FAILURE CAUSE CLASSIFICATION APPARATUS

• US 20150279129A1
• Filed: 02/18/2015
• Published: 10/01/2015
• Est. Priority Date: 03/25/2014
• Status: Active Grant

• Current Assignee: Hitachi High-Technologies Corporation (Hitachi, Ltd.)
• Original Assignee: Hitachi High-Technologies Corporation (Hitachi, Ltd.)
• Inventors: SUZUKI, Hideaki, HIRUTA, Tomoaki, MASUDA, Toshio, ISHIKAWA, Masayoshi, KIKEGAWA, Ken
• Granted Patent: US 9,384,603 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60K 35/00 Instruments specially adapted for vehicles; Arrangement of instruments in or on vehicles
• CPC Class Codes: G05B 23/0281 Quantitative, e.g. mathematical distance; Clustering; Neural networks; Statistical analysis
• CPC Class Codes: G06Q 10/20 Administration of product repair or maintenance
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005

Abstract

Selection of sensors requires the knowledge of individual sensors mounted on a target machine and the knowledge of mechanical features of the machine. In the past, experts having mechanical knowledge selected the sensors. The present invention involves analyzing sensor data at e of machine failure, extracting features from the sensor data regarding each failure cause, and comparing the extracted features so as to clarify the difference between the sensor data about the failure causes and present an operator with the clarified difference thereby to support sensor selection. The invention makes it possible to select more simply than before the sensors considered effective for classifying failure causes. For example, the sensors deemed effective for classifying failure causes without mechanical knowledge can be selected.

Claims

1. A failure cause classification apparatus comprising a processing part, the processing part being configured to:

(1) learn features from sensor data on a machine failure;

(2) given the result of learning, obtain similar features from among the features of at least two failure causes;

(3) compare the similar features obtained; and

(4) obtain an influence value serving as an index for selecting a sensor effective for classifying the machine failure from the result of comparing.

2. The failure cause classification apparatus according to claim 1, wherein the influence value includes at least one of an effectiveness value indicating whether a candidate sensor is effective for classifying the failure causes and a reliability value indicating whether the influence value is reliable.

3. The failure cause classification apparatus according to claim 2, wherein the reliability value is a function of the number of sensor data used for evaluating the effectiveness value.

4. The failure cause classification apparatus according to claim 3, wherein the influence value includes classification performance indicating the percentage of the failure causes classified correctly by the selected sensor among all classified failure causes.

5. The failure cause classification apparatus according to claim 4, further comprising a selection screen for selecting sensors, wherein the selection screen displays a sensor selection part that displays the influence value and allows the candidate sensor to be selected.

6. The failure cause classification apparatus according to claim 5, wherein the selection screen displays the classification performance and updates the displayed classification performance in accordance with the sensor selected by the sensor selection part.

7. The failure cause classification apparatus according to claim 6,

wherein the selection screen displays images indicative of the candidate sensors;

and

wherein the selection screen changes a method by which the images are displayed in accordance with the influence value.

8. The failure cause classification apparatus according to claim 7, wherein the selection screen displays failure causes and, when a specific failure cause is selected from the displayed failure cases, changes the display of the influence value in accordance with the selected failure cause.

9. The failure cause classification apparatus according to claim 7, wherein the selection screen has a function of changing the display of the influence value in accordance with a specific image when the specific image is selected from among the images.

10. The failure cause classification apparatus according to claim 9, wherein the selection screen displays a history of the influence value in the past.

11. The failure cause classification apparatus according to claim 10, wherein the selection screen displays a history of the images previously selected.