公交系统因运行时间不稳定、到达时间难以被准确预估而使得出行者满意度较低。随着城市的多元化发展，公交线路也逐步多样化，不同类型线路公交车的运行时间波动差异大，造成公交车调度运营困难、乘客出行不便。针对上述问题，文中首先以簇内误差平方和（SSE）为衡量指标，采用K-means++算法对站点进行聚类，将不同类型公交线路的运行特性和可靠性影响因素作为考虑因素，确定各线路大站快车备选站点集；然后以最小化公交车辆运行成本、乘客出行成本和可靠性成本为目标，考虑全程车和大站快车的运行过程、车头时距等约束，构建大站快车与调速联合策略优化模型，以决策不同类型公交线路大站快车站点、全程车与大站快车的发车时刻和车辆路段运行速度；最后采用遗传算法对优化模型进行求解，选取北京市公交线路进行案例分析。结果表明：大站快车策略有利于降低公交车辆的运行成本，调速策略能更好地降低乘客出行成本和可靠性成本，而大站快车和调速联合优化策略可有效地降低公交系统的总成本。

The unstable running time and the difficulty to accurately estimate the arrival time reduce passengers’ satisfaction with bus traveling. With the diversification of cities, bus line types are gradually becoming more diverse, and the variations in bus operating time of the various bus line types cause trouble in bus scheduling and inconvenience for passengers. To solve above problems, firstly, this paper used K-means ++ algorithm to cluster the stations with the sum of squares of error (SSE) as the measurement index. The operation characteristics and reliability influencing factors of different types of bus lines were taken into consideration to determine the alternative station sets of limited-stop bus service. Then, a joint optimization strategy model of limited-stop bus service and speed regulation was proposed to determine the limited-stop bus station, the departure time, and the running speed of all buses. This model took the minimization of bus operation cost, passenger travel cost, and reliability cost as the objectives, and took the constraints of operation process and headway of limited-stop bus service and all-stop bus service into consideration. Finally, genetic algorithm was used to solve the optimization model and Beijing bus system was selected for case analysis. The results show that the limited-stop bus service can reduce the operation cost of public transport, the speed regulation strategy can better lower the passenger travel cost and reliability cost, and the joint optimization strategy of limited-stop bus service and speed regulation can effectively reduce the total cost of the bus system.