Identifier: CX-CP-1.

13
Document Type: Corporate Procedure
Revision: 18

Title: Capability Study and Statistical Process Control

PURPOSE
Provide instructions and guideline to facilitate the application of statistical techniques
including Statistical Process Control and capability study in ChampionX Chemical
Technologies business units and manufacturing facilities.

SCOPE
This procedure applies to all ChampionX business Chemical Technologies units and
manufacturing facilities that use such statistical techniques.

RELATED DOCUMENTS
CX-CP-2.14 Analysis Plan Authorization Procedure
CX-CP-1.14 Gage R&R Procedure

ACRONYMS, ABBREVIATIONS AND DEFINITIONS

SPC – Statistical Process Control

SQC – Statistical Quality Control, often used exchangeable with SPC

TRASAR – A trade name for select treatment chemicals which use fluorescent tracer

Analytical Capability - ability of a site to produce analytical data within the documented precision
and accuracy of a given test method.

Analytical capability is independent of the product specification range. It is assumed that

the given test methods are appropriate to determine values in the range of the product.:

A. Range specification tests (e.g. percent solids, pH) – determined test value is within
plus or minus 3 standard deviations of the test method from the expected value. The
standard deviation of the test method is determined using the same sample used for
study.

B. Limit specification tests (e.g. Gardner color, turbidity) – determined test value is within
plus or minus 3 standard deviations of the test method from the average value. The
standard deviation of the test method is determined using the same sample used for
the study.

Analytical Limits

A. upper limit - expected or average value plus 3 times the standard deviation of the
test method.

____________________________________________________________________________
1
UNCONTROLLED COPY IF PRINTED
 Identifier: CX-CP-1.13
Document Type: Corporate Procedure
Revision: 18

Title: Capability Study and Statistical Process Control

B. lower limit - expected or average value minus 3 times the standard deviation of the
test method.

Average Value - value considered to be “true” for a limit specification test. Determined by taking
the average of all of the determined values submitted for the test.

Determined Value - value determined by a site for a particular test method.

Expected Value - value considered to be “true” for a range specification test. Determined by
Corporate Quality Chemist on the same sample as that used for the study using the documented
test method. Determined a minimum of nine times.

Limit Specification - specification with only one specified limit such as < 5 or > 90. Examples
might include Gardner color or turbidity.

Range Specification - specification with both upper and lower limits specified. Examples might
include % solids or pH.

ROLES AND RESPONSIBILITIES

The leadership team in each business unit or manufacturing facility is responsible for
identifying the needs for statistical techniques and provide such trainings to employees
when necessary.

PROCEDURE
Statistical techniques are recommended to be used at all ChampionX business units and
manufacturing locations. Such statistical techniques include Statistical Process Control (SPC) or
Statistical Quality Control (SQC) charts, evaluation of capability data for product analysis plans,
and evaluation of process and method potentials for commercialization of new products.

Each manufacturing facility is required to provide Statistical training as deemed appropriate by

plant management. It is recommended that Operators and laboratory analysts receive basic
Statistical training and Professionals receive advanced Statistical training.

DETAILED OPERATING PROCEDURES

A. SPC and SQC Charts

____________________________________________________________________________
2
UNCONTROLLED COPY IF PRINTED
 Identifier: CX-CP-1.13
Document Type: Corporate Procedure
Revision: 18

Title: Capability Study and Statistical Process Control

1.SPC and SQC charts should be constructed with a mean recorded and limits set at + 3
sigma. Sigma can be calculated using a software package such as NWA Quality Analyst,
scientific calculator, or equivalent.

2.Interpretation rules for these charts are documented in CX-CP-2.14 Analysis Plan
Authorization Procedure.

B. Analytical Capability Studies

1.The purpose of analytical capability studies is to assure a site is capable of analyzing a

critical parameter(s) for a particulate product.

2.Details on analytical capabilities are shown in Appendix I.

C. Product Analysis Plans

1.Product analysis plans are used to reduce our inspection of products where individual
parameters have been determined to be capable.

2.The submission, approval, and implementation of analysis plans are defined in CX-CP-
2.14 Analysis Plan Authorization Procedure.

D. Method and Process Potentials Requirements

1.Method and Process Potentials must be calculated and meet the established limits for all
new products.

2.Method potential is the percentage of the specification range that is occupied by the
method variation. The method potential is calculated from the following equation:

M.P. = 6 x STD.DEV x 100%/width of specification range.

For one sided specification (i.e. turbidity <10), a “manufactured” specification range using the
appropriate limit should be used in the above calculation. For example, if the specification range
is <10, the specification range used in the calculation should be 0-10. Likewise, if the specification
is >98%, the specification range used in the calculation should be 98-100. The above guidelines
should be followed, but the Chemist assigned to the project must make the final determination.

STD.DEV = Standard Deviation of the analytical test procedure used for the analysis.

____________________________________________________________________________
3
UNCONTROLLED COPY IF PRINTED
 Identifier: CX-CP-1.13
Document Type: Corporate Procedure
Revision: 18

Title: Capability Study and Statistical Process Control

Spec. range = difference between the upper and lower specification limits.

Mean = Arithmetic mean of the observed process values on the samples of interest.

3.Process potential is the percentage of the specification range that is occupied by the
process variation. The process potential is calculated from the following equation;

P.P. = 3 x (STD.DEV) x 100%/WSL

STD.DEV = Standard deviation of the observed data on lab or pilot plant samples.

Spec. range = difference between the upper and lower specification limits.

Mean = Arithmetic mean of the observed process values on the samples of interest.

WSL = value of the lower of either;

|Mean-upper spec limit|
|Mean-lower spec limit|

When a specification is a one-sided specification (i.e. < 100 ppm) then the WSL is calculated as

WSL = |Mean-Limit spec|

F. Process Capability Monitoring

1.One of ChampionX’s key goals is the development of capable processes.

2.The procedure for evaluation of product capability is shown in Appendix IV.

APPENDIX I

ANALYTICAL CAPABILITY STUDY

Analytical capability studies are conducted to determine the ability of a site to produce analytical
data within the documented precision and accuracy of a given test method.

Key steps in a study are as follows:

1.A sample, whose properties as measured by given test methods are known, is sent to each
participating laboratory. Specific instructions for the study are included with a memo, which is
sent with the sample.

____________________________________________________________________________
4
UNCONTROLLED COPY IF PRINTED
 Identifier: CX-CP-1.13
Document Type: Corporate Procedure
Revision: 18

Title: Capability Study and Statistical Process Control

2.Each laboratory analyzes the sample using the given test methods. Results are forwarded to the
Corporate Quality Chemist performing the evaluation.

3.The Corporate Quality chemist compares each site determined values with the analytical limits
specified for each test.

4.Analytical capability is determined based on the criteria defined for the particular study.

5.Laboratories not demonstrating analytical capability must conduct a self-appraisal to improve its
accuracy for a particular test.

APPENDIX II

PRODUCT CAPABILITY EVALUATION

1. Select product to be evaluated and generate SQC charts from NWA (North West
Analytical) scientific software package, or equivalent. Each specification listed on
the Material Specification Report must be evaluated.

2. For evaluation, initial final batch data (before any adjustments) must be used.

3. The statistical data is evaluated to assure:

a. All specifications are capable (cpk > 1.0).
b. The data is in statistical control.
c. At least 20 data points are available.

NOTE: Products can be combined as a family to generate the 20 data points

necessary to achieve capability. To qualify as a family, products must be
similar and use the same charging/manufacturing equipment. For example,
2 amine/water blend products that have different actives content or use a
different amine could be considered a family, provided the same equipment
is used.

4. Cpk = | WSL |
3

____________________________________________________________________________
5
UNCONTROLLED COPY IF PRINTED
 Identifier: CX-CP-1.13
Document Type: Corporate Procedure
Revision: 18

Title: Capability Study and Statistical Process Control

Where

WSL = value of the lower of either:

| mean - upper specification limit |
or
| mean - lower specification limit |

Where a specification is a one-sided specification, the WSL is calculated as:

| mean - limit specification |

5. If an out-of-control result is received for an existing or proposed capable product, the

product is usually removed from the capable product list. However, if the out-of-
control condition can be attributed to an assignable cause, and corrective action has
eliminated the cause, the product may still be considered capable.

6. This information is maintained in either hard copy format or an easily retrievable data
system.

REVISION HISTORY
Revision Date Revision Description Prepared By Approved
No By
01-15 Resides in the legacy system Rich Zwick
16 10/17/2019 New template and split old CP-1.13 into Xinjun Fan Jim Beaulieu
two separate procedures
17 02/05/2020 Update company name and logo Xinjun Fan Jim Beaulieu
18 01/26/2022 Update company logo Xinjun Fan Jim Beaulieu

____________________________________________________________________________
6
UNCONTROLLED COPY IF PRINTED