DỰ ĐOÁN LỰC CẮT SỬ DỤNG MÔ HÌNH MẠNG LAN TRUYỀN NGƯỢC KHI TIỆN KHÔ THÉP SKD11 SAU NHIỆT LUYỆN VỚI DỤNG CỤ CẮT CBN

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Thi Dieu Hoang, Van Binh Phung, Quoc Nam Tang

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Tạp chí Khoa học & Công nghệ - Trường Đại học Công nghiệp Hà Nội, 2023

Mô tả vật lý: tr.47

Bộ sưu tập: Metadata

ID: 363677

Thêm vào giỏ Liên kết toàn văn

Cutting force (CF) is one of the most important factors in improving machining efficiency. It directly affects the cutting tool life and the quality of the product. This paper presents the results of building a model to predict the value of the cutting force components using a back-propagation (BP) neural network when dry and hard turning SKD11 steel after heat treatment. The artificial neural network (ANN) training dataset is collected from 27 full dry turning experiments with CBN coated hard alloy cutting inserts and various cutting parameters including depth of cut, feed rate and cutting speed. The value of the cutting force components is measured by a specialized and modern force measuring device. The back-propagation neural network is established with many different structures to evaluate and select the most suitable structure. Indicators such as Coefficient of Regression (R2), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) are used to assesment the quality of neural networks. The research results show that the generated neural network can effectively predict the value of the shear force components within the trained range. This result is the foundation for further research on vibration and tool wear as well as building a cutting force monitoring model during machining.Lực cắt là một trong những yếu tố quan trọng nhất trong việc nâng cao hiệu suất gia công. Nó ảnh hưởng trực tiếp đến tuổi thọ của dụng cụ cắt và chất lượng sản phẩm. Bài báo này trình bày kết quả xây dựng mô hình dự đoán giá trị các thành phần lực cắt sử dụng mạng nơ ron lan truyền ngược khi tiện khô thép SKD11 sau nhiệt luyện. Bộ dữ liệu huấn luyện mạng nơ ron được thu thập từ 27 thực nghiệm toàn phần khi tiện khô với các mảnh cắt hợp kim cứng phủ CBN và các thông số cắt khác nhau bao gồm chiều sâu cắt, tốc độ chạy dao và vận tốc cắt. Giá trị các thành phần lực cắt được đo lường bằng thiết bị đo lực chuyên dụng và hiện đại. Mạng nơ ron lan truyền ngược được xây dựng với nhiều cấu trúc khác nhau để đánh giá và lựa chọn cấu trúc phù hợp nhất. Các chỉ số như hệ số hồi quy (Coefficient of Regression - R2), Root Mean Square Error - RMSE và sai số tuyệt đối phần trăm trung bình (Mean absolute percentage error - MAPE) được sử dụng để đánh giá chất lượng mạng nơ ron. Kết quả nghiên cứu cho thấy mạng nơ ron được ra có thể dự đoán hiệu quả giá trị các thành phần lực cắt trong phạm vi được đào tạo. Kết quả này là nền tảng để tiếp tục nghiên cứu về rung động và mòn dụng cụ cắt cũng như xây dựng mô hình giám sát lực cắt trong quá trình gia công.

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR