CN-122003646-A - Forecasting industrial asset faults

Abstract

Forecasting industrial asset faults is described. A system determines a data start value associated with an industrial asset at a data start time. The system determines a data end value associated with the industrial asset at a data end time. The system estimates the fault time when the trend, which is calculated from the data start value to the data end value, will reach the fault limit value. The system determines a distance to fault based on the fault limit value and the end of data value. The system outputs a failure forecast for the industrial asset associated with a failure time and a distance to failure.

Inventors

• P. Berghardt
• W. Bierke

Assignees

• 阿韦瓦软件有限责任公司

Dates

Publication Date

20260508

Application Date

20240819

Priority Date

20230823

Claims (20)

1. 1. A system for forecasting industrial asset failures, the system comprising: one or more processors, and A non-transitory computer-readable medium storing a plurality of instructions that, when executed, cause the one or more processors to: Determining a data start value associated with the industrial asset at a data start time; determining a data end value associated with the industrial asset at a data end time; estimating a fault time when a trend calculated from a data start value to a data end value will reach a fault limit value; Determining a distance to fault based on the fault limit value and the end of data value, and A failure forecast associated with a time to failure and a distance to failure for the industrial asset is output.
2. 2. The system of claim 1, wherein outputting the fault forecast includes outputting a distance to fault time, the distance to fault time being based on the fault time and the data end time, and the distance to fault time being normalized based on the data start time, the data end time, and the fault time, and the distance to fault being normalized based on the predicted data value, the data end value, and the fault limit value.
3. 3. The system of claim 2, wherein the plurality of instructions further cause the processor to: determining a temporal failure risk based on the normalized time to failure; determining a unit fault risk based on the normalized distance to fault distance, and Determining a failure risk of the industrial asset based on the time failure risk and the unit failure risk, wherein outputting the failure forecast includes outputting the failure risk of the industrial asset.
4. 4. The system of claim 3, wherein determining the failure risk of the industrial asset based on the time failure risk and the unit failure risk is further based on at least one of a time weight assigned by a system user to the time failure risk or a unit weight assigned by the system user to the unit failure risk.
5. 5. The system of claim 3, wherein determining the time-to-failure risk is based on an adjustment to a desired minimum response time.
6. 6. The system of claim 3, wherein the plurality of instructions further cause the processor to assign a corresponding one of a plurality of discrete levels of urgency to the risk of failure, wherein outputting the risk of failure of the industrial asset comprises outputting the assigned corresponding one of the plurality of discrete levels of urgency.
7. 7. The system of claim 6, wherein the plurality of instructions further cause the processor to: assigning a priority to a failure risk of the industrial asset based on the assigned corresponding one of the plurality of discrete urgency levels, and Another priority is assigned to another failure risk of another industrial asset based on another one of the plurality of discrete urgency levels.
8. 8. A computer-implemented method for forecasting industrial asset faults, the computer-implemented method comprising: Determining a data start value associated with the industrial asset at a data start time; determining a data end value associated with the industrial asset at a data end time; estimating a fault time when a trend calculated from a data start value to a data end value will reach a fault limit value; Determining a distance to fault based on the fault limit value and the end of data value, and A failure forecast associated with a time to failure and a distance to failure for the industrial asset is output.
9. 9. The computer-implemented method of claim 8, wherein outputting the fault forecast includes outputting a distance fault time, the distance fault time being based on the fault time and the data end time, and the distance fault time being normalized based on the data start time, the data end time, and the fault time, and the distance fault being normalized based on the expected data value, the data end value, and the fault limit value.
10. 10. The computer-implemented method of claim 9, wherein the computer-implemented method further comprises: determining a temporal failure risk based on the normalized time to failure; determining a unit fault risk based on the normalized distance to fault distance, and Determining a failure risk of the industrial asset based on the time failure risk and the unit failure risk, wherein outputting the failure forecast includes outputting the failure risk of the industrial asset.
11. 11. The computer-implemented method of claim 10, wherein determining the failure risk of the industrial asset based on the temporal failure risk and the unit failure risk is further based on at least one of a temporal weight assigned by a system user to the temporal failure risk or a unit weight assigned by the system user to the unit failure risk.
12. 12. The computer-implemented method of claim 10, wherein determining a time-to-failure risk is based on an adjustment to a required minimum response time.
13. 13. The computer-implemented method of claim 10, wherein the computer-implemented method further comprises assigning a corresponding one of a plurality of discrete urgency levels to the failure risk, wherein outputting the failure risk of the industrial asset comprises outputting the assigned corresponding one of the plurality of discrete urgency levels.
14. 14. The computer-implemented method of claim 13, wherein the computer-implemented method further comprises: assigning a priority to a failure risk of the industrial asset based on the assigned corresponding one of the plurality of discrete urgency levels, and Another priority is assigned to another failure risk of another industrial asset based on another one of the plurality of discrete urgency levels.
15. 15. A computer program product comprising a non-transitory computer readable medium having computer readable program code embodied therein for execution by one or more processors, the program code comprising instructions for: Determining a data start value associated with the industrial asset at a data start time; determining a data end value associated with the industrial asset at a data end time; estimating a fault time when a trend calculated from a data start value to a data end value will reach a fault limit value; Determining a distance to fault based on the fault limit value and the end of data value, and A failure forecast associated with a time to failure and a distance to failure for the industrial asset is output.
16. 16. The computer program product of claim 15, wherein outputting the fault forecast includes outputting a distance to fault time, the distance to fault time being based on the fault time and the data end time, and the distance to fault time being normalized based on the data start time, the data end time, and the fault time, and the distance to fault being normalized based on the expected data value, the data end value, and the fault limit value.
17. 17. The computer program product of claim 16, wherein the program code comprises further instructions for: determining a temporal failure risk based on the normalized time to failure; determining a unit fault risk based on the normalized distance to fault distance, and Determining a failure risk of the industrial asset based on the time failure risk and the unit failure risk, wherein outputting the failure forecast includes outputting the failure risk of the industrial asset.
18. 18. The computer program product of claim 17, wherein determining the failure risk of the industrial asset based on the temporal failure risk and the unit failure risk is further based on at least one of a temporal weight assigned by a system user to the temporal failure risk or a unit weight assigned by the system user to the unit failure risk.
19. 19. The computer program product of claim 17, wherein determining a time-to-failure risk is based on an adjustment to a required minimum response time.
20. 20. The computer program product of claim 17, wherein the program code comprises further instructions for: Assigning a corresponding one of a plurality of discrete urgency levels to the failure risk, wherein outputting the failure risk of the industrial asset includes outputting the assigned corresponding one of the plurality of discrete urgency levels; assigning a priority to a failure risk of the industrial asset based on the assigned corresponding one of the plurality of discrete urgency levels, and Another priority is assigned to another failure risk of another industrial asset based on another one of the plurality of discrete urgency levels.

Description

Forecasting industrial asset faults Cross Reference to Related Applications The present application is in accordance with the priority of U.S. patent application No.63/534,196 filed on day 23 of 8, 2023, either in 35 u.s.c. ≡119 or in paris convention, which patent application is incorporated herein by reference in its entirety as if set forth in its entirety herein. Background Analyzing the operational trends of industrial facilities is time consuming. Each industrial asset may have many sensors and an industrial facility may include hundreds or thousands of industrial assets or equipment. This analysis problem is further multiplied when an enterprise has multiple industrial facilities scattered over a wide geographic area. The amount of data generated by these sensors is too large to maintain very frequent physical monitoring and assessment of each trend. Further complicating the problem, only those operators familiar with the equipment are able to determine risk from the abnormal trends, as each trend has its own units and fault limits, as shown in fig. 1, fig. 1 illustrates an example trend 100 of equipment data depicted by a system for forecasting industrial asset faults, according to some embodiments. Conventional forecasting systems currently exist that use sample trend data to extrapolate time to failure. But these prior art systems are often found to be unreliable in predicting equipment failure. Drawings FIG. 1 illustrates example trends in equipment data depicted by a system for forecasting industrial asset failure, according to some embodiments. FIG. 2 illustrates an example display portion depicted by a system including software configured to find anomalies in data trends to forecast industrial asset failures, in accordance with some embodiments. FIG. 3 illustrates an example alert tab portion depicted by a system for forecasting industrial asset failure, according to some embodiments. FIG. 4 illustrates an example chart of a time fault domain emphasized by a system for forecasting industrial asset faults, according to some embodiments. FIG. 5 illustrates an example chart emphasizing unit fault domains by a system for forecasting industrial asset faults, according to some embodiments. FIG. 6 illustrates an example failure risk assessment formula used by a system for forecasting industrial asset failure, according to some embodiments. FIG. 7 illustrates an example risk designation category used by a system for forecasting industrial asset failure, according to some embodiments. FIG. 8 illustrates an example chart of time and distance risk assessment depicted by a system for forecasting industrial asset faults, according to some embodiments. FIG. 9 illustrates an expected failure path for a linear trend in a graph depicted by a system for forecasting industrial asset failure, according to some embodiments. FIG. 10 illustrates a real world example of current trends in the circle domain of a graph depicted by a system for forecasting industrial asset failure, in accordance with some embodiments. FIG. 11 illustrates an example comparison of problems that a conventional system in accordance with some embodiments has in accurately predicting the trend of change of a fault when predicting a fault of an industrial asset. FIG. 12 illustrates a comparison of a unit-weighted left-side risk representation (conventional system) and a unit-weighted right-side risk representation defined by a system for forecasting an industrial asset failure, in accordance with some embodiments. FIG. 13 illustrates a modification of a risk assessment equation used by a system for forecasting industrial asset failure, where the time to failure includes a minimum response time component, according to some embodiments. FIG. 14 illustrates example time-to-failure trend segments on an analysis display depicted by a system for forecasting industrial asset failure, according to some embodiments. FIG. 15 illustrates a block diagram of an example system for forecasting industrial asset faults, according to some embodiments. FIG. 16 is a flowchart illustrating an example computer-implemented method for forecasting an industrial asset failure, according to some embodiments. FIG. 17 is a block diagram illustrating an example hardware device in which the subject matter may be implemented. Detailed Description Prior art systems are often found to be unreliable because they only provide an estimate of the time to failure limit, and do not consider how close the overall trend is to failure limit. Conventional forecasting systems perform poorly in assessing the overall risk of failure for problems involving high/low rates of change or magnitudes from failure limits. For example, for the current trend, conventional systems may estimate a time to failure of 10 days for a temperature limit without taking into account that only a one-degree increase in temperature that may occur as a change in the process may cause a failure at any time. Consider