Dynamic Weighing Based On Bp Network Algorithm Research And Design Of The Control System

The dynamic quantitative weighing process is studied in this thesis. A new control method base on PID control tuned by BP neural network is proposed. The control system is designed and the related simulation experiments are made. According to the study on the specifications of spiral feeding quantitative weighing process, the control method is used to design a real project and a weighing computer control system is designed. The main contents are composed of the following parts:1. The thesis summarizes the survey of dynamic quantitative weighing systems, proposes the key matter of a dynamic quantitative weighing system-precision, and points out that the emphases studied in this paper is a spiral feeding dynamic quantitative weighing process.2. The physics mechanism of a spiral feeding dynamic quantitative weighing process is studied and the mathematics model is established. The correlative simulation experiments are carried out, too.3. The thesis studies on BP Neural Network's structure and BP algorithm. A simple direct m ethod of e stimating the appropriate h ide n odes i s introduced in this paper based on experiments and previous experience. This method has simplified the determination of hide nodes and achieved good result. In order to improve the speed and the accuracy of BP algorithm, an improved BP algorithm is proposed in this paper. The experiment results show that the learning accuracy and speed of BP algorithm with two times adaptive adjust of learning parameters is high than that of traditional BP Algorithm. So it possesses better value of application.4. Not only Intelligent Control, but also the basic principle of control method based on PID control tuned by BP neural network is described in this thesis. The result of simulation tests indicates that control method based on PID control tuned by BP neural network achieves satisfied performances.5. According to the specifications of dynamic quantitative weighing process control in a spiral feeding dynamic quantitative weighing system, the control method base on PID control tuned by BP neural network control method is applied for a real work. A dynamic quantitative weighing computer control system is designed, which includes hardware, realization method of software and flow chart of it.6. Reviewing works of this thesis and prospecting future more works.