Automatic abnormal trend detection of real time drilling data for hazard avoidance
An abnormal trend detection system for detecting one or more hazards may provide for a safe and effective drilling operation as any of the one or more hazards may be avoided. Several indicators may be defined including a first, second, third and fourth indicator. The indicators are used to identify in a trend analysis abnormal trends. One or more thresholds may be defined. When a trend analysis indicates that a threshold has been reached or exceeded an alarm may be triggered, a drilling operation may be altered or a combination thereof.
1. A method for detecting an abnormal trend in a drilling operation, comprising:
receiving real-time drilling data comprising a plurality of drilling parameters measured during the drilling operation;
determining one or more trend indicators based, at least in part, on the received real-time drilling data, wherein determining the one or more trend indicators comprises:
determining a first trend indicator, wherein the first trend indicator comprises a moving average of the real-time drilling data;
determining a second trend indicator, wherein the second trend indicator comprises a slope of moving linear regression;
determining a third trend indicator, wherein the third trend indicator comprises an average trend, wherein determining the third trend indicator comprises determining:
M
A
K
t
=
∑
i
w
i
,
t
*
M
K
i
,
t
∑
i
w
i
,
t
,
wherein
w
i
,
t
=
1
1
+
exp
[
-
2
i
-
0.5
+
n
-
t
0
.
1
]
,
wherein
i=t−n+1, t−n+2, . . . , t, and wherein n defines a time scale; and
determining a fourth trend indicator, wherein the fourth trend indicator comprises a difference of moving slope average;
determining a trend analysis based, at least in part, on the one or more trend indicators; and
triggering an alarm based, at least in part, on a threshold and the trend analysis.
2. The method of claim 1 , further comprising altering the drilling operation based, at least in part, on the trend analysis.
3. The method of claim 1 , wherein determining the first indicator comprises determining:
DMA t =MA α,t −MA β,t , wherein, α<β, and wherein MA α,t and MA β,t are moving average value at time t with a window length of α and β, respectively.
4. The method of claim 1 , wherein determining the second indicator comprises determining MK t , wherein MK t represents one or more local trends of the received drilling data, and wherein positive values represent positive trends and negative values represent negative trends.
5. The method of claim 1 , wherein determining the fourth trend indicator comprises determining DMAK t =MAK α,t −MAK α,t (α<β), wherein MAK α,t and MAK α,t are MAK t at time t with a window length of α and β, respectively.
6. The method of claim 1 , further comprising:
determining a kick risk index, wherein determining the kick risk index (KRI) comprises determining KRI=w d P d +w f P f , wherein P f and P d represent probability of abnormal conditions of flow parameter group and drilling parameter group, respectively, and wherein w d and w f are weighting factors of P f and P d , respectively, wherein triggering the alarm is based, at least in part, on the kick risk index.
7. The method of claim 1 , wherein the threshold is based, at least in part, on one or more of user input and historical data.
8. A non-transitory computer-readable medium storing one or more instructions that, when executed by a processor, cause the processor to:
receive real-time drilling data;
determine one or more trend indicators based, at least in part, on the received real-time drilling data, wherein determining the one or more trend indicators comprises:
determining a first trend indicator, wherein the first trend indicator comprises a moving average of the real-time drilling data;
determining a second trend indicator, wherein the second trend indicator comprises a slope of moving linear regression;
determining a third trend indicator, wherein the third trend indicator comprises an average trend, wherein determining the third trend indicator comprises determining:
M
A
K
t
=
∑
i
w
i
,
t
*
M
K
i
,
t
∑
i
w
i
,
t
,
wherein
w
i
,
t
=
1
1
+
exp
[
-
2
i
-
0.5
+
n
-
t
0
.
1
]
,
wherein
i=t−n+1, t−n+2, . . . , t, and wherein n defines a time scale; and
determining a fourth trend indicator, wherein the fourth trend indicator comprises a difference of moving slope average;
determine a trend analysis based, at least in part, on the one or more trend indicators; and
trigger an alarm based, at least in part, on a threshold and the trend analysis.
9. The computer-readable medium of claim 8 , wherein determining the first indicator comprises determining:
DMA t =MA α,t −MA β,t , wherein α<β, wherein MA α,t and MA β,t are moving average value at time t with a window length of α and β, respectively.
10. The computer-readable medium of claim 8 , wherein determining the second indicator comprises determining MK t , wherein MK t represents one or more local trends of the received drilling data, and wherein positive values represent positive trends and negative values represent negative trends.
11. The computer-readable medium of claim 8 , wherein determining the fourth trend indicator comprises determining DMAK t =MAK α,t −MAK α,t (α<β), wherein MAK α,t and MAK β,t are MAK t at time t with a window length of α and β, respectively.
12. The computer-readable medium of claim 8 , wherein the one or more instructions that, when executed by a processor, further cause the processor to determine a kick risk index, wherein determining the kick risk index (KRI) comprises determining KRI=w d P d +w f P f , wherein P f and P d represent probability of abnormal conditions of flow parameter group and drilling parameter group, respectively, and wherein w d and w f are weighting factors of P f and P d , respectively, and wherein triggering the alarm is based, at least in part, on the kick risk index, and wherein triggering the alarm is based, at least in part, on the kick risk index.
13. An information handling system comprising:
a memory;
a processor coupled to the memory, wherein the memory comprises one or more instructions executable by the processor to:
receive real-time drilling data;
determine one or more trend indicators based, at least in part, on the received real-time drilling data, wherein determining the one or more trend indicators comprises:
determining a first trend indicator, wherein the first trend indicator comprises a moving average of the real-time drilling data;
determining a second trend indicator, wherein the second trend indicator comprises a slope of moving linear regression;
determining a third trend indicator, wherein the third trend indicator comprises an average trend, wherein determining the third indicator comprises determining:
M
A
K
t
=
∑
i
w
i
,
t
*
M
K
i
,
t
∑
i
w
i
,
t
,
wherein
w
i
,
t
=
1
1
+
exp
[
-
2
i
-
0.5
+
n
-
t
0
.
1
]
,
wherein
i=t−n+1, t−n+2, . . . , t, and wherein n defines a time scale; and
determining a fourth trend indicator, wherein the fourth trend indicator comprises a difference of moving slope average;
determine a trend analysis based, at least in part, on the one or more trend indicators; and
trigger an alarm based, at least in part, on a threshold and the trend analysis.
14. The information handling system of claim 13 , wherein determining the first indicator comprises determining:
DMA t =MA α,t −MA β,t (α<β), wherein MA α,t and MA β,t are moving average value at time t with a window length of α and β, respectively.
15. The information handling system of claim 13 , wherein determining the second indicator comprises determining MK t , wherein MK t represents one or more local trends of the received drilling data, and wherein positive values represent positive trends and negative values represent negative trends.
16. The information handling system of claim 13 , wherein determining the fourth trend indicator comprises determining DMAK t =MAK α,t −MAK β,t (α<β), wherein MAK α,t and MAK β,t are MAK t at time t with a window length of α and β, respectively.
17. The information handling system of claim 13 , wherein the one or more instructions further executable by the processor to determine a kick risk index, wherein determining the kick risk index (KRI) comprises determining KRI=w d P d +w f P f , wherein P f and P d represent probability of abnormal conditions of flow parameter group and drilling parameter group, respectively, and wherein w d and w f are weighting factors of P f and P d , respectively, and wherein the triggering the alarm is based, at least in part, on the kick risk index.