CN-121997693-A - Method, device, equipment and storage medium for determining corrosion condition of equipment

CN121997693ACN 121997693 ACN121997693 ACN 121997693ACN-121997693-A

Abstract

The embodiment of the disclosure provides a corrosion condition determining method, device and equipment of equipment and a storage medium. The method comprises the steps of obtaining first fluid state data for determining corrosion conditions, inputting the first fluid state data into a corrosion condition determination model, outputting predicted corrosion index data corresponding to the first fluid state data, and determining and displaying the corrosion conditions corresponding to target equipment based on the predicted corrosion index data. The technical scheme of the embodiment of the disclosure solves the problem that the corrosion state of the oil refining device cannot be accurately judged in time in the related technology, realizes the automatic monitoring of the corrosion condition, and can ensure the accuracy and precision of the determined result so as to ensure the safety and reliability of equipment.

Inventors

ZHENG YUNDONG
ZHENG GUOQING
XU ZHENNING
WEI HAIOU
GAO ZHONGWEN
WANG DONGSHENG
LI JIA

Assignees

昆仑数智科技有限责任公司
中国石油天然气集团有限公司

Dates

Publication Date: 20260508
Application Date: 20241107

Claims (12)

1.A method for determining corrosion conditions of an apparatus, comprising: acquiring first fluid state data for determining corrosion conditions, wherein the first fluid state data is used for representing state data corresponding to fluid in target equipment; inputting the first fluid state data into a corrosion condition determining model, and outputting predicted corrosion index data corresponding to the first fluid state data, wherein the corrosion condition determining model is a multi-layer feedforward neural network trained based on historical fluid state data, the first historical fluid state data is recorded based on the historical fluid state data, and the predicted corrosion index data comprises a sulfur dew point value; and determining and displaying the corrosion condition corresponding to the target equipment based on the predicted corrosion index data.
2. The method of claim 1, wherein the predicted corrosion indicator data comprises upper and lower values of a target indicator comprising at least one of a sulfur dew point value, a water dew point value, an ammonium salt crystallization point value; The determining, based on the predicted corrosion index data, a corrosion condition corresponding to the target device includes: if the predicted corrosion index data is in a first numerical range of the corresponding type index data, determining that the corrosion condition corresponding to the target equipment is a first type condition, wherein the first type condition is used for indicating that the corrosion degree of the target equipment does not reach the degree of maintenance; If the predicted corrosion index data is not in the first numerical range of the corresponding type index data, determining that the corrosion condition corresponding to the target equipment is a second type condition, wherein the second type condition is used for indicating that the corrosion degree of the target equipment reaches the degree requiring maintenance; if the corrosion condition is the second type of condition, generating and sending out prompt information corresponding to the corrosion condition.
3. The method of claim 1, wherein the corrosion condition determination model is obtained by: determining the number of input layer nodes and the number of output layer nodes in the target model based on the predicted corrosion index data; Determining a training data set and a testing data set of a target model based on sample data generated by the mechanism model corresponding to the target device, wherein the mechanism model is used for representing a model for performing simulation on a process flow of the target device; Inputting the training data set into a target model, and training the target model to obtain a trained target model; inputting the test data set into a trained target model, and optimizing the target model based on a set precision target; And taking the optimized target model as the corrosion condition determining model.
4. The method of claim 3, wherein determining the number of input layer nodes and the number of output layer nodes in the target model based on the predicted corrosion indicator data comprises: The type number of the predicted corrosion index data is used as the output layer node number; determining the type of input data corresponding to the target model based on the type of the target index in the predicted corrosion index data; The number of input layer nodes is determined based on the input data type.
5. The method of claim 4, wherein the input data of the mechanism model is input state data of a fluid input into the target device and the output data of the mechanism model is output state data of a fluid output from the target device; the sample data includes simulation input data input into the mechanism model and simulation output data calculated by the target model based on the simulation input data.
6. The method of claim 5, wherein the determining the training data set and the test data set for the target model based on the sample data generated by the target device corresponding mechanism model comprises: Based on the input data types, determining alternative training data from corresponding sample data in the mechanism model; the training data set and the test data set are determined from the alternative training data based on a set number of groups.
7. A method according to claim 3, wherein said inputting the test dataset into a trained target model and optimizing the target model based on a set precision target comprises: Inputting the test data set into a trained target model, and determining deviation between an output result of the trained target model and corresponding data in the test data set; Optimizing target parameters in the target model based on a first precision target, wherein the target parameters comprise parameters of an activation function in the target model, the number of hidden layers in the target model, the number of nodes in each hidden layer, the iteration times of the target function and the learning rate.
8. The method according to any one of claims 3 to 7, wherein the inputting the first fluid state data into a corrosion condition determination model, after outputting predicted corrosion index data corresponding to the first fluid state data, further comprises; taking the predicted corrosion index data and the corresponding first fluid state data as training data, and adding the training data into an optimized data set; inputting the optimized data set into the corrosion condition determining model, and performing optimization training on the corrosion condition determining model based on the output result of the corrosion condition determining model.
9. A corrosion condition determining apparatus of a device, characterized in that the corrosion condition determining apparatus of the device comprises: A determining module, configured to obtain first fluid status data for determining a corrosion condition, where the first fluid status data is used to represent status data corresponding to a fluid in a target device; The processing module is used for inputting the first fluid state data into a corrosion condition determining model and outputting predicted corrosion index data corresponding to the first fluid state data, wherein the corrosion condition determining model is a multi-layer feedforward neural network trained based on historical fluid state data, the first historical fluid state data is recorded based on the historical fluid state data, and the predicted corrosion index data comprises a sulfur dew point value; and the analysis module is used for determining the corrosion condition corresponding to the target equipment based on the predicted corrosion index data.
10. A control apparatus, characterized by comprising: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein the memory stores instructions executable by the at least one processor to cause the control device to perform the corrosion condition determining method of the device of any one of claims 1 to 8.
11. A computer-readable storage medium, in which computer-executable instructions are stored, which when executed by a processor are adapted to carry out the method of determining the corrosion condition of an apparatus according to any one of claims 1 to 8.
12. A computer program product comprising computer-executable instructions for implementing the method of determining the corrosion condition of an apparatus according to any one of claims 1 to 8 when executed by a processor.

Description

Method, device, equipment and storage medium for determining corrosion condition of equipment Technical Field The disclosure relates to the technical field of petrochemical production, in particular to a method, a device, equipment and a storage medium for determining corrosion conditions of equipment. Background In petrochemical enterprises, periodic and unscheduled maintenance of equipment is an important part of equipment management. The oil refining device is easily affected by corrosion due to long-term bearing of impurities such as sulfur, nitrogen, salt and the like contained in the oil refining device and the influence of severe environmental conditions such as high temperature, high pressure and the like, so that the mechanical performance of the device is reduced, and safety accidents such as leakage, explosion and the like can be possibly caused. Thus, the refinery is periodically inspected to determine its corrosion state so that maintenance can be performed in time when the corrosion state of the refinery is high. In the related art, the corrosion state of the oil refining device is judged by indexes such as a sulfur dew point and a water dew point, but the indexes can only be collected and analyzed by special equipment, so that the calculation is more troublesome, or the range judgment is carried out based on experience of production personnel, so that the corrosion condition of the oil refining device is lower in accuracy and insufficient in reliability, and therefore, the equipment cannot be effectively maintained in time. Disclosure of Invention The embodiment of the disclosure provides a method, a device, equipment and a storage medium for determining corrosion conditions of equipment, so as to solve the problem that the corrosion state of an oil refining device cannot be accurately judged in time in the related art. In a first aspect, an embodiment of the present disclosure provides a method for determining a corrosion condition of an apparatus, where the method includes: Acquiring first fluid state data for determining corrosion conditions, wherein the first fluid state data is used for representing state data corresponding to fluid in target equipment; Inputting the first fluid state data into a corrosion condition determining model, and outputting predicted corrosion index data corresponding to the first fluid state data, wherein the corrosion condition determining model is a multi-layer feedforward neural network trained based on historical fluid state data, the first historical fluid state data is recorded based on the historical fluid state data, and the predicted corrosion index data comprises a sulfur dew point value; And determining and displaying the corresponding corrosion condition of the target equipment based on the predicted corrosion index data. In a second aspect, an embodiment of the present disclosure provides an apparatus for determining a corrosion condition of a device, including: the determining module is used for acquiring first fluid state data for determining corrosion conditions, wherein the first fluid state data is used for representing state data corresponding to fluid in target equipment; The processing module is used for inputting the first fluid state data into a corrosion condition determining model and outputting predicted corrosion index data corresponding to the first fluid state data, wherein the corrosion condition determining model is a multi-layer feedforward neural network trained based on historical fluid state data, the first historical fluid state data is recorded based on the historical fluid state data, and the predicted corrosion index data comprises a sulfur dew point value; and the analysis module is used for determining the corrosion condition corresponding to the target equipment based on the predicted corrosion index data. In a third aspect, embodiments of the present disclosure further provide a control apparatus, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the control device to perform a corrosion condition determining method of the device as in the first aspect of the present disclosure. In a fourth aspect, embodiments of the present disclosure also provide a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, are configured to implement a method for determining corrosion condition of an apparatus according to the first aspect of the present disclosure. In a fifth aspect, embodiments of the present disclosure also provide a computer program product comprising computer-executable instructions for implementing a method of corrosion condition determination of an apparatus as in the first aspect of the present disclosure when executed by a processor. According to the corrosion condition determining method, device, equipme