Third in a series exploring sample exam questions.
Test yourself with the third five questions from an ASQ sample exam. If you have other ways to sort out these questions, please comment and let us learn and compare approaches.
Questions 11-13 refer to the following information.
A reliability engineer needs to use an accelerated test plan to select a new material. The failure modes are known to be temperature-related.
11. Which of the following stress-related characteristics should be considered by the reliability engineer during the material selection stage?
(B) Flexural energy
(C) Tensile strength
(D) Compression strength
Answer
One way to plan for and analyze accelerated test data is with the use of an acceleration model. These typically describe the relationship between the stress level and time to failure.
B refers the bending energy and may have a temperature related parameter. Depending on the nature of the material and it uses this might be useful energy. We would need the relationship between temperature and the change in flexural energy to assist with creating an accelerated life test. Flexural energy alone is generally not sufficient.
C and D refer to the ability of a material in a specific shape (with the specific process of creation, i.e. extrusion vs molding, etc) to withstand a force attempting to pull (tensile) or crush (compression) the material. Again, depending on the nature of the material and it uses this might be useful information. We would need the relationship between temperature and the change in strength to assist with creating an accelerated life test. The strength values alone are generally not sufficient.
A is the correct answer. Activation energy is a term that along with the Arrhenius rate equation describes the change in material (generally a chemical process like corrosion or polymer chain scission). The formula has also been useful as an empirical description of temperature effects on behavior. The activation energy is the key parameter for this equation. If there is a known activation energy it may simplify the accelerated test plan with the use of the acceleration model.
Reference: Ireson, W. Grant, Clyde F. Coombs, Jr. and Richard Y. Moss, eds., Handbook of Reliability Engineering and Management, 2nd ed., New York: McGraw-Hill Professional, 1996, pp. 12.1-12.3. ISBN 0070127506
12. Which of the following test techniques would allow the reliability engineer to evaluate the material quickly?
(A) Ambient temperature test
(B) Step-stress test
(C) Full system test
(D) Durability test
Answer
The criterion is ‘quickly’ for the accelerated test plan described above.
A is not correct as using ambient conditions would not accelerate the temperature accelerated failure mechanism overuse conditions (assuming ambient refers to use conditions).
C may or may not be correct. We do not have enough information to determine if using the full system would allow quicker assessment or not. For material testing, using a coupon or sample of the material permits faster temperature changes and assessments (i.e. color change, tensile strength, etc.).
D may or may not be correct. Again need more information. If the feature of the material is its ability to be durable, then measuring something related to the material durableness would be appropriate. Like full system testing, durability testing does not address the specific test approach and does not imply it is quicker or not.
B is correct. Step-stress testing is an accelerated test method that increments the stress upward, in this case, temperature, to increase the rate of failure. It is a quicker than ambient temperature testing. Full system and durability could use step-stress testing as an approach. So, this is the best selection as it directly addresses the question.
Reference: Nelson, Wayne, Accelerated Testing, Statistical Models, Test Plans and Data Analyses, New York: John Wiley and Sons, Inc., 1990, pp. 18-19, 30-31. ISBN 0471522775
13. Which of the following approaches should be used for a field validation test of the new material?
(A) Implement the material change and monitor field performance.
(B) Field test a sample of only the new material in the system.
(C) Field test samples of both old and new material in the system.
(D) Run lab tests on two systems.
Answer
The idea of a field validation is to check if the new material works in use conditions. The term ‘should’ implies a best method or manner to conduct the experiment.
D is not correct as it uses a lab approach and not the requested field use approach.
A B and C are all methods for field validation and all could be correct. This is a problem of which is most correct. Depending on specifics which are not provided any could be perfectly correct making this judgment of which is best in general.
A is risky as a method of validation as it exposes customers or ends users of the product containing the new material to possible adverse or unwanted material behavior.
B is less risky as it limits the exposure to only a sample, the risk is in the selection of the field location and conditions. The experiment relies on being able to judge the new material’s performance given the field conditions.
C provides a means to compare the new and old material in field conditions lessening the risks to customers and to field condition variation. A comparison test is often the most efficient way to determine performance differences if any.
C is correct.
Reference: Ireson, W. Grant, Clyde F. Coombs, Jr. and Richard Y. Moss, eds., Handbook of Reliability Engineering and Management, 2nd ed., New York: McGraw-Hill Professional, 1996, pp. 12.1-12.2. ISBN 0070127506
14. Which of the following statements best describes the set of all values of a random variable?
(A) It is finite.
(B) It is an interval.
(C) It can be discrete or continuous.
(D) It can be tracked by using control charts or scatter plots.
Answer
A random variable definition is needed here. The key phrase is ‘best describe’ that implies more than one correct answer and we are looking for one that describes or defines.
According to Wikipedia (September 12th, 2013)
In probability and statistics, a random variable or stochastic variable is a variable whose value is subject to variations due to chance (i.e. randomness, in a mathematical sense).[1]:391 As opposed to other mathematical variables, a random variable conceptually does not have a single, fixed value (even if unknown); rather, it can take on a set of possible different values, each with an associated probability.
A may or may not be true. A random variable could be infinite and only limited by our ability to measure the value, say length.
B again may or may not be true. The random variable may or may not be defined as belonging to an interval.
D is true and does not describe a random variable vs any other type of variable which also could be tracked with various charts or plots.
C is true and names two types of random variables. While not the definition directly it appears to be the closest to actual describing random variable qualities. While continuous or discrete variables do not have to be random, these terms are often used to label a random variable.
C is correct.
References:
- Montgomery, Douglas C., Design & Analysis of Experiments, 6th ed., New York: John Wiley and Sons, 2004, p 25. and Juran, Joseph M., Juran’s Quality Handbook, 5th ed., New York, McGraw-Hill, 1999, pp. 46.43-46.47.
15. Which of the following is the best description of randomization?
(A) A technique used to increase the precision of an experiment
(B) A means of assuring representative sampling
(C) The repetition of an observation or measurement
(D) The relationship between two or more variables
Answer
Another definition, this time of randomization. This should trigger knowledge of basic statistical terms. The wording ‘best description’ implies there may be more than one correct response and we are looking for the most appropriate response. Be careful to not assume information that is not included with the question or based on your experience with a particular industry.
According to Wikipedia (September 12th, 2013) randomization is
Randomization is the process of making something random; this means:
- Generating a random permutation of a sequence (such as when shuffling cards).
- Selecting a random sample of a population (important in statistical sampling).
- Allocating experimental units via random assignment to a treatment or control condition.
- Generating random numbers: see Random number generation.
- Transforming a data stream (such as when using a scrambler in telecommunications).
Randomization is not haphazard. Instead, a random process is a sequence of random variables describing a process whose outcomes do not follow a deterministic pattern, but follow an evolution described by probability distributions. For example, a random sample of individuals from a population refers to a sample where every individual has a known probability of being sampled. This would be contrasted with nonprobability sampling where arbitrary individuals are selected.
A is not necessarily true, while it does help with precision, a better method to increase precision is to reduce measurement error or increase sample size. Randomization may help reduce sampling error.
C defines replicates in experimentation and while it may benefit from randomization the phrase defines a different term.
D define correlation, another statistical term definition and doesn’t really pertain to randomization directly.
B is correct as it restates one of the primary reasons for doing randomization when statistically sampling a population.
Reference: Montgomery, Douglas C., Design & Analysis of Experiments, 7th ed., New York: John Wiley and Sons, 2009, p 12.
Leave a Reply