Method for leakage detection
AssigneeRosenxt Holding AG
InventorHermann Rosen
Life of this patent
Estimating the term…
Abstract
The invention relates to a method for leakage detection on an object flown through by a medium, in particular a pipe or a pipeline. According to the invention, a pattern is identified in the determined values for the change of the flow rate and the pressure of the medium and for a temperature change, and a probability for the presence of a leak is determined based on the identified pattern and due to self-learning systems.
Claims13
A method for leakage detection on a pipeline carrying a flow of a medium, the method comprising:
- ascertaining a value for a change in a flow rate of the medium, for a pressure change in the medium, and a temperature value change at each of a plurality of measurement points on a contiguous section of pipeline carrying the flow of the medium to known tapping points, wherein at least part of the contiguous section of the pipeline is buried in the ground, wherein a length of the contiguous section of the pipeline is such that at least some of the plurality of measurement points are outside a same measurement housing, and wherein the ascertained values are recorded and statistically evaluated by a data processing device;
- identifying, by the data processing device, a pattern in a group of values that is formed from the ascertained values and from data, obtained via an external source, that describes geological composition of the ground surrounding the part of the contiguous section of the pipeline;
- and
- determining, by the data processing device and based on the identified pattern, a likelihood of a presence of a leak in the contiguous section of the pipeline at a location between a first measurement point on the contiguous section of the pipeline and a second measurement point on the contiguous section of the pipeline by:
- applying a classification algorithm and a pattern analysis algorithm to the identified pattern;
- and
- applying a learning algorithm, that comprises the classification algorithm and the pattern analysis algorithm, to the group of values, wherein output of the learning algorithm is indicative of the likelihood of the presence of the leak,
- wherein the learning algorithm is trained using stored and simulated values before being applied to the ascertained values and/or the group of values, and
- wherein the stored and simulated values are associated with an actual and a simulated presence of a leak on the contiguous section of the pipeline.
A non-transitory computer program product comprising instructions for determining a likelihood of a presence of a leak on a pipeline carrying a flow of a medium, wherein the instructions are for causing a data processing device to:
- ascertain a value for a change in a flow rate of the medium, for a pressure change in the medium, and for a temperature value change at each of a plurality of measurement points on a contiguous section of the pipeline carrying the flow of the medium to known tapping points, wherein at least part of the contiguous section of the pipeline is buried in the ground, wherein a length of the contiguous section of the pipeline is such that at least some of the plurality of measurement points are outside of a same measurement housing,
- identify a pattern in a group of values formed from the ascertained values and from data, obtained via an external source, that described geological composition of the ground surrounding the part of the contiguous section of the pipeline;
- determine, based on the identified pattern, a likelihood of a presence of a leak in the contiguous section of the pipeline at a location between a first measurement point on the contiguous section of the pipeline and a second measurement point on the contiguous section of the pipeline by:
- applying a classification algorithm and a pattern analysis algorithm to the identified pattern;
- and
- applying a learning algorithm, that comprises the classification algorithm and/or the pattern analysis algorithm, to the group of values, wherein output of the learning algorithm is indicative of the likelihood of the presence of the leak, wherein the learning algorithm is trained using stored and simulated values before being applied to the group of values, and wherein the stored and simulated values are associated with an actual and/or a simulated presence of a leak on the contiguous section of the pipeline.
Dependencies are inferred from the claim text.