Health management system, fault diagnosis system, health management method, and fault diagnosis method

1. A fault diagnosis computer system for diagnosing a fault of mechanical equipment, comprising:

a processor; and

a memory storing instructions that, when executed by the processor, cause the computer system to:

acquire as time-series data, sensor data from a plurality of sensors installed in the mechanical equipment, or the sensor data and environmental data indicating an installation environment of the mechanical equipment;

calculate a multi-dimensional vector extending from a normal state to a fault state of the mechanical equipment by a statistical method using the time-series data as learning data;

estimate an equipment state or health state of the mechanical equipment using the multi-dimensional vector;

detect whether a starting point position of the multi-dimensional vector changes by a predetermined value or more to determine a recovery effect of a maintenance work on the health state, wherein the multi-dimensional vector is calculated from time-series data in a period before and after the maintenance work is performed on the mechanical equipment;

extract from the time-series data, sensor data that contributes to the change in the starting point position of the multi-dimensional vector;

analyze changes in health state based on the time-series data on the health state to determine an estimated time period from a present time to an estimated time at which the health state decreases below a predetermined threshold;

determine a time at which maintenance work is to be next conducted based on the estimated time period received and the recovery effect of the maintenance work on the health state received;

display the extracted sensor data as an index indicating the health state of the mechanical equipment; and

direct performance of maintenance work,

wherein the environmental data, if included in the time-series data, includes at least one type of data among event data indicating an operation state of the mechanical equipment, operation data indicating an operation time of the mechanical equipment, load data indicating a load state of the mechanical equipment, and maintenance history data indicating a history of the maintenance work of the mechanical equipment.

2. The fault diagnosis computer system of claim 1 , further comprising:

transforming a feature of the time-series data through independent component analysis of the time-series data, and wherein the calculating of the multi-dimensional vector is via the transformed time-series data.

3. The fault diagnosis computer system of claim 2 , further comprising:

extracting a trend component indicating a tendency of a change for the time-series data, and wherein the calculating of the multi-dimensional vector is via the time-series data including the trend component.

4. The fault diagnosis computer system of claim 3 , further comprising:

calculating, in performing the independent component analysis on the time-series data, a weight from a mixing coefficient matrix indicating a relationship between the time-series data and an independent component, and controlling the size of a signal of the independent component using the weight.

5. The fault diagnosis computer system of claim 3 , wherein the statistical method is any one of a Gaussian process, any other regression procedure, a k-nearest neighbor (k-NN) method, a local subspace method, and any other recognition procedure,

and wherein the fault diagnosis computer system further displays the starting point of the multi-dimensional vector so as to enable visual recognition of the change in the starting point on a time-series basis.

6. The fault diagnosis computer system of claim 2 , further comprising:

calculating, in performing the independent component analysis on the time-series data, a weight from a mixing coefficient matrix indicating a relationship between the time-series data and an independent component, and controlling the size of a signal of the independent component using the weight.

7. The fault diagnosis computer system of claim 6 , wherein the statistical method is any one of a Gaussian process, any other regression procedure, a k-nearest neighbor (k-NN) method, a local subspace method, and any other recognition procedure,

and wherein the fault diagnosis computer system further displays the starting point of the multi-dimensional vector so as to enable visual recognition of the change in the starting point on a time-series basis.

8. The fault diagnosis computer system of claim 2 , wherein the statistical method is any one of a Gaussian process, any other regression procedure, a k-nearest neighbor (k-NN) method, a local subspace method, and any other recognition procedure,

and wherein the fault diagnosis computer system further displays the starting point of the multi-dimensional vector so as to enable visual recognition of the change in the starting point on a time-series basis.

9. The fault diagnosis computer system of claim 1 , further comprising:

displaying the starting point of the multi-dimensional vector so as to enable visual recognition of the change in the starting point on a time-series basis, and wherein the statistical method is any one of a Gaussian process, any other regression procedure, a k-nearest neighbor (k-NN) method, a local subspace method, and any other recognition procedure.

10. A fault diagnosis method for diagnosing a fault of mechanical equipment, the method comprising:

a time-series data acquisition step of acquiring, as time-series data, sensor data from a plurality of sensors installed in the mechanical equipment, or the sensor data and environmental data indicating an installation environment of the mechanical equipment;

a multi-dimensional vector calculation step of calculating a multi-dimensional vector extending from a normal state to a fault state of the mechanical equipment by a statistical method using the time-series data as learning data;

a state estimation step of estimating an equipment state or health state of the mechanical equipment using the multi-dimensional vector;

a starting point change detection step of detecting whether the starting point position of the multi-dimensional vector calculated in the multi-dimensional vector calculation step changes by a predetermined value or more to determine a recovery effect of a maintenance work on the health state, the multi-dimensional vector calculated from time-series data acquired in the time-series data acquisition step in a period before and after a maintenance work is performed on the mechanical equipment;

a sensor data extraction step of extracting, from the time-series data, sensor data that contributes to the change in the starting point position of the multi-dimensional vector;

a remaining useful life calculation step of analyzing changes in health state based on the time-series data on the health state to determine an estimated time period from a present time to an estimated time at which the health state decreases below a predetermined threshold;

a maintenance timing determination step of determining a time at which maintenance work is to be next conducted based on the estimated time period and the recovery effect of the maintenance work on the health state;

an output step of displaying or outputting to an outside the extracted sensor data as an index indicating the health state of the mechanical equipment; and

a directing step for directing the performance of maintenance work,

wherein the environmental data includes at least one type of data among event data indicating an operation state of the mechanical equipment, operation data indicating an operation time of the mechanical equipment, load data indicating a load state of the mechanical equipment, and maintenance history data indicating a history of the maintenance work of the mechanical equipment.