Circuit board component offset detection method
By combining multiple independent variables for circuit board component offset detection, the problem of inaccurate component offset judgment in the prior art is solved, missing and overkill is reduced, and detection accuracy is improved.
Patent Information
- Application Number
- CN202311632785.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-01
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2043-12-01
AI Technical Summary
During the installation of circuit board components, it is difficult for the prior art to accurately judge the deviation of components, resulting in missed and oversold, resulting in customer use risks and loss of production costs.
The X-direction displacement ΔX, Y-direction displacement ΔY, the angle displacement θ, the length of the component edge exceeds the pad length C, and the ratio S exceeding the pad area to the total area S as independent variables, and the logistic regression function is used to determine it. If the function value is greater than The threshold is determined to be offset.
Improve the accuracy of component offset detection, reduce the situation of missed and oversold, and improve the reliability of detection.
Smart Images

Figure CN117729766B_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of offset detection, and in particular relates to a circuit board component offset detection method. Background Art
[0002] When mounting components on a circuit board, various defects may occur: such as offset, tombstone, missing parts, wrong parts, deformation, foreign matter, etc. Among them, the offset of connect components is difficult to define the threshold using conventional algorithms.
[0003] At present, there are three main independent variables for judging the offset of connect components: X-direction displacement, Y-direction displacement and angle displacement. If thresholds are set for the three variables respectively, two situations may occur: 1. Missing: judging a product that should be offset as qualified, resulting in missing, causing risks for customers; 2. Over-killing: judging a product that should be qualified as offset, resulting in over-killing, causing cost losses for the manufacturer.
[0004] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention, and should not necessarily be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention
[0005] The present invention aims to solve the above technical problems at least to a certain extent. To this end, the present invention aims to provide a circuit board component offset detection method.
[0006] The technical solution adopted by the present invention is:
[0007] A circuit board component offset detection method comprises the following steps:
[0008] Obtain the X-direction displacement ΔX, Y-direction displacement ΔY, and angular displacement θ of the component on the pad;
[0009] Calculate the length C of the side of the component beyond the pad and the ratio S of the area of the component beyond the pad to the total area of the component;
[0010] The X-direction displacement ΔX, the Y-direction displacement ΔY, the angle displacement θ, the length C and the ratio S are substituted into the logistic regression function to obtain the function value. If the function value is greater than the threshold, it is determined to be an offset.
[0011] Preferably, the formula for calculating the length C of the side length of the component beyond the pad is:
[0012]
[0013] The formula for calculating the ratio S of the area of the component extending beyond the pad to the total area of the component is:
[0014]
[0015] Among them, a is the width of a single PIN on the component, b is the length of a single PIN on the component, m is the pad width corresponding to a single PIN, and l is the overall length of the component.
[0016] Preferably, an image of the circuit board is captured, and an X-direction displacement ΔX, a Y-direction displacement ΔY, and an angular displacement θ of the component on the pad are obtained through image recognition.
[0017] Preferably, the data set is divided into a training set and a validation set in a ratio of 8:2, and input into a logistic regression function to obtain a threshold.
[0018] The beneficial effects of the present invention are:
[0019] The circuit board component offset detection method provided by the present invention uses five parameters, namely, X-direction displacement ΔX, Y-direction displacement ΔY, angular displacement θ, length C of component side length exceeding pad, and ratio S of area of component exceeding pad to total area of component, as independent variables to judge the offset. The judgment is more accurate and can reduce missed kills and over-kills. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 Schematic diagram of pads and components of the present invention.
[0021] Figure 2 is a schematic diagram of the components of the present invention.
[0022] Figure 3 It is a test data diagram of the circuit board component offset detection method of the present invention. DETAILED DESCRIPTION
[0023] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0024] It should be understood that it should also be noted that in the embodiment, the functions / actions that appear may be different from the order in which the drawings appear. For example, depending on the functions / actions involved, they can actually be executed substantially concurrently, or two figures shown in succession can sometimes be executed in the reverse order.
[0025] like Figure 1 and Figure 2 As shown, the circuit board component offset detection method of this embodiment includes the following steps:
[0026] S1. Take a picture of the circuit board, and obtain the X-direction displacement ΔX, Y-direction displacement ΔY, and angle displacement θ of component 2 on pad 1 through image recognition, wherein the X-direction displacement ΔX, Y-direction displacement ΔY, and angle displacement θ are all based on pad 1, and the three parameters of X-direction displacement ΔX, Y-direction displacement ΔY, and angle displacement θ can be directly identified.
[0027] S2. Calculate the length C of the side of the component beyond the pad and the ratio S of the area of the component beyond the pad to the total area of the component; the two parameters of length C and ratio S need to be obtained through calculation. The formula for calculating the length C of the side of the component beyond the pad is:
[0028]
[0029] The formula for calculating the ratio S of the area of the component (single pin) beyond the pad to the total area of the component (single pin) is:
[0030]
[0031] Among them, a is the width of a single PIN on the component, b is the length of a single PIN on the component, m is the pad width corresponding to a single PIN, and l is the overall length of the component.
[0032] S3. Substitute the X-direction displacement ΔX, the Y-direction displacement ΔY, the angle displacement θ, the length C and the ratio S into the logistic regression function to obtain the function value. If the function value is greater than the threshold, it is determined to be offset, otherwise it is determined to be qualified.
[0033] The threshold value corresponding to each parameter is obtained by the following method: collect a data set, which should include five parameters and corresponding judgment results (offset or qualified), divide the collected data set into a training set and a validation set with a ratio of 8:2, input it into the logistic regression function, and obtain the threshold value.
[0034] The logistic regression function has a wide range of applications in binary classification problems. It can be used for prediction, probability estimation, feature importance assessment, and providing explanations. It is a simple and effective classification algorithm model.
[0035] like Figure 3 As shown, the circuit board component offset detection method is the optimized method, and the previous method is the method using three independent variables mentioned in the background technology. It can be seen that the optimized method of this embodiment is more accurate than the previous method.
[0036] The present invention is not limited to the above-mentioned optional implementation modes. Anyone can derive other various forms of products under the inspiration of the present invention. However, no matter what changes are made in the shape or structure, all technical solutions that fall within the scope defined by the claims of the present invention fall within the protection scope of the present invention.
Claims
1. A circuit board component offset detection method, characterized in that: The following steps are involved: Obtain the X-direction displacement ΔX, Y-direction displacement ΔY, and angular displacement θ of the component on the pad; Calculate the length C of the side of the component beyond the pad and the ratio S of the area of the component beyond the pad to the total area of the component; Substitute the X-direction displacement ΔX, the Y-direction displacement ΔY, the angle displacement θ, the length C and the ratio S into the logistic regression function to obtain the function value. If the function value is greater than the threshold, it is determined to be an offset. The formula for calculating the length C of the component side beyond the pad is: The formula for calculating the ratio S of the area of the component extending beyond the pad to the total area of the component is: Among them, a is the width of a single PIN on the component, b is the length of a single PIN on the component, m is the pad width corresponding to a single PIN, and l is the overall length of the component.
2. The circuit board component deviation detection method according to claim 1, characterized in that: The circuit board image is captured, and the X-direction displacement ΔX, Y-direction displacement ΔY, and angle displacement θ of the component on the pad are obtained through image recognition.
3. The circuit board component deviation detection method according to claim 1, characterized in that: The data set is divided into a training set and a validation set with a ratio of 8:2, and input into the logistic regression function to obtain the threshold; The data set includes X-direction displacement ΔX, Y-direction displacement ΔY, angular displacement θ, length C and ratio S, as well as corresponding determination results.
