Optimizing inventory management in the automotive industry: A comparative study of crisp and fuzzy systems

<ns3:p>Background Inventory management is essential to ensure cost efficiency and operational continuity in the automotive sector. Traditional (crisp) inventory systems assume fixed values for the input parameters, which may not reflect real-world variability. This study compares the performance of crisp and fuzzy inventory models in managing uncertainty in demand and costs, using Tesla as a case context. Methods Inventory models were developed under crisp and fuzzy frameworks, incorporating a quadratic time-dependent demand function, holding costs, deterioration, production, and setup costs. In the fuzzy model, the key parameters were represented using trapezoidal fuzzy numbers, and the centroid method was applied for defuzzification. Mathematica 14.0, was used to compute the optimal cycle time and total cost for both systems. A sensitivity analysis was conducted to assess the impact of variations in each parameter. Results The fuzzy inventory model produced a lower total cost ($57.06) compared to the crisp model ($143.33), reflecting an 86.11% reduction. The fuzzy system also demonstrated improved robustness to changes in production rate, setup cost, and deterioration rate. Both models produced similar economic order quantities, but were more economical and flexible to parameter variations. Sensitivity analysis proved that the system was more sensitive to minor changes in input values for the crisp model, raising the overall cost higher than that of the fuzzy model. Conclusions Fuzzy inventory systems can address demand uncertainty and cost variability in the automotive industry. It can be noted that applying inventory planning within fuzzy logic can save costs and aid in reacting better to fluctuations in the market. Such applications can be applied to companies considering the high demand and production variability. Subsequent studies can further develop multi-item models and combine stochastic lead times or dynamic prices.</ns3:p>