论文标题
动态学习和遗忘过程对医疗设备全方位服务的定价合同的优化建模的影响
The Effects of Dynamic Learning and the Forgetting Process on an Optimizing Modelling for Full-Service Repair Pricing Contracts for Medical Devices
论文作者
论文摘要
储层计算是预测湍流的有力工具，其简单的架构具有处理大型系统的计算效率。然而，其实现通常需要完整的状态向量测量和系统非线性知识。我们使用非线性投影函数将系统测量扩展到高维空间，然后将其输入到储层中以获得预测。我们展示了这种储层计算网络在时空混沌系统上的应用，该系统模拟了湍流的若干特征。我们表明，使用径向基函数作为非线性投影器，即使只有部分观测并且不知道控制方程，也能稳健地捕捉复杂的系统非线性。最后，我们表明，当测量稀疏、不完整且带有噪声，甚至控制方程变得不准确时，我们的网络仍然可以产生相当准确的预测，从而为实际湍流系统的无模型预测铺平了道路。
In order to improve the profitability and customer service management of original equipment manufacturers (OEMs) in a market where full-service (FS) and on-call service (OS) co-exist, this article extends the optimizing modelling for pricing FS repair contracts with the effects of dynamic learning and forgetting. Along with considering autonomous learning in maintenance practice, this study also analyses how induced learning and forgetting process in a workplace put impact on the pricing optimizing model of FS contracts in the portfolio of FS and OS. A numerical analysis based on real data from a medical industry proves that the enhanced FS pricing model discussed here has two main advantages: (1) It could prominently improve repair efficiency, and (2) It help OEMs gain better profits compared to the original FS model and the sole OS maintenance. Sensitivity analysis shows that if internal failure rate increases, the optimized FS price rises gradually until reaching the maximum value, and profitability to the OEM increases overall; if frequency of induced learning goes up, the optimal FS price rises after a short-term downward trend, with a stable profitability to the OEM.
