Manual assembly is still widely used in industry, but the analysis of human work efficiency is difficult due to the high variability and unpredictability of human factors. Employee turnover and low qualifications of new employees are a major problem. However, after some time passes and a task is performed multiple times, the experience effect occurs, and employees begin to work more efficiently. This phenomenon is described as a learning curve, which represents the increase in operator skills over time, and translates into reduced assembly time, fewer errors, increased production efficiency, and lower costs. In order to analyze the assembly line start-up process, the learning curve of students during workshops was examined using an example of assembling a car model. Three different learning curve models were used; the curve parameters were estimated and then the production process was simulated. The highest average correlation coefficient R = 0.978 was observed for the exponential curve model. Simulation experiments have shown that the line start-up takes 2 h, and afterward the production process stabilizes.