Method for trouble managing of equipment

• US 9,696,718 B2
• Filed: 09/09/2009
• Issued: 07/04/2017
• Est. Priority Date: 11/25/2008
• Status: Active Grant

• Current Assignee: Mitsubishi Heavy Industries, Ltd.
• Original Assignee: Mitsubishi Heavy Industries, Ltd.
• Inventors: Nishimura, Nobuhiko, Sakata, Fumitoshi, Saito, Mayumi, Satake, Kouji, Kumano, Shintaro
• Primary Examiner(s): Gart, Matthew
• Assistant Examiner(s): Swartz, Stephen S
• Application Number:
  US12/921,494
• Publication Number:
  US 20110046995A1
• Time in Patent Office: 2,855 Days
• CPC Class Codes: G01H 17/00 Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups see provisionally also G01H1/00
• CPC Class Codes: G05B 23/0278 Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/0631 Resource planning, allocation, distributing or scheduling for enterprises or organisations
• CPC Class Codes: G06Q 10/20 Administration of product repair or maintenance
• CPC Class Codes: G06Q 50/04 Manufacturing
• CPC Class Codes: Y02P 90/30 Computing systems specially adapted for manufacturing

Abstract

A method for trouble managing in equipment is provided, with which optimal timing of repairing the equipment and occurrence of malfunction probable to occur concurrently with present malfunction or later stage can be inferred with sufficient accuracy, and which can be adopted for large-scale equipment used in a plant. The method for trouble managing of equipment by monitoring operation condition of the equipment with a monitoring means and inferring cause of malfunction of the equipment by an inference means which infers the cause of the malfunction using measured data concerning the operation condition obtained by the monitoring means when malfunctions occur as nodes of the inference means, comprises selecting acoustic data most similar to sound emitted from the equipment in which malfunction has occurred from among a plurality of acoustic data provide beforehand, selecting morphologic data most similar to a pattern of operating condition in the equipment from among a plurality of morphologic data provide beforehand, adding the selected acoustic data and the selected morphologic data to the nodes, and performing inference of cause of the malfunction of the equipment by a first Bayesian network base on the nodes.

Claims

1. A system for trouble managing of equipment used in a plant, the system comprising:

a monitoring device for monitoring an operating condition of the equipment;

a memory device for storing data concerning the operating condition, and the memory device in which a plurality of acoustic data corresponding to abnormal noises of the equipment and a plurality of morphologic data corresponding to moving images of combustion condition of the equipment being previously stored;

a first outputting device for outputting the plurality of acoustic data;

a first selecting device for selecting desired acoustic data from the outputted acoustic data of the first outputting device;

a second outputting device for output the plurality of morphologic data;

a second selecting device for selecting desired morphologic data from the outputted morphologic data of the second outputting device;

an inferring device for, when an abnormal signal is detected by the monitoring device, receiving the stored data corresponding to the abnormal signal from the memory device, adding to the node each of the desired acoustic data selected by the first selecting device and the desired morphologic data selected by the second selecting device, and performing inference of cause of the malfunction of the equipment by a first Bayesian network based on the nodes.

2. The system for trouble managing of equipment used in a plant according to claim 1, wherein the inferring device is configured to:

establish a second Bayesian network concerning correlation between the cause inferred by the first Bayesian network and actual implemented repair corresponding to the cause; and

infer measure against the cause inferred by the first Bayesian network based on the second Bayesian network.

3. The system for trouble managing of equipment used in a plant according to claim 1, wherein

the memory device is further configured to store cause of malfunction of the equipment or analogous equipment in past times and expense required to repair the equipment or analogous equipment in a case appropriate action was not taken as a database,

the inferring device is configured to:

perform inference of probability of occurrence of malfunction which may occur if present malfunction is neglected by the first Bayesian network base on the database; and

calculate risk cost by multiplying the inferred probability by the expense required to repair in a case appropriate action was not taken responding to the inference of cause of malfunction.

4. The system for trouble managing of equipment used in a plant according to claim 3, wherein

the inferring device is configured to:

estimate the expense to repair the present malfunction; and

compare the expense with the risk cost.

5. The system for trouble managing of equipment used in a plant according to claim 1, wherein

the inferring device is configured to:

input a time series data in which the malfunctions occurred in each unit of the plant are inputted in order of time to the first Bayesian network; and

perform the inference of causes of malfunctions highly probable to occur next to the present malfunction and probabilities of their occurrence.