JP2023085836A - Chemical plant management device, chemical plant management system and chemical plant management method - Google Patents

Abstract

To specify a relation between a raw material or an operating condition and a production result in a chemical plant production.SOLUTION: A chemical plant management device comprises: a storage unit for storing information about a first product produced by charging a first raw material into a first reactor and using a first operating condition in a chemical plant; an input unit for inputting a second product produced in a second reactor; and a control unit for generating a plurality of property groups each containing a plurality of first products having a predetermined range of properties based on the information about the first product, wherein a predetermined property group including the second product out of the plurality of property groups is identified based on the property of the second product and a range of properties of the plurality of property groups, and a second raw material and a second operating condition are specified for producing the input second product in the second reactor.SELECTED DRAWING: Figure 1

Description

The present invention relates to a chemical plant management device, a chemical plant management system and a chemical plant management method.

Conventionally, there is a technique described in Japanese Patent Laying-Open No. 2020-187616 (Patent Document 1) for managing a plant. In this publication, ``The plant monitoring model creation device of the present application includes a weighting factor calculation unit that calculates weighting factors for a plurality of trained models, and calculates an average feature model using the weighting factors calculated by the weighting factor calculation part. and a trained model generator that generates a trained model for the monitored plant by using difference learning between the average feature model calculated by the average feature model calculator and the plant data of the monitored plant. is provided, a plant monitoring model can be created in a short period of time.”

JP 2020-187616 A

However, the conventional technology was not intended for chemical plants and could not cope with the production of a wide variety of products. In the production of a wide variety of products in a chemical plant, a wide variety of products with different raw materials, operating conditions, etc. are produced, and the production volume of each product is smaller than in the conventional production. For a specific product, it is important for production management to specify the relationship between raw materials, operating conditions, and production results. It was difficult to identify relationships.

Accordingly, an object of the present invention is to specify the relationship between raw materials, operating conditions, and production results in production at a chemical plant.

In order to achieve the above object, one of the typical chemical plant management devices and chemical plant management systems of the present invention is a chemical plant in which information on a first raw material to be fed into a first reactor; a storage unit storing information on one operating condition and information on a first product produced by charging the first raw material into the first reactor and using the first operating condition; , the input unit for inputting the second product produced in the second reactor, the input second raw material for producing the second product and the second operating conditions, the first and a control unit that specifies based on the raw material, the first operating condition, and the information on the first product.
In addition, one of the typical chemical plant management methods of the present invention includes, in a chemical plant, information on a first raw material to be fed into a first reactor, information on a first operating condition, A step of storing and storing information on the first product produced using the first operating conditions by introducing the first raw material into the reactor of and storing in a storage unit; a step of receiving an input of a second product to be produced; determining based on conditions and information about the first product.

Advantageous Effects of Invention According to the present invention, it is possible to specify the relationship between raw materials, operating conditions, and production results in production at a chemical plant. As a result, when producing a product under new conditions, it is possible to efficiently determine new manufacturing conditions based on information on raw materials and operating conditions. Problems, configurations, and effects other than those described above will be clarified by the following description of the embodiments.

Explanatory drawing about management of a chemical plant in an embodiment Configuration diagram of a chemical plant management system according to an embodiment Configuration diagram showing the configuration of a chemical plant management device Concrete example of product table Specific example of raw material table Operating condition table Explanatory diagram of spectroscopic analysis Illustration of predictive reaction model An illustration of creating a model from theory Illustration of creating a model using machine learning Explanatory diagram of the use of the predictive reaction model (Part 1) Explanatory diagram of the use of the predictive reaction model (Part 2) Flowchart showing the processing procedure of the chemical plant management device Specific example of display output by the display unit

Hereinafter, representative embodiments for carrying out the present invention will be described with appropriate reference to the drawings.
Drawing 1 is an explanatory view about management of a chemical plant in an embodiment.
In this embodiment, a chemical plant that produces a wide variety of products is targeted for management. Therefore, chemical plants provide data on multiple types of products. The multiple types of products are, for example, products with different product numbers, reactors, raw materials, operating conditions, and the like.

The item number is identification information for identifying items within a range that can be regarded as being the same in subsequent processing and supply as a product. If the product number is the same, the basic composition and the like can be specified, but details of raw materials, operating conditions, and quality are not necessarily the same. In other words, even when the same product number is produced, the quality varies due to differences in raw materials, operating conditions, reactors, environmental factors, and the like. Therefore, in order to efficiently produce substances of desired quality, it is necessary to finely adjust raw materials, operating conditions, and the like.

The chemical plant management system disclosed in this embodiment generates a predictive reaction model from existing product data for multiple types of products. Existing product data includes part numbers, reactors, raw materials and operating conditions. If a prediction reaction model is generated using these data and the results of generation, it is possible to obtain raw materials and operating conditions suitable for the generation of the product.

Predictive reaction models are generally based on models derived from theory, etc., and their accuracy is gradually improved by feeding back the results of generation. However, when generating a new product, since there is no existing generation result, sufficient accuracy cannot be expected as it is. And if the required production volume is small, the production will end before the accuracy is sufficiently improved.

Accordingly, the disclosed chemical plant management system utilizes existing predicted reaction models for other products in creating a predicted reaction model for a new product.
Specifically, the disclosed chemical plant management system stores a plurality of existing predicted reaction models obtained from existing product data, and groups the plurality of predicted reaction models according to similarity.
Here, grouping of a plurality of prediction reaction models will be described. Groupings may be based on product type, such as part number, chemical properties, physical properties, raw materials, reactor, or operating conditions involved in particular processes involved in the product. In addition, those that cannot be grouped by these criteria may be grouped on the key explanatory factors of the predictive response model. By using clustering based on feature values in combination with the above-described criteria, grouping can be performed reliably and efficiently, contributing to the management of chemical plants that handle a wide variety of products.
When the disclosed system receives input about data for a new product, it searches for existing products similar to the new product and identifies the group to which the product belongs as a similar group (1). . Then, by ensemble learning of a plurality of prediction reaction models included in a similar group, a new product prediction reaction model is created (2).
New product data can include part numbers and reactors. Existing products that are similar to new products may be determined by part number matching and reactor matching. For example, when classifying by reactor using group Gr1 and group Gr2, a similar group is identified by the reactor specified by the new product data, and multiple predicted reactions created for the same reactor The model will generate a predictive reaction model for the new product.
In addition, regarding grouping, we explained the case of creating a set of groups for the multidimensional parameters of the product, but for each of the multiple characteristic types related to the product, create a group for each characteristic type You can That is, as an example, when attention is paid to certain two characteristic types A and B, grouping for the characteristic type A (pattern 1) and grouping for the characteristic type B (pattern 2) are performed separately. . In this case, when receiving input about new product data, a similar group is identified for each type, and by ensemble learning of a plurality of predictive reaction models included in the identified plurality of similar groups, a new create a predictive reaction model for the products of

Using the predicted reaction model of the new product thus produced and similar groups of feedstocks and operating conditions, the feedstocks and operating conditions to be applied to produce the new product can be identified.
In addition, the result of production can be predicted by using the raw materials and operating conditions used for production and the prediction reaction model.

FIG. 2 is a configuration diagram of a chemical plant management system according to the embodiment. As shown in FIG. 2, the chemical plant management system includes a chemical plant management device 10 and a data integration platform 20. The data integration platform 20 collects data from various devices installed in the chemical plant and outputs the data to the chemical plant management device 10 .

Specifically, raw material data 31, control performance data 32, quality data 33, and the like are obtained from the chemical plant.
The raw material data 31 is data indicating the raw material charged into the reactor.
The control performance data 32 is data indicating the performance of the reactor control obtained from the controller of the equipment related to the control of the reactor.
The quality data 33 is data indicating the quality of the product. Any index can be used to evaluate the quality of the product, but in this embodiment, the case of using spectroscopic analysis is exemplified. As another example, the quality data 33 may be a prediction result obtained by the chemical plant management device 10 predicting the production result during operation. The quality data 33 may be acquired by communicating with a system that integrates and manages product quality control data in chemical plants.

The chemical plant management device 10 is a device that manages a chemical plant using raw material data 31, control performance data 32, quality data 33, and the like. The chemical plant management device 10 can create and store reaction prediction models for various products, and output prediction results using the reaction prediction models to the manager. Based on the output of the chemical plant management device 10, the manager can determine raw materials, operating conditions, etc., and operate the chemical plant.

In addition, the chemical plant management apparatus 10 can accept new product data, identify a similar group, and create a new product prediction reaction model from the similar group prediction reaction models.

In addition, the chemical plant management device 10 uses the reaction prediction model to determine raw materials and operating conditions, generates information about control instructions for equipment related to reactor control, transmits the information to the controller of the equipment, It may be configured to automatically control the chemical plant.
The chemical plant management device 10, before or during operation, based on the quality data 33 of the newly generated product (for example, information on the emission spectrum inside the reactor that generates the product), the current It may be configured to automatically verify the validity of the current operating conditions by evaluating the actual production results and operating conditions, and predicting and evaluating future production results.
Furthermore, the chemical plant management device 10 evaluates the current production results and operating conditions, and predicts future production results based on the control performance data 32 and the quality data 33 before or during operation. It is also possible to automatically verify the validity of the current operating conditions by evaluating the above. At that time, determine whether it is necessary to change the current operating conditions, identify new operating conditions after the change, and provide information on control instructions for equipment related to reactor control so that the operating conditions can be changed to the new operating conditions. may be generated and automatically sent to the controller of the device. This configuration can contribute to automatic operation of chemical plants.

FIG. 3 is a configuration diagram showing the configuration of the chemical plant management device 10. As shown in FIG. As shown in FIG. 3 , the chemical plant management device 10 has an arithmetic device 11 , a main storage device 12 , an input section 13 , a display section 14 , a communication interface 15 and an auxiliary storage device 16 .

The arithmetic unit 11 is, for example, a CPU (Central Processing Unit), and operates as a control unit described in the claims.
The main storage device 12 is, for example, a RAM (Random Access Memory). The arithmetic device 11 develops various programs and data in the main storage device 12 and sequentially executes the programs, thereby controlling the operation of the chemical plant management device 10 .

The input unit 13 is, for example, a keyboard, and receives operation inputs from the administrator. Specifically, the input unit 13 is used to input data for new products.
The display unit 14 is, for example, a liquid crystal display, and is used to display and output various information to the administrator.

The communication interface 15 acquires various data (raw material data 31 , control performance data 32 , quality data 33 , etc.) from the chemical plant via the data integration platform 20 .
The communication interface 15 functions as an acquisition unit described in the claims by acquiring the control performance data 32 .
Further, the communication interface 15 acquires the spectroscopic analysis result (first emission spectrum) of the existing product as the quality data 33, thereby functioning as the first spectroscopic input section described in the claims.
Further, the communication interface 15 functions as a second spectroscopic input unit described in the claims by acquiring the spectroscopic analysis result (second emission spectrum) of the new product as the quality data 33 .

The auxiliary storage device 16 is a storage unit that stores various data. The auxiliary storage device 16 stores a product table 41, a raw material table 42, an operating condition table 43, a predicted reaction model 44, and the like.

The product table 41 is a table of information on existing products. If the reactor used for the production of the existing product is the first reactor, the raw material fed into the first reactor is the first raw material, and the operating conditions of the existing product are the first operating conditions , the information about the existing product is "information about the first product produced by charging the first reactor with the first feedstock and using the first operating conditions."
The raw material table 42 is a table of information on the first raw material charged into the first reactor.
The operating condition table 43 is a table of information on operating conditions of existing products.
The predicted reaction model 44 is the predicted reaction model information regarding the reaction that produces the first product in the first reactor. Since the prediction reaction model is one kind of information about the first product, it may be stored in the product table 41, but for the sake of convenience, it is treated as separate data.

FIG. 4 is a specific example of the product table. The product table 41 shown in FIG. 4 has items of product, product number, quality control value 1 and quality control value 2 .
The product entry indicates the generic name of the product, such as "Polymer A" or "Polymer B".
The product number item indicates identification information such as "A-0001" and "B-0002" for identifying the same within a range that can be regarded as the same in subsequent processing and supply as a product.
Quality control value 1 and quality control value 2 indicate the range of evaluation values indicating the quality of the product.

FIG. 5 is a specific example of the raw material table. The raw material table 42 shown in FIG. 5 has items of product, product number, and raw material 1 to raw material 5 .
Items of product and product number are the same as those of the product table 41 . Raw materials 1 to 5 indicate raw materials (first raw materials) used to produce the products. Raw materials may include solvents, initiators, monomers, catalysts, and the like. Also, the raw material table may include arbitrary data regarding raw materials other than the example given in FIG. As an example, it may include data regarding the quantity of each arbitrary ingredient related to ingredients.

FIG. 6 is a specific example of the operating condition table. The operating condition table 43 shown in FIG. 6 has items such as product, product number, reactor, heating time, reaction temperature 1, reaction temperature 2, and hold time as operating conditions (second operating conditions).
Items of product and product number are the same as those of the product table 41 .
The reactor is information specifying the reactor (first reactor) used to produce the product.
Heating time, reaction temperature 1, reaction temperature 2, hold time, etc. are conditions relating to the temperature of the reactor.
Also, the operating condition table may include any operating conditions other than the examples given in FIG. As an example, the input timing for each raw material may be included.

FIG. 7 is an explanatory diagram of spectroscopic analysis. As shown in FIG. 7, the production part is sent from the inside of the reactor and spectroscopic analysis is performed. By obtaining spectral data of the product using a photometer and constructing a regression equation, it is possible to create a regression equation for obtaining a quality value from the spectral data.
Spectral data obtained from an existing product is obtained as a first emission spectrum. The first emission spectrum or the quality value obtained from the first emission spectrum is stored in the product table 41 to be stored in the storage unit.
Spectral data obtained from the new product is obtained as a second emission spectrum. The second emission spectrum or the quality value obtained from the second emission spectrum is used for output to managers and for operation control of chemical plants.
In addition, in FIG. 7, the product fed from the reactor is used for the spectroscopic analysis, but the configuration may be such that the light emission inside the reactor is spectroscopically obtained to acquire the emission spectrum.

FIG. 8 is an explanatory diagram of the predictive reaction model. The predictive reaction model is a reactor model that simulates a reactor on a computer, and when input as an explanatory variable, it outputs an objective variable.

Objective variables of the predictive response model are quality values and the like.
Explanatory variables include raw materials, amounts of raw materials, operating conditions, reactors, theoretical formulas, room temperature, production volume, and the like.
Of the explanatory variables, raw materials and operating conditions are operable factors that can be manipulated during production.
Of the explanatory variables, room temperature and the like are environment variables. The reactor can also be included in the environment variables if the reactor to be used is specified.
Of the explanatory variables, the amount of raw materials and the amount of production are load variables.

The predictive reaction model can be created from theory or by machine learning, and it is also possible to combine creation from theory and creation by machine learning for each parameter. Here, as an example of creating a prediction reaction model from theory, after preparing and analyzing a basic prediction model formula based on chemical theory considering the reaction system, the coefficients can be corrected by data analysis. can.
A theoretical model created from theory does not require existing data, and has the advantage of being able to predict unknown reactions from experimental data. Such parts can be supplemented with machine learning models.
Which model to use and how to combine each model can be automatically determined by machine learning.

FIG. 9 is an explanatory diagram of creating a model from theory.
In the first step (STEP 1), physical modeling is performed as follows.
For example, the production rate of the product [C] is evaluated as follows from the concentration [Ai] of the raw material i (i=1 to n), the catalyst concentration [Cat], and the Arrhenius equation.
d[C]/dt = -(1/ai)・d[Ai]/dt = k・[Cat]**a・exp(-E/RT)・Πi[Ai]**ai
Then, a physical model is created by incorporating it into the material balance formula relating to the raw material.

In the next step (STEP 2), the activation energy E, action orders α and ai (i=1 to n) are determined by multiple regression analysis.
In the next step (STEP 3), analysis values are predicted from actual operation data based on the created model, and deviations from the actual data are corrected by data analysis to improve accuracy.
For example, a raw material vaporization term is created using apparatus data, and a raw material addition term is created from the raw material addition amount, raw material analysis value, and the like.

FIG. 10 is an explanatory diagram of creating a model using machine learning.
In the first step (STEP 1), a theoretical model of the predicted reaction is created based on machine learning.
In the next step (STEP 2), terms related to reactions are created as individual explanatory variables in the theoretical model constructed. For example, a term for raw material evaporation and a term for raw material reflux can be created.
In the next step (STEP 3), the data created in STEP 2 are added to the prediction formula as explanatory variables, thereby improving the prediction accuracy.

11 and 12 are explanatory diagrams of the use of the predictive reaction model.
In FIG. 11, in the process including the first to third steps, data up to the second step are used as explanatory variables of the predictive reaction model to predict events after the second step.
Also, one or more progress analysis points are set during the second step, and a final analysis point is set after the third step, and the quality of the product is confirmed at the progress analysis points and the final analysis points.
If the data up to the second step are given as explanatory variables to the predictive reaction model, the quality values at the progress analysis point and the final analysis point can be obtained as objective variables. The first to third steps are a combination of steps in which the reaction is accelerated by changing the temperature or keeping the temperature constant, and the chemical change is performed by changing the state or stabilizing the reaction.

In FIG. 12, a model that predicts the future based on current information makes it possible to predict even a process involving large control.
For example, if the current time is between the first and second follow-up analysis points, give data including the quality at the first follow-up analysis point to the predictive response model as an explanatory variable. , the quality values of the second progress analysis point and one final analysis point can be obtained as objective variables.

FIG. 13 is a flow chart showing the processing procedure of the chemical plant management device 10. As shown in FIG. The chemical plant management device 10 first accumulates data on existing products (step S101). The existing product data includes information on the raw materials, reactors, and operating conditions that produce the product. The chemical plant management device 10 creates a prediction reaction model from existing product data and stores it in the auxiliary storage device 16 as a storage unit (step S102).
Here, the quality data 33 of each product may be used when creating a predictive reaction model from existing product data. As an example, information on the spectroscopic analysis of the product may be used as one of the feature values of the explanatory variables, or may be used as the objective variable. In particular, in chemical plants that handle a wide variety of products, there are many cases where there is a lack of information that can be used as objective variables.
The chemical plant management device 10 obtains the degree of similarity for the created predictive reaction models, and groups similar predictive reaction models so that they belong to the same group (step S103).
Grouping may be based on product type, such as part number, chemical or physical properties of the product, treatment of a particular process involved in the reactor or operating conditions, and the like. In addition, those that cannot be grouped by these criteria may be grouped on the key explanatory factors of the predictive response model.

When the chemical plant management apparatus 10 receives the input of new product data (step S104), it identifies a group similar to the new product data (step S105). Here, the new product data includes information on the reactor that produces the product. Then, a new product prediction reaction model is created from the prediction reaction models of the similar group and stored in the auxiliary storage device 16 as a storage unit (step S106).

The chemical plant management device 10 identifies the raw materials and operating conditions of the new product from the similar group of raw materials, operating conditions, etc. and the predicted reaction model of the new product (step S107). Then, the specified raw materials and operating conditions are output (step S108), and the process ends.
The output is, for example, providing information to the administrator. Further, by using the output to control the operation of the chemical plant, automatic operation of the chemical plant may be performed. Additionally, it is possible to modify the predictive reaction model based on the output and the actual results produced.
Here, regarding the grouping in step S103, the case of creating a set of groups for the multidimensional parameters of the product has been described. You can create a group in . In this case, when input is received for new product data, in step S105, similar groups are identified for each type, and in step S107, a plurality of Identify new product feedstocks and operating conditions from predictive reaction models. As a result, it is possible to perform specification that considers the influence of each type of a plurality of characteristics. Here, the chemical plant management device 10 determines a similar group based on the type of characteristic that is more important in identifying the raw material and operating conditions of the new product from among the similar groups identified for each type of characteristic, may be used to identify the raw materials and operating conditions for the products of As a result, it is possible to specify the degree of influence of each characteristic type, and an improvement in accuracy can be expected.
Here, when producing a new product in a reactor, the products in the existing predictive reaction model that are included in the analogous group used to create the predictive reaction model for the new product are the new products may be configured to be the same as That is, when specifying the materials and operating conditions for making a new product in a reactor, the materials and operating conditions for the same product as the new product produced in a different reactor in the past. may be configured to use
Also, the reactor that produces the new product and the reactor in the existing predictive reaction model that is included in the similar group used to create the predictive reaction model for the new product should be the same reactor. may be configured. That is, when specifying the materials and operating conditions for making a new product in a reactor, the materials and operating conditions for a product different from the new product produced in the same reactor in the past. and may be configured to use.

The output of raw materials and operating conditions by the predictive reaction model may be executed before production or during production.
For example, it may be used to detect anomalies in the production of new products. As an example, determination information, which is information about a predetermined condition indicating the occurrence of an abnormality in the production of a product, is stored in the auxiliary storage device 16 or the like, and prediction is performed in real time using a prediction reaction model during production, and the prediction result and the It may be determined whether an abnormality occurs by comparing the determination information. Here, the predetermined conditions indicating the occurrence of abnormality are various conditions determined for each plant facility or product. Examples include conditions such as product properties failing to meet desired conditions and pressure being greater than a predetermined threshold. Then, when it is determined that an abnormality has occurred, it identifies how the operating conditions should be changed based on the information on the abnormality, the operating conditions up to that point, and the past operating performance data, and changes the identified operating conditions to the first. It can be output as three operating conditions.
In addition, instead of outputting the specified operating conditions as the third operating condition, predictions are made in real time using the prediction reaction model during generation, and the operating conditions, etc. are automatically changed to the controller that controls the plant equipment. The configuration may be such that an instruction is given.

FIG. 14 is a specific example of display output by the display unit. The display output in FIG. 14 shows a quality prediction curve, product information, operating parameters, and quality prediction values.
The quality prediction curve is a graphical representation of the prediction results of the prediction reaction model, and can indicate the prediction of quality under various operating conditions. Also, the quality control value as the target range of the quality value is shown in the graph, and it can be confirmed whether or not the quality value reaches the quality control value.

Product information includes date of manufacture, product, part number, lot, reactor, and range of quality control values.
The operating parameters indicate the current temperature and pressure, and the recommended operating temperature and pressure.
The quality prediction value indicates the current reaction end time and quality prediction value, and the reaction end time and quality prediction value of the recommended operation.
Recommended operation in operating parameters and quality prediction values correspond to guidance indications of the quality prediction curve.

In addition, arbitrary information regarding generation can be used for the display output.
For example, for each explanatory variable in the predictive reaction model of a new product, the correlation with the objective variable of the predictive reaction model is evaluated using machine learning, and the information of the explanatory variable and the correlation of the explanatory variable with the objective variable are evaluated. The index information to be shown may be displayed in descending order of correlation with the objective variable.
With such a display, it is possible to clearly indicate what factors influence the quality of the product.
Further, the chemical plant management apparatus 10 may store a reactor model that simulates a reactor on a computer in the auxiliary storage device 16 . In this case, the chemical plant management device 10 inputs information specified as raw materials and operating conditions for generating a new product into the reactor model and performs calculations to determine the substance generated by the reactor model. can be specified. By simulating the second reactor in this way, the substance obtained as the second product can be predicted.
In addition, by inputting information on arbitrary raw materials and operating conditions into a reactor model and performing calculations, by specifying substances produced by the reactor model, the information on the input raw materials and operating conditions and virtually obtained A new predictive reaction model can be obtained from the information on the substances produced by the reactor model obtained. As a result, it is possible to increase the number of samples of existing predictive reaction models to be used when creating new models.

As described above, the disclosed chemical plant management device 10 provides, in a chemical plant, information on the first raw material to be fed into the first reactor, information on the first operating conditions, information on the first reaction, and a storage unit storing information about a first product produced by introducing the first raw material into the reactor and using the first operating conditions; and a second product produced in the second reactor. an input unit for inputting an entity; and a control unit for generating a plurality of property groups based on the information about the first product so that each of the plurality of first products having a property within a predetermined range is included. , wherein the control unit selects, based on the properties of the second product and the range of properties of the plurality of property groups, a predetermined selection of the plurality of property groups that includes the second product identifying a property group and producing the second product in the input second reactor based on information about the plurality of first products included in the identified predetermined property group; It is characterized by specifying a second raw material and a second operating condition for.

Such a configuration utilizes experience with a known product (first product) to classify the first product into one of a plurality of property groups, and the product of interest (second product) It is possible to specify the raw materials and operating conditions of the second product by specifying the property groups that should be classified based on the properties of the target product (secondary product). It is possible to identify the raw materials and operating conditions of the target product from information on products with similar properties.

Further, the control unit generates a plurality of property groups each including a plurality of the first products having properties within a predetermined range, based on the information about the first product, for each property type, The information about the second product is provided with the information of the characteristic group in which the second product is included, and the second raw material and the second operating condition for producing the second product are determined. , may be specified based on the first raw material and the first operating condition included in the assigned characteristic group.
In such a configuration, the first product is grouped by property, the second product is identified into a group to be classified by property, and the first product is grouped by each property of the second product. can be extracted and the extracted first product can be used as a similar product to identify the source and operating conditions for the second product.

Also, the range of the characteristics of the first product is determined based on information on the part number of the product representing the first product.
Since the product number is assigned according to the composition of the product, it is possible to easily identify similar products by using the product number as a characteristic.

Further, the storage unit stores a second reactor model that simulates the second reactor on a computer, and the control unit stores information on the second raw material and the second operation By inputting information on conditions into the second reactor model and performing calculations, substances produced by the second reactor model are specified.
By simulating the second reactor in this way, the substance obtained as the second product can be predicted.

Further, the storage unit stores a first reactor model that simulates the first reactor on a computer, and the control unit stores information on the first raw material and the first operation By inputting the condition information into the first reactor model and performing calculations, the substance produced by the first reactor model is specified, and the information of the first raw material and the first operating condition are specified. The second raw material and the second operating conditions for producing the second product may be specified based on the information and the information on the substance produced by the first reactor model.
With such a configuration, the first reactor can be simulated, and the raw materials and operating conditions for the second product can be specified based on the virtually obtained information on the first product.

The first product and the second product may be of the same product type.
Also, the first reactor and the second reactor may be the same reactor.
In this way, by using the information on the first product that matches the product and reactor, the information on the second product can be obtained with high accuracy.

Further, it has a first spectroscopic input unit that spectroscopically emits light inside the first reactor and acquires a first emission spectrum, and the control unit receives information on the acquired first emission spectrum. stored in a storage unit, and when specifying the second raw material and the second operating condition, based on the first emission spectrum in addition to the first operating condition and the first operating condition It is good also as a structure to specify.
Further, it has a second spectroscopic input unit that spectroscopically emits light inside the second reactor and acquires a second emission spectrum, and the control unit receives information on the acquired second emission spectrum. stored in the storage unit, and displaying information on the second operating conditions or changes in the second operating conditions on the display unit based on the second emission spectrum before or during the operation of the second reactor; It is good also as a structure which displays.
In this way, spectroscopic analysis can be used to assess the quality of the first product and the second product, thereby predicting the quality of the second product and determining the raw materials and operations to meet quality requirements. Conditions can be specified.

Further, a display unit for displaying information to the administrator is further provided, and the storage unit further includes information regarding an index related to generation of the product, which relates to a predetermined condition indicating the occurrence of an abnormality in the generation of the product. Judgment information, which is information, is stored, and the control unit inputs the information on the second raw material and the information on the second operating conditions to the second reactor model, and calculates the result and the Based on the determination information, it is determined whether an abnormality will occur when the vehicle is operated under the second operating condition, and if it is determined that an abnormality will occur when the vehicle is operated under the second operating condition, A third operating condition may be specified based on the information on the abnormality and the second operating condition, and the third operating condition may be displayed on the display unit.
According to such a configuration, it is possible to predict the production result of the second product in real time and display the operating conditions for avoiding the abnormality.

Further, it has an acquisition unit that acquires information about the second product produced in the second reactor and control performance data of the device from the controller of the device related to the control of the second reactor. and the control unit generates information about control instructions for equipment related to control of the second reactor based on the specified second raw material and the second operating condition, and is transmitted to the controller, the acquired information about the second product produced in the second reactor and the control performance data are stored in the storage unit, and the second reactor is in operation or The second operating conditions may be changed before operation based on the information on the second product produced in the second reactor and the control performance data.
According to such a configuration, the production result of the second product can be predicted in real time, and the chemical plant can be automatically operated.

Further, the information about the first product includes information of a predicted reaction model about the reaction that generates the first product in the first reactor, and the control unit transmits the information about the first product to the When performing the process of dividing the first product into one of a plurality of groups based on the range of characteristics of the first product, determining the similarity of the predicted reaction model based on at least the range of characteristics of the first product, Classifying the information about the first product into one of the plurality of groups based on the degree of similarity, and identifying a predetermined group in which the characteristics of the second product are included in the range of characteristics of the group. and when specifying the second raw material and the second operating condition based on the first raw material and the first operating condition included in the specified group, the specified creating a predicted reaction model for the reaction that produces the second product in the second reactor based on the predicted reaction model for the first product included in the predetermined group; The second raw material and the second operating condition may be specified based on a model.
In such a configuration, the predicted reaction model of the first product similar to the second product is used to generate the predicted reaction model of the second product, and the raw materials and operating conditions of the second product are obtained. be able to.

In addition, the control unit evaluates the correlation with the objective variable of the predicted reaction model for each explanatory variable in the predicted reaction model regarding the reaction that produces the second product in the second reactor, and the explanatory variable and the index information indicating the correlation between the explanatory variable and the objective variable may be displayed on the display unit in descending order of the correlation with the objective variable.
With such a configuration, it is possible to simply indicate what kind of factor affects the quality of the second product.

In addition, the present invention is not limited to the above-described embodiments, and includes various modifications. For example, the above-described embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to those having all the described configurations. Moreover, not only deletion of such a configuration but also replacement and addition of the configuration are possible.

For example, in the above embodiment, for the sake of simplicity, a novel product that has not been produced so far was described as an example of the “second product”, but in the first reactor The product produced may be used as a "second product" when produced in the second reactor.
In addition, the reason for exemplifying the production of a small amount of a wide variety of products is to show that prediction is possible regardless of the presence or absence of a track record for the target product, and the present invention is applied to products that are planned to be produced in large quantities. It does not prevent
Also, the timing of executing the grouping of the prediction reaction models may be executed in advance and stored in the storage unit, or may be executed as needed when the data of the second product is received. may

10: chemical plant management device, 11: arithmetic device, 12: main storage device, 13: input unit, 14: display unit, 15: communication interface, 16: auxiliary storage device, 20: data integration base, 31: raw material data, 32: control performance data, 33: quality data, 41: product table, 42: raw material table, 43: operating condition table, 44: prediction reaction model

Claims (15)

In a chemical plant, information on a first raw material to be charged into a first reactor, information on first operating conditions, and the first operation by charging the first raw material to the first reactor a storage unit storing information about the first product generated using the conditions;
an input unit for inputting a second product produced in the second reactor;
a control unit that generates a plurality of property groups based on information about the first product so that each of the plurality of first products having a property within a predetermined range is included;
The control unit
identifying a predetermined property group among the plurality of property groups that includes the second product based on the property of the second product and the range of properties of the plurality of property groups;
a second feedstock for producing the second product in the input second reactor based on information about the plurality of first products included in the identified predetermined property group; and a second operating condition. In the plant management device according to claim 1,
The control unit
generating a plurality of property groups each containing a plurality of the first products having properties within a predetermined range, based on the information about the first product, for each property type;
giving information about the second product with information about the property group in which the second product is included;
characterized in that the second raw material and the second operating conditions for producing the second product are specified based on information of the plurality of first products included in the assigned property group. and chemical plant management equipment. In the chemical plant management device according to claim 1,
A chemical plant management apparatus, wherein the range of characteristics of the first product is determined based on information of a product number indicating the first product. In the chemical plant management device according to claim 1,
The storage unit stores a second reactor model that simulates the second reactor on a computer,
The control unit inputs the information on the second raw material and the information on the second operating conditions to the second reactor model and performs calculations to determine the substance produced by the second reactor model. A chemical plant management device characterized by specifying. In the chemical plant management device according to claim 4,
The storage unit stores a first reactor model that simulates the first reactor on a computer,
The control unit
inputting the information of the first raw material and the information of the first operating condition into the first reactor model and performing calculations to identify substances produced by the first reactor model;
a second raw material that produces the second product and a first A chemical plant management device characterized by specifying two operating conditions. In the chemical plant management device according to claim 1,
The chemical plant management device, wherein the first product and the second product are of the same product type. In the chemical plant management device according to claim 1,
A chemical plant management apparatus, wherein the first reactor and the second reactor are the same reactor. In the chemical plant management device according to claim 1,
a first spectroscopic input unit that spectroscopically emits light inside the first reactor to obtain a first emission spectrum;
The control unit
storing the acquired information of the first emission spectrum in a storage unit;
A chemical plant characterized in that when specifying the second raw material and the second operating conditions, the specification is made based on the first emission spectrum in addition to the information on the plurality of first products. management device. In the chemical plant management device according to claim 1,
a second spectroscopic input unit that spectroscopically emits light inside the second reactor to obtain a second emission spectrum;
The control unit
storing the acquired information of the second emission spectrum in a storage unit;
characterized by displaying information on the second operating condition or a change in the second operating condition on the display unit based on the second emission spectrum before or during the operation of the second reactor. chemical plant management equipment. In the chemical plant management device according to claim 4,
Furthermore, it has a display unit that displays information to the administrator,
The storage unit further stores determination information, which is information about an index related to the generation of the product, and is information about a predetermined condition indicating the occurrence of an abnormality in the generation of the product,
The control unit inputs the information of the second raw material and the information of the second operating condition into the second reactor model, and based on the result of calculation and the judgment information, the second Determine whether an abnormality occurs when operating under the operating conditions,
When it is determined that an abnormality occurs when the vehicle is operated under the second operating condition, a third operating condition is specified based on the information on the abnormality and the second operating condition, and the third operating condition is specified. is displayed on the display unit. In the chemical plant management device according to claim 1,
an acquisition unit that acquires information about the second product produced in the second reactor and control performance data of the device related to control of the second reactor from a controller of the device; cage,
The control unit
generating information about control instructions for devices related to control of the second reactor based on the identified second raw material and the second operating conditions, and transmitting the information to the controller;
storing the acquired information about the second product produced in the second reactor and the control performance data in a storage unit;
Changing the second operating conditions during or before the operation of the second reactor based on the information regarding the second product produced in the second reactor and the control performance data. A chemical plant management device characterized by: In the chemical plant management device according to claim 1,
the information about the first product includes predicted reaction model information about the reaction that produces the first product in the first reactor;
The control unit
When performing the process of dividing the information about the first product into one of a plurality of groups based on the range of characteristics of the first product, the similarity of the predicted reaction model is at least the first product and classifying the information about the first product into one of the plurality of groups based on the similarity,
identifying a predetermined group in which the properties of the second product fall within the range of the properties of the group, and based on the first raw material and the first operating condition included in the identified predetermined group Then, when specifying the second raw material and the second operating condition, the second reaction is performed based on a predicted reaction model for the first product included in the specified predetermined group creating a predictive reaction model for the reaction that produces the second product in the reactor, and specifying the second raw material and the second operating conditions based on the predictive reaction model Plant management equipment. In the chemical plant management device according to claim 12,
The control unit
For each explanatory variable in the predicted reaction model for the reaction that produces the second product in the second reactor, evaluate the correlation with the objective variable of the predicted reaction model,
A chemical plant management apparatus, wherein information on the explanatory variable and information on an index indicating a correlation between the explanatory variable and the objective variable are displayed on a display unit in descending order of correlation with the objective variable. In a chemical plant, information on a first raw material to be charged into a first reactor, information on first operating conditions, and the first operation by charging the first raw material to the first reactor a storage unit storing information about the first product generated using the conditions;
an input unit for inputting a second product produced in the second reactor;
a control unit that generates a plurality of property groups based on information about the first product so that each of the plurality of first products having a property within a predetermined range is included;
The control unit
identifying a predetermined property group among the plurality of property groups that includes the second product based on the property of the second product and the range of properties of the plurality of property groups;
a second feedstock for producing the second product in the input second reactor based on information about the plurality of first products included in the identified predetermined property group; and a second operating condition. In a chemical plant, information on a first raw material to be charged into a first reactor, information on first operating conditions, and the first operation by charging the first raw material to the first reactor storing information about the first product generated using the conditions in a storage unit;
receiving input of a second product to be produced in the second reactor;
generating a plurality of property groups each containing a plurality of said first products having a predetermined range of properties based on information about said first products;
identifying a predetermined property group of the plurality of property groups in which the second product is included based on the property of the second product and the range of properties of the plurality of property groups;
a second feedstock for producing the second product in the input second reactor based on information about the plurality of first products included in the identified predetermined property group; and identifying a second operating condition.

Images