Welcome to TCLR Documentation
—— Tree-Classifier for Linear Regression
Tree-Classifier for Linear Regression (TCLR) is a novel Machine learning model to capture the functional relationships between features and a target based on correlation. GitHub Location : GitHub.
线性回归树分类器, GitHub 开源地址 : GitHub.
The latest version : 
By incorporating the TCLR into a thermodynamic kinetic framework, it becomes possible to accurately predict the rates of chemical reactions as a function of temperature, pressure, and other system variables. This can be useful in a variety of fields, including materials science, chemical engineering, and biochemistry, where accurate modeling of reaction rates is essential for the design and optimization of chemical processes.
Content / 内容
TCLR employs a data-driven approach to derive a mathematical relationship between the research variables and physical variables, including time index, that adhere to the principles of dynamics and thermodynamics. The resulting display formula facilitates the modeling and analysis of physical processes such as corrosion and creep, and enables the design of high-performance alloys with desirable properties, such as superior corrosion resistance. The optimization of the activation energy and time index via the derived formula can further enhance the efficiency and effectiveness of the design process
TCLR 算法通过提供的数据集得到研究变量和时间指数等物理变量之间的显示公式，适用于腐蚀、蠕变等满足动力学或者热力学的物理过程。通过最大化激活能和最小化时间指数可以高效地设计具有高耐腐蚀等优异性能的合金。
In previous research, the TCLR has been employed to effectively capture the interdependence between latent variables. Utilizing TCLR, the activation energy Q in the Arrhenius equation: exp(-Q/RT), has been modelled in function with alloy composition, material testing conditions, material processing technology, and other pertinent factors. Similarly, the time exponent n in the kinetic equation: k*t^n has been mathematically represented as a function of alloy composition, material testing conditions, material processing technology, and other relevant variables. For further details, please refer to the relevant section in the chapter titled "Applications".
在相关研究中，TCLR被用来捕捉隐藏变量之间的关系。通过TCLR可以将Arrhenius equation : exp(-Q/RT) 中的激活能Q和合金成分、材料测试条件、材料加工工艺等因素建立公式化的联系。将动力学方程 :k*t^n中时间指数n建模为合金成分、材料测试条件、材料加工工艺等因素的公式表达。见章节: "Applications"。
Installing / 安装
pip install TCLR- install package.
Updating / 更新
pip install --upgrade TCLR- update project.
graphviz (recommended installation) package is needed for generating the graphical results, which can be downloaded from the official website http://www.graphviz.org/.
graphviz (推荐安装)用于生成TCLR的图形化结果, 下载地址: http://www.graphviz.org/.
Cite / 引用
- Cao B, Yang S, Sun A, Dong Z, Zhang TY. Domain knowledge-guided interpretive machine learning: formula discovery for the oxidation behavior of ferritic-martensitic steels in supercritical water. J Mater Inf 2022;2:4. http://dx.doi.org/10.20517/jmi.2022.04
Papers related / 相关研究
Google Scholar : Google Scholar
Contributing / 共建
Contribution and suggestions are always welcome. In addition, we are also looking for research collaborations. You can submit issues for suggestions, questions, bugs, and feature requests, or submit pull requests to contribute directly. You can also contact the authors for research collaboration.