Praise Analysis and Simulation

Praise Analysis

The identification of improvement opportunities and implementation of quality improvement process of the TQM Process is through a six-step activity sequence, identified by the acronym ‘PRAISE’. Following are the steps involved in PRAISE Analysis:

Simulation

1. Simulation is a quantitative procedure which describes a process by developing a model of that process, followed by a series of controlled trial and error experiments to determine the process’s behavior over time. In real life, simulation technology is beneficial in the following ways:
2. It is impossible to create a mathematical model and solutions without certain fundamental assumptions.
3. It may be too expensive to really monitor a system.
4. It is possible that there will not be enough time to enable the system to work for an extended period.
5. The operation and monitoring of a genuine system may be too disturbing.
6. Steps in Simulation Process
7. Define the issue and system you want to emulate.
8. Develop the model you wish to employ.
9. Test the model and compare it to the behavior of the real issue environment.
10. Identify and gather data for testing the model.
11. Run the simulation.
12. Analyze the simulation findings and, if necessary, modify the solution you are assessing.
13. Rerun the simulation to test the new solution.
14. Validate the simulation to enhance the likelihood of correct conclusions.
15. Advantage: Simulation is easier for non-technical management to understand compared to sophisticated mathematical models. Simulation does not need the same level of simplification and assumption as analytical solutions do. A simulation model is simpler to convey to management staff since it describes the behavior of a system or process.
16. Instead of using the real operating system, simulation approaches enable you to experiment with a system model. Experimenting with the actual system itself may be expensive and, in many situations, disruptive. For example, if you are comparing two methods of delivering meal service in a hospital, the confusion that would arise from running two distinct systems long enough to get good observations may be too considerable. Similarly, running a huge computer mainframe on a variety of operating systems may be too costly.
17. Simulation enables users to study huge, complicated situations for which analytical findings are unavailable. For example, in an inventory issue, if the demand and lead time distributions for an item follow a standard distribution, such as the poison distribution, a mathematical or analytical solution may be discovered. However, if theoretically suitable distributions do not apply to the situation, an analytical study may be difficult. A simulation model is an effective solution for such difficulties.
18. Sometimes there isn’t enough time to enable the real system to run fully. For example, if we were looking at long-term patterns in global population, we couldn’t wait the necessary amount of years to observe results. Simulation helps managers to add time into their analyses. In a computer simulation of company operations, the management may condense the results of several years or periods into a few minutes of operating time.
19. Limitations:
20. The choice of random numbers is subjective.
21. A probability distribution based on previous data may not accurately predict the future.
22. The number of iterations required to attain a given outcome is subjective.
23. It gives estimates for important choices such as capital budgeting and stock levels.
24. It is a time-consuming and lengthy activity.
25. It creates a method of assessing solutions but not the solution itself.
26. All scenarios cannot be turned into simulation models.
27. Different iterations may offer different answers, leading to perplexity for the evaluator.
28. A Monte Carlo simulation:
29. Define the issue and choose a measure of its efficacy, such as inventory shortages per period.
30. Identify the factors that have a major impact on the measure of effectiveness, such as the number of units in inventory.
31. Determine the appropriate cumulative probability distribution of each chosen variable using the probability on the vertical axis and the variable values on the horizontal axis.
32. Obtain a collection of random numbers.
33. Consider each random number to be a decimal value of the cumulative probability distribution, which enters the cumulative distribution plot from the vertical axis. Project this point horizontally until it crosses the cumulative probability distribution curve. Then, project the point of intersection downward into the vertical axis.
34. Then, enter the value created into the formula obtained from the selected measure of effectiveness. Calculate and record the value. This number measures the efficacy of the simulated value. Repeat the processes above until the sample size is big enough to satisfy the decision maker.