With the rapid growth of global urbanization and the rising demand for sustainable development, it is essential to study the performance a

nd durability of building materials. As a traditional and widely employed building material, play a significant role in traditional Chinese architecture. However, traditional methods for assessing structural surface damage necessitate the time-consuming and labor-intensive assessment

and judgment of trained professionals. Consequently, it is crucial to employ machine learning techniques for automatic damage type identification. This study identifies the types of damage to Chinese clay tiles in Macau by employing machine learning techniques and

the YOLOv4 object detection model. A total of 363 photographs of on-site Chinese clay tiles were used as training samples, and 200 epochs of the model training were performed. The primary findings of this study are as follows: (1) The machine learning method, based on the YOLOv4 model, provides an effective and precise solution for the automatic identification of Chinese clay tiles damage types

, overcoming the human and time-cost constraints of conventional evaluation methods.

(2) The detection accuracy of the detection model in this study is 95.42% for the detection of Chinese clay tiles cracks, 80.91% for the detection of stains, and 89.34% for the detecti

on of surface wear, with an overall accuracy of 88.98%, which meets the basic detection requirements. (3) The experimental results demonstrate the viability and efficacy

of the proposed method for identifying clay tile damage types and provide a method reference for the preservation and sustainable development of historical buildings.

Automatic Detection and Recognition Method of Chinese Clay Tiles Based on YOLOv4: A Case Study in Macau

• 这篇文章的内容是关于怎样运用机器学习技能和 YOLOv4 政策检测模型，主动辨认 澳门世遗建筑 的大阶砖铺装的危害类型，以便于对前史建筑进行维护和可继续发展。文章运用了 363 张现场的大阶砖相片作为操练样本，操练了一个检测模型，该模型能够准确地检测出大阶砖的裂缝、污渍和表面磨损等危害类型。文章的试验效果表明，该方法比传统的人工点评方法更有用和准确，且节省了人力和时间本钱。文章为中国瓦片的功用和耐久性研讨供应了一种新的方法，并为前史建筑的维护和可继续发展供应了一种技能支撑。

Problem Statement

研讨问题

由于大阶砖在出产进程中需要运用大量粘土，天然形成的粘土的产量正在减少，这将导致未来的出产本钱更高。由于工艺难度较高，所以现在产量相对较低，娴熟的修正专家也越来越少。本文提出运用机器学习中的 YOLOv4 模型主动检测前史建筑的开裂、污渍、磨损等危害，以进步对建筑危害的辨认和后续修正本钱的预算。在本文中，研讨人员查询了五个问题：

（1）在搜集现场勘测和拍摄数据的进程中，能够差异多少种不同类型的大阶砖损坏？
（2）YOLOv4 怎样为有助于检测大阶砖各种损坏的核心技能的开发做出贡献？
（3）操练 YOLOv4 模型的效果怎样？与人工辨认比较，主动检测的准确度怎样？
（4）大阶砖的图像辨认和危害分析效果怎样？
（5）怎样将日常检查与维护结合起来，完成建筑的可继续运用？

Sample processing and YOLOv4 model design

模型操练与检验

(4) YOLOv4 模型操练。在这个阶段，研讨团队运用了 YOLOv4 政策检测模型对处理和标明好的样本进行操练。本研讨挑选了 YOLOv4 模型是由于它在政策检测范畴具有较高的功用和准确率。模型操练是一个迭代的进程，研讨团队将样本数据输入模型中进行 200 代的操练。通过不断调整模型参数和优化丢失函数，模型逐步学习到了大阶砖危害类型的特征和形式。

(5) 模型检验。由于操练进程中每一代的丢失函数都会发生改动，因此会生成一系列具有不同参数的模型。在这个阶段，研讨团队对这些操练得到的模型进行了检验，以找出表现最优异的模型。通过将检验集数据输入模型，研讨团队点评了每个模型在危害类型辨认方面的准确率。本研讨比较了不同模型之间的功用差异，挑选了表现最佳的模型作为进一步使用的模型。

(6) 效果分析。在模型使用的进程中，研讨团队对模型检测效果进行了详细的分析。首要，与人工对模型检测效果进行了比对，点评了模型在危害类型辨认方面的准确性。其次，对不同大阶砖危害的状况进行了辨认准确性的分析和判别。通过效果分析，研讨团队对模型的功用和可靠性进行了全面点评，总结了模型在大阶砖危害类型辨认方面的优势和局限性。

(7) 模型使用。本研讨的政策检测模型将被使用于前史建筑中，作为前史建筑日常性维护和可继续发展的重要工具。通过该模型，相关人员能够快速准确地辨认大阶砖的危害类型和所在位置，为前史建筑的维护和办理供应有用支撑。

95.42%

大阶砖开裂检测的准确率

80.91%

大阶砖污渍检测的准确率

89.34%

大阶砖表面磨损检测的准确率

Author contributions

Conceptualization, L.Z. and Y.C.; methodology, L.Z. and L.Y.; software, L.Z. and L.Y.; validation, L.Z. and L.Y.; formal analysis, Y.C. and L.Z.; investigation, L.Z. and Y.C.; resources, Y.C.; data curation, Y.C.; writing — original draft preparation, L.Z. and Y.C.; writ-ing — review and editing, L.Z. and Y.Z.; visualization, Y.Z.; supervision, L.Z. and L.Y.; project administration, L.Y.; funding acquisition, L.Y. All authors have read and agreed to the published version of the manuscript.

Liang Zheng

Yile Chen

Lina Yan

Yi Zhang