Detecting and diagnosing faults in HVAC equipment

• US 7,444,251 B2
• Filed: 08/01/2006
• Issued: 10/28/2008
• Est. Priority Date: 08/01/2006
• Status: Active Grant

• Current Assignee: Mitsubishi Electric Research Laboratories, Inc. (Mitsubishi Electric Corporation)
• Original Assignee: Mitsubishi Electric Research Laboratories, Inc. (Mitsubishi Electric Corporation)
• Inventors: Radhakrishnan, Regunathan, Divakaran, Ajay, Nikovski, Daniel N., Peker, Kadir A.
• Primary Examiner(s): Hofsass; Jeff
• Assistant Examiner(s): WANG, JACK K
• Application Number:
  US11/498,289
• Publication Number:
  US 20080033674A1
• Time in Patent Office: 819 Days
• Field of Search: 340/679, 621/26, 621/27, 702/81, 702/108, 702/113, 700/79, 700/108
• US Class Current: 702/81
• CPC Class Codes: F24F 11/30 for purposes related to the operation of the system, e.g. for safety or monitoring
• CPC Class Codes: F24F 11/38 Failure diagnosis
• CPC Class Codes: F24F 11/52 Indication arrangements, e.g. displays
• CPC Class Codes: F24F 11/62 characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
• CPC Class Codes: F24F 2110/00 Control inputs relating to air properties
• CPC Class Codes: G05B 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks

Abstract

A method and system detects and diagnoses faults in heating, ventilating and air conditioning (HVAC) equipment. Internal state variables of the HVAC equipment are measured under external driving conditions. Expected internal state variables are predicted for the HVAC equipment operating under the external driving conditions using a locally weighted regression model. Features are determined of the HVAC based on differences between the measured and predicted state variables. The features are classified to determine a condition of the HVAC equipment.

Claims

1. A method for detecting and diagnosing faults in heating, ventilating and air conditioning (HVAC) equipment, comprising the steps of:

measuring internal state variables of HVAC equipment operating under external driving conditions;

predicting expected internal state variables for the HVAC equipment operating under the external driving conditions using a locally weighted regression model;

determining features of the HVAC based on differences between the measured and predicted state variables; and

classifying the features to determine a condition of the HVAC equipment.

2. The method of claim 1, in which locally weighted regression model is constructed by measuring the HVAC equipment operating under normal external driving conditions.

3. The method of claim 1, in which the classifying uses a plurality of classifiers, each classifier trained by measuring the HVAC equipment operating under a known condition.

5. The method of claim 1, in which a regression model uses logistic regression.

6. The method of claim 1, in which the regression model is local.

7. The method of claim 1, in which the regression model is global.

8. The method of claim 1, in which the regression model determines a mean squared error of the regression model is optimized.

9. The method of claim 7, in which the regression model uses polynomial regression.

10. The method of claim 1, in which the classifiers distinguishes between three conditions the equipment.

4. A system for detecting and diagnosing faults in heating, ventilating and air conditioning (HVAC) equipment, comprising the steps of:

sensors configured to measure internal state variables of HVAC equipment operating under external driving conditions;

a locally weighted regression model configured to predict expected internal state variables for the HVAC equipment operating under the external driving conditions using;

means for determining features of the HVAC based on differences between the measured and predicted state variables; and

a classifier configured to classify the features to determine a condition of the HVAC equipment.