So sánh hiệu suất thuật toán hồi quy tuyến tính, học sâu và rừng ngẫu nhiên cho bài toán dự báo chịu tải cực hạn của khung thép phi tuyến tính phi đàn hồi

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: MẠNH THIỀU NGÔ, THỊ THANH THÚY NGUYỄN, TIẾN CHƯƠNG NGUYỄN, VIỆT HÙNG TRƯƠNG

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Tạp chí Xây dựng, 2023

Mô tả vật lý: tr.153

Bộ sưu tập: Metadata

ID: 338099

Thêm vào giỏ Liên kết toàn văn

Sự phát triển nhanh chóng và mạnh mẽ của ngành khoa học máy tính và khả năng tính toán trong vài thập kỷ gần đây đã thúc đẩy những ứng dụng của các phương pháp phân tích tiên tiến vào các bài toán thiết kế kỹ thuật xây dựng nói chung và thực hành thiết kế khung thép nói riêng. Một trong những hướng khả thi và phổ biến là áp dụng các thuật toán học máy vào dự đoán các ứng xử của kết cấu khung thép trong phân tích phi đàn hồi phi tuyến tính. Điều này cho thấy những ưu điểm rõ ràng như đẩy nhanh được quá trình ra quyết định, giảm tỷ lệ lỗi và tăng hiệu quả tính toán. Trong nghiên cứu này, 3 thuật toán học máy phổ biến hiện nay được nghiên cứu cho bài toán dự báo khả năng chịu tải của khung thép bao gồm: Hồi quy tuyến tính, Học sâu và Rừng ngẫu nhiên. Hiệu quả khi áp dụng các phương pháp học máy được xem xét qua một ví dụ số khảo sát một khung thép phẳng 5 nhịp 14 tầng. Phân tích phi đàn hồi phi tuyến tính nâng cao được thực hiện cho khung thép nhằm tạo bộ dữ liệu cho huấn luyện để giảm thiểu thời gian phân tích. Các biến đầu vào của bài toán là các đặc điểm hình học của tiết diện thanh dầm cột được chọn từ danh mục có sẵn. Hiệu suất của các thuật toán học máy được đánh giá bằng cách sử dụng các chỉ số về lỗi gồm sai số bình phương trung bình (MSE), hệ số xác định (R2) và Kết quả cho thấy phương pháp rừng ngẫu nhiên có hiệu quả tốt nhất trong ba phương pháp học máy lựa chọn. Từ khóa: Khung thép
phân tích phi đàn hồi phi tuyến tính
học máy
The rapid and powerful development of computer science and computing power in recent decades has promoted the application of advanced analytical methods to engineering design problems in general and steel frame design practice in particular. One of the possible and popular directions is to apply machine learning algorithms to predict the behavior of steel frame structures in nonlinear inelastic analysis. This shows obvious advantages such as speeding up the decision-making process, reducing error rates, and increasing computational efficiency. In this paper, the effectiveness of three popular machine learning algorithms is studied for the prediction of the load-carrying capacity of steel frames including Linear Regression, Deep Learning, and Random Forest. A numerical example surveying a 5-span 14-story planar steel frame is considered. An advanced nonlinear inelastic analysis is performed for the steel frame to generate training datasets to minimize analysis time. The input variables of the problem are the geometrical characteristics of the beam and column cross-section selected from the available list. The performance of the machine learning algorithms was evaluated using error indexes including mean square error (MSE), and coefficient of determination (R2) and the results showed that the random forest method is the most effective among the three machine learning methods selected. Keyword: Steel frame
nonlinear inelastic analysis
machine learning

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR