The focus of this thesis is on evaluating two different algorithms to provide the field engineers of the cement industry to achieve high-quality cement with the minimal production cost. This thesis also helps in increasing the efficiency of the cement plant by reducing energy consumption, which in turn helps reduce the impact on the environment. To help understand and present better, this thesis is mainly focused on the Portland cement industry. However, algorithms presented can be easily modifiable and applicable in similar industries such as industrial waste management systems, coal industries, etc. The raw materials for cement production are a mixture of oxides mainly comprising of silicon, calcium, aluminum, ferric and magnesium oxide. The concept is to optimize the blending process of these mixtures to achieve homogeneity. The optimization process considers the process constraints such as quality control parameters, feed rates, and their bounds. This optimization process can be formulated as constrained nonlinear programming problem. Optimization algorithms implemented are (i) deterministic approach – sequential quadratic programming and (ii) stochastic approach - genetic algorithm. The optimization toolbox of MATLAB is used to implement the algorithms. Percentages of oxides are varied by simulating a sine wave. For each time period algorithms are executed, and results are plotted. The algorithms are run to an optimum solution where constraint tolerance is less than function evaluation. The genetic algorithm is much slower because of its high number of function evaluations.