times based on catalyst design may be further included (S240).

[0083] The steps are briefly described as follows: First, in step (S210), the main factors required for the segment analysis are selected. For example, the main factors can be selected, and the main factors include: at least one of the yield, conversion rate, and selectivity as target values, and the main tags that affect these target values. For this, Figure 5 The eight main factors selected in step ( S210 ) are schematically shown.

[0084] Next, in the step of splitting into segments (S20), the inflection points of the main factors are searched and analyzed to determine the segments at one time. The specific method of analyzing the inflection points to search for the segments is as follows: (i) calculating the inflection points of one or more factors required for selecting the segments within a period, (ii) clustering the calculated inflection points, and (iii) selecting the inflection points that become the segment boundaries from the clustered inflection points to determine the segments.

[0085] More specifically, in step (i), for example, the inflection point can be calculated using a known method such as a plateau detection method. Figure 6 The results of detecting the inflection point using the deformation stationary detection method are shown. Figure 6 The graph is a graph of the air temperature (Regen Air temperature) during catalyst regeneration. At this time, the X-axis represents the time within a cycle (or a variable corresponding to the time such as "cumulative production"), and the Y-axis represents the temperature.

[0086] Then, in step (ii), clustering is performed on the inflection points. For example, Figure 7The density-based clustering algorithm (DBSCAN, Density-Based Spatial Clustering of Applications with Noise) that uses data density (density) to achieve clustering is shown, and the clustering achieved for the inflection point is shown. DBSCAN is one of the well-known clustering methods, and of course, the present invention is not limited to this method.

[0087] Next, among the clustered inflection points in step (iii), the inflection points that serve as segment boundaries are selected to determine the segments at once. For example, Figure 8 The result of determining the first segment in which the step (iii) is split into four segments is shown.

[0088] In one embodiment, the segment splitting result determined last time can be used to proceed to the next step (for example, Figure 2 In the embodiment of the alternative scheme, after step (S220), a step (S230) of integrating or splitting the segments and re-determining the segments may be further included. In step (S230), for example, the average and deviation of different segments may be calculated based on the different segments determined once, and the segments determined once may be integrated or split based on the calculated average and deviation, and the segments may be determined twice. Fig. 9 The segment splitting result determined twice in step ( S230 ) is shown. Fig. 9 In the figure, the dotted line schematically represents the first segment splitting result obtained in step (S220), and the blue solid line schematically represents the second segment splitting result obtained in step (S230).

[0089] In one embodiment, the segment splitting result determined twice as above can be used to proceed to the next step (for example, Figure 2 Alternatively, after step (S230), a step (S240) of determining the segments three times based on the catalyst productivity design may be further included. In step (S240), for example, considering the cumulative output of the product (e.g., 600,000 tons, 1.8 million tons, 2.4 million tons, etc.), the similarity with the catalyst design is compared, and the segment splitting is finally determined.

[0090] For example, Fig.10 The segment splitting result finally determined by this step (S240) is shown. Fig.10 As shown, when the catalyst life is regarded as one cycle (for example, 4 years), one cycle is divided into 4 sections (SG1 to SG4). Fig.10In the figure, the red graph shows the air temperature during catalyst regeneration (Regen Air temperature), and the gray graph and the light green graph show the yield and selectivity, respectively.

[0091] like Fig.10 As shown, the first section (SG1) is a period in which a catalyst is added to gradually increase the Regen Air temperature and tend to stabilize. The second section (SG2) is a steady-state period in which the Regen Air temperature is maintained at a steady state, and the yield and selectivity are steady. From the third section (SG3), it can be seen that the yield gradually decreases with the aging of the catalyst. That is, although this step increases the Regen Air temperature, the yield will not be maintained or increased, but will gradually decrease due to the aging of the catalyst. The fourth section (SG4) is a step in which the yield further decreases sharply. Even if the Regen Air temperature is further increased, the yield and selectivity will not increase further, but will decrease sharply.

[0092] As described above, the present invention can consider the trend of increase or decrease in yield caused by catalyst life during a period, and can divide the intervals showing similar trends into segments, and according to the divided segments, in the subsequent steps (for example, Figure 2 The key factor analysis step (S50), yield prediction step (S60), yield prediction simulation step (S80), etc. shown in the figure are used to implement modeling according to different sections, and derive the overall analysis / prediction results for one cycle, thereby improving the accuracy of yield prediction.

[0093] Reference now Fig.11 and Fig.12 Describe the data realization steps ( Figure 2 The schematic method of S30 is shown in the figure. The data realization step (S30) generates data for the remaining period of the second period based on the data of the first period and the first half of the data of the second period and realizes it. The yield prediction step (S60) described in the present invention applies the data of the previous period (the first period) to predict the next period (the second period). More specifically, after the data of the second period is generated based on the data of the first period, the data of the second period is input into the yield prediction model to predict the yield of the second period. At this time, if there is data for a part of the second period (hereinafter, "the first half of the second period"), the data realization step (S30) applies the data of the first half of the second period to generate data for the remaining period of the second period.

[0094] For example, the following is taken as a premise: a cycle period is 4 years, the first cycle is from January 2017 to December 2020, and the second cycle is from January 2021 to December 2024. Assuming that the current time point is August 2022, the data storage unit 200 stores the process operation data of the first cycle and the first half of the second cycle (i.e., from January 2021 to July 2022).

[0095] At this time, the data realization processing unit 130 generates data for the remaining period of the second cycle (i.e., from August 2022 to December 2024) based on the process operation data of the first cycle and the first half of the second cycle. At this time, considering the trend or average characteristics of the first cycle data and the characteristics of the first half of the second cycle data, the data realization processing unit 130 can generate data for the remaining period of the second cycle.

[0096] However, due to differences in catalyst addition amount, initial operating conditions, etc., the process operation data (e.g., each tag data) of the first cycle and the second cycle tend to have different trends or values ​​in the two cycles. Therefore, it is difficult to generate data for the second cycle using the operating condition data of the first cycle. Therefore, the data realization step (S30) of the present invention corrects the data of the first cycle to make it consistent with the trend of the second cycle, thereby generating data for the second cycle.

[0097] In one embodiment, the method for realizing each tag data may at least include an average difference reflection method and a random number generation method.

[0098] When there is an average difference between the first cycle and the second cycle, the average difference reflection method can be applied. In one embodiment, when the data change trends in a given period of the first cycle and the second cycle are similar, but the average values ​​are different, the average point of the first cycle data is moved to generate the data of the second cycle. For example, Fig.11 Schematic label data to which the mean difference reflection method can be applied are shown. Fig.11 In the graph, the X-axis is the axis corresponding to the time of one cycle, and the Y-axis represents the data value of the tag. In addition, the black chart is the data of the first cycle of the tag (CY1), and the red chart is the first half of the data of the second cycle (CY21). It should be understood that the time point when the first half of the data of the second cycle (CY2) ends is the current time point.

[0099] Comparing the data of the first cycle (CY1) with the data of the first half of the second cycle (CY21), it can be seen that the trends of the two data are similar, and the average value of the data of the second cycle is larger. Therefore, at this time, the average difference reflection method can be applied to increase the data of the corresponding period of the first cycle to the average difference, thereby generating the data of the remaining period of the second cycle. At this time, in one embodiment, the data of the corresponding period of the first cycle is increased to the average and used directly. Alternatively, at least for a part of the interval, the data can also be modified by generating random numbers and other methods to generate the second data.

[0100] When the data for a given period is incomplete or contains outliers, a random number generation method can be applied. In one embodiment, when there is incomplete data in the first period, a random number is generated to generate data for the second period. For example, Fig.12 Schematic label data to which the random number generation method can be applied is shown.

[0101] Fig.12 In the chart, the X-axis is the axis corresponding to the time of one cycle, and the Y-axis shows the data value of the tag. The black chart is the data of the first cycle of the tag (CY1), and the orange chart is the first half of the data of the second cycle (CY21). The time point at which the first half of the data of the second cycle (CY2) ends means the current time point.

[0102] like Fig.12 As shown, the first cycle data (CY1) is generated after a certain time point. That is, the tag data may mean that the sensor was not set or the sensor was not working before the specific time point. However, the first half of the second cycle data (CY21) exists, and the data of the remaining interval (CY22) is based on the data of the first cycle, and the second half of the data (CY22) is generated by generating random numbers. At this time, for example, the average and dispersion of the previous given interval (for example, the previous 30 days (D30) at the current time point) are calculated at the current time point, and while maintaining the average and dispersion, the second half of the data (CY22) is generated by generating random numbers for the data at individual moments.

[0103] Reference now Figures 13 to 15 Describe the steps of aging factor analysis ( Figure 2 The schematic method of step S40 is shown in FIG. 1 . The purpose of implementing the aging factor analysis step (S40) is to reflect the aging of the process catalyst, and the purpose of using the catalyst in the process is to more accurately predict the process yield. In the PDH process for producing propylene, as the cumulative production of propylene increases, the life of the catalyst is shortened, resulting in a sharp drop in the yield of the catalyst in the second half of the process. Therefore, in order to accurately reflect the yield change caused by the change in process conditions and the yield reduction caused by the life of the catalyst in the yield prediction, preferably, the aging factor of the catalyst is used to implement the yield prediction.

[0104] In one embodiment, as shown in the following formula, the aging factor of the catalyst converts the value obtained by dividing the daily propylene production by the heat applied to the catalyst into an index, reflecting the yield reduction value.

[0105] AF (Aging Factor) = (Daily Propylene Production) / (Heat Applied to Catalyst)

[0106] In the above formula, for example, the "heat amount applied to the catalyst" can be obtained by multiplying the tag data value indicating the Regen Air temperature by the flow rate.

[0107] For example, Fig.13 As shown, the yellow graph is the yield (Y1) of the first cycle in a cycle along with time, and the red graph represents the aging factor (AF1) of the first cycle. It can be seen that the aging factor (AF1) increases and decreases in a trend similar to the yield (Y1). Fig.10 The description made is that the fourth section is the last section of the cycle. No matter how the temperature is increased, the yield will decrease. At this time, until the third section, the yield decreases relatively linearly, while in the fourth section, the yield decreases nonlinearly.

[0108] In addition, the grass green chart is the yield (Y2) of the second cycle up to the current time point, and the blue chart represents the aging factor (AF2) of the second cycle up to the current time point, extending in a trend similar to the yield (Y2) and aging factor (AF1) of each first cycle. Therefore, it can be predicted that the corresponding yield (Y2) during the fourth segment will still decrease nonlinearly. In order to make a more accurate prediction, the yield is calculated by reflecting the aging factor (AF) corresponding to the second cycle.

[0109] For example, Fig.14 As shown, regarding the aging factor (AF1) of the first cycle, first, an average value (AF1m) can be calculated according to different sections, and the calculated average values ​​of each section can be applied to each section of the second cycle as a weighted value. In one embodiment, even if the aging factor (AF) is not applied to the first and second sections, the yield prediction model can still accurately predict the yield. Therefore, the aging factor can be not applied to the first and second sections, while the aging factor (AF) can be applied to the third and fourth sections. In another embodiment, the yield of the third section decreases more linearly, and the yield prediction model can be accurately predicted to a certain extent. Therefore, the aging factor (AF) can be applied only to the fourth section.

[0110] Fig.15 This is a diagram showing the trend of the predicted yield when the aging factor (AF) is not applied to the first and second segments and only the aging factor (AF) is applied to the third and fourth segments. If the aging factor (AF) is not applied to the third and fourth segments, the yield prediction is as follows Fig.15 In the blue graph shown, the difference between the predicted yield (blue solid line) and the actual yield (black dashed line) is not large in the first and second segments, but the error shown in the third and fourth segments is large. However, as described in the present invention, when the aging factor (AF) is applied to the third and fourth segments, as shown in the red dashed line, the yield prediction becomes closer to the actual yield.

[0111] In addition, if Figure 2 As shown, the results of the aging factor analysis step (S40) can be applied in the implementation of the yield prediction simulation (80). However, in an alternative embodiment, the aging factor analysis results can also be applied in the yield prediction step (S60).

[0112] Now refer to it again Figure 2 The key factor analysis step (S50) is briefly described. The key factor analysis step (S50) uses the data preprocessed by the data preprocessing unit (110) to extract the key factors of the process that affect the yield. For example, the key factors of the second cycle data generated by the data realization step (S30) can be extracted according to the different sections split by the section analysis step (S20). For example, the key factor extraction method can be implemented by a well-known machine learning algorithm, for example, a machine learning algorithm using a feature selection method, such as the Boruta algorithm.

[0113] In the subsequent yield prediction step (S60), the key factors extracted in step (S50) can be applied to the yield prediction model. For example, in step (S50), more than 100 key factors are selected from more than 9,000 tags of the factory, and then, in the yield prediction step (S60), the yield prediction is implemented based on the tag data values ​​of the selected more than 100 key factors. In addition, in one embodiment, the key factors can also be applied in the tag variation analysis step (S70).

[0114] like Figure 2 As shown, the yield prediction step (S60) uses the pre-processed data and key factors to predict the target of the process (at least one of the yield, conversion rate, and selectivity). For example, the yield of the second cycle can be predicted based on the different segments split in the segment analysis step (S20) and the second cycle data generated in the data realization step (S30).

[0115] For example, the yield prediction model can integrate bagging algorithms such as random forest and boosting algorithms such as XGBoost and LightGBM (LGBM), adopt a yield prediction model with high predictive power, and use the first cycle data as learning data for model learning.

[0116] The bagging series algorithm is a method of random sampling and statistics in parallel for multiple iterations, and has the characteristic of increasing learning data. Therefore, even if the learning data is not enough, sufficient learning effect can be obtained, which has the effect of preventing underfitting and overfitting. The boosting series algorithm also implements multiple random samplings, but it is not implemented in parallel, but implemented in sequence, and therefore has the characteristic of adjusting the weighted value of the next learning data based on the previous learning effect to achieve learning. That is, a high weighted value is given to wrong answers, and therefore, it has a high accuracy effect. In the above-mentioned model, preferably, the shorthand forest algorithm or error widely used in the bagging series algorithm for preventing overfitting and underfitting is used, and the LGBM model in the boosting series algorithm for improving accuracy is used for modeling. However, this yield prediction model is schematic, and of course, it will not use a known suitable machine learning method according to the specific embodiment of the present invention.

[0117] Fig.16 The schematic diagram of the yield prediction result using the above integrated model is shown. Fig.16 The predicted yield (Y) during the second cycle is shown in the orange graph.

[0118] refer to Fig.17 Describe the steps of label variation analysis ( Figure 2 The tag variation analysis step (S70) uses a tag variation analysis model to analyze the tag variation. The tag variation analysis model calculates the variation of at least a portion of the remaining tags based on the variation of one or more control tags in the yield prediction data.

[0119] In one embodiment, at least one or more operable control tags are selected from the tags used in the yield prediction. Wherein, "control tags" means tags that can be operated by the user in the process conditions of the chemical process, for example, it can include at least one tag of the air temperature (Regen Air temperature) during catalyst regeneration, the raw material heating temperature (Charge Heater temperature), the air flow rate (Regen Air flow) during catalyst regeneration, and the reactor raw material injection flow rate (Reactor Feed flow). Therefore, for example, it can be understood that when the yield prediction uses 100 factors (tags), the 4 tags become control tags, and at least a part of the remaining 96 tags become tags that change according to the changes in the 4 Confucius tags.

[0120] The label change analysis unit 170 can calculate the change of at least a portion of the remaining labels according to the change of the one or more control labels. For example, the segment analysis step can calculate the change of at least a portion of the remaining labels according to the change of the one or more control labels. For example, according to the different segments split in the segment analysis step (S20), the second cycle data generated in the data set realization step (S30) and the key factor analysis (S50) are used to perform label change analysis (S70) on the selected labels.

[0121] In this regard, Fig.17 An illustrative user interface (UI) for analyzing tag deltas is shown. Fig.17 In the embodiment shown, it should be understood that four tags, namely, the air temperature during catalyst regeneration (Regen Air temperature), the charge heater temperature (ChargeHeater temperature), the air flow rate during catalyst regeneration (Regen Air flow rate) and the reactor feed injection flow rate (ReactorFeed flow rate) are used as control tags. For example, an arrow key (10) is displayed on the right side of the Regen Air temperature tag for the staff to adjust the tag value to increase or decrease it. The other three control tags are also adjusted by the arrow keys. In addition, as described above, after the staff adjusts at least one of the four control tags to an arbitrary value, when the "Start Analysis" key (20) below is pressed (for example, when clicking with a mouse), the tag change analysis model can calculate the change amount of the other tags according to the change of the control tag and output it.

[0122] Furthermore, as described above, the label variation analysis result achieved by the label variation analysis step (S70) can be used as an input variable in the subsequent yield prediction simulation step (S80). The yield prediction simulation step (S80) simulates the change in yield based on the yield predicted by the yield prediction unit (160) and the label variation analysis result calculated by the label variation analysis unit (170). That is, based on the second cycle data generated by the yield prediction step (S60) through data realization (S30), the future yield is statically predicted. In contrast, when the user changes the control label to an arbitrary value through the label variation analysis (S70), the yield prediction simulation step (S80) predicts how the future yield will change when the remaining label values ​​are also changed. Therefore, in the yield prediction simulation step (S80), the yield prediction simulation (180) inputs the predicted yield calculated by the yield prediction unit (160) and the analysis result calculated by the label change analysis unit (170) into the yield prediction simulation model to simulate the yield change.

[0123] And, if Figure 2As shown, in one embodiment, the yield prediction simulation step (S80) can simulate the change in yield based on the yield predicted by the yield prediction unit (160), the label change analysis result calculated by the label change analysis unit (170), and the catalyst aging factor calculated by the aging factor analysis step (S40). At this time, the aging factor is only used as a weighted value during the third and fourth segments or the fourth segment of the second cycle.

[0124] The yield prediction simulation model can be implemented through machine learning algorithms. For example, a bagging series of algorithms such as random forest and a boosting series of algorithms such as XGBoost and LGBM can be integrated to adopt a yield prediction model with high predictive power.

[0125] Fig.18 A schematic yield prediction simulation result according to an embodiment is shown. Fig.18 In the figure, the orange-yellow graph is the yield (Y) predicted in the yield prediction step (S60), which is consistent with Fig.16 The yield graphs shown are identical. Fig.18 In the figure, the pink graph is the yield (Ys) simulated in the yield prediction simulation step (S80). Fig.17 The screen changes at least one control tag value, thereby displaying the simulated yield while the remaining tag values ​​are also changed. Therefore, the present invention not only simply uses the second cycle data to implement static yield prediction, but also dynamically simulates and displays whether the yield changes according to the change of the control tag when the main control tag is changed, thereby more accurately analyzing and predicting the yield according to the change of the main tag.

[0126] As described above, any person skilled in the art can make various modifications and variations from the descriptions of these specifications. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined by the following claims and equivalents thereof.

[0127] [Possibility of industrial application]

[0128] The present invention relates to a yield prediction of a chemical process, and more specifically, to a yield prediction simulation system and method, which can predict the yield during a second cycle based on process operation data during a first cycle, reflect label changes, and simulate the yield prediction.

Claims

1. A yield prediction simulation method, characterized in that: In a yield prediction simulation method for predicting the yield of a second cycle based on the yield prediction data of a first cycle in a chemical process, include; A step of preprocessing the first cycle data (S10); Based on the pre-processed data, a step of dividing the first cycle into a plurality of segments (S20); as well as A step (S60) of respectively building yield prediction models according to the split multiple different sections to predict the yield of the second cycle.

2. The yield prediction simulation method according to claim 1, characterized in that: The first cycle and the second cycle are determined according to the life of the catalyst used in the chemical process.

3. The yield prediction simulation method according to claim 1, characterized in that: The step of splitting into segments (S20) includes the following steps: calculating the inflection points of one or more factors required for selecting segments within the first period, clustering the calculated inflection points, selecting inflection points as segment boundaries from several clustered inflection points, and determining the segments once (S220).

4. The yield prediction simulation method according to claim 3, characterized in that: The step of splitting into segments (S20) further includes the following steps: according to the different segments determined once, calculating the average and deviation of different segments, and integrating or splitting the segments determined once based on the calculated average and deviation, and the step of re-determining the segments (S230).

5. The yield prediction simulation method according to claim 1, characterized in that: Further including: According to the split multiple different sections, key factor analysis models are respectively built, and a key factor analysis step (S50) of selecting key factors is performed, The yield prediction step (S60) predicts the yield of the second cycle based on the pre-processed first cycle data and the key factors derived from the analysis of the key factors of the different sections, and according to the multiple different sections, respectively using the modeled yield prediction model.

6. The yield prediction simulation method according to claim 5, characterized in that: It further includes a label variation analysis step (S70), which models the label variation analysis model according to the multiple different segments that have been split, and the label variation analysis model calculates the variation of at least a part of the remaining labels according to the change of one or more control labels in the yield prediction data.

7. The yield prediction simulation method according to claim 6, characterized in that: The multiple control tags are tags related to the process conditions of the chemical process that can be adjusted by the user.

8. The yield prediction simulation method according to claim 6, characterized in that: The method further comprises a yield prediction simulation step (S80), which simulates the yield of the second cycle based on the predicted yield calculated by the yield prediction model and the label change analysis result calculated by the label change analysis model. The label variation analysis result includes: a control label value arbitrarily changed by a user and label values ​​of several labels outputted by inputting the control label value into the label variation analysis model.

9. A computer-readable recording medium having a computer program recorded thereon for implementing the yield prediction simulation method according to any one of claims 1 to 8.

Images