NED UNIVERSITY OF ENGINEERING AND TECHNOLOGY

DEPARTMENT O INDUSTRIAL AND MANUFACTURING

COMPLEX ENGINEERING PROBLEM IM-213

COURSE: METROLOGY AND QUALITY CONTROL

COURSE CODE: IM-213
GROUP MEMBERS:
ELSA HASEEB (IM-312)
MIRZA MISBAH BAIG (IM-60)
MUHAMMAD UMER (IM-67)
AIMAN NAQVI (IM-311)

SUBMITTED TO: MISS RABIA SIDDIQUI

TABLE OF CONTENT:

Abstract ----------------------------------------------------------------- 03
Introduction ------------------------------------------------------------ 03
Literature Review ----------------------------------------------------- 03
Research Methodologies--------------------------------------------- 04
 Data stratification ------------------------------------------- 04
 Check Sheets ------------------------------------------------- 04
 Histogram ----------------------------------------------------- 05
 Pareto Chart -------------------------------------------------- 06
 Scatter Diagram ---------------------------------------------- 06
 Control Chart ------------------------------------------------- 08
 Cause & Effect Diagram ------------------------------------ 09
Conclusion -------------------------------------------------------------- 10
Recommendations ---------------------------------------------------- 10
References -------------------------------------------------------------- 10
ABSTRACT:
Quality is a dynamic aspect that involves products, services, people, processes, and the
environment to meet or exceed expectations. It is the main factor for consumers when choosing
products. For XYZ company, which produces zinc roofing, maintaining high quality and
productivity is essential to stay competitive. In 2019, XYZ company produced 824,574 units, out
of which 49,660 were defective, resulting in a 5.95% defect rate, exceeding the company's 2%
tolerance limit. The high number of defective products led to rework and losses, harming the
company. This study applies statistical quality control techniques to ensure the quality of roofing
and reduce defects. The analysis with a P control chart shows that while defect numbers are
within control limits, the Cp value of 0.9410 is low, indicating a need for product or process
improvements to continue enhancing quality.

INTRODUCTION:
In the current era of technological development, the industrial business is a key factor in the
growth of developing countries. The manufacturing sector, both domestic and international,
faces intense competition to meet consumer demand with precise specifications. Quality
control is a crucial strategy for companies to compete globally.
XYZ Company, which produces flat zinc and corrugated roofing, operates in the zinc sheet steel
industry. Roofing is a critical component in construction, and the rising demand for zinc
products has increased business competition among zinc producers. Therefore, stringent
product quality control is essential.
Production data from January to December 2019 revealed many products that did not meet
specifications. Randomly selected samples were inspected, and analysis identified poor
management of lubricants and wrenches from different vendors as the cause of defective
component connections.

LITERATURE REVIEW:
Statistical Quality Control (SQC) is a valuable tool for monitoring production quality; ensuring
products remain within control limits from the initial material quality through the production
process to the final product. SQC uses statistical methods to collect and analyze data,
maintaining production standards at minimal costs. Its advantage lies in its reliance on objective
data and facts rather than subjective opinions.
SQC encompasses seven major statistical tools, as outlined by Hazier and Render in their book
on Operations Management: Check Sheets, histograms, control charts, Pareto charts, fishbone
diagrams, scatter diagrams, and design of experiments (DOE). The concept of SQC was first
introduced by Shewhart in 1931 in his book on control charts. The primary functions of quality
control tools in SQC are to enhance process improvement capabilities.
RESEARCH METHODOLOGY:
In this study, we utilize statistical quality control (SQC) to analyze production quality in the
manufacturing industry, identify the causes of quality issues, and propose improvements. The
SQC method involves several statistical tools: check sheets, stratification, scatter diagrams,
Pareto diagrams, histograms, control charts, and cause-and-effect diagrams.

 Check sheets are practical tools for simply and easily collecting, grouping, and analyzing
data.
 Data stratification involves grouping data into categories with similar characteristics.
 Histograms are bar graphs that display data grouped into various classes with specific
intervals.
 Pareto diagrams sort types of defects from largest to smallest, then calculate the
percentage and cumulative percentage for each defect type.
 Scatter diagrams illustrate the correlation between a factor causing defects and the type
of product defects.
 Control charts graphically depict the stability of a process.
 Cause-and-effect diagrams help analyze and determine significant factors that influence
the quality characteristics of the output.

DATA STRATIFICATION:
Stratification involves grouping data based on similar characteristics. In this study, the data
collected is stratified according to defects in zinc products, which are categorized into four
types: Scratches, Wrong Milling, White Spots, and Black Spots.

CHECK SHEETS:
A check sheet is a straightforward document used for collecting data during the production
process. It records information on items, causes of defects, and serves as a real-time inspection
confirmation tool at the location where the data is generated. The check sheet data for zinc
products is available for review.
 Table. Check sheet data of defective roofing product

Defective Types Mount

(kp)Period Production Milling Black White
Percentage Scratch Percentage Percentage Percentage
Error Spot Spot
January 83.803 1.391 1,66% 2.405 2,87% 545 0,65% 578 0,69% 4.919
February 70.277 1.181 1,68% 1.722 2,45% 548 0,78% 632 0,90% 4.083
March 50.285 820 1,63% 1.192 2,37% 357 0,71% 498 0,99% 2.866
April 49.315 853 1,73% 1.287 2,61% 345 0,70% 424 0,86% 2.910
May 60.195 1.059 1,76% 1.625 2,70% 403 0,67% 590 0,98% 3.678
June 74.234 1.321 1,78% 1.967 2,65% 512 0,69% 483 0,65% 4.283
July 62.345 1.116 1,79% 1.590 2,55% 424 0,68% 530 0,85% 3.660
August 80.564 1.515 1,88% 2.038 2,53% 596 0,74% 596 0,74% 4.745
September 90.358 1.509 1,67% 2.485 2,75% 714 0,79% 705 0,78% 5.412
October 60.358 1.068 1,77% 1.533 2,54% 380 0,63% 531 0,88% 3.513
November 92.495 1.563 1,69% 2.525 2,73% 657 0,71% 888 0,96% 5.633
December 50.345 876 1,74% 1.173 2,33% 362 0,72% 554 1,10% 2.965
Total 824.574 14.272 1,73% 21.542 2,61% 5.844 8,47% 7.009 10,38% 48.668

Based on the table, the defects are ranked from most to least frequent as follows: scratches,
wrong milling, white spots, and black spots, with a total of 48,668 defective items.

HISTOGRAM:
Based on the histogram above, the highest proportion of defects is due to scratches, followed
by milling errors, white spots, and black spots.

PARETO CHART:

A Pareto diagram is used to determine the contribution of each type of defect in a company.
The process involves sorting each type of defect from the largest to the smallest number of
occurrences. Then, the percentage and cumulative percentage of each type of defect are
calculated.
From the Pareto diagram below, it is clear that the major causes of zinc product defects are
scratches (44.3%) and milling errors (29.3%). Together, these two types account for a cumulative
percentage of 73.6%. According to the Pareto 80/20 rule, where 80% of defects are caused by
20% of the defect types, focusing on controlling scratches and milling errors can address 80% of
the defects. This targeted approach is more efficient, saving time, costs, and resources
compared to trying to control all types of defects.

Scatter Diagrams:
The graphs show a linear relationship between production volume and the number of defects.
The calculated correlation values indicate a strong relationship between production volume and
both scratch defects (correlation value of 0.9861) and milling errors (correlation value of
0.9812). This significant relationship implies that as production increases, the number of defects
also tends to increase. Given this insight, corrective action is necessary to reduce defect levels
despite the high production rates.
CONTROL CHARTS:
The most common types of defects are scratches and milling faults. The next step involves
analyzing the number of zinc product defects using the P control chart to determine if the
defect rate is within acceptable limits.

 Total defects (Σnp) = 48,668 units

 Total inspections (Σn) = 824,574 units
 Total inspections for subgroup 1 (n1) = 883,803 units
 Total defects for subgroup 1 (np1) = 4,919 units
 Proportion of defects in subgroup 1 is P = 0.0587
 Upper Control Limit (UCL) value = 0.0615 and Lower Control Limit (LCL) value = 0.0566
This analysis helps assess whether the defect rate falls within acceptable bounds.

The analysis of the data suggests that the rate of disabilities in each group is acceptable (within
control limits). This allows us to calculate the process capability (Cp) for quality control in
manufacturing non-defective products. The resulting Cp value is:
Cp = 1 - p̅ = 1 - 0.0590 = 0.9410 = 94.10%.
CAUSE & EFFECT DIAGRAM:
Cause and Effect Diagram or called the cause and effect diagram is used to analyze and find
factors that have a significant effect in determining the quality characteristics of work output or
to find out the factors that cause a decrease in the quality of roofing products.

Cause-and-Effect Diagram
Material Personnel

Operator is not careful in setting

the wind blade nozzle
Poor quality of raw materials
Operators are too rough in
laying roofing that has been cut

Operators less in understanding

Raw materials from suppler the procedure
are bad
Less of supervision during the
production process

Scartch

lack of maintainance
Unstructed allocation of work
structions
age of engine is old
Cleaning of engine
components is less
Surface of equipment that has
scheduled
potential to cause scratches
Lack of supervision of the
production process Poor engine performance

Methods Machines

Cause-and-Effect Diagram
Material Personnel

Operators are not careful in

positioning roofing
Quality raw material is not Operators are too rough in
good laying roofing
Fatigue

Bad raw materials from Supervision is not routine in the

supplier production process
Operators in a hurry and careless

Milling

Less of understanding how to

operate the machine
Laying is done manually The inspection process is carried
out at the final process
Machine is too old

Complex grinding process Poor engine performance

procedure
Engine settings are not quite
right

Methods Machines
CONCLUSION:
Many manufacturers struggle with assignable causes, which can significantly reduce production
flexibility and output. As defects increase due to these issues, overall productivity suffers. By
identifying and eliminating assignable causes through root cause analysis, companies can
improve.
XYZ Company, for example, experiences scratch defects and rolling errors. To address scratches,
they could implement stricter daily supervision, pre-production briefings, and detailed machine
maintenance checklists. Additionally, scheduling regular maintenance outside of production
hours is recommended. For milling faults, installing a buffer to improve zinc positioning could be
beneficial.
Although current control charts show defect rates within acceptable limits, the following
recommendations are suggested to minimize future problems and production costs:

 Implement the proposed solutions to reduce scratches and milling errors.

 Develop a more systematic division of tasks, including dedicated inspection and
maintenance teams for machinery.

RECOMMENDATIONS:
 Minimize Defects and Costs: The company should prioritize implementing the suggested
solutions to significantly reduce both scratch defects and milling errors. This will
ultimately lead to lower production costs.
 Enhance Task Management: A more systematic approach to task allocation is necessary.
This means ensuring everyone focuses on their specific responsibilities. Crucially, this
includes forming dedicated teams for equipment inspection and maintenance.

REFERENCES:
Google Scholar
[1] Ishak A, Ginting R and Chandra V 2019 IOP Conference Series: Materials Science and
Engineering 505 012143
[2] Runtuwene, Vayska E, et al Quality Control Analysis Using Statistical Quality Control at PT
Massindo Sinar Pratama Manado Jurnal Riset Ekonomi, Manajemen, Bisnis Dan Akuntansi 5 (2)
pp 2516-2525
[3] Andri R et al 2020 Perbaikan Kualitas pada Produk Pembuatan Tas Backpack Menggunakan
Metode Statistical Quality Control (SQC) dan Failure Mode and Effect Analysis (FMEA) Prosiding
Teknik Industri 6 (1) pp 9-17
[4] Rakhmad A 2010 Penerapan Statistical Quality Control dalam Pengendalian Proses Produksi
Batik dengan Menggunakan Control Chart P
[5] Anggraini M et al Analisis Pengendalian Kualitas Pengolahan Produk Karet Remah Sir 20
Dengan Pendekatan Statistical Quality Control Jurnal Rekayasa, Teknologi, Dan Sains 3 (1) pp 21-
26
[6] Andriani D P et al Analisis Pengendalian Kualitas Mesh Size Distribution pada Kristal
Monosodium Glutamat (MSG) dengan Statistical Quality Control Prosiding SENIATI 2019 pp 198-
204
[7] Nuchpho P, Nansaarng S and Pongpullponsak A 2018 Modified Fuzzy FMEA Application in the
Reduction of Defective Poultry Product Eng. J. 23 (1) pp 171-190
[8] Ariyanto B and Y H Kusuma 2017 Analisis Pengendalian Kualitas Produksi Seng Lembaran
Jenis B2g 0,20 X 914 dengan Menggunakan Seven Tools pada PT. Kerismas Witicko Makmur
[9] De Andrade M. G et al 2017 Statistical Quality Control For The Evaluation Of The Uniformity
of Microsprinkler Irrigation With Photovoltaic Solar Energy Renewable and Sustainable Energy
Reviews 78 pp 743–753
[10] Haryanto I. 2020 Penerapan Metode SQC (Statistical Quality Control) Untuk Mengetahui
Kecacatan Produk Shuttlecock Pada Ud Ardiel Shuttlecock (Doctoral Dissertation; ITN Malang)
pp 186-191
[11] Hariyani I and Linda M R 2019 Penerapan Pengendalian Mutu Produksi Dengan Statistical
Quality Control (SQC) Dan Six Sigma Pada Liberty Shoes Kota Padang Jurnal Kajian Manajemen
dan Wirausaha 1 (2) pp 24-33
[12] Kulkarni S, Kulkarni C, Vimal K. E. K. and Jayakrishna K 2019 Statistical Quality Control of
Torque renches Used in Automotive Assembly Department Advances in Manufacturing
Technology pp 199-208
[13] Montgomery D C 2009 Introduction to Statistical Quality Control, Sixth Edition (USA: John
Wiley & Sons, Inc.)
[14] Tjiptono F 1995 Total Quality Management (TQM) (Yogyakarta: ANDI)
[15] Besterfield D H 1998 Quality Control Fifth Edition (Prentice Hall International Inc. New
Jersey: Simon & Schuster)
[16] Nastiti H 2014 Analisis Pengendalian Kualitas Produk Dengan Metode Statistical Quality
Control (Studi Kasus: pada PT “ X” Depok) Sustainable Competitive Advantage (SCA) pp 414-423
[17] Anggraini M 2019 Analisis Pengendalian Kualitas Pengolahan Produk Karet Remah Sir 20
Dengan Pendekatan Statistical Quality Control Jurnal Rekayasa, Teknologi, dan Sains 3( 1) pp 21-
26
[18] Rusdianto A S et al Application of Statistical Quality Control (SQC) on Robusta Coffee
Processing Unit with Semi Wet Proces Jurnal Agrotek 5 (2) pp 1-10
[19] Haming M and Nurnajamuddin M 2007 Manajemen Produksi Modern Operasi Manufaktur
dan Jasa (Jakarta: Bumi Aksara)
[20] Heizer J and Render B 2006 Operations Management, 7th (Jakarta: Salemba Empat)
[21] Indrayanto G 2018 Recent development of quality control methods for herbal derived drug
preparations Natural Product Communications 13 (12)