MALFUNCTION PREDICTION FOR COMPONENTS AND UNITS OF TECHNICAL ENTITIES

• US 20170236065A1
• Filed: 08/03/2015
• Published: 08/17/2017
• Est. Priority Date: 08/20/2014
• Status: Active Grant

• Current Assignee: Hitachi Energy Limited (Hitachi, Ltd.)
• Original Assignee: Cassantec AG (ABB Limited)
• Inventors: Kirschnick, Frank
• Granted Patent: US 10,657,453 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Abstract

Predicting a malfunction of a component of a unit includes providing a transition matrix of a parameter of the component, wherein the transition matrix includes for a number of discrete value states of the parameter probabilities to switch from one discrete value state to another within a certain time period; providing the conditional probability distribution for the malfunction given the discrete value states; providing a current discrete value state of the parameter; determining a conditional probability distribution of the discrete value states given the current discrete value state for a future point in time based on the current discrete value state and on the transition matrix by use of a Markov chain; and determining a probability for the malfunction for the future point in time based on the conditional probability distribution of the discrete value states for the future point in time and the conditional probability distribution for the malfunction.

Claims

1. Method for predicting a malfunction of a mechanical or electrical component of a unit comprising the steps of:

measuring a current value of a parameter of the component;

in an apparatus, determining a conditional probability distribution of the parameter for a future point in time given the current value of the parameter based on the current value of the parameter;

in the apparatus, determining a conditional probability for a malfunction at the future point in time given the current value of the parameter based on the conditional probability distribution of the parameter for the future point in time given the current value of the parameter and on a conditional probability distribution for the malfunction given the parameter, and

predicting the malfunction of the component on the basis of the conditional probability for a malfunction at the future point in time given the current value of the parameter.

2. Method according to claim 1 comprising transmitting the current value over a communication network to the apparatus.

3. Method according to claim 1, wherein the current value is measured by a sensor of the component.

4. Method according to claim 1, wherein the conditional probability distribution for the malfunction given the parameter is determined based on the conditional probability distribution of the parameter given the malfunction, the probability of the malfunction and the probability distribution of the parameter.

5. Method according to claim 1 comprising the further steps of:

providing a transition matrix, wherein the transition matrix is based on probabilities to switch from one of a number of discrete value states to another of the discrete value states;

providing the conditional probability distribution for the malfunction given the parameter being a conditional probability distribution for the malfunction given the discrete value states of said parameter;

providing the current discrete value state of said parameter on the basis of the current value of the parameter;

wherein the step of determining the conditional probability distribution of the parameter of the component for the future point in time given the current value of the parameter comprises the step of determining a conditional probability distribution of the discrete value states of said parameter for the future point in time given the current discrete value state of the parameter based on the current discrete value state of the parameter and on the transitional matrix;

wherein the step of determining the conditional probability for the malfunction at the future point in time given the current value of the parameter comprises the step of determining a conditional probability for the malfunction at the future point in time given the current value state based on the conditional probability distribution of the discrete value states of said parameter for the future point in time given the current value state and on the conditional probability distribution for the malfunction given the discrete value states of said parameter.

6. Method according to claim 5, wherein intervals between the discrete value states are equidistant.

7. Method according claim 5, wherein intervals between the discrete value states are logarithmic or exponential.

8. Method according to claim 5, wherein the size of a value interval corresponding to a discrete value state of the discrete value states depends on the probability of the respective discrete value state.

9. Method according to claim 5, comprising the step of recording the values of the parameter and the step of determining the transition matrix on the basis of the recorded values of the parameter.

10. Method according to claim 5, comprising the step of determining the transition matrix on the basis of values of the parameter from the component and/or from other comparable components.

11. Method according to claim 1, wherein the statistical significance of the data underlying the probability for the malfunction at the future point in time given the current value of the parameter is calculated on the basis of the statistical significance of the data underlying the conditional probability distribution of the parameter given the current value of the parameter.

12. Method according to claim 1, wherein the probability for the malfunction given the current value of the parameter is determined for a number of future points in time.

13. Method according to claim 12, comprising the step of estimating a remaining useful life of the component on the basis of probabilities for the malfunction of the component given the number of future points in time.

14. Method according to claim 1, wherein

the component is a gas turbine, and the malfunction of the transformer is one of a bearing defect, compressor defect, flow malfunction, turbine malfunction, or output malfunction, and the parameter for predicting the malfunction is temperature, lubricant condition in the bearings or in the oil tank, shaft or casing vibration, pressure of the gas in the turbine, electric output of a generator coupled with the turbine, ambient air condition or humidity, or a combination thereof;

or

the component is a transformer, and the malfunction of the component is one of an insulation defect or a cooling system defect of the transformer, and the parameter for predicting the malfunction is one or a combination of temperature of the coils, vibrations of the cooling fans, a condition of the oil surrounding the coils;

or

the component is a diesel engine, and the malfunction of the component is one of bearing defect or turbo charger defect, and the parameter for predicting the malfunction is one or a combination of temperature, vibrations, lubricant condition, outlet pressure of the compressor and fuel analysis.

15. Method according to claim 1, wherein the conditional probability for the malfunction at the future point in time given the current value of the parameter is determined on the basis of the integral over the parameter of the product of the conditional probability distribution of the parameter for the future point in time given the current value of the parameter with the conditional probability distribution for the malfunction given the parameter.

16. Method according to claim 15, wherein the current value of the parameter is associated to one of a plurality of discrete value states of said parameter which yields a current discrete value state, and the integral is determined on the basis of the sum of the products of the conditional probability distribution of the discrete value state of the parameter for the future point in time given the current discrete value state of the parameter with the conditional probability distribution for the malfunction given the discrete value state of the parameter over all discrete value states.

17. Method according to claim 1 comprising the steps:

determining probabilities for N single malfunctions of the component at a future point in time given current parameters; and

determining a total probability of a malfunction of the component at the future point in time given the current parameters on the basis of the probabilities for single malfunctions of the component at the future point in time given current parameters.

18. Method according to claim 1 comprising the steps of:

determining a probability for a malfunction of a unit comprising the component on the basis of the probability of the malfunction of the of the component and on the basis of probabilities of malfunction of other components of the unit.

20. Non-transitory computer program with instructions configured to perform the steps of claim 1 when executed on a processor.

19. (canceled)

21. Apparatus for predicting a malfunction of a mechanical or electrical component of a unit comprising:

a parameter value prediction section for determining a conditional probability distribution of a parameter of the component for a future point in time given the current value of the parameter based on the current value of the parameter;

a component malfunction prediction section for determining a conditional probability for a malfunction at the future point in time given the current value of the parameter based on the conditional probability distribution of the parameter for the future point in time given the current value of the parameter and on a conditional probability distribution for the malfunction given the parameter.