Control method of light-type direct-current transmission system converter of offshore wind power station

Abstract

The invention relates to a control method of a light-type direct-current transmission system converter of an offshore wind power station, belonging to the technical field of power transmission. In the invention, a PID (Piping and Instruments Diagram) neural network controller is designed based on a particle group optimizing method, the traditional PI (Piping and Instruments) regulator is substituted, step input is used to train a neural network, that is to say, multi-group particles are set to search in the neural network weight space of searching, and the position and speed of the particles are continuously updated according to an adaptive value function of the neural network to obtain the optimum weight of the neural network. The invention adopts the method of using the optimum weight value obtained by training in combination with the error forward broadcast of the neural network to substitute the traditional PI regulator to control the operation of the system, thereby reducing the parameter to be regulated and improving the transient response performance of the system; the neural network weight value is obtained by training a nonlinear model of a controlled system so as to approach to a true system. Only the forward broadcast process of the PID neural network is controlled in the operation process of the system. The method is relatively simple and is easy to achieve.

Description

technical field [0001] The invention relates to a control method in the technical field of electric power transmission, in particular to a control method for a converter of a light direct current transmission system of an offshore wind farm. Background technique [0002] In the grid-connected system of offshore wind farms, DC and AC are usually used to connect to the grid. Among them, the structure of the AC grid-connected system is relatively simple, but there are many disadvantages, such as the need for a large-capacity reactive power compensation device, serious electromagnetic pollution of the environment, large line loss, and not suitable for long-distance transmission. [0003] DC transmission methods can be divided into two methods: traditional DC transmission and light DC transmission. The traditional DC transmission technology is relatively mature, but due to the use of semi-controlled power electronic devices, such as thyristors (SCR), there are certain limitations...

AI Technical Summary

Problems solved by technology

The steady-state performance of the system is good, but there are the following deficiencies: 1) both ends are PI regulators, the outer ring needs two regulators for active power or DC voltage and reactive power, and the inner ring still needs two regulators for active current and reactive current PI regulators, so the one-end converter needs at least 4 PI regulators, and the two-end converter needs 8 PI regulators in total. There are too many regulator parameters, and it is difficult to adjust and implement in practical applications.

Most of the engineering tuning methods of PI parameters are based on the system transfer function, but this kind of technology is relatively complicated. Most of the PI parameters calculated by the equivalent method of simple transfer function have large deviations, and often need to be gradually adjusted on site based on manual experience. To ensure system performance more difficult

2) There is a certain dependence on the system parameters, the inner loop feedforward control, the system inductance and other parameters are used in the dynamic process, the accuracy of these parameters is difficult to guarantee in the actual system, sometimes the deviation is large, and it varies with the system operating conditions Therefore, the output performance of the regulator designed according to the conventional nominal system parameters may deviate from the expected value in actual operation

3) The mathematical model of the light direct current transmission system itself has the characteristics of strong coupling and nonlinearity, and the PI regulator is designed according to the steady-state linearization model of the system. Therefore, the dynamic performance of the system cannot be guaranteed, and the adjustment effect cannot be optimal

In summary, there are too many parameters that need to be adjusted in this technology, and it is difficult to adjust in actual engineering, and the system performance is difficult to guarantee; at the same time, due to the strong coupling and nonlinear characteristics of the controlled object, the controller designed with a linear system cannot obtain a relatively good performance. Good transient response performance

Images