CN-121998791-A - Method, device, equipment and storage medium for optimizing production operation of fractionating tower

CN121998791ACN 121998791 ACN121998791 ACN 121998791ACN-121998791-A

Abstract

The invention discloses a fractionating tower production operation optimization method, device, equipment and storage medium, wherein the method comprises the steps of determining production operation condition ratings of m fractionating towers according to technological parameters corresponding to the m fractionating towers, determining target technological parameters corresponding to target fractionating towers to be optimized based on the production operation condition ratings, inputting the target technological parameters into an integrated prediction model to obtain carbon number conversion rate corresponding to side extraction temperature output by the integrated prediction model, establishing an optimization model taking minimized carbon number conversion rate as an optimization target, and optimizing production operation of the target fractionating towers to be optimized based on the optimization model, wherein the integrated prediction model comprises a plurality of sub prediction models based on different machine learning algorithms. The invention solves the technical problem that the production operation of the fractionating tower cannot be optimized timely and accurately in the related art.

Inventors

SUN LIANG
LUO FEI
CAO YANMING
DONG FENGLIAN
WANG NAN
SHAN CHAO
LIU PENGFEI

Assignees

中国石油天然气股份有限公司

Dates

Publication Date: 20260508
Application Date: 20241104

Claims (10)

1. A method for optimizing production operation of a fractionation column, the method comprising: determining the production running condition rating of the m fractionating towers according to the corresponding technological parameters of the m fractionating towers, wherein m is a positive integer; Determining target technological parameters corresponding to a target fractionating tower to be optimized based on the production running condition rating; Inputting the target process parameters into an integrated prediction model to obtain carbon number conversion rate corresponding to the lateral line extraction temperature output by the integrated prediction model, wherein the integrated prediction model comprises a plurality of sub-prediction models based on different machine learning algorithms; and establishing an optimization model taking the minimized carbon number conversion rate as an optimization target, and optimizing the production operation of the target fractionating tower to be optimized based on the optimization model.
2. The method of optimizing production operation of a fractionation column according to claim 1, wherein the step of determining a production operating condition rating for the m fractionation column based on the corresponding process parameters of the m fractionation column comprises: determining the index type corresponding to each technological parameter corresponding to each fractionating tower in the m fractionating towers; Performing benefit index homodromous treatment and vector normalization treatment on the technological parameters corresponding to each index type to obtain a normalized decision matrix; determining index weights corresponding to each technological parameter based on an objective weight method, and determining a weighted decision matrix according to the index weights and the normalized decision matrix; determining an optimal solution and a worst solution according to the weighted decision matrix, and calculating Euclidean distance between the technological parameters corresponding to each fractionating tower and the optimal solution and the worst solution; and calculating the relative proximity of each fractionating tower according to the Euclidean distance, and determining the production running condition rating of each fractionating tower according to the relative proximity.
3. The method for optimizing the production run of a fractionation column according to claim 2, wherein the process parameters include a column bottom temperature, a column top temperature, a column pressure, a column bottom liquid level, a column top liquid level, and a feed flow rate; the index types include a benefit type index, a cost type index, an intermediate type index and an interval type index.
4. The method for optimizing production operation of a fractionating tower according to claim 2, wherein the step of performing benefit type index homodromous processing and vector normalization processing on the process parameters corresponding to each index type to obtain a normalized decision matrix comprises the steps of: Converting the technological parameters corresponding to each index type into benefit indexes through conversion formulas corresponding to the cost type indexes, the intermediate type indexes and the interval type indexes respectively; And carrying out vector normalization processing on the original data matrix subjected to benefit index homodromous processing to obtain a normalized decision matrix.
5. The method of optimizing production operations of a fractionation column according to claim 1, wherein the sub-predictive model comprises at least one of a decision tree model, a random forest model, and a support vector machine model.
6. The method of optimizing production operation of a fractionation column according to claim 5, wherein said step of inputting said target process parameter into an integrated prediction model to obtain a carbon number conversion corresponding to a side draw temperature outputted from said integrated prediction model comprises: inputting the target process parameters into each sub-prediction model included in the integrated prediction model to obtain a sub-carbon number conversion rate corresponding to the sub-side extraction temperature output by each sub-prediction model; And carrying out weighted average on the sub carbon number conversion rate corresponding to the sub side extraction temperature output by each sub prediction model to obtain the carbon number conversion rate corresponding to the side extraction temperature output by the integrated prediction model.
7. The method for optimizing production operation of a fractionating tower according to claim 6, wherein the step of weighted averaging the sub carbon number conversion rate corresponding to the sub side draw temperature outputted from each sub prediction model to obtain the carbon number conversion rate corresponding to the side draw temperature outputted from the integrated prediction model comprises: determining an evaluation index of each sub-prediction model based on the test set; determining the weight corresponding to each sub-prediction model according to the evaluation index; And carrying out weighted average on the sub carbon number conversion rate corresponding to the sub side extraction temperature output by each sub prediction model based on the weight to obtain the carbon number conversion rate corresponding to the side extraction temperature output by the integrated prediction model.
8. A fractionation column production run optimization apparatus, the apparatus comprising: the information determining module is configured to determine the production running condition rating of the m fractionating towers according to the process parameters corresponding to the m fractionating towers, wherein m is a positive integer; the information acquisition module is configured to input the target process parameters into an integrated prediction model to obtain carbon number conversion rate corresponding to the side line extraction temperature output by the integrated prediction model, wherein the integrated prediction model comprises a plurality of sub prediction models based on different machine learning algorithms; and the optimization model construction module is used for establishing an optimization model taking the minimized carbon number conversion rate as an optimization target, and optimizing the production operation of the target fractionating tower to be optimized based on the optimization model.
9. An electronic device comprising a memory and a processor for reading and executing a computer program stored in the memory to perform the steps of the fractionation column production run optimization method of any one of claims 1-7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed perform the steps of the fractionation column production run optimization method of any one of claims 1-7.

Description

Method, device, equipment and storage medium for optimizing production operation of fractionating tower Technical Field The invention relates to the technical field of fractionating towers, in particular to a method, a device, equipment and a storage medium for optimizing production operation of a fractionating tower. Background At present, in the fractionating tower of naphtha and aviation kerosene products, products with different prices are mixed or overlapped due to overlapping distillation ranges, so that high-value products are doped in low-value products to influence production benefits, and therefore, the accurate control of the extraction temperature of side line products and the operation parameters of the tower top becomes important. In the related art, the production operation of the fractionating tower is optimized by using an expert subjective method, however, due to the complexity of process control of the fractionating tower, the target response has delay hysteresis, which means that an optimization space needs to be found in time, otherwise, the optimal adjustment time is missed. However, the technical method is difficult to master, popularize and apply for common operators, greatly reduces the accuracy and feasibility of process optimization, and leads to incapability of timely and accurately optimizing the production operation of the fractionating tower. Disclosure of Invention The invention provides a method, a device, equipment and a storage medium for optimizing production operation of a fractionating tower, which can solve the technical problem that the production operation of the fractionating tower cannot be optimized timely and accurately in the prior art. In order to achieve the above purpose, the present invention provides the following technical solutions: In a first aspect, embodiments of the present invention provide a method for optimizing production operation of a fractionation column, the method comprising: determining the production running condition rating of the m fractionating towers according to the corresponding technological parameters of the m fractionating towers, wherein m is a positive integer; Determining target technological parameters corresponding to a target fractionating tower to be optimized based on the production running condition rating; Inputting the target process parameters into an integrated prediction model to obtain carbon number conversion rate corresponding to the lateral line extraction temperature output by the integrated prediction model, wherein the integrated prediction model comprises a plurality of sub-prediction models based on different machine learning algorithms; and establishing an optimization model taking the minimized carbon number conversion rate as an optimization target, and optimizing the production operation of the target fractionating tower to be optimized based on the optimization model. Optionally, the step of determining the production running condition rating of the m fractionation columns according to the corresponding technological parameters of the m fractionation columns includes: determining the index type corresponding to each technological parameter corresponding to each fractionating tower in the m fractionating towers; Performing benefit index homodromous treatment and vector normalization treatment on the technological parameters corresponding to each index type to obtain a normalized decision matrix; determining index weights corresponding to each technological parameter based on an objective weight method, and determining a weighted decision matrix according to the index weights and the normalized decision matrix; determining an optimal solution and a worst solution according to the weighted decision matrix, and calculating Euclidean distance between the technological parameters corresponding to each fractionating tower and the optimal solution and the worst solution; and calculating the relative proximity of each fractionating tower according to the Euclidean distance, and determining the production running condition rating of each fractionating tower according to the relative proximity. Optionally, the process parameters include column bottom temperature, column top temperature, column pressure, column bottom liquid level, column top liquid level, and feed flow; the index types include a benefit type index, a cost type index, an intermediate type index and an interval type index. Optionally, the step of performing benefit type index homodromous processing and vector normalization processing on the process parameters corresponding to each index type to obtain a normalized decision matrix includes: Converting the technological parameters corresponding to each index type into benefit indexes through conversion formulas corresponding to the cost type indexes, the intermediate type indexes and the interval type indexes respectively; And carrying out vector normalization processing on the original data matrix sub