Method and device for dynamically adjusting pressure intensity of true boiling point distillation instrument device

Abstract

The invention relates to a method and device for dynamically adjusting the pressure intensity of an actual boiling point distillation instrument device, and the method comprises the following steps: fitting a linear equation according to a plurality of historical pressure intensity values and a plurality of historical toluene boiling point values corresponding to the historical pressure intensity values by adopting a least square method to obtain the linear equation; substituting at least part of the historical pressure values in all the historical pressure values into a linear square; constructing an input sequence by using the plurality of fitted toluene boiling point values, performing causal convolution processing on the input sequence to obtain a causal convolution value at a prediction moment t, and taking the causal convolution value at the prediction moment t as a y value of a linear equation to calculate a pressure value corresponding to the causal convolution value at the prediction moment t; and when the prediction time t is reached, if the pressure intensity value corresponding to the causal convolution value at the prediction time t is determined to be out of the toluene boiling point standard range, adjusting the pressure intensity of the true boiling point distillation instrument device to the pressure intensity value corresponding to the causal convolution value at the prediction time t, thereby solving the technical problem of hysteresis caused by manual adjustment.

Description

Technical Field

[0001] The present invention relates to the field of quality control, and in particular to a method and a device for dynamically adjusting the pressure of a true boiling point distillation device. Background Art

[0002] Currently, existing solutions generally adjust the pressure of the true boiling point distillation device based on product quality or technician experience. However, due to the lag in manual adjustment, there is a high risk of product quality issues. Summary of the Invention

[0003] (1) Technical issues to be resolved

[0004] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a method and apparatus for dynamically adjusting the pressure of a true boiling point distillation apparatus, which solves the technical problem of hysteresis caused by manual adjustment in the prior art.

[0005] (2) Technical solution

[0006] In order to achieve the above objectives, the main technical solutions adopted by the present invention include:

[0007] In a first aspect, an embodiment of the present invention provides a method for dynamically adjusting the pressure of a true boiling point distiller, comprising: obtaining a historical production report data set of a toluene production process of the true boiling point distiller in the past specified time period through a LIMS system; wherein the historical production report data set includes historical pressure values ​​at multiple historical detection moments and historical toluene boiling point values ​​corresponding to each of the multiple historical pressure values; using the least squares method to fit a linear equation based on the multiple historical pressure values ​​and the multiple historical toluene boiling point values ​​corresponding thereto, to obtain a linear equation y=ax+b; wherein y is the fitted toluene boiling point value, x is the pressure value, and the slope a and the intercept b are constants; and all the historical pressure values ​​are fitted. At least part of the historical pressure values ​​are substituted into the linear equation y=ax+b to obtain a plurality of fitted toluene boiling point values ​​corresponding to at least part of the historical pressure values; an input sequence is constructed using the plurality of fitted toluene boiling point values, and the input sequence is causally convolved to obtain the causal convolution value at the predicted time t, and the causal convolution value at the predicted time t is used as the y value of the linear equation y=ax+b to calculate the pressure value corresponding to the causal convolution value at the predicted time t; when the predicted time t is reached, if it is determined that the pressure value corresponding to the causal convolution value at the predicted time t is outside the toluene boiling point standard range, the pressure of the actual boiling point distillation apparatus is adjusted to the pressure value corresponding to the causal convolution value at the predicted time t.

[0008] In one possible embodiment, a linear equation is fitted based on multiple historical pressure values ​​and their corresponding multiple historical toluene boiling point values ​​using the least squares method to obtain the linear equation y=ax+b, including: preprocessing the multiple historical pressure values ​​and their corresponding multiple historical toluene boiling point values ​​to obtain preprocessed data; wherein the preprocessing includes deleting missing values ​​and deleting outliers; and fitting a linear equation based on the preprocessed data using the least squares method to obtain the linear equation y=ax+b.

[0009] In a possible embodiment, the slope a is calculated as follows:

[0010]

[0011] Where n represents the total number of historical pressure values ​​or historical toluene boiling point values, and n is a positive integer; x i represents the i-th historical pressure value, where i is a positive integer less than or equal to n; y i Represents the i-th historical toluene boiling point value.

[0012] In one possible embodiment, the calculation expression of the intercept b is:

[0013]

[0014] Where, It represents the average value of all historical toluene boiling point values; Indicates the average value of all historical pressure values.

[0015] In a second aspect, an embodiment of the present invention provides a device for dynamically adjusting the pressure of a real boiling point distiller, comprising: an acquisition module for acquiring, through a LIMS system, a historical production report data set of a toluene production process of the real boiling point distiller in the past specified time period; wherein the historical production report data set includes historical pressure values ​​at multiple historical detection moments and historical toluene boiling point values ​​corresponding to each of the multiple historical pressure values; a fitting module for fitting a linear equation based on multiple historical pressure values ​​and their corresponding multiple historical toluene boiling point values ​​using a least squares method to obtain a linear equation y=ax+b; wherein y is the fitted toluene boiling point value, x is the pressure value, the slope a and the intercept b is a constant; a substitution module is used to substitute at least part of the historical pressure values ​​in all the historical pressure values ​​into the linear equation y=ax+b to obtain multiple fitted toluene boiling point values ​​corresponding to at least part of the historical pressure values; a causal convolution module is used to construct an input sequence using the multiple fitted toluene boiling point values, and to perform causal convolution on the input sequence to obtain the causal convolution value at the predicted time t, and to use the causal convolution value at the predicted time t as the y value of the linear equation y=ax+b to calculate the pressure value corresponding to the causal convolution value at the predicted time t; an adjustment module is used to adjust the pressure of the actual boiling point distillation apparatus to the pressure value corresponding to the causal convolution value at the predicted time t when the predicted time t is reached.

[0016] In one possible embodiment, the fitting module is specifically used to: preprocess multiple historical pressure values ​​and their corresponding multiple historical toluene boiling point values ​​to obtain preprocessed data; wherein the preprocessing includes deletion of missing values ​​and deletion of outliers; and use the least squares method to fit a linear equation based on the preprocessed data to obtain the linear equation y=ax+b.

[0017] In a possible embodiment, the slope a is calculated as follows:

[0018]

[0019] Where n represents the total number of historical pressure values ​​or historical toluene boiling point values, and n is a positive integer; x i represents the i-th historical pressure value, where i is a positive integer less than or equal to n; y i Represents the i-th historical toluene boiling point value.

[0020] In one possible embodiment, the calculation expression of the intercept b is:

[0021]

[0022] Where, It represents the average value of all historical toluene boiling point values; Indicates the average value of all historical pressure values.

[0023] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a memory for storing a computer program; a processor for executing the computer program stored in the memory, and when the computer program is executed, the processor is used to execute the method for dynamically adjusting the pressure of the true boiling point distillation apparatus as described above.

[0024] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium, which includes computer instructions. When the computer instructions are run on an electronic device, the electronic device executes the method of dynamically adjusting the pressure of the true boiling point distillation device as described above.

[0025] (3) Beneficial effects

[0026] The beneficial effects of the present invention are:

[0027] The present application obtains a historical production report data set of a toluene production process of a real boiling point distiller in the past specified time period through a LIMS system, wherein the historical production report data set includes historical pressure values ​​at multiple historical detection moments and historical toluene boiling point values ​​corresponding to each of the multiple historical pressure values, and uses the least squares method to fit a linear equation based on the multiple historical pressure values ​​and the multiple historical toluene boiling point values ​​corresponding to them, to obtain a linear equation y=ax+b, wherein y is the fitted toluene boiling point value, x is the pressure value, the slope a and the intercept b are constants, and at least part of the historical pressure values ​​in all the historical pressure values ​​are substituted into the linear equation y=ax+b to obtain a linear equation corresponding to at least part of the historical pressure values. A plurality of fitted toluene boiling point values ​​corresponding to historical pressure values ​​are obtained, and an input sequence is constructed using the plurality of fitted toluene boiling point values, and the input sequence is causally convolved to obtain the causal convolution value at the predicted time t, and the causal convolution value at the predicted time t is used as the y value of the linear equation y=ax+b to calculate the pressure value corresponding to the causal convolution value at the predicted time t, and when the predicted time t is reached, if it is determined that the pressure value corresponding to the causal convolution value at the predicted time t is outside the toluene boiling point standard range, the pressure of the actual boiling point distillation device is adjusted to the pressure value corresponding to the causal convolution value at the predicted time t, thereby solving the technical problem of hysteresis caused by manual adjustment in the prior art.

[0028] In order to make the above-mentioned objectives, features and advantages to be achieved by the embodiments of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 A flow chart showing a method for dynamically adjusting the pressure of a true boiling point distillation apparatus provided in an embodiment of the present application is shown;

[0031] Figure 2 A structural block diagram of a device for dynamically adjusting the pressure of a true boiling point distillation apparatus provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0032] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0033] In modern oil production processes, the correlation and verification of product quality and production parameters still present significant pain points. Traditional quality control methods, such as empirical analysis, localized indicator calculations, and static management models, leverage the massive amounts of data accumulated during production operations, making it difficult to establish a systematic quality control system across the entire production chain. These methods, lacking the ability to dynamically analyze multi-dimensional data, are unable to effectively uncover the underlying patterns within the data, making it difficult for companies to maintain sustained and efficient operations in a complex and volatile market environment. More advanced quality control technologies and digital management strategies are urgently needed.

[0034] Furthermore, the existing pressure adjustment method has the following disadvantages:

[0035] Poor real-time performance: Pressure is adjusted based on product quality or technician experience, which results in a lag and increases the risk of product quality issues.

[0036] High Cost: Currently, the process relies on post-distillation quality testing of finished products to verify the rationality of key production parameters, such as pressure. Once product quality deviations occur, repeated adjustments to pressure parameters and multiple verifications of production indicators are required to troubleshoot the issue. This not only significantly prolongs production cycles but also exponentially increases trial-and-error costs.

[0037] In response to the above problems, the embodiments of the present application provide a method and device for dynamically adjusting the pressure of a true boiling point distillation apparatus. By real-time analysis of historical data of the distillation process, the pressure change trend is accurately predicted, and the pressure of the apparatus is dynamically adjusted based on the prediction results, ensuring that the distillation process is always in the optimal working condition, effectively solving the technical difficulties existing in traditional distillation equipment in pressure control, and significantly improving distillation efficiency and energy utilization efficiency.

[0038] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. Instead, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0039] It should be noted that a liquid has a vapor pressure at a specific temperature, which increases as the temperature rises. When the vapor pressure equals the atmospheric pressure, the liquid boils, i.e., reaches its boiling point. Every pure liquid organic compound has a fixed boiling point at a specific pressure. Distillation is the process of boiling a liquid into vapor by heating, and then condensing it into a liquid, which can be used for separation and purification. This application studies the relationship between predicted pressure and the boiling point of toluene, thereby achieving dynamic regulation by predicting the pressure parameters of the toluene production process.

[0040] See Figure 1 , Figure 1 A flowchart illustrating a method for dynamically adjusting the pressure of a true boiling point distiller provided in an embodiment of the present application is provided. It should be understood that this method can be performed by a device for dynamically adjusting the pressure of the true boiling point distiller, and the specific configuration of the device can be configured based on actual needs, and the embodiments of the present application are not limited thereto. For example, the device can be a computer or a server. Specifically, the method includes:

[0041] Step S110: Obtain a historical production report dataset of toluene production processes of the actual boiling point distiller during a specified past time period through the LIMS system. The historical production report dataset includes historical pressure values ​​at multiple historical detection moments and historical toluene boiling point values ​​corresponding to each of the multiple historical pressure values.

[0042] It should be understood that the specific time period of the past specified time period can be set according to actual needs, and the embodiments of the present application are not limited to this.

[0043] For example, the past designated time period may be the past month, the past week, the past day, the past hour, or the like.

[0044] In order to facilitate understanding of the embodiments of the present application, a description is given below using specific embodiments.

[0045] Specifically, the user can select "Gasoline Distillation" as an input item on the LIMS system interface, and can choose the types of report data to be output as "Pressure" and "Toluene Boiling Point." The user can also select a specific time period within the past specified time period and set a specific time interval between adjacent detection moments. The LIMS system can then output a historical production report dataset of the toluene production process of the actual boiling point distillation device within the past specified time period based on the user's input information. The specific time interval can be set based on actual needs, for example, it can be 1 minute or 5 minutes. The historical production report dataset includes multiple historical detection moments, the historical pressure value at each historical detection moment, and the historical toluene boiling point value at each historical detection moment.

[0046] Therefore, the embodiment of the present application realizes automatic data collection and analysis through the LIMS system, reduces manual intervention and improves efficiency.

[0047] Step S120 , using the least squares method to fit a linear equation based on the multiple historical pressure values ​​and their corresponding multiple historical toluene boiling point values, obtains the linear equation y=ax+b, where y is the fitted toluene boiling point value, x is the pressure value, and the slope a and intercept b are constants.

[0048] Specifically, multiple historical pressure values ​​and their corresponding historical toluene boiling point values ​​are preprocessed to obtain preprocessed data. This preprocessing includes removing missing values ​​and outliers. For example, if the toluene boiling point is determined to be less than 135°C or greater than 140°C, the data can be identified as outliers, and the row of data containing the historical detection time, historical pressure value, and historical toluene boiling point value can be deleted. A linear equation is fitted to the preprocessed data using the least squares method to obtain the linear equation y = ax + b. The preprocessed data includes n historical detection times, the historical pressure value for each of the n historical detection times, and the historical toluene boiling point value corresponding to each historical pressure value. y is the fitted toluene boiling point value, x is the pressure value, and the slope a and intercept b are constants. Furthermore, the data preprocessing follows the petrochemical industry standard for normalized filtering data, dynamic convolution kernel parameters, and a complete methodology for updating historical data using causal convolution.

[0049] It should be understood that the specific process of fitting the linear equation based on the preprocessed data using the least squares method to obtain the linear equation y=ax+b can be set according to actual needs, and the embodiments of the present application are not limited to this.

[0050] Alternatively, for the preprocessed data, the historical pressure values ​​can be used as x values ​​in the coordinate system, and the corresponding historical toluene boiling point values ​​can be used as y values, thereby obtaining n data points in the coordinate system, i.e., one data point for each historical detection moment. Furthermore, a straight line y = ax + b can be found such that the sum of the squared errors of all data points to this line is minimized. The objective function is defined as:

[0051]

[0052] Where min a,b It represents the values ​​of a and b that make the straight line y=ax+b minimize the sum of squared errors of all data points to this straight line.

[0053] In order to find the minimum a and b values, the application can take partial derivatives of a and b and set them equal to zero, specifically:

[0054] Find the partial derivative with respect to a:

[0055] Find the partial derivative with respect to b:

[0056] Based on the above two derivatives, we can get a system of linear equations in two variables:

[0057]

[0058] Thus, the closed-form solution of slope a and intercept b can be obtained as:

[0059]

[0060] Where n represents the total number of historical pressure values ​​or historical toluene boiling point values ​​in the preprocessed data, and n is a positive integer; x i represents the i-th historical pressure value, where i is a positive integer less than or equal to n; y i represents the i-th historical toluene boiling point value; It represents the average value of all historical toluene boiling point values; Indicates the average value of all historical pressure values.

[0061] Step S130 , substituting at least a portion of all historical pressure values ​​into the linear equation y=ax+b to obtain a plurality of fitted toluene boiling point values ​​corresponding to at least a portion of the historical pressure values. The all historical pressure values ​​may refer to all historical pressure values ​​in the preprocessed data.

[0062] Specifically, after obtaining the slope a and the intercept b, at least some of the historical pressure values ​​of all the historical pressure values ​​in the preprocessed data can be used as the x values ​​in the linear equation y=ax+b, thereby obtaining multiple fitted toluene boiling point values ​​corresponding to at least some of the historical pressure values. In this application, at least some of the historical pressure values ​​of all the historical pressure values ​​can be substituted into the linear equation y=ax+b, or all of the historical pressure values ​​can be substituted into the linear equation y=ax+b. This operation can be performed according to actual needs, and the embodiments of the application are not limited thereto.

[0063] It should be noted here that the multiple fitted toluene boiling point values ​​obtained by the linear equation y=ax+b are data from the steady-state period of data analysis, and the data from this period can be used as a causal convolution data set for causal convolution processing.

[0064] Step S140, constructing an input sequence using multiple fitted toluene boiling point values, and performing causal convolution processing on the input sequence to obtain the causal convolution value at the predicted time t, and using the causal convolution value at the predicted time t as the y value of the linear equation y = ax + b to calculate the pressure value corresponding to the causal convolution value at the predicted time t.

[0065] It should be noted here that the core convolution parameters of the causal convolution processing are shown in Table 1 below.

[0066] Table 1

[0067]

[0068] And, the mathematical expression used in the causal convolution process is:

[0069]

[0070] For example, in the case of a simple smoothing kernel w=[0.5, 0.3, 0.2] and K=3, when t(2)=(08:33:00), y[2]=0.5*137.3232+0.3*135.1523+0.2*135.5924=136.3342.

[0071] In addition, this application also involves other processing processes, please refer to Table 2 below for details.

[0072] Table 2

[0073]

[0074] And, boundary values: the output of the first K-1 time points (e.g., (t=0,1)) is usually set to 0 or ignored because insufficient historical data can be obtained (in practical applications, this can be handled by filling the historical mean or zero);

[0075] Kernel weight design: If you need to extract trend features, you can design decreasing weights such as (w = [0.6, 0.3, 0.1]) to strengthen the influence of recent data;

[0076] Extended scenario: If the input is a multivariate time series (such as one containing both pressure and temperature), it is necessary to define a convolution kernel for each variable separately and perform weighted aggregation.

[0077] Also, when the causal convolution value at the predicted time t is obtained, the causal convolution value at the predicted time t can be used as the y value of the linear equation y = ax + b, and since the slope a and the intercept b are known, the x value corresponding to the y value at this time can be calculated, that is, the pressure value corresponding to the causal convolution value at the predicted time t.

[0078] Step S150, when the predicted time t is reached, if it is determined that the pressure value corresponding to the causal convolution value at the predicted time t is outside the standard range of the toluene boiling point, the pressure of the actual boiling point distillation device is adjusted to the pressure value corresponding to the causal convolution value at the predicted time t.

[0079] It should be noted here that the standard range of toluene boiling point can be a range set within the LIMS system or a user-defined range.

[0080] In summary, with the help of the above technical solution, the present application obtains the historical production report data set of the toluene production process of the real boiling point distillation device in the past specified time period through the LIMS system, wherein the historical production report data set includes historical pressure values ​​at multiple historical detection moments and historical toluene boiling point values ​​corresponding to each of the multiple historical pressure values, and uses the least squares method to fit a linear equation based on the multiple historical pressure values ​​and their corresponding multiple historical toluene boiling point values ​​to obtain the linear equation y=ax+b, wherein y is the fitted toluene boiling point value, x is the pressure value, the slope a and the intercept b are constants, and at least part of the historical pressure values ​​in all the historical pressure values ​​are substituted into the linear equation y=ax+b to obtain the linear equation corresponding to at least part of the historical pressure values. The method comprises the following steps: first, obtaining a plurality of fitted toluene boiling point values ​​corresponding to the predicted time t, constructing an input sequence using the plurality of fitted toluene boiling point values, and performing causal convolution on the input sequence to obtain the causal convolution value at the predicted time t, and using the causal convolution value at the predicted time t as the y value of the linear equation y=ax+b to calculate the pressure value corresponding to the causal convolution value at the predicted time t, and adjusting the pressure of the actual boiling point distillation device to the pressure value corresponding to the causal convolution value at the predicted time t when the predicted time t is reached, thereby realizing dynamic monitoring and precise control of the production process, effectively reducing the product defective rate, shortening the production cycle, and significantly reducing energy consumption and production costs while improving the core competitiveness of the product, providing innovative solutions for enterprises to achieve lean production and high-quality development.

[0081] In addition, the present application can automatically adapt to complex working conditions such as raw material changes and equipment aging, avoiding control failures caused by fixed parameters in traditional methods.

[0082] It should be understood that the above method of dynamically adjusting the pressure of the true boiling point distillation apparatus is merely exemplary, and those skilled in the art may make various modifications based on the above method, and the modified schemes also fall within the scope of protection of this application.

[0083] See Figure 2 , Figure 2 The following is a block diagram of a device 200 for dynamically adjusting the pressure of a true boiling point distiller according to an embodiment of the present application. It should be understood that the device 200 is capable of executing each step in the above-described method embodiment. The specific functions of the device 200 can be found in the description above. To avoid repetition, a detailed description is omitted herein. The device 200 includes at least one software function module that can be stored in a memory in the form of software or firmware or embedded in the operating system (OS) of the device 200. Specifically, the device 200 includes:

[0084] An acquisition module 210 is configured to acquire, through a LIMS system, a historical production report dataset of a toluene production process of the actual boiling point distiller during a specified past time period; wherein the historical production report dataset includes historical pressure values ​​at multiple historical detection moments and a historical toluene boiling point value corresponding to each of the multiple historical pressure values;

[0085] A fitting module 220 is configured to fit a linear equation based on multiple historical pressure values ​​and their corresponding multiple historical toluene boiling point values ​​using a least squares method to obtain a linear equation y=ax+b, wherein y is the fitted toluene boiling point value, x is the pressure value, and the slope a and intercept b are constants;

[0086] a substitution module 230 for substituting at least a portion of all historical pressure values ​​into the linear equation y=ax+b to obtain a plurality of fitted toluene boiling point values ​​corresponding to at least a portion of the historical pressure values;

[0087] a causal convolution module 240 for constructing an input sequence using a plurality of fitted toluene boiling point values, performing causal convolution on the input sequence to obtain a causal convolution value at a predicted time t, and using the causal convolution value at the predicted time t as the y value of the linear equation y = ax + b to calculate a pressure value corresponding to the causal convolution value at the predicted time t;

[0088] The adjustment module 250 is configured to adjust the pressure of the true boiling point distiller to a pressure value corresponding to the causal convolution value at the predicted time t when the predicted time t is reached.

[0089] In one possible embodiment, the fitting module 220 is specifically used to: preprocess multiple historical pressure values ​​and their corresponding multiple historical toluene boiling point values ​​to obtain preprocessed data; wherein the preprocessing includes deletion of missing values ​​and deletion of outliers; and use the least squares method to fit a linear equation based on the preprocessed data to obtain the linear equation y=ax+b.

[0090] In a possible embodiment, the slope a is calculated as follows:

[0091]

[0092] Where n represents the total number of historical pressure values ​​or historical toluene boiling point values, and n is a positive integer; x i represents the i-th historical pressure value, where i is a positive integer less than or equal to n; y i Represents the i-th historical toluene boiling point value.

[0093] In one possible embodiment, the calculation expression of the intercept b is:

[0094]

[0095] Where, It represents the average value of all historical toluene boiling point values; Indicates the average value of all historical pressure values.

[0096] Since the apparatus described in the above embodiments of the present invention is used to implement the method of the above embodiments of the present invention, those skilled in the art will be able to understand the specific structure and variations of the apparatus based on the method described in the above embodiments of the present invention, and thus will not be described in detail here. All apparatuses used in the method of the above embodiments of the present invention fall within the scope of protection of the present invention.

[0097] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions.

[0099] It should be noted that, in the claims, any reference signs placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims enumerating several means, several of these means may be embodied by one and the same hardware. The use of the words first, second, third etc. is for convenience only and does not indicate any order. These words may be understood as part of the component name.

[0100] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0101] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments after learning the basic creative concept. Therefore, the claims should be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0102] Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if such modifications and variations fall within the scope of the claims and their equivalents, the present invention shall also include such modifications and variations.

Claims

1. A method for dynamically adjusting the pressure of a true boiling point distillation apparatus, characterized in that: include: Obtaining, through the LIMS system, a historical production report data set of a toluene production process of the true boiling point distiller during a specified past time period; wherein the historical production report data set includes historical pressure values ​​at a plurality of historical detection moments and a historical toluene boiling point value corresponding to each of the plurality of historical pressure values; Using the least squares method to fit a linear equation based on the multiple historical pressure values ​​and their corresponding multiple historical toluene boiling point values, a linear equation y=ax+b is obtained; wherein y is the fitted toluene boiling point value, x is the pressure value, and the slope a and the intercept b are constants; Substituting at least a portion of the historical pressure values ​​into the linear equation y=ax+b to obtain a plurality of fitted toluene boiling point values ​​corresponding to at least a portion of the historical pressure values; An input sequence is constructed using the multiple fitted toluene boiling point values, and a causal convolution process is performed on the input sequence to obtain a causal convolution value at a predicted time t, and the causal convolution value at the predicted time t is used as the y value of the linear equation y=ax+b to calculate a pressure value corresponding to the causal convolution value at the predicted time t; When the predicted time t is reached, if it is determined that the pressure value corresponding to the causal convolution value at the predicted time t is outside the standard range of the toluene boiling point, the pressure of the actual boiling point distillation device is adjusted to the pressure value corresponding to the causal convolution value at the predicted time t.

2. The method according to claim 1, characterized in that The least square method is used to fit a linear equation based on the multiple historical pressure values ​​and the corresponding multiple historical toluene boiling point values ​​to obtain a linear equation y=ax+b, including: Preprocessing the plurality of historical pressure values ​​and the corresponding plurality of historical toluene boiling point values ​​to obtain preprocessed data; wherein the preprocessing includes deleting missing values ​​and outliers; The least square method is used to fit a linear equation based on the preprocessed data to obtain the linear equation y=ax+b.

3. The method according to claim 1, characterized in that The calculation expression of the slope a is: Wherein, n represents the total number of the historical pressure values ​​or historical toluene boiling point values, and n is a positive integer; x i represents the i-th historical pressure value, where i is a positive integer less than or equal to n; y i Represents the i-th historical toluene boiling point value.

4. The method according to claim 3, characterized in that The calculation expression of the intercept b is: Where, represents the average value of all the historical toluene boiling point values; Represents the average value of all the historical pressure values.

5. A device for dynamically adjusting the pressure of a true boiling point distillation apparatus, characterized in that: include: an acquisition module, configured to acquire, through a LIMS system, a historical production report data set of a toluene production process of the true boiling point distiller during a specified past time period; wherein the historical production report data set includes historical pressure values ​​at a plurality of historical detection moments and a historical toluene boiling point value corresponding to each of the plurality of historical pressure values; A fitting module, configured to fit a linear equation based on the plurality of historical pressure values ​​and their corresponding plurality of historical toluene boiling point values ​​using a least squares method, to obtain a linear equation y=ax+b; wherein y is the fitted toluene boiling point value, x is the pressure value, and the slope a and the intercept b are constants; a substitution module, configured to substitute at least a portion of the historical pressure values ​​into the linear equation y=ax+b to obtain a plurality of fitted toluene boiling point values ​​corresponding to at least a portion of the historical pressure values; a causal convolution module, configured to construct an input sequence using the multiple fitted toluene boiling point values, and perform causal convolution on the input sequence to obtain a causal convolution value at a predicted time t, and use the causal convolution value at the predicted time t as the y value of the linear equation y=ax+b to calculate a pressure value corresponding to the causal convolution value at the predicted time t; An adjustment module is used to adjust the pressure of the true boiling point distiller to the pressure value corresponding to the causal convolution value at the predicted time t when the predicted time t is reached.

6. The device according to claim 5, characterized in that The fitting module is specifically used to: preprocess the multiple historical pressure values ​​and their corresponding multiple historical toluene boiling point values ​​to obtain preprocessed data; wherein the preprocessing includes deletion of missing values ​​and deletion of outliers; use the least squares method to fit a linear equation based on the preprocessed data to obtain the linear equation y=ax+b.

7. The device according to claim 5, characterized in that The calculation expression of the slope a is: Wherein, n represents the total number of the historical pressure values ​​or historical toluene boiling point values, and n is a positive integer; x i represents the i-th historical pressure value, where i is a positive integer less than or equal to n; y i Represents the i-th historical toluene boiling point value.

8. The device according to claim 7, characterized in that The calculation expression of the intercept b is: Where, represents the average value of all the historical toluene boiling point values; Represents the average value of all the historical pressure values.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor is used to execute the computer program stored in the memory. When the computer program is executed, the processor is used to execute the method for dynamically adjusting the pressure of the true boiling point distillation apparatus as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the method for dynamically adjusting the pressure of a true boiling point distillation apparatus as described in any one of claims 1 to 4.

Images