MOISTURE SENSOR AND/OR DEFOGGER WITH BAYESIAN IMPROVEMENTS, AND RELATED METHODS

• US 20160275409A1
• Filed: 06/02/2016
• Published: 09/22/2016
• Est. Priority Date: 01/10/2006
• Status: Active Grant

• Current Assignee: Guardian Glass LLC (KOCH Industries Incorporated)
• Original Assignee: Guardian Industries Corporation (KOCH Industries Incorporated)
• Inventors: VEERASAMY, Vijayen S.
• Granted Patent: US 10,229,364 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B32B 17/10036 comprising two outer glass sheets
• CPC Class Codes: B32B 17/10174 Coatings of a metallic or dielectric material on a constituent layer of glass or polymer
• CPC Class Codes: B32B 17/10761 containing vinyl acetal
• CPC Class Codes: B60Q 1/1423 Automatic dimming circuits, i.e. switching between high beam and low beam due to change of ambient light or light level in road traffic
• CPC Class Codes: B60Q 2300/112 Vehicle speed
• CPC Class Codes: B60Q 2300/314 Ambient light
• CPC Class Codes: B60S 1/0818 including control systems responsive to external conditions, e.g. by detection of moisture, dirt or the like
• CPC Class Codes: B60S 1/0822 characterized by the arrangement or type of detection means
• CPC Class Codes: B60S 1/0825 Capacitive rain sensor
• CPC Class Codes: B60S 1/087 including an ambient light sensor control of vehicle lights B60Q
• CPC Class Codes: G01D 5/24 by varying capacitance
• CPC Class Codes: G01J 1/42 using electric radiation detectors optical or mechanical part G01J1/04; by comparison with a reference light or electric value G01J1/10
• CPC Class Codes: G01N 27/223 for determining moisture content, e.g. humidity rain detectors on vehicle windows B60S1/0825
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

In certain example embodiments, moisture sensors, defoggers, etc., and/or related methods, are provided. More particularly, certain example embodiments relate to moisture sensors and/or defoggers that may be used in various applications such as, for example, refrigerator/freezer merchandisers, vehicle windows, building windows, etc. When condensation or moisture is detected, an appropriate action may be taken (e.g., actuating windshield wipers, turning on a defroster, triggering the heating of a merchandiser door or window, etc.). Bayesian approaches optionally may be implemented in certain example embodiments in an attempt to improve moisture detection accuracy. For instance, models of various types of disturbances may be developed and, based on live data and a priori information known about the model, a probability of the model being accurate is calculated. If a threshold value is met, the model may be considered a match and, optionally, a corresponding appropriate action may be taken.

Claims

1-21. -21. (canceled)

22. A method of detecting moisture on a glass substrate, the method comprising:

providing a parameterized model (M) for a possible moisture-related disturbance;

providing background information (I) concerning the model, I being known a priori;

calculating a prior probability of M given I, P(M|I);

collecting data from at least one sensor (D) connected to the substrate;

computing a probability of the model given D and I, P(M|D,I);

repeating the computing of P(M|D,I) as additional data is collected; and

accepting the model if P(M|D,I) meets and/or exceeds a predetermined threshold,

wherein the glass substrate is a part of a vehicle window, building window, or merchandiser window; and

wherein acceptance of the model triggers an action to be taken relative to the glass substrate, the action being selected from the group consisting of;

(i) causing a wiper to remove moisture from a vehicle window, (ii) heating the glass substrate, and (iii) defrosting the glass substrate.

23. The method of claim 22, wherein the at least one sensor is configured to sense disturbances in an electric field proximate the substrate for a given frame in time.

24. The method of claim 22, wherein D is proportional to the product of a prior probability distribution and a maximum likelihood distribution.

25. The method of claim 22, wherein P(M|D,I) is P(M|I) P(D|M,I)/P(D|I), where:

P(M|I) is a prior distribution,

P(D|M,I) is a likelihood function when considered as a function of M, and

P(D|I) is evidence.

26. The method of claim 22, wherein the at least one sensor includes a capacitive sensor configured to measure a disturbance in the capacitive field set up by the sensor, the capacitive field having different detected intensities at different positions in the field.

27. The method of claim 22, wherein the at least one sensor includes a light sensor.

29. A method of detecting moisture on a glass substrate, the method comprising:

providing a plurality of parameterized models (Mx) for different possible disturbances;

providing background information (Ix);

calculating a prior probability of Mx given Ix, P(Mx|Ix);

collecting data from at least one sensor (D) connected to the substrate;

computing a probability of each said model given D and Ix, P(Mx|D,Ix);

repeating the computing of P(Mx|D,Ix) as additional data is collected;

comparing the probability of each said model to a predetermined threshold;

accepting or rejecting each said model based on the comparing; and

when a particular model is accepted, causing an action to be taken relative to the glass substrate in dependence on the particular model that is accepted, the action being one or more of;

(i) causing a wiper to active on a vehicle window, (ii) heating the glass substrate, (iii) defrosting the glass substrate, and (iv) turning on or off vehicle lights.

30. The method of claim 29, wherein parameterized models are provided for moisture-related disturbances.

31. The method of claim 29, wherein the moisture-related disturbances include the presence of liquid condensation, frost, and ice.

32. An electronic device for detecting moisture on a glass substrate, the electronic device comprising:

a first memory location storing a plurality of parameterized models (Mx) for different possible disturbances;

a second memory location storing background information (Ix) concerning each of the models;

at least one sensor configured to collect data from at least one sensor (D) connected to the substrate; and

at least one processor configured to;

calculate a prior probability of Mx given Ix, P(Mx|Ix);

compute a probability of each said model given D and Ix, P(Mx|D,Ix);

repeat computations of P(Mx|D,Ix) as additional data is collected by the at least one sensor;

compare the probability of each said model to a predetermined threshold; and

accept or reject each said model based on the comparison, wherein acceptance of a model triggers an action to be taken relative to the glass substrate, the action being one or more of;

(i) causing a wiper to remove moisture from a vehicle window, (ii) heating the glass substrate, (iii) defrosting the glass substrate, and (iv) turning on or off vehicle lights.