US5439160A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and apparatus for obtaining reflow oven settings for soldering a PCB
Assignee: Siemens Corp
•
Filing: 1993-03-31
•
Granted: 1995-08-08
•
Expires: 2013-03-31
Abstract
Abstract An artificial neural network is trained to recognize inputted thermal and physical features of a printed circuit board, for providing settings for a reflow oven for obtaining acceptable soldering of the printed circuit board.
Inventors
- 👤 Angelo R. Marcantonio
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-01 20:54
CPC Classifications
G; G05; G05D; G05D23/00; G05D23/19; G05D23/1917; B; B23; B23K; B23K1/00; B23K1/008; H; H05; H05K; H05K3/00; H05K3/30; H05K3/32; H05K3/34; H05K3/3494; B23K2101/00; B23K2101/30; B23K2101/36; B23K2101/42; H05K2203/00; H05K2203/16; H05K2203/163
Claims Analysis
Total Claims: 20
Claim 1
Independent Claim
216 words
A method for determining a reflow oven temperature profile for soldering a printed circuit board (PCB), comprising the steps of: configuring said oven with a predetermined number of temperature zones, and range of associated conveyor belt speeds for conveying PCB's through said oven; determining thermal characteristics for each one of a representative plurality of different samples of printed circuit boards typical of a range of printed circuit boards that may be run through said reflow oven; combining said thermal characteristics for each sample PCB with identifiable physical characteristics thereof, for obtaining identifying and distinguishing input features for each sample PCB; determining for each sample PCB the belt speed, and temperatures of said temperature zones, respectively, for obtaining acceptable soldering, said temperatures and belt speed being designated as output features for each associated sample PCB board; training a neural network by sequentially and iteratively applying said input features to input nodes of said neural network, respectively, and applying said output features to output nodes of said neural network, respectively, for each sample PCB; and applying input features of a non-sample PCB to said trained neural network, for obtaining as outputs from said neural network a desired belt speed, and temperature settings for each zone of said oven, for setting up said oven to solder said non-sample PCB.
Claim 2
Independent Claim
216 words
A method for determining a reflow oven temperature profile for soldering a printed circuit board (PCB), comprising the steps of: configuring said oven with a predetermined number of temperature zones, and range of associated conveyor belt speeds for conveying PCB's through said oven; determining thermal characteristics for each one of a representative plurality of different samples of printed circuit boards typical of a range of printed circuit boards that may be run through said reflow oven; combining said thermal characteristics for each sample PCB with identifiable physical characteristics thereof, for obtaining identifying and distinguishing input features for each sample PCB; determining for each sample PCB the belt speed, and temperatures of said temperature zones, respectively, for obtaining acceptable soldering, said temperatures and belt speed being designated as output features for each associated sample PCB board; training a neural network by sequentially and iteratively applying said input features to input nodes of said neural network, respectively, and applying said output features to output nodes of said neural network, respectively, for each sample PCB; and applying input features of a non-sample PCB to said trained neural network, for obtaining as outputs from said neural network a desired belt speed, and temperature settings for each zone of said oven, for setting up said oven to solder said non-sample PCB.
Claim 3
Dependent Claim
90 words
The method of claim 1, wherein said step of determining the thermal characteristics for each sample PCB includes the steps of: attaching a mole temperature measurement device to a selected sample PCB; presetting said reflow oven to a given belt speed, and given temperature setting for each of the plurality of temperature zones of said oven, respectively; running said sample PCB through said reflow oven; and repeating said attaching, presetting, and running steps with identical combinations of belt speed, and temperature settings, for each one of said sample PCB's, respectively.
Claim 4
Dependent Claim
147 words
The method of claim 1, wherein said step of determining for each sample PCB the belt speed, and temperatures of said temperature zones, respectively, for obtaining acceptable soldering, includes the steps of: running a plurality of identical ones of a selected said sample PCB board, respectively, through said reflow oven; changing the temperatures in selected ones of said temperature zones, and/or the speed of said conveyor belt, for each run of a different one of said plurality of identical ones of the selected said sample PCB board, respectively; selecting the best soldered one of said plurality of identical ones of said selected sample PCB board, for obtaining the optimum settings for the belt speed and temperature of said temperature zones, for the selected said sample PCB board; and repeating said running, changing, and selecting steps, until each one of said different samples PCB boards have been processed.
Claim 5
Dependent Claim
76 words
The method of claim 2, wherein said step of selecting features includes selecting for each sample PCB its weight, thickness, size along oven belt in the direction of travel, size of PCB across oven belt in direction of travel, total surface area of thin integrated circuits (IC's) to be soldered to said PCB, total surface area of thick IC's to be soldered to said PCB, finish gloss total number of layers included therein, and finish color.
Claim 6
Dependent Claim
46 words
The method of claim 4, wherein said step of selecting input features further includes for said finish gloss of said sample PCB, input features including a rating of 4 for very high gloss, 3 for high gloss, 2 for medium gloss, and 1 for low gloss.
Claim 7
Dependent Claim
46 words
The method of claim 5 wherein said step of selecting input features further includes for said finish color of said sample PCB, input features including a rating of 4 for very light color, 3 for light color, 2 for medium color, and 1 for dark color.
Claim 8
Dependent Claim
54 words
The method of claim 6, wherein said step of selecting input features further includes: attaching a plurality of thermocouples to different positions on said sample PCB; and selecting test oven mole averages of the thermocouple temperatures at a plurality of different periods of time of travel of said sample PCB through said reflow oven.
Claim 9
Dependent Claim
68 words
The method of claim 7, wherein said periods of time of travel include a first period equal to one-quarter of the total time period for said PCB to travel through the temperature zones of said oven, a second period equal to one-half of this total time period, a third period equal to three-quarters of this total time period, and a fourth period equal to said total time period.
Claim 10
Dependent Claim
29 words
The method of claim 8, wherein said step of selecting input features further includes selecting a test oven mole average of the maximum temperatures of a plurality of thermocouples.
Claim 11
Dependent Claim
43 words
The method of claim 9, wherein said step of selecting input features further includes selecting as an input feature the test oven mole average of the periods of time of PCB travel associated with the maximum temperature of said plurality of thermocouples, respectively.
Claim 12
Dependent Claim
39 words
The method of claim 10, wherein said step of selecting input features further includes selecting as an input feature an average rate of change to a maximum temperature for said plurality of thermocouples associated with said test oven MOLE.
Claim 13
Dependent Claim
32 words
The method of claim 11, wherein said step of selecting input features further includes selecting as an input feature the time for said plurality of thermocouples to reach a given average temperature.
Claim 14
Dependent Claim
74 words
The method of claim 1, wherein said step of training a neural network further includes the steps of: forward passing said input features through said neural network to develop actual output signals; comparing said actual output signals to corresponding desired output signals for associated input features to develop error signals, respectively; backpropagating said error signals through said neural network for changing weighting factors therein to minimize said error signals for each sample PCB board.
Claim 15
Dependent Claim
74 words
The method of claim 12, wherein said steps of training a neural network further includes the steps of: forward passing said input features through said neural network to develop actual output signals; comparing said actual output signals to corresponding desired output signals for associated input features to develop error signals, respectively; backpropagating said error signals through said neural network for changing weighting factors therein to minimize said error signals, for each sample PCB board.
Claim 16
Dependent Claim
79 words
The method of claim 1, wherein said step of selecting input features includes selecting for each sample PCB its weight, thickness, size along oven belt in the direction of travel, size of PCB across oven belt in direction of travel, total surface area of thin integrated circuits (IC's) to be soldered to said PCB, total surface area of thick IC's, finish gloss of said PCB total number of layers included in said PCB, and finish color of said PCB.
Claim 17
Dependent Claim
45 words
The method of claim 15, wherein said step of selecting input features further includes for said finish gloss of said PCB, input features including a rating of 4 for very high gloss, 3 for high gloss, 2 for medium gloss, and 1 for low gloss.
Claim 18
Dependent Claim
45 words
The method of claim 16, wherein said step of selecting input features further includes for said finish color of said PCB, input features including a rating of 4 for very light color, 3 for light color, 2 for medium color, and 1 for dark color.
Claim 19
Dependent Claim
57 words
The method of claim 2, wherein said step of selecting input features further includes: attaching a plurality of thermocouples at different positions on said sample PCB; and selecting test oven mole averages of a plurality of thermocouple temperatures at a plurality of different periods of time of travel of said sample PCB through said IR reflow oven.
Claim 20
Dependent Claim
68 words
The method of claim 18, wherein said periods of time of travel include a first period equal to one-quarter of the total time period for said PCB to travel through the temperature zones of said oven, a second period equal to one-half of this total time period, a third period equal to three-quarters of this total time period, and a fourth period equal to said total time period.
References Cited (Backward Citations)
US4180199A
Cited
US5003160A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1998-08-07 | 1999-02-06 | 1999-08-08 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2002-08-07 | 2003-02-06 | 2003-08-08 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2006-08-07 | 2007-02-06 | 2007-08-08 | $7700.00 | Window Closed / Lapsed |