Enhancement and Verification of Input Selection Methods for Predictive Modeling in Life Cycle Management

该研究项目的目标是开发高效的输入选择方法，用于预测**建模应用程序，作为工业合作伙伴(TECSIS Corporation)正在进行的项目的一部分，这些项目使用数据分析工具对燃气轮机(GT)发动机的健康监测进行**量化。TECSIS**提供产品开发和研发服务，并在**生命周期管理(LCM)系统开发方面拥有活跃的研究组合。展望未来，作为其持续的产品**改进的一部分，TECSIS需要一种高效的方法来自动选择对输出有重大影响的最主要的输入，如废气温度(EGT)和功率，这些都是燃气轮机健康监测的主要**指标。同样的方法也可以应用于预测建模**，使用有限的大量模拟数据集来减少计算时间和成本。滑铁卢大学的研究小组将与工业合作伙伴的**技术专家和工程师密切合作，利用先进的机器学习和**优化技术开发对输入选择方法的**改进。拟议的投入选择**方法的好处包括提高了预测精度、更快和更具成本效益的预测模型和更好的**解释，以及由于涉及的投入更少而节省了下一轮数据收集的成本。这些**方法对于在TECSIS工作的其他机械、电气和软件系统中开发预测建模、分类和集群**应用程序也具有重要意义。将**提议的对输入选择方法的改进纳入其预测建模和其他模式识别**工具，将有助于TECSIS扩大其应用领域。该项目的成功将使工业**合作伙伴能够创造新的收入来源，并接触到新的客户。

The goal of this research project is to develop efficient input selection methods intended for predictive**modeling applications as part of industrial partner's (TECSIS Corporation) ongoing projects that deal with the**quantification of the health monitoring of a gas turbine (GT) engine using data analytics tools. TECSIS**provides product development and research and development services, and has an active research portfolio in**Life Cycle Management (LCM) system development. Going forward as part of their continuous product**advancements, TECSIS needs an efficient methodology to automatically select the most dominant inputs that**have significant influence on the output like exhaust gas temperature (EGT) and power which are major**indicators for health monitoring of gas turbines. The same approach can also be applied to predictive modeling**with limited sets of large amount of simulated data to reduce the computational time and cost. The proposed**enhancements to input selection methods will be developed utilizing advanced machine learning and**optimization techniques by the research team from the University of Waterloo in close collaboration with the**technical experts and engineers from the industrial partner. The benefits of the proposed input selection**methods include improved prediction accuracy, faster and more cost-effective predictive models with better**interpretations, and cost savings on the next round of data collection due to fewer inputs involved. These**methods also have significant implications for developing predictive modeling, classification, and clustering**applications in other mechanical, electrical, and software systems that TECSIS works in. Incorporation of the**proposed enhancements to input selection methods into its predictive modeling and other pattern recognition**tools will help TECSIS to expand its applications areas. The success of this project will enable the industrial**partner to create new source of revenue generation and reach out to new clientele.