Based on the characteristics that the tunnel pressure wave has a fixed-morphologic form when the same train passes through the same tunnel, an applicational approach based on the iterative learning control (ILC) is developed, aiming at overcoming the drawbacks of the traditional strategy for controlling the air pressure variation inside a high-speed train carriage. To achieve the goal, the control system is mathematically modelled. Then, the problem is formulated. The task of suppressing the influence of the tunnel pressure wave on the air pressure inside the carriages is shifted as an ILC problem of tracking the comfort index with varying trial length. The algorithm of refreshing the control signal from trial to trial is determined and the process of ILC control is designed. Next, the convergence of the newly-developed applicational ILC algorithm is discussed and the algorithm is simulated by the simulation signal and field-test signal. Results show that the applicational ILC algorithm be more adaptable in handling the control of the air pressure inside carriage under the excitation of varying-amplitude, varying-scale and varying-initial-states tunnel pressure wave. Meanwhile, the matching with tunnel pressure wave makes the applicational ILC algorithm will take both the riding comfort and fresh air into consideration, which upgrades the performances when the high-speed train passing through long tunnels.

针对同一列列车通过同一隧道时隧道压力波具有固定形态的特点，提出了一种基于迭代学习控制（ILC）的应用方法，旨在克服传统策略的弊端。控制高速列车车厢内的气压变化。为实现该目标，对控制系统进行数学建模。那么，问题就形成了。抑制隧道压力波对车厢内气压影响的任务被转移为跟踪不同试验长度的舒适指数的ILC问题。确定了每次试验刷新控制信号的算法，设计了ILC控制过程。下一个，讨论了新开发的应用ILC算法的收敛性，并通过仿真信号和现场测试信号对算法进行了仿真。结果表明，应用ILC算法更能适应变幅、变尺度、变初始状态隧道压力波激励下的车厢内气压控制。同时，与隧道压力波的匹配使得应用ILC算法会兼顾乘坐舒适性和新鲜空气，提升高速列车通过长隧道时的性能。结果表明，应用ILC算法更能适应变幅、变尺度、变初始状态隧道压力波激励下的车厢内气压控制。同时，与隧道压力波的匹配使得应用ILC算法会兼顾乘坐舒适性和新鲜空气，提升高速列车通过长隧道时的性能。结果表明，应用ILC算法更能适应变幅、变尺度、变初始状态隧道压力波激励下的车厢内气压控制。同时，与隧道压力波的匹配使得应用ILC算法会兼顾乘坐舒适性和新鲜空气，提升高速列车通过长隧道时的性能。