UNIT VI

AUTOMATED INSPECTION
Prepared By
Rajesh Kumar
Assistant Professor
Department of Mechanical Engineering
Aditya Engineering College, Surampalem, ADB Road
East Godavari District, Andhra Pradesh 533543
 Introduction to Automated Inspection
• In quality control, inspection is the way by which poor quality is
detected and good quality is assured.

• Inspection is traditionally accomplished using labor-intensive methods

that are time-consuming and costly.

• As a result manufacturing lead time and product cost are increased

without adding any real value to the products.

• In addition, manual inspection is performed after the process is

complete, often after a significant time delay.
• New approaches to quality control are addressing these problems and
drastically altering the way inspection is accomplished.

The new approaches include following:-

• 100% Automated inspection rather than sampling inspection by manual

methods

• On-line sensor systems to accomplish inspection during or

immediately after the manufacturing process, instead of off-line
inspection performed later

• Software tools to track and analyze the sensor measurements over

time for statistical process control
• Feedback control of the manufacturing operation, monitoring process
variables that determine product quality rather than the product itself

• Advanced inspection and sensor technologies, combined with

computer-based system to automate the operation of the sensor
systems.
Inspection Fundamentals
Inspection fundamentals Includes following topics:-
• Types of Inspection

• Inspection Procedure

• Inspection Accuracy

• Inspection vs. Testing

 Inspection Fundamentals
• The term inspection refers to the activity of examining the product, its
components, subassemblies, or the raw materials to determine whether
they conform to design specifications, which are defined by the product
designer.

• Inspections can be classified into two types, according to the amount

of information derived from the inspection procedure about the item’s
conformance to specification:
 Types of Inspection
1. Inspection for variables:- In This one or more quality characteristics of
interest are measured using an appropriate measuring instrument or
sensor.
2. Inspection for attributes:- In this the part or product is inspected to
determine whether it conforms to the accepted quality standard.
• The determination is sometimes based simply on the judgment of the
inspector.
• In other cases, the inspector uses a gage to aid in the decision.
• Inspection by attributes can also involve counting the number of defects
in a product.
 Example of Inspection for Variables and Inspection for Attributes

Inspection for Variables Inspection for Attributes

• Measuring the diameter of a cylindrical • Gaging a cylindrical part with a GO/NO-GO

part. gage to determine if it is within tolerance
• Measuring the temperature of a toaster • Determining the fraction defect rate of a
oven to see if it is within the range specified sample of production parts
by design engineering • Counting the number of defects in an
• Measuring the electrical resistance of an automobile as it leaves the final assembly
electronic component plant
• Measuring the specific gravity of a fluid • Counting the number of imperfections in a
chemical Product. production run of carpeting
 Inspection Procedure
• A typical inspection procedure performed on an individual item,
such as a part, subassembly or final product consists of the
following steps:-

1. Presentation.

2. Examination.

3. Decision.

4. Action.
Explanation of Procedure
• Presentation:-The item is presented for examination.

• Examination. The item is examined for one or more nonconforming

features.

In inspection for variables, examination consists of measuring a dimension or

other attribute of the part or product.

In inspection for attributes, it involves gaging one or more dimensions or

searching the item for flaws.
• Decision:- Based on the examination, a decision is made whether the item
satisfies the defined quality standards.
• The simplest case involves a binary decision, in which the item is deemed
either acceptable or unacceptable.
• In more complicated cases, the decision may involve grading the item into
one of more than two possible quality categories, such as grade A, grade B,
and unacceptable.

• Action. The decision should result in some action, such as accepting or

rejecting the item, or sorting the item into the most appropriate quality
grade.
• In the past few decades, massive growth has taken place in the sensor and
computer technology and this resulted in the wide ranging acceptance of
automated inspection systems for the maintenance of strict quality
standards.

• Emergence of Automated inspection system has put the manual inspection process in
the back seat due to advantages felt by the industries in terms of accuracy and time saving.

•
 Inspection Accuracy
• There are normally two errors committed on the part of manufacturers while
carrying out the inspection.

• These two kinds of mistake are called Type I and Type II errors.

• Type I error occurs when a good lot is rejected and is called producers risk.

• Type II error occurs when a bad lot is accepted and is called consumers risk.

• An error is committed by the inspector that misses some of the defect during
inspection of an assembly line.
 In manual inspection, these errors result from
factors such as :

(i) Complexity and difficulty incurred while performing an inspection

task.

(ii) Inherent variations in the inspection procedure.

(iii) Requirement of judgment by the human inspector.

(iv) Mental fatigue.

(v) Inaccuracies or problems with the gages or measuring instruments

used in the inspection procedure.
After establishing methodology for an automated system,
inspection errors occur due to factors such as :
(i) Complexity and difficulty of the inspection task.
(ii) Resolution of the inspection sensors affected by “gain” and similar control
parameters setting.
(iii) Malfunctioning of equipment's.
(iv) Faults or “bugs” in the computer program controlling the inspection
procedure.
 AUTOMATED INSPECTION

• Economic justification of an automated inspection system depends on

whether the savings in labour cost and improvement in accuracy will be more
than the investment and/or development costs of the system.

• Automated inspection is defined as the automation of one or more steps

involved in the inspection procedure.

• There are a number of alternative ways in which automated or semi-

automated inspection can be implemented:
1. Automated presentation of parts by an automatic handling system
with a human operator still performing the examination and decision
steps.

2. Automated examination and decision by an automatic inspection

machine, with manual loading (presentation) of parts into the machine.

3. Completely automated inspection system in which parts presentation,

examination, and decision are all performed automatically.
• In the first case, the inspection procedure is performed by a human
worker, with all of the possible errors in this form of inspection.

• In cases (2) and (3), the actual inspection operation is accomplished

by an automated system.

• The full potential of automated inspection is best achieved when it is

integrated into the manufacturing process, when 100% inspection is
used, and when the results of the procedure lead to some positive
action.
 Inspection techniques can be divided into two
broad categories

• They are as follows:-

1. Contact Inspection Techniques

2. Noncontact Inspection Technologies

 Contact inspection
• Contact inspection involves the use of a mechanical probe or other device
that makes contact with the object being inspected.

• The purpose of the probe is to measure or gage the object in some way.

• These techniques are widely used in the manufacturing industries, in

particular in the production of metal parts (machining, stamping, and other
metalworking processes).

• Contact inspection is also used in electrical circuit testing.

The principal contact inspection technologies are the
following:
Conventional measuring and gaging instruments

• Coordinate measuring machines (CMMs) and related techniques to measure

Mechanical dimensions

• Stylus-type surface texture measuring machines to measure surface

characteristics such as roughness and waviness

• Electrical contact probes for testing integrated circuits and printed circuit

boards.
 Noncontact Inspection Technologies.
• Noncontact inspection methods utilize a sensor located at a certain distance
from the object to measure or gage the desired features.

• The noncontact inspection technologies can be classified into two

categories: optical and non-optical.

• Optical inspection technologies use light to accomplish the measurement or

gaging cycle.

• The most important optical technology is machine vision

• Non-optical inspection technologies utilize energy forms other
than light to perform the inspection; these other energies include
various electrical fields, radiation (other than light), and
ultrasonic.
 Advantage of Non contact type Inspection
• They avoid damage to the part surface that might result from contact inspection.

• Inspection cycle times are inherently faster. Contact inspection procedures require
the contacting probe to be positioned against the part, which takes time.

• Most of the noncontact methods use a stationary probe that does not need
repositioning for each part.

• Noncontact methods can often be accomplished on the production line without the
need for any additional handling of the parts, whereas contact inspection usually
requires special handling and positioning of the parts.

• It is more feasible to conduct 100% automated inspection, since noncontact

methods have faster cycle times and reduced need for special handling.
 Coordinate Measuring Machines
• A coordinate measuring machine (CMM) is an electromechanical system
designed to perform coordinate metrology.

• Coordinate metrology is concerned with measuring the actual shape and

dimensions of an object and comparing these results with the desired shape
and dimensions, as might be specified on a part drawing.

• It has a contact probe that can be positioned in three dimensions relative to

the surfaces of a work part.

• The x, y, and z coordinates of the probe can be accurately and precisely

recorded to obtain dimensional data about the part geometry.
To accomplish measurements in three-dimensional space, the basic
CMM consists of the following components:

• Probe head and probe to contact the work part surfaces

• Mechanical structure that provides motion of the probe in three Cartesian

axes and displacement transducers to measure the coordinate values of each
axis.

In addition, many CMMs include the following:

• Drive system and control unit to move each of the three axes

• Digital computer system with application software.

 CMM Construction
• In CMM the probe is fastened to a mechanical structure that allows movement
of the probe relative to the part.
• The part is usually located on a worktable that is connected to the structure.
• The two basic components of the CMM are
1. Probe
2. Mechanical structure.
For Automated type of CMM additional components
1. Transducers
2. Controller
• In Addition to Mechanical probe Lasers can be used in some CMMs to project
a beam onto the part surface, using triangulation calculations to measure the
beam spot’s coordinate positions.
 CONTACT PROBE
• The contact probe indicates when contact has been made with the part
surface during measurement. The tip of the probe is usually a ruby ball.

• Ruby is a form of corundum (aluminum oxide), whose desirable properties in

this application include high hardness for wear resistance and low density for
minimum inertia.

• Probes can have either a single tip, as in Figure 22.4(a), or multiple tips as in
Figure 22.4(b).
 TOUCH-TRIGGER PROBES
• It actuate when the probe makes contact with the part surface.

• Various triggering mechanisms for touch-trigger probes are as following:-

(1) A highly sensitive electrical contact switch that emits a signal when the tip
of the probe is deflected from its neutral position.

(2) A contact switch that permits actuation only when electrical contact is
established between the probe and the (metallic) part surface

(3) A piezoelectric sensor that generates a signal based on tension or

compression loading of the probe.
 Mechanical Structure.
• There are various physical configurations for achieving the motion of the
probe, each with advantages and disadvantages.
• Nearly all CMMs have a mechanical structure that fits into one of the
following six types. They are as follows:-
(a) Cantilever

(b) Moving bridge

(c) Fixed bridge

(d) Horizontal arm

(e) Gantry.

(f) Column.
 CMM Operation and Programming
• Positioning the probe relative to the part can be accomplished in several
ways, ranging from manual operation to direct computer control (DCC).

• Computer-controlled CMMs operate much like CNC machine tools, and these
machines must be programmed.

• This section covers

(1) Types of CMM controls

(2) Programming of computer-controlled CMMs.

 1. CMM Controls.
• The methods of operating and controlling a CMM can be classified into four
categories:

(1) Manual drive

(2) Manual drive with computer-assisted data processing

(3) Motor drive with computer-assisted data processing

(4) DCC with computer-assisted data processing.

 2. DCC Programming.
• There are two principle methods of programming a DCC measuring machine:

• (1) Manual lead through

• (2) Off-line programming. In the manual lead through method

(1) Manual lead through

• In this method operator leads the CMM probe through the various motions
required in the inspection sequence, indicating the points and surfaces that
are to be measured and recording these into the control memory.

• During regular operation, the CMM controller plays back the program to
execute the inspection procedure.
 (2) Off-line programming. In the manual lead through method

• Off-line programming is accomplished in the manner of CAD/CAM NC part

programming.

• The program is prepared off-line based on the part drawing or CAD part
model and then downloaded to the CMM controller for execution.

• Most off-line programming of CMMs is based on CAD geometric data

representing the part.

• Off-line programming on a CAD system is facilitated by the Dimensional

Measuring Interface Standard (DMIS), an ANSI standard.
 Dimensional Measuring Interface Standard
(DMIS)
DMIS is a protocol that permits two-way communication between CAD systems
and CMMs. Use of DMIS has the following advantages:

(1) It allows any CAD system to communicate with any CMM.

(2) It reduces software development costs for CMM and CAD companies
because only one translator is required to communicate with the DMIS.

(3) Users have greater choice among CMM suppliers.

(4) User training requirements are reduced.

 CMM software
• CMM software can be divided into the following categories:

(1) Core software other than DCC programming

(2) Post-inspection software

(3) Reverse engineering and application-specific software

• This core software is generally applied either before or during the inspection
procedure. Core programs normally include the following:

• Probe calibration

• Part coordinate system definition.

• Geometric feature construction.

• Tolerance analysis.
 Post-Inspection Software.
• Post-inspection software is the set of programs that are applied after the
inspection procedure.

• These software adds significant utility and value to the inspection function.

• Among the programs included in this group are the following:

1. Statistical analysis.

2. Graphical data representation.

 CMM Advantages and Benefits
• Advantages of using CMMs over manual inspection methods are the following:

1. Reduced inspection cycle time.

2. Flexibility.

3. Reduced operator errors.

4. Greater inherent accuracy and precision.

5. Avoidance of multiple setups.

 Coordinate measuring machines are most appropriate for
applications possessing the following characteristics:

1. When repetitive manual inspection operations need to perform.

2. The application involves post-process inspection.

3. Measurement of geometric features requires multiple contact points.

4. Complex part geometry.

5. A wide variety of parts must be inspected.

6. Repeat orders are common.

 Machine Vision
• Machine vision is a growing technology, with its principal applications in
automated inspection and robot guidance.

• It consists of following:

• Acquisition of image data.

• Followed by the processing.

• Interpretation of these data by computer for some industrial application.

• Vision inspection can be accomplished at much higher speeds than

inspection with CMMs
Classification of vision system
• Vision systems are classified as following:
a) 2-D vision
b) 3-D vision.
• Two-dimensional systems view the scene as a 2-D image. This is quite
adequate for most industrial applications, since many situations involve a 2-D
scene.
• Examples include dimensional measuring and gaging, verifying the
presence of components and checking for features on a flat (or semi flat)
surface.

• Three-dimensional systems are being used increasingly in the automotive

industry to inspect surface contours of parts such as body panels and
dashboards.
• Certain applications require 3-D vision, such as scanning the contour of a
surface, inspecting cutting tools to check for breakage and wear, and
checking solder paste deposits on surface mount circuit boards.
 Operation of a machine vision system
• The operation of a machine vision system can be divided into the following
three functions:

(1) Image acquisition and digitization

(2) Image processing and analysis

(3) Interpretation.

These functions and their relationships are illustrated schematically in Figure

22.9.
 1. Image acquisition and digitization

• It is performed by using a digital camera and a digitizing system to store the

image data for subsequent analysis.

• The camera is focused on the subject of interest, and an image is obtained by

dividing the viewing area into a matrix of discrete picture elements (called
pixels) in which each element has a value i.e. proportional to the light
intensity of that portion of the scene.

• The intensity value for each pixel is converted into its equivalent digital value
by an ADC (analog-to-digital converter).
• The operation of viewing a scene consisting of a simple object that contrasts
substantially with its background, and dividing the scene into a corresponding
matrix of picture elements is shown in figure 22.10.

(a) (b) (c)

Figure 22.10 Dividing the image into a matrix of picture elements, where each
element has a light intensity value corresponding to that portion of the image:
(a) the scene (b) 12 * 12 matrix superimposed on the scene (c) pixel intensity
values, either black or white, for the scene.
• The figure shows the similar image obtained from the simplest type of vision
system called a binary vision system.

• In which the light intensity of each pixel is ultimately reduced to either of two
values(Colour), white or black, depending on whether the light intensity
exceeds a given threshold level.
• Each set of digitized pixel values is referred to as a frame.

• Each frame is stored in a computer memory device called a frame buffer.

• The process of reading all the pixel values in a frame is performed with a
frequency of 30 times/sec.

• Very high-resolution cameras often operate at slower frequencies (e.g., 15

frames/sec).
 Cameras
• Digital cameras operate by focusing the image onto a 2-D array of very small,
finely spaced photosensitive elements using conventional optical lenses.

• The photosensitive elements form a matrix of pixels on the surface of the

solid-state image sensor (which is an integrated circuit chip), located behind
the lens system of the camera.

• Image sensors used in machine vision cameras are either of two types:

1. Charge coupled device (CCD)

2. Complementary metal-oxide semiconductor (CMOS).

• CMOS is an advanced technology in comparison to CCD. CMOS has various
advantages over CCD like:- higher speed, lower cost and less power
consumption.

• The resolution of the vision system means its ability to sense fine details and
features in the image.

• Resolution depends on the number of picture elements used it means that

The more pixels designed into the image sensors, the higher its resolution.
 Illumination

• Illumination is another important aspect of machine vision.

• The scene viewed by the vision camera must be well illuminated, and the
illumination must be constant over time.

• Illumination almost always requires that special lighting be installed for a

machine vision application rather than relying on ambient light in the facility.

• Five categories of lighting can be distinguished for machine vision

applications.
• Different lighting category are as follows:-

• (a) front lighting (b) back lighting (c) side lighting (d) structured lighting

(e) strobe lighting.

• These categories represent differences in the positions of the light source

relative to the camera as much as they represent differences in lighting
technologies which include incandescent lamps, fluorescent lamps, sodium
vapor lamps, and lasers.
Types of illumination in machine vision: (a) front lighting, (b) back lighting
(c) side lighting,
(d) Structured lighting using a planar sheet of light (e) Strobe lighting.
 Grayscale system
• It is more sophisticated vision system which is capable of distinguishing and
storing different shades of gray in the image.

• It can determine not only an object’s outline and area characteristics, but also
its surface characteristics such as texture and color.

• Grayscale vision systems typically use 4, 6, or 8 bits of memory.

• Eight bits corresponds to 28 = 256 intensity levels, which is generally more

levels than the machine vision camera can really distinguish and certainly more
than the human eye can discern.

• Colors in the scene can be distinguished using color filters (red, yellow, blue)
combined with a grayscale system for each pixel to determine color brightness.
 2. Image Processing and Analysis
• The second function in the operation of a machine vision system is image processing and
analysis.

• A number of techniques have been developed for analyzing the image data in a machine
vision system.

• One techniques in image processing and analysis, called segmentation, is intended to

define and separate regions of interest within the image.

• Segmentation techniques has been categorized in two ways

1. Thresholding

2. Edge detection

Additional technique feature extraction.

 Thresholding
• It involves the conversion of each pixel intensity level into a binary value,
representing either white or black.

• This is done by comparing the intensity value of each pixel with a defined
threshold value.

• If the pixel value is greater than the threshold, it is given the binary bit value
of white, say 1.

• If less than the defined threshold, then it is given the bit value of black, say 0.

• Reducing the image to binary form by means of thresholding usually

simplifies the subsequent problem of defining and identifying objects in the
image.
 Edge detection
• It is concerned with determining the location of boundaries between an
object and its surroundings in an image.

• This is accomplished by identifying the contrast in light intensity that exists

between adjacent pixels at the borders of the object.

• A number of software algorithms have been developed for following the

border around the object.
 Feature Extraction
• This methods is designed to determine these features based on the area and
boundaries of the object (using thresholding, edge detection, and other
segmentation techniques).

• Most machine vision systems characterize an object in the image by means of the
object’s features:

• Its Area, Length, Width, Diameter, Perimeter, Center Of Gravity, And Aspect Ratio.

• For example, the area of the object can be determined by counting the number of
pixels that make up the object and multiplying by the area represented by one pixel.
Its length can be found by measuring the distance (in terms of pixels) between the
two extreme opposite edges of the part.
 Interpretation
• The objective of this task is to identify the object in the image by comparing it
with predefined models or standard values. Two commonly used
interpretation techniques are following:

• Template matching

• Feature weighting.

• The interpretation function is usually concerned with recognizing the object,

a task called object recognition or pattern recognition.
 Template matching
• It refers to a method that attempt to compare one or more features of an
image with the corresponding features of a model or template stored in
computer memory.

• The most basic template matching technique is one in which the image is
compared, pixel by pixel, with a corresponding computer model. Within
certain statistical tolerances, the computer determines whether the image
matches the template.

• One of the technical difficulties with this method is aligning the part in the
same position and orientation in front of the camera, to allow the comparison
to be made without complications in image processing.
 Feature weighting

• Feature weighting is a technique in which several features (e.g., area, length,

and perimeter) are combined into a single measure by assigning a weight to
each feature according to its relative importance in identifying the object.

• The score of the object in the image is compared with the score of an ideal
object residing in computer memory to achieve proper identification.
 Machine Vision Applications

• Machine vision applications in manufacturing divide into three

categories:

(1) Inspection

(2) Identification

(3) Visual guidance and control.

 Inspection
• Machine vision installations in industry perform a variety of automated
inspection tasks, most of which are either on-line/in-process or on-line/post-
process.
• The applications are almost always in mass production where the time
required to program and set up the vision system can be spread over many
thousands of units.
• Typical industrial inspection tasks include the following:
1. Dimensional measurement.
2. Dimensional gaging.
3. Verification of the presence of components.
4. Verification of hole location and number of holes.
5. Detection of surface flaws and defects.
6. Detection of flaws in a printed label.
 Other Applications.
• Part identification applications use a vision system to recognize and perhaps distinguish
parts or other objects so that some action can be taken.

• The applications include following:-

1. Part sorting

2. Counting different types of parts flowing past along a conveyor,

3. Inventory monitoring.

• Part identification can usually be accomplished by 2-D vision systems.

• Reading of two-dimensional bar codes and character recognition represent additional

identification applications performed by 2-D vision systems.