Anritsu机器学习应用于PCB外观检测.pdf - 第4页

Anritsu T echnical Revi ew No.28 September 2020 Application o f Machine Lear ning to Print ed Circuit Boar d External I nspection (4) This software was run on on e Image T raining PC on the AOI LAN (Figure 4). AOI-relate…

Anritsu Technical Review No.28 September 2020 Application of Machine Learning to Printed Circuit Board External Inspection

(3)

Figure 3 Examples of SMT Mounting Faults

(1) Poor wetting

The solder is not spread evenly in the correct amount over

the part leads and electrodes and the fillet form does not

appear wetted. The causes are insufficient solder, leads or

electrodes not in contact with land, and insufficient heat at

reflow.

(2) Solder bridging (shorts)

This problem tends to occur when using very small SOP

and QFP ICs with sizes of 0.5 mm and 0.4 mm

Note 4

or when

the correct amount of solder is not applied to adjacent leads.

The causes are poor solder printing, bent solder leads, and

poor parts mounting.

(3) Vertical chip (gravestone and Manhattan)

This problem occurs when both electrodes of a part are

not soldered simultaneously and surface tension at the end

wetted first causes the chip to stand vertically on one sol-

dered electrode.

The countermeasures are improving the land dimensions

and mounting accuracy, and preheating to reduce the solder

melt time difference.

(4) Non-contact, missing solder

This is caused by the solder paste not melting during re-

flow and remaining in a paste state. The causes are old

solder paste or poor reflow oven temperature control.

Missing solder is caused by lack of solder at the part and

is caused by poor solder paste printing.

(5) Rotated and slipped parts

Rotated or slipped parts are the result of part leads or

electrodes projecting outside the land or from poor posi-

tioning by the parts mounter. Vibration at mounting other

parts or at conveying/transport between processes can re-

sult in surface tension issues causing displacement as in

vertical chip faults.

Note 3: The land is a part where the copper forming the PC board

traces is exposed for soldering to the part leads and elec-

trodes. Sometimes the land surface is gold-plated.

Note 4: SOP and QFP describe IC packages. A SOP (Small Outline

Package) has L-shaped legs from two sides of the rectan-

gular package connecting to lands. A QFP (Quad Flat

Package) has multiple leads on all four sides of the package

connecting to lands.

4 AOI PC Board External Inspection Issues

AOI inspection sets strict evaluation criteria using mul-

tiple parameters so as to not allow fail products to pass in-

spection. As a result, so-called "excess watching" is a com-

mon problem. Excess watching is a phenomenon where

products passing at the visual-inspection level are evalu-

ated as fail by the AOI inspection system. If there is too

much excess watching, visual confirmation after automatic

inspection is increased.

To proactively suppress excess watching, the soldered

part digital evaluation criteria are readjusted repeatedly

over but there can be a problem where excess watching does

not decrease because fine-adjustment cannot be completed

due to momentary changes in the processing conditions

caused by PC board condition and parts mounting ran-

domness.

5 PC Board External Inspection using Machine

Learning

Applying machine learning to the visual confirmation

work following AOI inspection has helped with excess

watching inspection efficiency.

5.1 Leaned Image Data Acquisition

Collecting and annotating (labeling) images used for

machine learning is a key process in applying machine

learning. Consequently, we configured a system (Figure 4)

to capture AOI inspection image data for use as learning

images.

Generally, dedicated terminals are required to capture

AOI inspection results and inspection image data. In this

development, we obtained the terminal interface specifica-

tions from the AOI maker and developed software to di-

rectly capture inspection results and learning images (in-

spection images) at a connected personal computer (PC).

(a) Poor wetting

(b) Solder Bridge

(d) Missing Solder

(e) Rotated Part

Anritsu Technical Review No.28 September 2020 Application of Machine Learning to Printed Circuit Board External Inspection

(4)

This software was run on one Image Training PC on the

AOI LAN (Figure 4).

AOI-related PCs are connected over a dedicated AOI local

area network (LAN) from the viewpoint of higher security

and to prevent non-factory network problems affecting

plant mass-production.

To assure the independence of the AOI LAN, the ma-

chine-learning environment ( and  in Figure 4) was con-

figured on the in-company LAN via a separate independent

LAN (c. Independent LAN in Figure 4) and multiport Net-

work Attached Storage (NAS) ( in Figure 4).

Required data is shared via files on the NAS and the PC

for capturing learning images is programed to send images

and evaluation data stored on the AOI-DB server periodi-

cally to the machine-learning PC.

Generally, at machine learning, only images of pass

products are required, but not images of faulty products.

However, due to disk-space limitations at the AOI-DB serv-

er, there were problems with inability to save images for

products evaluated as pass. Consequently, the focus of at-

tention was only on trouble locations such as electrodes and

leads for images of parts evaluated as fail and machine

learning was used to capture images of fillets of electrodes

and leads of pass parts from within images of fail parts.

When introducing machine evaluation to external inspec-

tion, the learning model obtained from the Ma-

chine-Learning PC was transferred to the Machine Evalua-

tion PC and the result for the evaluated image was saved in

the AOI-DB server as the visual evaluation result that the

Image Training PC input to the AOI terminal. If images

evaluated by AIO as fail were evaluated by machine learn-

ing as pass, the operator in charge of visual evaluation

handled the image as if it had already been visually evalu-

ated.

Reduction of visual inspection and confirmation by eye is

expected with introduction of machine learning because

only parts evaluated as fail by both AOI and machine

learning are inspected.

5.2 Machine Learning Discriminator

Machine learning is a method for allowing a computer to

learn human-like recognition and evaluation. It is per-

formed using the following two processes: Learning, and

Evaluation

1), 2), 3)

(1) Learning Process

Even the best machine-learning algorithm is worthless

without a learning process which must be performed first

using learning data. Learning is repeated over until the

accuracy (learning mistakes) reach the required accuracy

and the learning model is completed.

(2) Evaluation Process

The discriminator (model with completed learning) eval-

uates whether input image data are pass or fail. For exam-

ple, a discriminator that has learned labelled (named)

product images can accurately evaluate the names of prod-

ucts for unknown images that have not been learned.

a. AOI LAN

b. Company LAN

(1) Training image and AOI evaluation result

(2)

Evaluation m

achine learning model

(3) Board evaluation image and result (at machine evaluation introduction)

(1)

(2)

(3)

(1)

c. Inde

endent LAN

 Image

Training PC

(Windows10)



AOI-DB

Server

AOI

Main

AOI

Terminal

AOI

Terminal

AOI

Terminal

 Machine

Learning PC

(Linux)

 Machine

Evaluation

PC (Linux)

Figure

Image Acquisition System Configuration

Anritsu Technical Review No.28 September 2020 Application of Machine Learning to Printed Circuit Board External Inspection

(5)

(3) Discrimination Procedure

We used a convolutional neural network with excellent

image-recognition performance as the machine-learning

discriminator. A convolutional neural network is configured

from a pile of levels, such as convolution layers and pooling

layers with various special functions to form a number of

deep levels. The convolutional neural netwok used in this

study had 10 levels composed of convoluted layers with co-

efficients of 3 × 3 and 3 × 1 (height × width).

Figure 5 illustrates the discrimination procedure. First,

pre-processing loads the image to be inspected and identi-

fies the solder locations. The solder locations identified by

the discriminator are output as numeric discrimination re-

sults in the range of 0.0 to 1.0 indicating the normality dis-

tribution of the solder locations, with a value of 1.0 being

maximum normality. The normality threshold value deter-

mines whether the solder joint condition is pass or fail.

As shown in Figure 6, this inspection uses multiple dis-

criminators and evaluation is performed using the model

average, which averages the output of each discriminator.

Better performance can be expected

1), 2)

with suppressed

randomness, etc., by changing the learning parameter de-

fault values and combining multiple discriminators than

when using a single discriminator.

Figure 6 Model Averaging

6 Evaluating Results of PC Board External In-

spection using Machine Learning

6.1 Detection Performance

The performance of the algorithm proposed in this article

was evaluated using the model averaging technique applied

to 560 inspection images of pre-specified parts (60 pass

parts and 500 fail parts). The images used for evaluation

were not used for learning.

The results are shown in Table 1; eight learning models

were provided. As shown in Table 1, model averaging was

performed without making a specific evaluation to suppress

randomness in the detection performance for each learning

model.

Figure 7 shows the cumulative distribution confirming

the normality distribution. The red line is the cumulative

distribution of normality for fail parts (493 locations) and

the blue line is the cumulative distribution of normality for

pass parts (65,168 locations). The fail parts cumulative dis-

tribution origin is 1.0, but is best if distributed in the lower

half with the origin at less than 0.5. In addition, the pass

parts cumulative distribution is the distribution with 0.0 as

the origin, but is best if distributed in the upper half with

the origin at more than 0.5. Since the cumulative distribu-

tions for the pass and fail locations intersect, evaluation

mistakes occur when evaluating using a threshold.

Machine

Learning

Discriminator 1

Machine

Learning

Discriminator 2

Model Average

Machine

Learning

Discriminator N

Machine

Learning

Discriminator

Inspection

Image

(Input Image)

Extraction of Slder

Joints at 5 Locations

Discrimination

Processing for Each

Location

Normality of Each

Joint

Pre-

processing

0.2

0.3

0.8

0.9

1.0

Figure 5 Discrimination Procedure using Machine Learning