Research On Neural Network Control Technology Of Range-Shifting And Lifting Of Tower Crane

Tower crane originated from western Europe. It is indispensable in modern construction, and it is the primary special heavy equipment in all of construction machines. Tower crane has following characteristics: discontinuous working, starting & braking frequently; there are noticeable vibration and impulsion in running; high lifting height and extend rang, heavy lifting moment, etc. With the advent of more and more high-rise and large-scale buildings, requirements for the efficiency, lifting height, lifting moment, and safety features are becoming higher and higher. In order to meet these requirements, Research on the application of PID and Neural Networks control theory to the movement control of tower crane was made to meet these requirements and therefore to get a better control system for tower crane.First, dynamic analysis and modeling were made for range-shifting and lifting machinery of tower crane respectively according to the working principles and characteristics. The interrelationship of the related parameters was got based on the analysis of the model, and the systematic analysis of the tower crane was made using the resultant transfer function.Secondly, controller of the system was designed. Although PID controller can improve the performance of the control system to some extent, it can not give a satisfied result using PID controller alone. NNPID control method was applied in this paper to improve the performance of the control system. PID control theory, RBF system, learning algorithm, and the combination of neural networks and PID, etc., were introduced. An emphasis was placed on the application of the controller determining PID parameters with RBF neural networks.Finally, the controller working based on the combination of RBF neural networks and traditional PID control was applied to in aclinic kinetic machinery and lifting machinery of tower crane. The simulation of this controller was made using Matlab, and the simulation results showed that the control system has some merits, such as quick response, little overshoot, well anti-jamming capacity, and little steady-state error, etc. Both the dynamic property and static characteristic of this controller are better than traditional PID controller, and meet the tower crane...