Measure, Analyze, Improve, and Control is the four phases outlined by Six Sigma (MAIC). The MAIC improvement phases are taught to students working toward a black belt. Process optimization utilizing MAIC typically requires multiple iterations of variable modification. According to Arcidiacono and Pieroni (2018), each iteration removes a potential source of poor process control and output during chemical engineering. The repeatability of a process can be evaluated using one of several software analysis tools. While their implementation might facilitate data analysis, they are optional for continuous improvement. Since these studies and computations require many quality assurance techniques, the process is time-consuming. In this study, we explore how to optimize methanol production by identifying the ranges of operability for each variable and developing a planned experiment to determine the optimum set of operating parameters.
Quality-by-control guidance, which has been shown to facilitate the implementation of continuous operation, makes it easier to identify the quality attributes, process parameters, and control strategies required to keep the process operation and the quality of the product under Control. This makes the identification of the quality attributes, process parameters, and control strategies more accessible (Xu et al., 2019). A recent proposal included the development of a three-tiered control plan by using the best practices in chemical engineering, emphasizing active process control. Afterwards, chemists developed this quality control method, concentrating on bringing chemical engineering into the 21st century by shifting away from batch manufacturing and toward continuous processing rather than relying on traditional methods.
The Design of Experiments (DOE) is a technique developed by Six Sigma that is used to analyze the influence that modifying one or more process inputs has on the final product of a project. The sheer quantity of data may often make it challenging to discern critical connections between the variables of a process. However, DOE can help uncover these linkages and reveal the most crucial inputs that need to be modified for maximum process performance. This is something that has to be done in order to maximize the effectiveness of the process. Once it has been decided which aspects of the procedure are the most significant, the Design of Experiments technique may be used to demonstrate to the project teams how various permutations of those aspects will influence the final product.
Using an OFAT approach, the following is how the identical experiment that seeks the ideal temperature and timing to maximize yield looks:
- Let us begin with the temperature: In a temperature range from 50 to 120 degrees, determine which produces the best results. First, complete eight separate tests. The experiment’s temperature is raised by 10 degrees with each attempt (i.e., 50, 60, and 70… all the way to 120 degrees). For 1b, we will keep time constant at 20 hours.
- Find out how much fruit each batch produces by choosing the best timing for the second experiment, and try out a range of values (between 4 and 24 hours).
- Conduct a total of six experiments to determine the goal of optimal conditions. Each iteration (4, 8, 12… 24 hours) raises the temperature by 2 degrees Celsius.
- Using 90 degrees as a controlled variable.
- Track the yield of each batch. Third, after 14 tests, we found that 90 degrees Fahrenheit and 12 hours produced the highest yield (86.7%).
- OFAT is a more methodical strategy than winging it.
- There is, however, a significant issue with OFAT: what if the ideal conditions for temperature and time look more like this?
- By examining the data, we can develop a statistical model to assess the impacts of time and temperature alone and together.
References
Arcidiacono, G., & Pieroni, A. (2018). The revolution leans six sigma 4.0. International Journal on Advanced Science, Engineering and Information Technology, 8(1), 141-149.
Xu, H. J., Xing, Z. B., Wang, F. Q., & Cheng, Z. M. (2019). Review on heat conduction, heat convection, thermal radiation and phase change heat transfer of nanofluids in porous media: Fundamentals and applications. Chemical Engineering Science, 195, 462-483.