The semiconductor industry is faced with great uncertainties in process technologies and demand. Capacity planning is a vital corporate task that has direct impact on profitability. There are at least two strategies of capacity: aggressive and conservative. The suitability of each strategy should depend on the lift cycle stages of individual corporations and the industry as a whole. In this paper, the capacity trajectory of a semiconductor manufacturing company is analyzed to construe the strategy and principle of capacity planning in the uncertain environment. In the first part, historical data of capacity cost, average selling price, direct expenses, and operating expenses are analyzed. The requirement of perpetual operations is discussed as a principle of capacity planning. In the second part, capacity strategies in various scenarios are analyzed by using experimental design and statistical methods. This paper presents a method for designing capacity strategies in industrial environment that is characterized by uncertain demand, intense price competition, and high investment cost.