Ứng dụng trí tuệ nhân tạo trong dự đoán sức chống cắt của đất sau biến dạng

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả:

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Tạp chí Khoa học và Công nghệ Thủy lợi, 2020

Mô tả vật lý: tr.106

Bộ sưu tập: Báo, Tạp chí

ID: 300099

Thêm vào giỏ Liên kết toàn văn

After being deformed due to disasters such as erosion, landslides, the soil will significantly change its shear strength. Therefore, it is necessary to forecast the reduction of the shear strength of these soils to predict the possibility of recurrence of unstable erosion with these deformed layers. In this paper, artificial intelligence (RF) will be applied to predict the remaining shear strength of soil after deformation. To perform the simulation, 131 experimental data were collected from literature. The data set consists of four input variables: LL liquid limit, PI plasticity index, Casagrande’s classification deviation ∆PI, CF clay content. The evaluation of the models was made and compared on training data set (70% data) and control data set (30% remaining data) by criteria of Pearson correlation coefficient (R) and RMSE error. The results of the study showed that the random forest model is feasible in determining the remaining shear strength of soil after soil deformation with a correlation coefficient for the training model is 0.97 and verified as 0.78. At the same time, the random forest model can show the importance of each soil property to the remaining shear strength of deformed soil, respectively in the order of Liquid Limit>
Casagrande classification deviation ∆PI>
Clay Fraction >
Plasticity index.Sau khi bị biến dạng do các tác động như như xói mòn, sạt lở, đất sẽ thay đổi đáng kể sức chống cắt. Do vậy công tác dự báo suy giảm cường độ chống cắt của các lớp đất này từ đó giúp dự đoán được khả năng tái diễn xạt lở mất ổn định với các lớp đất bị biến dạng này là một công tác hết sức cần thiết. Trong bài báo này sẽ ứng dụng trí thông minh nhân tạo mà cụ thể là thuật toán rừng ngẫu nhiên (RF) để dự báo sức chống cắt còn lại của đất sau biến dạng. Để thực hiện việc mô phỏng, 131 dữ liệu thí nghiệm đã được thu thập từ công bố quốc tế. Bộ dữ liệu bao gồm bốn biến đầu vào là giới hạn chảy LL, chỉ số dẻo PI, độ lệch biểu đồ phân loại Casagrande ∆PI, hàm lượng sét CF. Việc đánh giá các mô hình được thực hiện và so sánh trên tập dữ liệu huấn luyện (70% dữ liệu) và tập dữ liệu kiểm chứng (30% dữ liệu còn lại) bằng các tiêu chí là hệ số tương quan Pearson ® và sai số RMSE. Kết quả của nghiên cứu cho thấy mô hình rừng ngẫu nhiên khả thi trong việc xác định sức chống cắt còn lại của đất sau biến dạng của đất với hệ số tương quan cho mô hình huấn luyện là 0.97 và kiểm chứng là 0.78. Đồng thời, mô hình rừng cây ngẫu nhiên có thể chỉ ra tầm quan trọng của từng tính chất của đất đến sức chống cắt còn lại của đất biến dạng, lần lượt theo thứ tự là Giới hạn chảy >
Độ lệch biểu đồ phân loại Casagrande ∆PI >
Hàm lượng sét >
Chỉ số dẻo.

1.

Tạo bộ sưu tập với mã QR