DIAGNOSIS SYSTEM AND DIAGNOSIS METHOD FOR CONSTRUCTION MACHINE

• US 20120209570A1
• Filed: 10/19/2009
• Published: 08/16/2012
• Est. Priority Date: 10/19/2009
• Status: Active Grant

• Current Assignee: Hitachi Construction Machinery Company Limited (Hitachi, Ltd.)
• Original Assignee: Hitachi Construction Machinery Company Limited (Hitachi, Ltd.)
• Inventors: Furuno, Yoshinori, Suzuki, Hideaki, Nakamura, Kozo, Uchiyama, Hiroki
• Granted Patent: US 9,057,174 B2
• Time in Patent Office: Days
• US Class Current: 702/183
• CPC Class Codes: E02F 9/2025 Particular purposes of control systems not otherwise provided for E02F3/16, E02F3/26, sub-groups of E02F3/43, E02F3/651, sub-groups of E02F3/84, E02F3/907, E02F5/145 take precedence
• CPC Class Codes: E02F 9/267 Diagnosing or detecting failure of vehicles
• CPC Class Codes: G06Q 10/20 Administration of product repair or maintenance
• CPC Class Codes: G06Q 50/08 Construction

Abstract

Provided is a construction machine diagnosing system and method in which even a user who has little knowledge of any procedures and techniques for diagnosing construction machines can speedily diagnose a desired machine in a manner appropriate for particular data characteristics of the machine.

A diagnosis device 10 acquires diagnostic data from a diagnostic data storage device 30, extracts data characteristics from the information contained in the diagnostic data, acquires from a diagnostic knowledge storage device 20 any diagnosing techniques considered to be effective for the data characteristics, and presents to a user the diagnosing techniques along with respective degrees of effectiveness. The user uses the presented degrees of effectiveness to select a desired diagnosing technique and conduct a diagnosis. In addition, in order to make effective use of the diagnostic knowledge stored within the diagnostic knowledge storage device 20, a diagnostic knowledge generating section 107 classifies common data characteristics by elements of diagnosing techniques and stores the classified data characteristics and the elements of the diagnosing techniques, as new diagnostic knowledge.

Claims

1. A system for diagnosing a state of a construction machine in accordance with at least parameter data acquired by sensors, the system comprising:

a diagnosis device for diagnosing the construction machine;

a diagnostic knowledge storage device for storage of diagnostic knowledge including a diagnosing technique used for the diagnosis; and

a diagnostic data storage device for storage of diagnostic data including the sensor-acquired parameter data, the diagnostic data being used for the diagnosis;

wherein the diagnosis device includes;

an input and output section for data input and output with respect to outside;

a diagnostic data acquisition section for acquiring, on the basis of the data input to the input and output section, diagnostic data including appropriate parameter data, from the diagnostic data storage device;

a data characteristics acquisition section for acquiring data characteristics of the diagnostic data acquired by the diagnostic data acquisition section, from the acquired diagnostic data, the data characteristics being inclusive of at least parameter characteristics which denote characteristics of the parameter data;

a diagnostic knowledge acquisition section for acquiring, from the diagnostic knowledge storage device, any diagnosing techniques fitting the data characteristics acquired by the data characteristics acquisition section; and

a diagnosing section for conducting the diagnosis using both of the diagnostic data including appropriate parameter data acquired by the diagnostic data acquisition section, and the diagnosing techniques acquired by the diagnostic knowledge acquisition section.

3. The diagnosis system according to claim 1, wherein:

the diagnostic knowledge stored in the diagnostic knowledge storage device includes data characteristics of diagnostic data acquired in advance, and the diagnosing techniques previously determined to be effective for the diagnostic data used for the diagnosis;

the diagnostic knowledge acquisition section acquires at least the diagnosing techniques corresponding to the diagnostic knowledge to which data characteristics fitting the data characteristics acquired by the data characteristics acquisition section belong;

the diagnosing section conducts the diagnosis the diagnostic data acquired by the diagnostic data acquisition section using the diagnosing techniques acquired by the diagnostic knowledge acquisition section; and

the data characteristics of the diagnostic data acquired by the diagnostic data acquisition section, and the data characteristics of the diagnostic data contained in the diagnostic knowledge include, in addition to the parameter characteristics that denote the characteristics which the parameter data has, at least one of the following;

“

Target machine”

denoting the kind and name of machine being diagnosed;

“

Data acquisition date and time”

denoting a date and time of acquisition of the diagnostic data;

“

Data acquisition location”

denoting a location at which the diagnostic data was acquired; and

“

Number of parameters being monitored”

denoting the number of parameters being monitored in the target machine.

4. The diagnosis system according to claim 3, wherein the parameter characteristics include at least one of the following:

“

Parameter name”

denoting a name of one of the parameters;

“

Kind of sensor”

denoting the kind of sensor for which the parameter has been created;

“

Data volume”

denoting a data volume of the parameter;

“

Run mode count”

denoting how often the parameter significantly changed within a short time;

“

Data acquisition rate”

denoting a rate at which the parameter was repeatedly acquired;

“

Average value”

denoting an average value of the parameter;

“

Dispersion value”

denoting a dispersion value of the parameter;

“

Maximum value”

denoting a maximum value of the parameter;

“

Minimum value”

denoting a minimum value of the parameter; and

“

Variation tendency”

denoting a tendency for the parameter to change.

5. The diagnosis system according to claim 4, wherein the diagnosing techniques include at least one of the following:

“

Diagnostic purpose”

denoting a purpose of the diagnosis using the diagnostic data;

“

Data extraction method”

denoting those parameters within the diagnostic data, that are to be used for the diagnosis;

“

Preprocessing method”

denoting a method of preprocessing which, prior to the diagnosis, is conducted upon the parameters to be used for the diagnosis;

“

Diagnosis method”

denoting a scheme and algorithm to be used for the diagnosis; and

“

Result output method”

denoting a way to output execution results of the diagnosis.”

7. The diagnosis system according to claim 5, wherein:

the diagnosis device further includes an effective rate calculation section for calculating an effective rate of each diagnosing technique acquired by the diagnostic knowledge acquisition section;

before conducting the diagnosis, the diagnosing section selects, of the diagnosing techniques acquired by the diagnostic knowledge acquisition section, an optimal diagnosing technique according to particular results of the calculation of the degrees of effectiveness of the acquired diagnosing techniques by the effective rate calculation section;

the diagnostic knowledge further includes the number of application cases that denotes the number of application cases in which a combination of the data characteristics and one of the diagnosing techniques is effective;

the diagnostic knowledge acquisition section acquires the number of application cases in addition to the diagnosing technique; and

the effective rate calculation section calculates the effective rate from a product of two values, wherein one of the two values is a ratio between the number of elements in data characteristics input to the diagnostic knowledge storage device in order to acquire from the device a diagnosing technique fitting the data characteristics previously acquired by the data characteristics acquisition section, and the number of elements in the data characteristics contained in the diagnostic knowledge matching the input data characteristics, and the other value is the number of application cases that is contained in the diagnostic knowledge.

9. The diagnosis system according to claim 7, wherein:

the diagnosis device further includes a diagnostic knowledge generating section configured to first collect, among all diagnostic knowledge stored within the diagnostic knowledge storage device, only the diagnostic knowledge that contains common diagnosing technique elements, then generate, as new diagnostic knowledge, combinations of the diagnosing technique elements and what the data characteristics contained in the collected diagnostic knowledge have in common between the constituent elements of the data characteristics, and store the combinations into the diagnostic knowledge storage device.

10. The diagnosis system according to claim 9, wherein:

during the generation of the new diagnostic knowledge, the diagnostic knowledge generating section assigns the number of sets of diagnostic knowledge, each set containing the constituent elements of common data characteristics, as the number of application cases, to the new diagnostic knowledge.

2. (canceled)

6. (canceled)

8. (canceled)

11-13. -13. (canceled)

14. A method for diagnosing a state of a construction machine on the basis of at least parameter data acquired by sensors, the method comprising:

a first step of, on the basis of data input from an input and output section, acquiring diagnostic data including appropriate parameter data from a diagnostic data storage device in which is stored diagnostic knowledge including a diagnosing technique used for the diagnosis, the parameter data being inclusive of the sensor-acquired parameter data;

a second step of acquiring data characteristics of the diagnostic data acquired in the first step, the data characteristics being inclusive of at least parameter characteristics that denote characteristics which the parameter data has;

a third step of acquiring, from a diagnostic knowledge storage device in which is stored the diagnostic knowledge including the diagnosing technique used for the diagnosis, any diagnosing techniques fitting the data characteristics acquired in the second step; and

a fourth step of conducting the diagnosis using both of the diagnostic data including the parameter data acquired in the first step, and one of the diagnosing techniques acquired in the third step.

16. The diagnosis method according to claim 14, wherein:

the diagnostic knowledge stored in the diagnostic knowledge storage device includes data characteristics of diagnostic data acquired in advance, and the diagnosing technique determined to be effective for the diagnosis with the diagnostic data;

the third step is executed at least to acquire a diagnosing technique contained in diagnostic knowledge to which data characteristics that fit those acquired in the second step belong;

the fourth step is executed to conduct the diagnosis the diagnostic data acquired in the first step using the diagnosing technique acquired in the third step; and

the data characteristics of the diagnostic data acquired in the first step, and the data characteristics of the diagnostic data contained in the diagnostic knowledge include, in addition to the parameter characteristics that denote the characteristics which the parameter data has, at least one of the following;

“

Target machine”

denoting the kind and name of machine being diagnosed;

“

Data acquisition date and time”

denoting a date and time of acquisition of the diagnostic data;

“

Data acquisition location”

denoting a location at which the diagnostic data was acquired; and

“

Number of parameters being monitored”

denoting the number of parameters being monitored in the target machine.”

17. The diagnosis method according to claim 16, wherein the parameter characteristics include at least one of the following:

“

Parameter name”

denoting a name of one of the parameters;

“

Kind of sensor”

denoting the kind of sensor for which the parameter has been created;

“

Data volume”

denoting a data volume of the parameter;

“

Run mode count”

denoting how often the parameter significantly changed within a short time;

“

Data acquisition rate”

denoting a rate at which the parameter was repeatedly acquired;

“

Average value”

denoting an average value of the parameter;

“

Dispersion value”

denoting a dispersion value of the parameter;

“

Maximum value”

denoting a maximum value of the parameter;

“

Minimum value”

denoting a minimum value of the parameter; and

“

Variation tendency”

denoting a tendency for the parameter to change.

18. The diagnosis method according to claim 17, wherein the diagnosing techniques include at least one of the following:

“

Diagnostic purpose”

denoting a purpose of the diagnosis using the diagnostic data;

“

Data extraction method”

denoting those parameters within the diagnostic data, that are to be used for the diagnosis;

“

Preprocessing method”

denoting a method of preprocessing which, prior to the diagnosis, is conducted upon the parameters to be used for the diagnosis;

“

Diagnosis method”

denoting a scheme and algorithm to be used for the diagnosis; and

“

Result output method”

denoting a way to output execution results on the diagnosis.

20. The diagnosis method according to claim 18, further comprising:

a fifth step of calculating degrees of effectiveness of the diagnosing techniques acquired in the third step;

before the diagnosis takes place, the fourth step is executed to select, of the diagnosing techniques acquired in the third step, an optimal diagnosing technique allowing for the degrees of effectiveness of each diagnosing technique that were calculated in the fifth step;

the diagnostic knowledge further includes the number of application cases that denotes the number of application cases in which a combination of the data characteristics and one of the diagnosing techniques is effective;

the third step is executed to acquire the number of application cases in addition to the diagnosing technique; and

the fifth step is executed to calculate the effective rate from a product of two values, wherein one of the two values is a ratio between the number of elements in data characteristics input to the diagnostic knowledge storage device in order to acquire from the device a diagnosing technique fitting the data characteristics acquired in the second step, and the number of elements in the data characteristics contained in the diagnostic knowledge matching the input data characteristics, and the other value is the number of application cases that is contained in the diagnostic knowledge.

22. The diagnosis method according to claim 20, further comprising:

a seventh step of first collecting, among all diagnostic knowledge stored within the diagnostic knowledge storage device, only the diagnostic knowledge that contains common diagnosing technique elements, then generating, as new diagnostic knowledge, combinations of the diagnosing technique elements and what the data characteristics contained in the collected diagnostic knowledge have in common between the constituent elements of the data characteristics, and storing the combinations into the diagnostic knowledge storage device.

23. The diagnosis method according to claim 22, wherein:

during the generation of the new diagnostic knowledge, the seventh step is executed to assign the number of sets of diagnostic knowledge, each set containing the constituent elements of common data characteristics, as the number of application cases, to the new diagnostic knowledge.

15. (canceled)

19. (canceled)

21. (canceled)