System and methods monitoring the technical status of technical equipment

Patent metadata

Field	Value
Publication number	US-12019432-B2
Application number	US-202117207854-A
Country	US
Kind code	B2
Filing date	Mar 22, 2021
Priority date	Sep 24, 2018
Publication date	Jun 25, 2024
Grant date	Jun 25, 2024

Abstract

A computer-implemented method for determining an abnormal technical status of a technical system includes: receiving, from the technical system, a plurality of signals, each signal being sampled over time and reflecting the technical status of at least one system component; computing, for each signal with associated high and low alarm thresholds obtained from an alarm management system, at every sampling time point, a univariate distance to its associated alarm thresholds as a maximum of the distances between a value of the respective signal and its associated alarm thresholds to quantify a degree of abnormality for the respective at least one system component; computing, at every sampling time point, based on the univariate distances at the respective sampling time points, an aggregate abnormality indicator reflecting the technical status of the technical system; and providing, to an operator, a comparison of the aggregate abnormality indicator with a predetermined abnormality threshold.

First claim

What is claimed is:

1. A computer-implemented method for determining an abnormal technical status of a technical system, comprising:
receiving, from the technical system, a plurality of signals, each signal being sampled over time and reflecting the technical status of at least one system component;
computing, for each signal with associated high and low alarm thresholds obtained from an alarm management system, at every sampling time point, a univariate distance to its associated alarm thresholds as a maximum of the distances between a value of the respective signal and its associated alarm thresholds to quantify a degree of abnormality for the respective at least one system component;
computing, at every sampling time point, based on the univariate distances at the respective sampling time points, an aggregate abnormality indicator reflecting the technical status of the technical system, and
providing, to an operator, a comparison of the aggregate abnormality indicator with a predetermined abnormality threshold, the abnormality threshold ensuring with a given probability that an aggregate abnormality indicator value, when below the abnormality threshold, reflects normal operation of the technical system, the abnormal technical status being determined when the aggregate abnormality indicator exceeds the abnormality threshold,
wherein, prior to the computing steps, a steady-state detection algorithm is used to determine whether the technical system is operating in a steady-state process, and when the technical system is not operating in the steady-state process, the computing steps are suppressed.

2. The method of claim 1 , wherein the abnormality threshold is determined using a cumulative distribution function of the aggregate abnormality indicator during normal operation of the technical system.

3. The method of claim 1 , wherein the aggregate abnormality indicator at a particular sampling time point is computed as:
a Euclidian distance based on the univariate distances of the respective signals and a total number of signals, or
a weighted Euclidian distance based on the univariate distances of the respective signals and the total number of signals, each univariate distance contribution being weighted with a weighting factor corresponding to a severity of an alarm associated with the respective signal as defined in the alarm management system.

4. The method of claim 1 , further comprising:
providing to the operator a subset of the univariate distances at the respective sampling time points, the subset relating to such univariate distances with highest contributions to an augmentation of the aggregate abnormality indicator, with a size of the subset being predefined.

5. The method of claim 1 , wherein the univariate distance for a particular signal at a particular sampling time point is computed so that:
the distance value is between 0 and 1 if the sampled signal value is between the low alarm threshold and the high alarm threshold,
the distance value is 1 if the sampled signal value is less than or equal to the low alarm threshold, or greater than or equal to the high alarm threshold, and
the distance value is 0 if the sampled signal value corresponds to a predefined parameter value reflecting normal operation.

6. The method of claim 1 , wherein the univariate distance for a particular signal at a particular sampling time point is smoothened by exponential smoothing.

7. The method of claim 6 , wherein the univariate distance for a particular signal at a particular sampling time point is computed by introducing an interval defining a normal range [a 1 , a 2 ] of the signal, with an upper interval limit a 2 being less than a respective high alarm threshold x h and a lower interval limit a 1 being greater than a respective low alarm threshold x l , so that:
the distance value is 0 if the sampled signal value is inside the interval, and
the distance value is

(

x
⁡
(
t
)

-

a
1

x
l

-

a
1

)

a

for x(t)<a 1 , and the distance value is

(

x
⁡
(
t
)

-

a
2

x
h

-

a
2

)

a

for x(t)>a 2 , where a>1.

8. The method of claim 1 , wherein a component hierarchy of the technical system defines a plurality of functional blocks as child nodes of the technical system with each functional block comprising a plurality of child nodes including further functional blocks and/or system components, and
wherein the method further comprises:
computing, at every sampling time point, based on a subset of univariate distances associated with a particular functional block, at the respective sampling time points, an aggregate block abnormality indicator for the particular functional block, the block abnormality indicator reflecting the technical status of the functional block; and
providing, to the operator, a comparison of the block abnormality indicator with a predetermined block abnormality threshold, the block abnormality threshold ensuring with a given probability that an aggregate block abnormality indicator value, when being below the block abnormality threshold, reflects normal operation of the particular functional block.

9. The method of claim 1 , wherein a particular technical status parameter is represented by multiple sensor signals providing redundant information in specifying the particular technical status, and
wherein the method further comprises:
aggregating the univariate distances associated with the multiple sensor signals to provide a robust univariate distance for the particular technical status parameter.

10. A non-transitory computer-readable medium having processor-executable instructions stored thereon, wherein the processor-executable instructions, when executed by one or more processors, facilitate the method of claim 1 .

11. A computer system for determining an abnormal technical status of a technical system, the computer system comprising:
an interface configured to:
receive, from the technical system, a plurality of signals, each signal being sampled over time and reflecting the technical status of at least one system component, and
retrieve, from an alarm management system associated with the technical system, high alarm thresholds and low alarm thres

Assignees

• Abb Schweiz Ag

Inventors

• Chioua Moncef
• Lucke Matthieu
• Kolb Emanuel
• Hollender Martin
• Li Nuo
• Cohen Andrew

Classifications

• G06F2218/12

  Classification; Matching · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06F17/18

  for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title

• G06F17/15

  Correlation function computation {including computation of convolution operations (arithmetic circuits for sum of products per se, e.g. multiply-accumulators G06F7/5443; digital filters, e.g. FIR, IIR, adaptive filters H03H17/00)} · CPC title

• G05B23/0221

  Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods · CPC title