7 QC Tools
7 QC Tools
7 QC Tools
Plan Do Check
:Setup the Objectives and Means :Put the Plan into Practice :Observe the Results and the Process
Act :Standardize if Results are Satisfactory otherwise Re-plan and Follow the Cycle again
DO improvement Improvement activities PLAN improvement Management strategy Focus on vital few
D P
C A
Initiate improvement
Standardization
ACT to improve the standard or its use Daily work CHECK the work against the standard
A C
S D
DO the work according to the standard
PLAN
DO CHECK
ACT
ACT
CHECK
DO
Implement Solution
Follow Up
Summary
QC story and the Basic Seven Step Problem Solving Process. Concept of PDCA and its adaptation to problem solving in specific work situations.
We have two methods of analyzing and eliminating trouble in the manufacturing shop. One is by technological analysis; the other is by statistical analysis. QC uses statistical methods to analyze and improve the quality of products.
Quality Improvement: Problem Solving Problem solving, the isolation and analysis of a problem and the development of a permanent solution, is an integral part of the quality-improvement process.
Not hit or miss, but objective and systematic Not directed at symptoms, but rather at root causes
Why Statistics
It is more economical to assess a sample of product and use the result to predict the properties of the whole lot. It leads to predictions with a high degree of precision.
Base Population Taking actions Judgment STUDY Information Sample Data
Population-Sample Model
Confederation of Indian Industry
Types of data:
Statistical data can be characterized as VARIABLE DATA and ATTRIBUTE DATA. 1.1 Variable / Continuous Data: Data which can be measurable and can assume any value over some interval. Examples: - Dimension of a part measured - Temperature in degree centigrade. - Weight in Kg. - Time
Confederation of Indian Industry
1.2 Attribute / Discrete Data: Data which can be measurable and can assume only certain distinct values (integer values). Examples: - Defect or not. - Days of the Week / Months of the year. - Performance ranking. - The no. of defective pieces found in a sample. - Cracks in sheets by spots welds etc.
Confederation of Indian Industry
10 10 - 8.4 = 1.6 8 8 8.4 = -0.4 8 8 8.4 = -0.4 7 7 8.4 = -1.4 averages 8.4 0.0
Variance
Standard Deviation
S=
Check-sheet Pareto Histogram Control Chart Cause and Effect diagram Scatter Plot Stratification
Confederation of Indian Industry
1. CHECKSHEET
For problem solving, data is to be captured. Check list is a tool to capture the parameter. Check-sheet is a tool to capture data as per check list.
CHECKSHEET
Shift wise
ShiftShift-A TypeType-1 ShiftShift-B ShiftShift-C ShiftShift-G
Defect Type
TypeType-3
TypeType-2
TypeType-4
CHECKSHEET
CHECKSHEET
Check Sheets: To take down data simply and prevent inspection omission
Make boxes for filling in the required items
Product name Process name Measuring method CS20-5D No. 3 assembly line 100% visual operation Date / day Defect Loose screws Dirt in distance sensor Exterior scratches Soldering defect Bonding defect Operating defect Gap defect Part lost Exterior dirt Total Number inspected 18 2037
Add totals
Fill in data
Total 33 12 18 5 10
IIII IIII
II
IIII
IIII IIII
II II
IIII I
III
IIII
II I
IIII
I
IIII I II III
I III
IIII
I I
5 3 3
2 16 91 4.5%
Make a scratch of the product to be inspected. Decide on items to be checked. Every time a defect occurs, fill in a mark of number a corresponding location.
2. PARETO CHART
Vilfredo Pareto (1848-1923), An Italian economist 20% of the population has 80% of the wealth Juran used the term vital few, trivial many. He noted that 20% of the quality problems caused 80% of the dollar loss. Pareto charts are extremely useful because they can be used to identify those factors that have the greatest cumulative effect on the system, and thus screen out the less significant factors in an analysis.
Confederation of Indian Industry
PARETO CHART
Pareto Diagram allows the user to focus attention on a few important factors in a process. They are created by plotting the cumulative frequencies of the relative frequency data (event count data), in descending order. When this is done, the most essential factors for the analysis are graphical presentation and in an orderly format.
Confederation of Indian Industry
PARETO CHART
70 Percent from each cause 60 50 40 30 20 10 0 (13) (10) (6) (64)
(3)
(2)
(2)
Example
S. No. 1 2 3 4 5
No. of Defects 26 11 21 16 6
Pareto Chart
30 25 Numbers 20 15 10 5 0 Weld Missing Ovality Fittment NG Dent 33 26 21 59 16 11 6 79 100 93 100 80 60 40 20 0 Percentages
Other
EXERCISE
S.No 1 2 3 4 5
Exercise
Pareto Analysis
1600 1400 1200 1000 800 600 400 200 0 Plating NG Scaling Grinding NG Unfilled Cavity Cracks 33.8 65.1 684 435 298 1372 1266 92.7 81.9 100 100.0 90.0 80.0 70.0 60.0 50.0 40.0 30.0 20.0 10.0 0.0
Percentage (%)
No of Defects
3. HISTOGRAM
A histogram is a graphical summary of variation in a set of data. Histogram is a visual tool for presenting variable data. It organises data to describe the process performance. The pictorial nature of the histogram enables us to see patterns that are difficult to see in a table of numbers.
Confederation of Indian Industry
While studying histogram look for its Location of mean of the process Spread of the process Shape of the process
Smallest Value, S= 47 Largest Value, L = 55 Range, R = L-S = 8 No. of cells= 1 + 3.22 log10(50) = 7 Calculated cell width (C.W.)= R / No. of cells=1.14 Rounded off Cell width= 1
Starting value, A= 47 LCB (Lower Class Boundary)= A-(C.W. / 2)= 47-1/2= 46.5 UCB (Upper Class Boundary)= LCB + C.W.= 46.5+1= 47.5
Plotting Histogram
Lower 46.5 47.5 48.5 49.5 50.5 51.5 52.5 53.5 54.5 Upper 47.5 48.5 49.5 50.5 51.5 52.5 53.5 54.5 55.5 Mid value 47 48 49 50 51 52 53 54 55 Tally Mark I III Tally Mark Freq 1 3 10 16 11 2 5 1 1
Histogram
40 35 30 25 20 15 10 5 0
1 2 6 13 10 16 19 17 12 16 20 17 13 5 6 2 1
Types of Histogram
General Type
Comb Type
Plateau Type
NORMAL CURVE
If the number of observations are increased considerably, then the no. of cells increases and the width of the cell become smaller and smaller. The series of steps that constitutes the top line of the histogram will then approach a smooth curve. Such a curve is called Frequency curve. The frequency curves may be of different shapes. The most important of these curve as far as SQC is concerned is the NORMAL CURVE. It is symmetrical about its mean value and has Bell shape.
Confederation of Indian Industry
5. CAUSE AND EFFECT DIAGRAM Show the relationships between a problem and its possible causes. Developed by Kaoru Ishikawa (1953) Also known as
Fishbone diagrams Ishikawa diagrams
Quality Problem
People
Equipment
Fishbone Diagram
Measurement
Faulty testing equipment Incorrect specifications Improper methods
Human
Machines
Out of adjustment Tooling problems Old / worn
Quality Problem
Defective from vendor Not to specifications Materialhandling problems Poor process design Ineffective quality management Deficiencies in product design
Environment
Materials
Process
Fishbone Diagram
Use of untested materials Mix-up of materials Substandard material accepted on concession because of nonavailability of correct material Inconsistency in specifications on the part of vendors
Typical causes for non conformance/ defects Method factors Inadequate process controls Non availability of proper test equipments Test equipment out of calibration Vague inspection/ testing instructions Inspectors do not possess the necessary skill
MEN
PAPER / BOTTOM PANEL FITMENT
VOIDS
POURING HOLE MISMATCH DAMAGED PE SHEETS.
MACHINE
MATERIAL
6. SCATTER PLOT
Scatter diagrams are graphical tools that attempt to show the influence that one variable has on another. A scatter diagram shows the relationship between independent variable (cause) and dependent variable (effect).
Y Typical Relationship
Length of bar
X Pull Speed
Confederation of Indian Industry
Typical Relationship
Stamina
Life (Age)
Confederation of Indian Industry
7. STRATIFICATION
It is the process of segregating or regrouping the data on the basis of certain characteristics ( e.g. machine wise, operator wise etc.) for identifying the influence factors (i.e. identifying contributory causes to the problems being handled) Data on Customer Complaints may be segregated by a) Nature of Complaints: defective products, Delayed delivery etc. b) Department Responsible: Production, Design, Quality etc.
Confederation of Indian Industry
Benefits of Stratification
Separate Data into groups. Draw meaningful and correct inferences from the data. Diagnose and Localize problems i.e. establish clear relationship between cause and effect. Identify the influencing factors, thereby making it easier to solve the problems.
Confederation of Indian Industry
10 A
25 B Suppliers
15 C
5 D
10
30
25
15
20
Shops
Control Chart
Fundamental tool of statistical process control. It indicates the stability of the process. It helps determine whether a process is in control or if a special cause exists to change the process mean or variance.
Control Chart
Purpose In all production processes, we need to monitor the extent to which our products meet specifications. In the most general terms, there are two "enemies" of product quality: deviations from target specifications, and excessive variability around target specifications.
Significance of Control Chart ? The quality of a product manufactured in a process is inevitably accompanied by dispersion. Various Causes of such dispersion exist and they can be classified into the following two types. 1. Chance / Random cause: Dispersion by chance is natural and unavoidable i.e. inevitably occurs in a process, even if the operation is carried out using standardized raw materials and methods. It is impossible to avoid the Random cause variation.
Control Chart
2. Assignable / Special cause: Dispersion from an assignable cause is unusual and meaningful in that it is avoidable and cannot be overlooked. Example: Neglecting various standards or application of improper standards. In order to control a process it is necessary to eliminate assignable causes and take action to prevent their recurrence, while tolerating dispersion by chance / random cause.
A control chart was first used in 1924 by W.A. Shewhart, who belonged to the Bell Telephone Laboratories, with a view to classifying an abnormal process by distinguishing variations due to chance from those due to assignable causes.
Example of Control Chart Upper control Limit Central line Lower control Limit Control chart for controlled state
To make a control chart it is necessary to classify the process by type of raw materials, machine and line and further to classify these data into small groups such as time or shift. There are various types of control chart, according to the characteristic values or purpose. However, in any type of control chart the control limits are calculated by the formula : (average value) 3 x (standard deviation) Therefore such a chart is called a three sigma control chart.
The bounds of the control chart are marked by upper and lower control limits that are calculated by applying statistical formulas to data from the process. Data points that fall outside these bounds represent variations due to special causes, which can typically be found and eliminated. On the other hand, improvements in common cause variation require fundamental changes in the process.
Control Chart
24 21 UCL = 23.35
Number of defects
Sample number
Control Limits Upper Control Limit Target 3 x sd of means Lower Control Limit 1 2 3 4 5 6 7
Sample Number
Confederation of Indian Industry
Variables
X R Chart X s Chart
o o o o
Defect detection Cheaper to construct and maintain Cannot tell cause of defect Need large n (>100) A screening device to initiate variables control charting
Countable
n=1
Defects No
Defectives or Defects?
X-bar MR Chart
Constant n
Defectives
u Chart
Range, if n<10
Range or S.D
S.D, if n>10
Yes
Constant n
No
X-bar R Chart
np or p Chart
p Chart
Types of Charts
Variable control charts are : X bar R Chart Run Chart Attribute control Charts are : P Chart C chart U Chart
Types of Charts
Variable control charts are : X bar R Chart Run Chart
X bar R Chart
Shows both the mean value ( X ), and the range ( R ). The Xbar portion shows any changes in the mean value of the process, while the R portion shows any changes in the dispersion of the process. This chart is particularly useful in that it shows changes in mean value and dispersion of the process at the same time, making it a very effective method for checking abnormalities within the process
Confederation of Indian Industry
X bar R Chart
Formulas Used X bar Chart
Center Line = X
R Chart
Center Line = R
X bar R Chart
Example
PART NAME: SPACER FRAME CROSS MEMBER
SPECIFIC:
SNO. 1 2 3 4 5 Average X (x) Range 1 65.84 65.88 65.82 65.9 65.88
65.80.2
2 65.88 65.86 65.9 65.84 65.86 65.868 0.06 3 65.86 65.88 65.86 65.84 65.9 65.868 0.06 4 65.86 65.88 65.88 65.84 65.86 65.864 0.04 5 65.9 65.84 65.86 65.88 65.86 65.868 0.06 6 65.84 65.9 65.86 65.88 65.86 65.868 0.06 7 65.88 65.9 65.9 65.86 65.88 65.884 0.04 8 65.88 65.9 65.86 65.82 65.84 65.86 0.08 9 65.92 65.9 65.92 65.88 65.88 65.9 0.04 10 65.92 65.88 65.88 65.86 65.84 65.876 0.08
65.864 0.08
X bar R Chart
X = Average (Average X) = Average X =658.72/10 = 65.872 R = Average (Range) =0.6/10 = 0.06
X bar R Chart
For X bar Chart UCL = 65.872 + 0.590x0.06 = 65.907 X =65.872 LCL = 65.872 - 0.590x0.06 = 65.836 R Chart UCL = 0.06x2.110 = 0.1266
Center Line = R
Center Line = X
= 0.06
LCL = 0.06x0 = 0
Confederation of Indian Industry
Size of Sub-group
R Chart
n
2 3 4 5 6
A2
D3
-
D4
d2
X bar Chart
65.92 65.91 65.9 65.89 X bar 65.88 65.87 65.86 65.85 65.84 65.83 0 1 2 3 4 5 6 7 8 9 10
UCL = 65.905
X = 65.872
LCL = 65.836
R Chart
UCL = 0.126
R = 0.06
LCL = 0
X bar R Chart
Exercise
PART NAME: PIPE COMP. STRG. HEAD-KTEA
SPECIFIC:
SNO. 1 2 3 4 5 1 7.9 7.84 7.96 7.84 7.94
8+0 /-0.2
2 7.98 7.84 7.94 7.84 7.97 3 8 7.84 7.88 7.94 7.94 4 8.1 7.94 7.82 7.97 7.94 5 7.85 7.97 7.88 7.94 7.98 6 7.84 7.94 8.1 7.84 8.1 7 7.91 7.94 7.85 7.91 7.85 8 7.98 7.98 7.84 7.98 7.84 9 7.85 7.84 7.91 7.85 7.91 10 7.84 7.94 7.98 7.84 7.98
Attribute Charts:
Fraction Defective No. of Defects in a fixed sized Product No. of Defects in a varying sized product
p Chart
Control charts dealing with the proportion or fraction of defective product are called p chart (for proportion).
p Chart
Formulas Used
p Chart
Example
S.No. 1 2 3 4 5 6 7 8 9 Date 1st Jan 07 2nd Jan 07 3rd Jan 07 4th Jan 07 5th Jan 07 6th Jan 07 8th Jan 07 9th Jan 07 10th Jan 07 Total Quantity Produced 990 1000 1110 980 1000 1100 910 1080 985 Defective Qty. 87 93 189 126 109 102 145 90 81
p Chart
Step 1: Calculate Fraction Defective
S.No 1 2 3 4 5 6 7 8 9 Date 1st Jan 07 2nd Jan 07 3rd Jan 07 4th Jan 07 5th Jan 07 6th Jan 07 8th Jan 07 9th Jan 07 10th Jan 07 Total Total Quantity Produced 990 1000 1110 980 1000 1100 910 1080 985 9155 Defective Qty. 87 93 189 126 109 102 145 90 81 1022 Fraction Defective 87/990 =0.088 93/1000 =0.093 189/1110 =0.170 126/980 =0.129 109/1000 =0.109 102/1100 =0.093 145/910 =0.159 90/1080 =0.083 81/985 =0.82 1.006
p Chart
Step 2: Calculate UCL & LCL
p Chart
Step 3: Draw Chart
0.450 0.400 Fraction Defective 0.350 0.300 0.250 0.200 0.150 0.100 0.050 0.000
UCL = 0.422
P = 0.112 LCL = 0
c Chart
C Chart is used where each item inspected may have several nonconformities and each nonconformity is counted, and sample size is constant.
c Chart
Formulas Used Center line c = c /n UCL = c + 3 * LCL = c - 3 * c c
c Chart
Example
Lot Number 1 2 3 4 5 6 7 8 9 10 Number of pinholes 8 9 5 8 5 9 9 11 8 7 Lot Number 11 12 13 14 15 16 17 18 19 20 Total Number of pinholes 6 4 7 6 14 6 4 11 7 8 152
c Chart
Step 1: Calculate UCL & LCL Center line c = c /n UCL = c + 3 * LCL = c - 3 * c c c = 152/20 = 7.6 UCL = 7.6 + 3 * 7.6 = 15.85
c Chart
Step 2: Draw Chart
18 16 No. of Pinholes 14 12 10 8 6 4 2 0 0 1 2 3 4 5 6 7 8
UCL = 15.85
c = 7.6
9 10 11 12 13 14 15 16 17 18 19 20
LCL = 0
u Chart
A u-chart is an attributes control chart used with data collected in subgroups of varying sizes
u Chart
Formulas Used Center line u = u /n UCL = u + 3 * LCL = u - 3 * u /N u /N
Where u is the number of nonconformities in each sample n is the number of items in the sample N is the average sample size
u Chart
Example
S. No. 1 2 3 4 5 6 7 8 9 10 Total No. of parts Inspected 200 80 100 300 120 90 250 50 100 70 1360 Number of Nonconformities 5 7 3 15 4 6 10 1 6 2 59
Step 1: Calculate u
S. No. 1 2 3 4 5 6 7 8 9 10 Total
u Chart
Number of Nonconformities (B) 5 7 3 15 4 6 10 1 6 2 59 U = B/A 0.025 0.088 0.030 0.050 0.033 0.067 0.040 0.020 0.060 0.029
No. of parts Inspected (A) 200 80 100 300 120 90 250 50 100 70 1360
u Chart
Step 2: Calculate UCL & LCL N = 1360 / 10 = 136 Center line u = u /n UCL = u + 3 * LCL = u - 3 * u = 59/1360 = 0.043
u Chart
Step 3: Draw Chart
0.12 0.1 0.08 0.06 0.04 0.02 0 0 1 2 3 4 5 6 7 8 9 10 u
UCL = 0.097
u = 0.043
LCL = 0
Thank You!