# US 2025/0116185 A1 · Processes for monitoring corrosion and carrying out operational plans using same

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0116185 A1
- Document ID: US20250116185A1
- Status: Published application
- Kind: A1
- Application number: 18/483,330
- Filed: 2023-10-09
- Published: 2025-04-10
- Earliest claimed: 2023-10-09
- Assignees: Schlumberger Technology Corporation
- Applicants: Schlumberger Technology Corporation
- Inventors: Sachit Saumya; Apoorva Kumar; Wael Abdallah; Duaa Abdrabalamir Alsenan; Ali Hussein Al Ali
- Web page: https://patentgrep.com/patent/US20250116185A1

## CPC

- E21B 47/006: {Detection of corrosion or deposition of substances}
- E21B 2200/20: Computer models or simulations, e.g. for reservoirs under production, drill bits
- E21B 2200/22: Fuzzy logic, artificial intelligence, neural networks or the like
- G06N 20/00: Machine learning
- Y10S 138/06: Corrosion
- E21B: EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- Y10S: TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS

## Abstract

Processes for monitoring downhole corrosion and directing operational plans using same. In some embodiments, the process can include acquiring a plurality of corrosion factors for at least one well. The process can also include acquiring a plurality of corrosion loss logs for the at least one well. The plurality of corrosion factors and the plurality of corrosion loss logs can be provided to a repository. The repository can be provided to a machine learning model to generate a corrosion prediction. At least the plurality of corrosion factors, the plurality of corrosion loss logs, and the corrosion prediction can be combined into a user dashboard. The user dashboard can be used to determine an operational plan for the at least one well. The determined operational plan for the at least one well can be carried out.

## Claims

### Claim 1

A process, comprising:
acquiring a plurality of corrosion factors for at least one well;
acquiring a plurality of corrosion loss logs for the at least one well;
providing the plurality of corrosion factors and the plurality of corrosion loss logs to a repository;
providing the repository to a machine learning model to generate a corrosion prediction;
combining at least the plurality of corrosion factors, the plurality of corrosion loss logs, and the corrosion prediction into a user dashboard;
using the user dashboard to determine an operational plan for the at least one well; and
carrying out the determined operational plan for the at least one well.

### Claim 2 (depends on 1)

The process of claim 1, wherein the plurality of corrosion factors comprise two or more of: an age of the well, a location of the well, a lithology of the well, injection rates into the well, production rates recovered from the well, a salinity within the well, a pressure within the well, a temperature within the well, a completion quality of the well, a presence of a nearby aquifer, a presence of cement behind a casing in the well, a fluid type in a borehole of the well, a presence of an external coating, a H2S concentration in the well, and a CO2 concentration in the well.

### Claim 3 (depends on 1)

The process of claim 1, wherein the plurality of corrosion loss logs includes time lapse loss data.

### Claim 4 (depends on 1)

The process of claim 1, wherein the plurality of corrosion loss logs comprises logging data acquired from one or more mechanical tools, one or more ultrasonic tools, one or more electromagnetic tools, or a combination thereof.

### Claim 5 (depends on 1)

The process of claim 1, wherein the machine learning model comprises a retraining model to update the machine learning model using one or more changes to the repository and/or using direct data input.

### Claim 6 (depends on 1)

The process of claim 1, wherein the repository is updated using a new plurality of corrosion factors and/or a new plurality of corrosion loss logs from the at least one well or from at least one additional well.

### Claim 7 (depends on 1)

The process of claim 1, wherein the corrosion prediction comprises a present percentage of metal loss by mass, a dynamic corrosion rate, a future percentage of metal loss by mass, an estimated service lifetime of the at least one well, or a combination thereof.

### Claim 8 (depends on 1)

The process of claim 1, wherein the user dashboard comprises insights, corrosion heatmaps, corrosion hotspots, primary causative factors, and/or a risk profile based on the plurality of corrosion factors.

### Claim 9 (depends on 1)

The process of claim 1, wherein combining at least the plurality of corrosion factors and the plurality of corrosion loss logs further comprises data cleaning, data preparation, time normalization, or a combination thereof.

### Claim 10 (depends on 1)

The process of claim 1, wherein the determined operational plan comprises at least one of planning a well workover, planning a well remediation, planning a corrosion mitigation operation, planning a well completion, and planning a well operation schedule.

### Claim 11 (depends on 1)

The process of claim 1, wherein the machine learning model comprises user defined and controlled input weights.

### Claim 12 (depends on 1)

The process of claim 1, wherein the machine learning model provides a ranking of the corrosion factors according to a corrosion contribution value.

### Claim 13

A process for predicting corrosion to complete a new well, the process comprising:
acquiring a plurality of corrosion factors for at least one well;
acquiring a plurality of corrosion loss logs for the at least one well;
providing the plurality of corrosion factors and the plurality of corrosion loss logs to a repository;
providing the repository to a machine learning model to generate a corrosion prediction;
combining at least the plurality of corrosion factors, the plurality of corrosion loss logs, and the corrosion prediction into a user dashboard;
using the user dashboard to determine an operational plan for at least one new well; and
completing the at least one new well using the determined operational plan.

### Claim 14 (depends on 13)

The process of claim 13, wherein the plurality of corrosion factors comprise two or more of: an age of the well, a location of the well, a lithology of the well, injection rates into the well, production rates recovered from the well, a salinity within the well, a pressure within the well, a temperature within the well, a completion quality of the well, a presence of a nearby aquifer, a presence of cement behind a casing in the well, a fluid type in a borehole of the well, a presence of an external coating, a H2S concentration in the well, and a CO2 concentration in the well.

### Claim 15 (depends on 13)

The process of claim 13, wherein the plurality of corrosion loss logs includes time lapse loss data.

### Claim 16 (depends on 13)

The process of claim 13, wherein the corrosion prediction comprises a present percentage of metal loss by mass, a dynamic corrosion rate, a future percentage of metal loss by mass, an estimated service lifetime of the at least one well, or a combination thereof.

### Claim 17 (depends on 13)

The process of claim 13, wherein the machine learning model comprises a retraining model to update the machine learning model using one or more changes to the repository.

### Claim 18 (depends on 13)

The process of claim 13, wherein combining at least the plurality of corrosion factors and the plurality of corrosion loss logs further comprises data cleaning, data preparation, time normalization, or a combination thereof.

### Claim 19 (depends on 13)

The process of claim 13, wherein the machine learning model includes user defined and controlled input weights.

### Claim 20 (depends on 13)

The process of claim 13, wherein the machine learning model provides a ranking of the corrosion factors according to a corrosion contribution value.
