# US 2024/0003246 A1 · Systems and methods for detecting abnormal flowback

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

- Number: US 2024/0003246 A1
- Document ID: US20240003246A1
- Status: Published application
- Kind: A1
- Application number: 18/343,870
- Filed: 2023-06-29
- Published: 2024-01-04
- Earliest claimed: 2022-06-30
- Assignees: Schlumberger Technology Corporation
- Applicants: Schlumberger Technology Corporation
- Inventors: Chao Mu; Florian Le Blay; Tao Yu
- Web page: https://patentgrep.com/patent/US20240003246A1

## CPC

- E21B 21/08: Controlling or monitoring pressure or flow of drilling fluid, e.g. automatic filling of boreholes, automatic control of bottom pressure (valve arrangements therefor E21B21/10)
- E21B 47/10: Locating fluid leaks, intrusions or movements
- E21B 44/00: Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions
- G08B 21/182: {Level alarms, e.g. alarms responsive to variables exceeding a threshold}
- E21B: EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS

## Abstract

A method of analyzing flowback of a downhole system includes generating active flowback data by monitoring an active flowback from a wellbore. Historic flowback data for historic flowback from the wellbore is used to determine a flowback cluster. The flowback cluster is selected based on comparing the active flowback data to the historic flowback data and determining one or more data instances of the historic flowback data that have features that are similar to that of the active flowback data. Based on the flowback cluster, one or more thresholds may be determined in order to generate an alert when the active flowback data exceeds the thresholds.

## Claims

### Claim 1

A method of analyzing flowback of a downhole system, comprising:
generating active flowback data by monitoring an active flowback from a wellbore;
identifying historic flowback data for historic flowback from the wellbore;
determining a flowback cluster based on comparing the active flowback data to the historic flowback data;
generating a flowback threshold based on the flowback cluster; and
generating an alert based on the active flowback data exceeding the flowback threshold.

### Claim 2 (depends on 1)

The method of claim 1, further including identifying an active pump off period of the downhole system, wherein the active flowback data corresponds to the active pump off period.

### Claim 3 (depends on 2)

The method of claim 2, wherein the historic flowback data corresponds to at least one instance of a prior pump off period.

### Claim 4 (depends on 2)

The method of claim 2, wherein the active flowback data is generated during a same run of a downhole tool corresponding with the historic flowback data.

### Claim 5 (depends on 1)

The method of claim 1, wherein determining the flowback cluster includes identifying at least one instance of the historic flowback data having similar prior conditions as the active flowback data.

### Claim 6 (depends on 5)

The method of claim 5, wherein the similar prior conditions include at least one of: a flow rate, a depth of a downhole tool, a standpipe pressure, and a flow pattern.

### Claim 7 (depends on 1)

The method of claim 1, wherein the flowback threshold includes an upper bound and generating the alert is based on the active flowback data exceeding the upper bound.

### Claim 8 (depends on 1)

The method of claim 1, further including adjusting a parameter of the downhole system based on the alert.

### Claim 9 (depends on 1)

The method of claim 1, wherein determining the flowback cluster includes filtering at least one instance of the historic flowback data based on a data quality of the at least one instance.

### Claim 10 (depends on 1)

The method of claim 1, wherein identifying the historic flowback data includes generating and caching the historic flowback data by monitoring a historic flowback from the wellbore.

### Claim 11 (depends on 1)

The method of claim 1, further including clearing a cache of the historic flowback data based on tripping a downhole tool from the wellbore.

### Claim 12 (depends on 1)

The method of claim 1, further including clearing at least one instance of the historic flowback data from a cache of the historic flowback data based on a time interval.

### Claim 13 (depends on 1)

The method of claim 1, further comprising canceling the alert based on the active flowback data passing an alert-off threshold that is different than the flowback threshold.

### Claim 14 (depends on 1)

The method of claim 1, wherein the flowback threshold is automatically generated in real time upon identifying an active pump off period.

### Claim 15

A method of analyzing flowback of a downhole system, comprising:
generating active flowback data by monitoring an active flowback from a wellbore;
identifying historic flowback data for historic flowback from the wellbore;
determining a flowback cluster based on comparing the active flowback data to the historic flowback data; and
predicting the active flowback based on the flowback cluster.

### Claim 16 (depends on 15)

The method of claim 15, wherein predicting the active flowback includes generating a best fit curve based on the flowback cluster.

### Claim 17 (depends on 16)

The method of claim 16, wherein predicting the active flowback includes computing a probabilistic distribution of the flowback cluster based on the best fit curve.

### Claim 18 (depends on 17)

The method of claim 17, wherein predicting the active flowback includes generating a threshold based on a standard deviation of the probabilistic distribution.

### Claim 19 (depends on 17)

The method of claim 17, wherein the probabilistic distribution is a gaussian distribution.

### Claim 20

A system, comprising:
at least one processor;
memory in electronic communication with the at least one processor; and
instructions stored in the memory, the instructions being executable by the at least one processor to:
generate active flowback data by monitoring an active flowback from a wellbore;
identify historic flowback data for historic flowback from the wellbore;
determine a flowback cluster based on comparing the active flowback data to the historic flowback data;
generate a flowback threshold based on the flowback cluster; and
generate an alert based on the active flowback data passing the flowback threshold.
