Method for monitoring performance of a heat transfer device

• US 8,046,191 B2
• Filed: 09/28/2007
• Issued: 10/25/2011
• Est. Priority Date: 09/30/2004
• Status: Active Grant

• Current Assignee: BL Technologies Inc. (Ashland Global Holdings, Inc.)
• Original Assignee: General Electric Company
• Inventors: Jammu, Vinay Bhaskar, Vora, Nishith Pramod, Babu, Ravi Yoganatha, Mahajanam, Rama Venkata
• Primary Examiner(s): WACHSMAN, HAL D
• Application Number:
  US11/864,191
• Publication Number:
  US 20080015816A1
• Time in Patent Office: 1,488 Days
• Field of Search: 702/85, 702/132, 702182-185, 700274-278, 700299-300, 714 47- 48, 165276-277, 237/19
• US Class Current: 702/182
• CPC Class Codes: G05B 23/0221 Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods

Abstract

A method is provided for the monitoring of heat transfer devices. The method includes the acts of receiving data from a heat transfer device, and computing a performance indicator indicative of an incipient anomaly condition of the heat transfer device based upon the received data, and/or computing a normalized efficiency of the heat transfer device. The normalized efficiency represents a corrected efficiency that isolates effects of a process parameter on performance of the heat transfer device. The data represents a measurable process parameter or a change in a measurable process parameter in the heat transfer device. The method receives the data and computes a performance indicator to predict performance degradation of the heat transfer device over time based upon the received data.

Claims

1. A method, comprising:

diagnosing, via a knowledge based network implemented on one or more computer-based systems, at least one probable cause of performance degradation of a heat transfer device based on at least one symptom indicating a change in performance of the heat transfer device;

analyzing, via the knowledge based network, the at least one probable cause of performance degradation in the heat transfer device to estimate a time to failure of the heat transfer device; and

validating, via the knowledge based network, the at least one probable cause based on at least a previous occurrence of the change in performance of the heat transfer device.

2. The method as defined in claim 1, comprising determining a detectability and an isolation capability for the probable cause of occurrence of the performance change based upon a cause and effect network.

3. The method as defined in claim 1, further comprising monitoring the at least one symptom at a plurality of locations on the heat transfer device.

4. A method, comprising:

providing data representing a measurable process parameter or a change in a measurable process parameter in a heat transfer device to an analysis module to compute a performance indicator or to an efficiency correction unit to calculate an initial efficiency;

detecting an anomaly condition in the heat transfer device via a trend detection module based upon the a performance indicator;

generating one or more prediction models based on an anomaly condition, and the prediction model provides one or more probable causes of failure;

detecting incipient failure of the heat transfer device via the one or more prediction models; and

providing an anomaly reduction medium to the heat transfer device based on the initial efficiency or on the incipient failure detection to reduce the effects of at least one of the anomaly conditions and thereby to defeat the failure mode.