Đánh giá hiệu quả mặt trượt pid và mạng rbf-nn cho mobile robot=Performance evaluation of a pid sliding surface and radial basis function neural network for mobile robot

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Trung Hiếu Trần

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Khoa học Giáo dục KT, 2024

Mô tả vật lý: tr.22-32

Bộ sưu tập: Metadata

ID: 246498

Thêm vào giỏ

A proportional integral derivative sliding surface (PIDSS) and radial basis function neural network (RBF-NN) for Mobile robot are applied in this study. This robot has many advantages such as simple structure, energy saving, high moving speed, and low production costs. The sliding mode control (SMC) controller using PIDSS (PIDSS-SMC) is designed so that the robot’s actual output approaches the standard input and reduces the chattering phenomena around the sliding surface. The RBF-NN is used to approximate the nonlinear components in the Pw matrix of the PIDSS-SMC controller. The weights of this neural network are trained online using the Gradient Descent algorithm. Lyapunov theory is used to prove the stability of the system. The actual output of the xw and yw converges to the reference xd and yd with the steady-state error converges to zero, the rising time reaches 0.0832s and 0.0764s, the settling time is 0.1309s and 0.1226s, the overshoot is 0.0042% and 0.0055%, respectively, and the chattering phenomena was reduced.Mặt trượt vi tích phân tỷ lệ và mạng RBF-NN cho Mobile robot được ứng dụng trong nghiên cứu này. Đây là robot có nhiều ưu điểm như cấu trúc đơn giản, tiết kiệm năng lượng, tốc độ di chuyển cao, và chi phí sản xuất thấp. Bộ điều khiển trượt sử dụng mặt trượt PID (PIDSS-SMC) được thiết kế sao cho ngõ ra thực tế của robot tiến về ngõ vào chuẩn và giảm hiện tượng chattering quanh mặt trượt. Mạng RBF-NN được sử dụng để xấp xỉ các thành phần phi tuyến trong ma trận Pw của bộ điều khiển PIDSS-SMC. Các trọng số của mạng được huấn luyện trực tuyến sử dụng giải thuật Gradient Descent. Lý thuyết Lyapunov được sử dụng để chứng minh tính ổn định của hệ thống. Ngõ ra thực tế của xw và yw hội tụ về xd và yd tham chiếu với sai số xác lập hội tụ về 0, thời gian tăng đạt 0,0832s và 0,0764s
thời gian xác lập là 0,1309s và 0,1226s
độ vọt lố là 0,0042% và 0,0055% tương ứng, và hiện tượng chattering được giảm.

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR