Abstract : The energy crisis and increased environmental awareness have led to a stronger demand for new, pollution-free energy sources, and wind power generation has gradually come into focus under this trend. 0. Introduction The energy crisis and increased environmental awareness have led to a stronger demand for new, pollution-free energy sources, and wind power generation has gradually come into focus under this trend. From constant pitch to variable pitch, and the introduction of doubly-fed speed control, all are aimed at improving the utilization rate of wind energy. When effectively controlling wind turbines, whether using classical or modern control methods, model building is necessary. However, the randomness of wind speed and direction, and the uncertainty of aerodynamics, make the establishment of wind turbine nacelle models difficult. Adaptive tracking of wind force and direction by the nacelle is a prerequisite for increasing the efficiency and power of wind turbines. Under this premise, intelligent control avoids the need for mathematical model building and has a good effect on the control of multivariable nonlinear wind turbines. 1. The Rotation Working Principle of Wind Turbine Nacelles While the control methods used in modern wind turbines differ (e.g., doubly-fed speed control, stall control, etc.), the mechanisms for adjusting the nacelle vary when capturing wind energy. However, the underlying principle remains the same. Information from an anemometer and wind vane is transmitted from the top of the nacelle to the CPU board at the bottom of the turbine. Through analog-to-digital conversion, the digital signal is input to the central processing unit (CPU). The CPU analyzes and processes the data, determining whether to adjust the yaw motor. Using a power mechanism (most commonly a hydraulic mechanism), the attitude of the generator nacelle is adjusted to ensure the turbine blades always face the wind, maximizing the utilization of available wind resources. Alternatively, when the wind speed exceeds the rated maximum, the yaw brake motor is activated, or a 90° yaw is initiated to ensure safe and normal operation. Conversely, when the wind speed is too low, to prevent the electricity generated by the turbine from falling short of the energy absorbed from the grid by its rotor excitation, the turbine may disconnect from the grid, conserving power resources. This method requires feeding back wind resource information, such as wind direction and speed, to the bottom information processing motherboard of the wind turbine, increasing the load on the central processing unit and delaying the nacelle's rotation time. Considering these factors, we designed an intelligent wind turbine nacelle based on fuzzy control, allowing the nacelle's wind energy capture mechanism to directly become the intelligent terminal of the wind turbine system, reducing the load on the central processing unit. 2. Design of the Intelligent Nacelle Hardware System The hardware schematic diagram of the intelligent nacelle is shown in Figure 1 below: As can be seen, traditional wind turbines transmit the collected wind energy information to the ground control console, while this design gives the nacelle a degree of autonomy. The principle is that when the wind speed sensor and wind vane collect wind resource information, the information is amplified and converted from analog to digital, then fed into the microcontroller using a fuzzy control algorithm for intelligent processing. The result is then transmitted through a back channel to drive a hydraulic motor, causing the nacelle to rotate to the windward direction. If the wind speed and direction change slightly, the wind speed sensor and wind vane re-collect information, enabling real-time control of the wind turbine and full utilization of wind energy. Of course, if manual operation is required, such as inspection and maintenance of the wind turbine, a shutdown signal can be sent to the nacelle through the human-machine interface platform in the central control room. If the wind speed is less than or greater than the rated wind speed, the microcontroller sends a command to deviate from the windward direction to prevent damage to the wind turbine in strong winds and to avoid impact on the power grid. The system host uses the 80C552 fuzzy controller microcontroller. This is because the system software needs to use fuzzy control algorithms, as this microcontroller combines fuzzy logic control theory with microcontroller technology, which simplifies software development. Secondly, the 80C552 has an internal 8-channel 10-bit A/D converter, which simplifies the circuitry. Furthermore, the 80C552 has an internal watchdog protection circuit to prevent program overruns during field operation, improving system stability. Since this microcontroller only has 256 bytes of RAM and no ROM, system expansion is necessary. The system output can be divided into two parts: the first part is output from one parallel port of the 80C552 to the LED digital tube to display the current wind speed; the second part is output from another parallel port to the power amplifier to drive the hydraulic motor. When the sensor detects wind speed and direction signals, the microcontroller sends a drive signal. Since the signal from the microcontroller is relatively small, it needs to be amplified to drive the various hydraulic motors to bring the nacelle into a windward or leeward position. For communication with the bottom of the wind turbine and the central control room, because the 80C552 has a full-duplex asynchronous serial communication port SIO0 and an I2C serial bus port SIO2, serial communication can be achieved simply by replacing the CMOS signal from the microcontroller with a standard RS-232 signal. This allows for reliable communication not only with the main board at the bottom of the wind turbine but also directly with the central control room. This enables reliable shutdown of the wind turbine and access to the nacelle for repairs during maintenance or when a malfunction occurs. 3. Implementation of the Intelligent Cabin System Software Due to the randomness and uncertainty of aerodynamics, it is difficult to establish a definite mathematical relationship between wind speed and direction. To achieve the best control effect, we adopted a fuzzy control algorithm. The system control principle diagram is as follows: When the wind speed or direction is lower (or higher) or deviates from the set value Vmin (or Vmax), the wind turbine automatically shuts down and disconnects from the power grid (even rotating the nacelle to the leeward direction). When the information detected by the sensors is within the set values, the microcomputer system compares the current wind speed and direction information with the previously obtained information to determine the error values ​​of wind speed and direction, and sets the universe of discourse as: X=[-4, -3, -2, -1, 0, 1, 2, 3, 4] Y=[-4, -3, -2, -1, 0, 1, 2, 3, 4] where the universe of discourse for wind speed deviation e is X, and the universe of discourse for wind direction deviation change q is Y. These two linguistic variables are fuzzified and represented by E and Q, respectively. The controller output is u, fuzzified and represented by U. The range of e and q between [-4, 4] is divided into 5 categories: {NB (negative large), NS (negative small), ZE (zero), PS (positive small), (PB positive large)}. The universe of discourse for U is also [-4, -3, -2, -1, 0, 1, 2, 3, 4]. Since the system input consists of two variables, the control language of the fuzzy algorithm is as follows: IF E AND Q THEN U, where E represents wind speed and Q represents wind direction, yielding a control table (omitted). If the detected information is not a fixed point as described above, a triangular function is used as the membership function, and the numerical fuzzification is performed using the single-value membership method. During numerical defuzzification, the centroid algorithm is used to obtain the control quantity for nacelle rotation, maximizing the capture of wind resources. The signal response curve obtained by MATLAB simulation of the above fuzzy statement is as follows: [align=center] Figure 3 System response curve[/align] As can be seen from the above system response curve, although this design has an overshoot, its proportion is not large, and the system can achieve a relatively stable output in a short time. Since the nacelle rotates at high altitude, a too fast response would not be good for the nacelle itself, as it would make the nacelle unstable. Therefore, when the system controls the rotation of the nacelle, this response time should be considered a relatively fast control response time. Therefore, based on the above analysis, this design has good overall performance. 4. Conclusion and Outlook The central processing microcontroller of this system, by adjusting the coefficients and combining with the control table, not only reduces the load on the central processing unit of the wind turbine base, but also performs real-time control of the wind turbine nacelle to ensure that the wind turbine fully utilizes wind resources, which has a certain mitigating effect on the energy crisis. References : [1] Zhang Jili. Fuzzy-Neural Network Control Principles and Engineering Applications [M]. Harbin Institute of Technology Press, 2004 (6) [2] Zhang Weiguo, Yang Xiangzhong. Fuzzy Control Theory and Application [M]. Northwestern Polytechnical University Press, 2000 (10) [3] Gong Jingyuan. Wind Power Plant Engineering Technology Handbook [M]. Machinery Industry Press, 2004 (3) [4] Wang Chengxu, Zhang Yuan. Wind Power Generation [M]. China Electric Power Press, 2003 (3) [5] Tong Jihong, Wang Jizhong. Research on Adaptive Control System of Single-Chip Microcomputer Boiler [J]. Journal of Beihua University (Natural Science Edition), 2005 (6), -278-280