Page 129 - Solid Waste Analysis and Minimization a Systems Approach

IMPROVE 107

The failure mode and effect analysis is used to show the potential failures reducing
the critical failures of the process (Gupta et al., 2007). Usually when creating a failure
mode and effect analysis each potential failure is ranked from 1 to 10 in relation to the
damage the failure could cause. Then solutions are thought of to prevent each failure,
putting priority on the highest ranked failure.

6.5 Improve

The improvement phase is designed to identify actions remedying the root cause of the
waste or inefficiency of a process (Gupta et al., 2007). The following tools can be
implemented to solve a problem:

■ Systems thinking
■ Testing of hypothesis
■ Comparative experiments
■ Design of experiments

Systems thinking involves making a decision based on data and facts. Often deci-
sions are based on thoughts and studies are not done to find the true causes of prob-
lems. Systems thinking is conducting tests and using tool to find these problems, and
fix the problems based on these facts.
A statistical hypothesis is an assertion or conjecture concerning one or more popu-
lations. Testing of a hypothesis is an inferential technique used to make a statement
about an activity or process based on its output (Gupta et al., 2007). One can either fail
to reject a hypothesis or reject it. Fail to reject implies that the data does not give suf-
ficient evidence; on the other hand rejection implies the sample evidence refutes the
hypothesis. Rejecting the hypothesis means when the hypothesis is true there is a
small probability of that sample occurring again. There are always two hypotheses the
null and the alternative. The test is against the null; if the test is rejected then the alter-
native is accepted.
Comparative experiments is measuring a control group then conducting an experi-
ment and seeing if there is a difference in results (Gupta et al., 2007).
The design of experiments relates to comparative experiments. It is a nonbiased way
of creating an experiment while getting the wanted answers to the problem. The three
goals of an experiment are

1 The experimenter should clearly set forth his/her objectives before proceeding with
the experiment.
2 The experiment should be described in detail. The treatments should be clearly
defined.
3 An outline of the analysis should be drawn up before the experiment is started
(Graham, 1993).