1.9.1 Model Sensitivity AnalysisSensitivity analysis is the study of how uncertainty in the output of a model or mathematical system (numerical or other) can be distributed between different sources of uncertainty in its inputs. A related practice is uncertainty analysis, which places more emphasis on the quantification of uncertainty and its propagation. Ideally, uncertainty and sensitivity analyzes should be performed in tandem. As the optimization method provides the best set of inputs for an optimal result, the input parameters are always different and a superlative situation may not be rewarded. Some input factors may have a moderate effect on output, while others have a dominant effect. Although this situation is not common in an ideal situation, it is highly recommended to check the most dominant input parameter that will impact the output. This will enhance the manufacturing company's understanding of the areas where control is required. To address this need, sensitivity analysis is performed using MS Frontline 12.5 solver for regression and dimensional analysis. 1.9.2 Univariate Analysis Univariate analysis is one of the methods of analyzing data on a single variable at a time. Univariate analysis explores each variable in the dataset, separately. So it is ultimately a post-optimality method for defining the most influential input parameters. It mainly calculates the dy/dx differential values ​​for all inputs. The value of one of the variables is increased by 1 and the change in the output is recorded. This provides a better idea of ​​the interaction between the process and the variable. In order to decrease production, the most dominant factor is incremented. Sensitivity is checked after each increment. The......middle of the article......is constructed by extending the logical basis of contemporary simulation models. Sometimes these 35 parameters may fail to explain the noise observed during the forecast. This simply means that some vital data must be included. The extraneous direction and the effect of some unknown variables may have an effect on the measurement, which must be part of chance. The most promising results are obtained using ANN simulation in the present investigation. The relationship between independent and dependent variables is well integrated by ANN but may not be inclusive for general understanding. The enigmatic nature of this sensitive affair is quiet and harsh. The remaining deterministic modeling methods are simple to understand. The accuracy of ANN compared to other deterministic modeling methods must be respected. The multifaceted structure of the ANN model is dominated by its accuracy..