Abstract The cranes are usually controlled by a variety of actions including handling, lifting, carrying, then lowering and gripping the load. An intelligent control system could provide the operator with important advantages when performing all these operations. As the load cycle times are reduced, the operations are then performed more efficiently, and hence saving time, costs and increasing the overall productivity. As the control system optimizes the motion of the crane, the crane and its components are subjected to load and related stresses for shorter length of time leading to longer lifespans. Most importantly, the likelihood of human error is reduced and security is increased. Especially the transportation of fragile, sensitive materials or load transfer in dangerous conditions makes the operator control very difficult. The present study demonstrates how to perform a artificial intelligence assisted transport operation under variable conditions with hybrid control methods on a simple pendulum. Zero Vibration (ZV) input shaping (IS) method was implemented to a simple pendulum experiment setup with different heights and variable weights. Neural Network (NN), General Regression NN (GRNN), and Radial Basis Function Network (RBFN) were used with serial as a closed-loop intelligent control methods. The presented results indicate that the proposed approach constributes to the overall performance for elimination of residual vibrations.

中文翻译：

---

一种门式起重机智能串联混合控制方法

摘要 起重机通常由多种动作控制，包括搬运、提升、搬运、下降和抓取负载。在执行所有这些操作时，智能控制系统可为操作员提供重要优势。随着装载周期时间的减​​少，操作的执行效率更高，从而节省了时间、成本并提高了整体生产力。由于控制系统优化了起重机的运动，因此起重机及其组件在较短的时间内承受负载和相关应力，从而延长使用寿命。最重要的是，减少了人为错误的可能性并提高了安全性。尤其是在危险条件下运输易碎、敏感材料或负载转移，使操作员控制非常困难。本研究展示了如何在简单摆锤上使用混合控制方法在可变条件下执行人工智能辅助运输操作。零振动 (ZV) 输入整形 (IS) 方法已应用于具有不同高度和可变重量的简单摆锤实验装置。神经网络 (NN)、一般回归神经网络 (GRNN) 和径向基函数网络 (RBFN) 被用作串行作为闭环智能控制方法。所呈现的结果表明，所提出的方法有助于消除残余振动的整体性能。零振动 (ZV) 输入整形 (IS) 方法已应用于具有不同高度和可变重量的简单摆锤实验装置。神经网络 (NN)、一般回归神经网络 (GRNN) 和径向基函数网络 (RBFN) 被用作串行作为闭环智能控制方法。所呈现的结果表明，所提出的方法有助于消除残余振动的整体性能。零振动 (ZV) 输入整形 (IS) 方法已应用于具有不同高度和可变重量的简单摆锤实验装置。神经网络 (NN)、一般回归神经网络 (GRNN) 和径向基函数网络 (RBFN) 被用作串行作为闭环智能控制方法。所呈现的结果表明，所提出的方法有助于消除残余振动的整体性能。